Exploring the role of health-related quality of life measures in predictive modelling for oncology: a systematic review.

Plain English summary

The review lays the groundwork for the new field of using quality of life in prediction for oncology. It summarizes how quality of life is used in prediction models, identifying the factors of quality of life that are used. It also assesses the quality of reporting and model development of models including quality of life for cancer patients.

It has been found that the factors that associated with symptoms and physical functioning of a patient are used the most. Quality of life factors are mainly used as predictors, while a few models try to use quality of life to predict quality of life. Improvements are needed for reporting the development of models with quality of life, as the majority has a high risk of bias and are missing steps according to guidelines.

To summarize, the field of quality of life in prediction models has grown over the years, but is far from having a model used by patients and doctors in the clinic.

Introduction

Health related quality of life (HRQoL) can be measured using patient-reported outcome measures (PROMs), which are standardized questionnaires completed by patients that quantify the impact of the disease on their daily life and HRQoL [ 1 , 2 ], and are used to monitor patients in routine clinical care and as a measure of quality of care in registries [ 3 ]. The integration of PROMs in clinical routine has rapidly increased in recent years [ 4 ] and is accompanied by a substantial increase of available data on patients’ HRQoL [ 5 ]. In its aggregated form, this data is currently mainly used in decision aids and as quality indicators of care [ 6 ].

HRQoL data could further improve individual care by its use in prediction modelling, which uses a patient’s available data to predict a prognostic or diagnostic outcome or event at a later time point [ 7 ]. In oncology, models that predict survival and treatment outcomes are at the forefront, like PREDICT and GAIL score [ 8 – 10 ]. These prediction models and their outcomes are currently based on clinical and disease characteristics of patients and are used by clinicians to inform patients about their life expectancy or course of treatment [ 7 , 9 , 11 , 12 ].

Integration of HRQoL in prediction models for oncology is a recent advancement, as the volume of collected HRQoL data has grown [ 13 ]. Although a comprehensive overview of model applications does not yet exist, examples include prediction of overall survival (OS) or progression free survival (PFS) by physical functioning and symptom scales [ 14 , 15 ], and HRQoL outcomes can be predicted by treatment type or cancer characteristics [ 16 , 17 ]. Fatigue at baseline is predictive for later global HRQoL, demonstrating HRQoL as predictor and outcome in the same model [ 18 ]. Furthermore, the choice of prediction model methods depends on study design, outcome, and type of data available [ 19 ]. Currently, there are two methodological approaches distinguishable in prediction modelling: Artificial intelligence (AI) and the more traditional “classical statistical” methods. As there can be overlap between methods (e.g. regression), the distinction lies in the aim of the prediction, while for classical methods the aim is inference, the aim of AI methods is to uncover patterns and hidden layers in the data regardless of causation. At this point, it remains unclear if AI has added value and if there is a preference for a prediction method for incorporating HRQoL data.

Whilst the field of HRQoL prediction modelling in oncology has expanded from proof-of-concept models to the first validated models [ 13 ], there is no published overview that summarizes this emerging field. The aim of this review is to provide a synthesis regarding which HRQoL domains play a role in the field of oncological predictions. The research questions that are addressed in this review are:

Which analysis and methods are used in oncological prediction that include HRQoL domains?

Which HRQoL domains are used as predictors, outcomes, or both in the field of oncological prediction?

What are the predictors’ relations with the outcome and vice versa?

Methods

This review was registered in PROSPERO (CRD42023456777). No protocol was developed for this review. The ‘transparent reporting of a multivariable prediction model for individual prognosis or diagnosis: checklist for systematic review and meta-analysis’ (TRIPOD-SRMA) was used for reporting this review [ 20 ]. PubMed, Embase via Embase.com, SCOPUS and CINAHL via EBSCO databases were systematically searched using search terms covering HRQoL, PRO(s) and PRO measures, development and validation of prediction models, and any type of cancer. Both MeSH terms and Emtree terms were used where appropriate. As no MeSH terms exist for prediction model related keywords, the search filter for prediction methods was based on Geersing et al. [ 21 ]. For the full search terms, see Appendix A. The search was performed in February 2023, and updated in January 2024.

For each publication, the abstract was screened using RAYYAN by two independent screeners (TvdH and either KdL or BdR) [ 22 ]. Conflicting decisions were judged unblinded by a third screener, whose judgment was final (KdL or BdR). For the abstract screening, the inclusion criteria were limited to studies that involved adult cancer patients aged 18 years or older; the study also had to report a statistical or AI-based model that includes HRQoL (functioning or symptoms) as an independent or dependent variable. Finally, the study had to be longitudinal with a minimum of two time points spaced at least three months apart, with at least one time point including HRQoL measurement. Publications about PROMs development and validation, case reports, conference abstracts, not in English, and literature reviews were excluded.

The full-text screening was done by two independent reviewers (TvdH, KdL, BdR) using RAYYAN. Conflicting decisions were judged unblinded by a third screener (KdL or BdR), who’s judgment was final. For the full-text screening, inclusion criteria were: the publication aimed to develop or validate a prediction model, full multivariate models were reported, and any performance measure (e.g. R 2 , C-statistic or ROC) of the model was reported.

Quality of reporting assessments of the publications were done by one independent reviewer (either TvdH or BdR) using an adapted version of the ‘transparent reporting of a multivariable prediction model for individual prognosis or diagnosis’ (TRIPOD) checklist [ 23 ] (See Appendix B). Publications that did not fulfil at least the majority (≥ 7 out of 13) of the, for this review, selected criteria were deemed of insufficient quality of reporting and were therefore excluded.

All remaining publications were eligible for data extraction. The risk of bias of the prediction models described in the remaining publications was assessed by one independent reviewer (either TvdH or BdR) using the ‘prediction model risk of bias assessment tool’ (PROBAST) [ 24 ], assigning certainty assessment to each publication to indicate the quality of the described models.

For each included publication, the study design, type of analysis, type of cancer, type of PROMs, HRQoL used as outcome or predictor, number of time points, type of performance measures and development/validation of model were extracted to report the overview of prediction models in HRQoL of cancer. No synthesis of the performance measures was performed as the focus of this review was on how HRQoL is used in prediction models. Data extraction was performed using a excel sheet by one independent reviewer (BdR or TvdH). Missing items from extraction were left as is.

Results

Record screening

The search yielded 10726 records; after de-duplication, 4747 records were eligible for the abstract screening. Of those, 645 were eligible for full text screening. Main reasons for exclusion at this stage were that studies did not apply a longitudinal study design (n = 1162), did not present a prediction model (n = 901), or included a population not affected by cancer (n = 366). After full text screening, 128 records remained for quality screening. Excluded records after full text screening did not report a full prediction model (n = 94), or did not report HRQoL in model (n = 215; Fig. 1 ).

Quality of reporting

After quality screening, 98 records remained that were eligible for data extraction and risk of bias assessment (Fig. 1 ). From the included papers, 43% of the publications were not transparent or unclear in their reporting of how missing data was handled for development of a prediction model (Appendix B). In addition, a description how model performance was assessed was lacking in 24% of publications. For the results section, 86% of publications reported a full model, 75% reported model performance measures (e.g. R 2 , C-statistic or ROC). However, updating or validation of a model after initial development was only described in 10% of the records.

Risk of bias

The risk of bias of each study was assessed using PROBAST (Robert F. [ 24 ]). Only 23% of the studies were assessed as having a low risk of bias (RoB) (Appendix C). Reporting of predictors, outcomes, and population of the models was of sufficient quality. However, the poor reporting of the analysis was the main cause of the high RoB rating of 71% the studies, which included the use of univariate associations to select the variables for multivariate models, the lack of a missing data strategy, or model overfitting and optimism not being accounted for.

Emerging field of research

Of all included publications, the first was published in 2006; from 2013 on, the publications steadily increased over 10 years to 19 publications per year in 2023 (Appendix D). Of note is the introduction of the AI based models from 2020, which contributed to the accelerated increase of publications and thus interest in this field (Appendix D). The majority of the included publications (76%) was published in journals in the first quartile of the SCImago journal ranking (SCImago). 18% of publications were in Q2 ranked journals, 4% of publications in Q3, none in Q4. However, 2% of publications were in unranked journals.

Population

The most included patient populations were patients with lung (15%), breast (15%), head and neck (11%), or prostate (10%) cancer (Appendix E), whilst 7% of studies included all cancer types. The size of the populations for the models varied from 34 to 30.969 patients. The distribution is strongly right skewed with a median of 294 (177.5–891.5 IQR) patients (Appendix E).

Questionnaires

Nearly half of the studies used the European Organisation for Research and Treatment of Cancer (EORTC) QLQ-C30 (43%) to measure HRQoL, 9% used Functional Assessment of Cancer Therapy (FACT) and 3% Patient-Reported Outcomes Measurement Information System (PROMIS) questionnaires (Appendix E). For assessing and predicting emotional domains, the Hospital Anxiety and Depression Scale (HADS) (10%), Center for Epidemiologic Studies (CES)-Depression (2%) and Distress thermometer (2%) were frequently used. Of the disease-specific questionnaires, EORTC QLQ-LC13 (7%) and Expanded Prostate Cancer Index Composite-26 (EPIC-26) (6%) questionnaires were the most frequently used (Appendix E).

Time points of HRQoL measurement

Most studies measured HRQoL at two time points (51%); the median was 2 (IQR 2-4) with a maximum of 15 (Appendix E). In eight studies (8%), HRQoL was measured at one of two included time points, meaning that HRQoL was predicted by another type of input data or vice versa. Three publications did not report how often they measured HRQoL in the methods, yet from the models was derived that they had at least a minimum of two HRQoL time points.

Methods of prediction models

The majority of papers in this review described the use of classical statistical models (84%), mostly including Cox proportional hazard (CPH) regression (36%), linear (19%) and logistic regression (18%) while in 16% of papers AI models were used (Appendix E). For AI methods (16%), tree based methods like random forest (6%) and gradient boosting (6%) were mostly used, followed by neural networks (4%) (Appendix E). Of note is the trend that the AI papers were published from 2020 on, while the first classical model including HRQoL in this review is from 2006 (Appendix D).

Health-related quality of Life as predictor or outcome

In the majority of studies included in this review, HRQoL variables were included in the models as predictors (76%) (Table 1 ; Appendix E). Global QoL (26%) and physical functioning (21%) were most frequently included as predictors. Furthermore, emotional symptoms including anxiety/depression (13%), emotional functioning (8%) and role functioning (7%) were used as predictors. Other predictors included symptom scales such as fatigue (16%), pain (15%), dyspnoea (9%) and loss of appetite (8%).

Twenty-three studies (23%) included HRQoL as both predictor and outcome in the prediction model (Appendix E). Nearly all of them used a baseline or later score to predict HRQoL further in time. Three studies selected change in HRQoL as predictor for their models [ 25 – 27 ].

HRQoL was used as a modelled outcome in 21 (21%) studies, with the domains of sexual functioning (9%), fatigue (7%), physical functioning (7%) and urinary function (7%) being the most commonly selected outcomes (Appendix E). Few models focused on summary score (6%) and global QoL score (5%), which is an aggregate score of (almost) all scales of the questionnaire. However, these outcomes are predicted by non-HRQoL variables like demographic characteristics, treatment type, dosage and location of treatment [ 28 – 34 ], and (bio) markers [ 35 ].

Predictive relations

Almost 40% of the models that included HRQoL as predictor showed a predictive relation between HRQoL and survival, predicted through Cox regression analyses (OS, PFS) (Appendix E; Appendix G ). For instance, change in HRQoL score at disease progression predicted survival in lung cancer patients [ 36 ]; EQ-5D scores predicted survival in glioma patients [ 37 ], and physical functioning predicted survival in pancreatic cancer patients [ 38 ].

Other models focused on the relation between HRQoL and treatment. In the prostate cancer models, symptoms like urinary incontinence and irritation were predicted by the dose and location of radiotherapy [ 28 , 31 , 32 , 34 ]. During chemotherapy, cancer patients could be discriminated and assigned to different HRQoL trajectories over time based on baseline HRQoL scores [ 29 , 82 ]. Misra et al. [ 43 ] found that receiving chemotherapy was predictive of fatigue in breast cancer.

Subsequent HRQoL scores predicted by previous scores were frequently based on patients’ baseline scores. For example, functional problems were predicted by self-reported anxiety and/or depression scores [ 28 ], and baseline fatigue was predictive of fatigue at a later time point [ 61 ]. Only one study used all baseline HRQoL domains to predict the summary score of a PROM [ 64 ] (see Table S3).

Discussion

The aim of this review was to identify and synthesize the HRQoL domains that are most relevant to oncological predictions. In our review of 98 studies on HRQoL prediction in oncology, we found that three-quarters of the selected publications used HRQoL domains as predictors. In contrast, HRQoL was less commonly included as an outcome (21%), where it was primarily predicted by treatment. Physical functioning and symptoms were more frequently included in prediction models than role, cognitive and social functioning. Emotional functioning was often included as predictor, but mostly in models aiming to predict future HRQoL scores based on other HRQoL domains.

Methods of HRQoL prediction in oncology

AI versus classical models

In this review, no notable differences in variable selection were found between AI and classical statistical methods; similar outcomes and predictors were included in both. However, AI models represented only one eighth of the included publications and had been published more recently (2020-present). This may be explained by the recent increase in volume of available HRQoL data needed for AI-predictions and the general shift in focus towards AI and exploring AI opportunities [ 123 ]. Several publications compared multiple AI based strategies to explore which methods work to predict with HRQoL [ 34 , 46 ]. For large datasets, AI based prediction methods are considered a better option than classical methods, as these methods better account for the complexity of the underlying data [ 124 , 125 ]. Interestingly, in this review, sample sizes varied across all approaches and included only four large datasets (> 5.000 patients); several smaller sized studies (< 100, n = 13) appeared to be underpowered [ 93 , 126 ]. In the current review, we noted that the majority of publications used AI methods in an explorative manner. Therefore, our findings do not facilitate a direct comparison of AI and classical methods, and thus, we cannot conclude whether AI methods outperform classical methods.

HRQoL dichotomization

We noted that HRQoL as outcome or predictor was either expressed in its original continuous format, dichotomized using a threshold score, or expressed as a change score (over time) (data not shown). While clinically relevant thresholds for impairment have been developed, just a few of the models took this approach [ 127 ]. This approach has upsides and downsides. Using a dichotomised variable over a continuous variable can make a model less accurate and requires a larger sample size [ 128 ]. Therefore, from a modelling perspective, continuous and change score modelling are preferred for HRQoL prediction modelling. However, binary scores might be preferred from a clinical perspective as these facilitate clinical interpretation: it clearly discriminates between patients who are in need of extra care and those who do not. We would argue that a cut-off can be applied on a continuous outcome score, thus balancing both clinical and modelling preferences.

Methodological limitations with current HRQoL prediction models

All current models have contributed to finding HRQoL predictors and outcomes that can be used in predictive modelling. Yet, other methods of modelling not mentioned in this review could also be used. Importantly, dynamic models using joint modelling approaches were not reported in this review [ 129 ]. This is a major gap in both knowledge and implementation, as clinical settings continually generate new data over time through repeated HRQoL assessments and routine clinical tests. Dynamic models, which update predictions as new information becomes available, more accurately reflects the real-world situation in the clinic [ 130 , 131 ].

Furthermore, the quality of reporting and bias assessments reveal significant gaps in current model development, highlighting simple yet crucial steps needed for improvement in this field.

A crucial first step is to accurately assess model performance which was not done or reported in a substantial proportion of the models (90%). Assessing model performance both in a training- and test dataset (i.e. internal validation) is essential to ensure model validity and to apply corrections like penalization and shrinkage, reducing overfitting and model optimism.

Secondly, many models either did not report a missing data strategy or only addressed it for part of the data types (e.g. only for HRQoL). Some publications applied complete case analysis, which is valid only if sensitivity analysis confirm that included and excluded groups are similar. We believe that using the full dataset, even if imputed, is preferable to complete case analysis as it minimizes overfitting and optimism by utilizing all available data.

Development standards for prediction models

The majority of the solutions to the issues identified in the models in this review are outlined in guidelines for development, validation and reporting of prediction models [ 23 ].Few papers included in this review explicitly mentioned the use of the TRIPOD standard for developing or reporting prediction models; even though this checklist was published in 2015 and 90 (92%) included publications were published after 2015. The quality check using TRIPOD criteria revealed that the level of the reporting was deemed poor. Notably, most of the AI-based models had higher reporting quality compared to the publications using classical statistical models based on the TRIPOD criteria. This difference in scoring might be due to the nature of the AI models, as they follow standard development procedures that include the majority of the selected TRIPOD criteria like model performance and validation. In contrast, classical models are also used to find possible predictors based on association rather than correlation. Therefore, these do not require rigorous development standards, because the aim of the research is not the complete development of a model.

Since the publication of the TRIPOD checklist in 2015, several additional TRIPOD guidelines have been published, like TRIPOD-AI for AI models and TRIPOD-Cluster for clustered data [ 132 , 133 ]. Thus, to improve model development, transparency and reporting quality we strongly urge new studies in the field of HRQoL prediction to use the available TRIPOD checklists.

HRQoL domains in oncological prediction models

HRQoL as predictor

Fatigue and physical functioning domains and baseline scores for all sorts of domains were most often applied as predictors, regardless of model type, outcome or cancer type. This selection may have been driven by the recommendations about important outcomes for cancer research by the FDA [ 134 ]. A large number of studies found that symptoms like fatigue and physical functioning were associated with outcomes like OS and PFS [ 135 ], [ 15 ]. Several of the models confirmed evidence that a better physical health before treatment may lead to better physical health after treatment, including a lower disease/symptom burden [ 42 , 92 ]. This underlines that physical functioning and symptoms scales are important predictors for oncological outcomes.

HRQoL as outcome

The majority of the domains that have been included in prediction models as outcome are symptoms or a physical functioning scales; which is the same trend seen in the predictors. Physicians may favor symptoms over functioning domain as physicians may have more affinity or experience with these, for instance by registering CTCAE-graded symptoms. HRQoL outcomes were predicted by non-HRQoL factors treatment, comorbidities, age, gender, and previous malignancy. The noticeable absence of disease characteristics, like TNM staging or biomarkers, as predictors of HRQoL in the majority of publications was surprising, given their role in informing treatment decisions. However, from this observation it seems that treatment factors are favoured over disease characteristics as predictors of HRQoL as an outcome. An possible explanation is that treatment factors are more actionable variables for a clinician, and thus after prediction of HRQoL a treatment can be changed or adjusted to increase a patients chance on better HRQoL.

HRQoL as predictor and outcome

Several papers included HRQoL as both a predictor and outcome in one model and focused on predicting symptoms. For example, Dess et al. [ 40 ] found that baseline QoL score was predictive of erectile function in prostate cancer patients; Pfob et al. [ 39 ] showed that ‘satisfaction with breasts’ and ‘sexual wellbeing’ domains of the Breast-Q predicted satisfaction with breasts one year after surgery. The prediction of functioning domain scores with previous HRQoL scores seems to be a knowledge gap in the current literature. The prediction of HRQoL by HRQoL is still in its infancy as shown by the current models, but provide a promising avenue for future research. Combining HRQoL prediction models with previous research on association and clustering between HRQoL domains and distinct patient trajectories for HRQoL [ 136 , 137 ], leads towards the possiblity to use prediction models to classify patients into risk categories. This classification is taking a first step towards tailored personalized treatment, which is the ultimate goal of personalized prediction.

Implications of the selected domains

The skewed focus on physical functioning and symptoms scales as predictors and outcomes reiterates the need to incorporate other HRQoL domains (emotional, role, cognitive functioning) in model development. This is important, as prediction with and of HRQoL could be a tool where patients and clinicians get insight in what can happen during treatment and disease under different treatment choices. Which HRQoL domains are important may differ from patient to patient and between cancer types. Therefore, limiting and skewing the models towards physical functioning and symptoms will limit the applicability in the clinic and intended population. The introduction of value based health care in oncology has shifted the focus from treating disease to treating the patient, which is exactly the shift the model development decisions must undergo.

Necessary steps for future HRQoL model development

As HRQoL in cancer prediction models is a rapidly evolving field, the results of this review point out several recommendations for future research to advance the field. First, the standard use of prediction model development and validation guidelines like TRIPOD and TRIPOD-AI is recommended to improve the model development standards and the poor reporting quality of models. Second, any HRQoL prediction model should at least have undergone internal validation to reduce overfitting and optimism in the model caused by the training data. Preferably, this should be followed by an external validation step if the models are intended for use in clinical practice. Third, other predictive methods using HRQoL data need to be tested, including dynamic models such as landmarking or joint modelling approaches that predict the next HRQoL time point based on the patient’s historical HRQoL while using all available data [ 138 ]. The dynamic aspect allows for better application and implementation of the model in the clinic, because it is one equation that can adjust its prediction at each new timepoint when new information becomes available [ 130 ].

Fourth, when designing the studies that underlie the next generation of HRQoL models, it is advised to power the sample size for AI based strategies in order to evaluate whether AI outperforms the classical methods. Most of the existing datasets of HRQoL do not reach sufficient sample size number, while some AI techniques require 200 events per candidate feature [ 139 ]. Of note, as HRQoL is a construct that measures the impact of the disease on every other domain of life, it is highly variable among different patient groups, cancer types, and even countries or regions. New studies in this field need to account for region/country differences, based on cultural and health care system differences, even when using validated PROMs [ 140 ]. To overcome both sample size as cultural differences issues, the internationally scattered HRQoL data needs to be brought together into one database for development of future prediction models.

Our final recommendation, is that all HRQoL domains should at least be included in the possible candidate predictors for the new generation models that predict any outcome for a cancer patient. This is needed to prevent the skew towards physical functioning and symptom scales, and thus possible include other domains (e.g. emotional or role) in the models that may be of more importance for cancer patients.

Strengths and limitations of the review

This review provides an overview of the emerging field of HRQoL prediction in oncology, which is important as HRQoL has become a central part of cancer treatment in recent years. This review lays the ground work for further development of HRQoL prediction models/field. A strength is the use of TRIPOD and PROBAST in the study, as recommended by the prediction modelling field [ 24 ].

One of the limitations of this study is the search terms, which were chosen to broadly capture prediction models, as proposed by Geersing et al. [ 21 ]. Due to the poor indexing of terms related to prediction and prediction modelling, it is possible to miss publications regarding HRQoL prediction modelling, even when using the Geersing filter. Specifically, our review may have missed relevant AI-based HRQoL prediction publication as no specific AI-terms were included in the used filter . Another limitation is the use of keywords surrounding the EORTC quality of life questionnaires in the search term. This may have biased this review towards finding a majority of studies that included these questionnaires. This may explain the relative lack of PROMIS and FACT questionnaires as it is clear from the HRQoL literature that they are used more frequently than was found in this review [ 141 ].

Future research

For future research, a review focussing solely on the AI HRQoL prediction models is needed as the current review includes mainly explorative models in this field. A review on machine-learning and PRO’s in oncology is currently being conducted by Krepper et al. [ 142 ]. Further research should also explore the impact of the dissemination through scientific literature, especially due to the varying nature of the publishing quality of the articles itself as well as the impact of the journal it was published in. Most of the articles (76%) were published in a first quartile ranked journal (SCImago journal ranking (SJR)), which ranges from first quartile to the fourth quartile based on a weighted average of how many times the previous three years (e.g. 2020–2022) of publications are cited in the year after (2023) (SCImago). Reporting quality of the model thus did not impact publication in high ranking journals.

All publications in this review described the development and/or validation of prediction models but did not address their further implementation or practical applications. The next step should be to evaluate the clinical use of prediction models. This will help accelerate understanding on which models are both feasible and desired by clinicians and patients.

Conclusion

To conclude, prediction modelling of and with HRQoL in oncology is still in its infancy. However, this review underscores the potential of using HRQoL as a tool for predicting disease outcomes and as a valuable resource for informing patients about the potential consequences of their disease and treatment. To enhance the transparency of reporting, the authors would strongly advocate adherence to the TRIPOD (-AI) checklist for development and validation in the design and reporting of any HRQoL prediction model study [ 23 , 132 ].

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 389 KB)

Acknowledgements

The authors are grateful for the support of the Netherlands Cancer Institute librarians for the support with retrieving all publications.

Author contributions

Conceptualization: TvdH, BdR, KdL, LvdP. Literature search: SvdM. Screening: TvdH, KdL, BdR. Data extraction: TvdH, BdR. Writing—original draft preparation: TvdH. Writing—review and editing: KdL, BdR, LvdP, NH, BH, SvdM. Supervision: KdL, LvdP, BdR.

Funding

This research was funded by the European Organisation for Research and Treatment of Cancer (EORTC) Quality of Life Group, grant number 007-2022 (EORTC 2052). The EORTC QLG business model involves license fees for commercial use of their instruments. Academic use of EORTC instruments is free of charge. TvdH is supported by EORTC Quality of Life Group, grant number 007–2022 (EORTC 2052). NH is supported by EORTC Quality of Life Group, grant number 007-2022 (EORTC 2052). BdR is supported by the Health Outcomes Observatory (H2O) funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No 945345-2.

Data availability

The templates for data extraction and data extracted from the literature are available from the authors upon reasonable request.

Declarations

Competing interests

TvdH: None to declare, KdL: None to declare, SvdM: None to declare, NH: None to declare, BH: None to declare, LvdP: None to declare, BdR: None to declare.

Ethical approval

No approval needed for this literature review.

Footnotes

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

References

1. Aaronson, N. K., Ahmedzai, S., Bergman, B., Bullinger, M., Cull, A., Duez, N. J., Filiberti, A., Flechtner, H., Fleishman, S. B., Haes, J. C., & Kaasa, S. (1993). The european organization for research and treatment of cancer QLQ-C30: A quality-of-life instrument for use in international clinical trials in oncology. JNCI: Journal of the National Cancer Institute, 85 (5), 365–376.

2. Cella, D. F., Tulsky, D. S., Gray, G., Sarafian, B., Linn, E., Bonomi, A., Silberman, M., Yellen, S. B., Winicour, P., & Brannon, J. (1993). The Functional assessment of cancer therapy scale: Development and validation of the general measure. Journal of Clinical Oncology, 11 (3), 570–579.

3. Greenhalgh, J., Gooding, K., Gibbons, E., Dalkin, S., Wright, J., Valderas, J., & Black, N. (2018). How do patient reported outcome measures (PROMs) support clinician-patient communication and patient care? A realist synthesis. Journal of patient-reported outcomes, 2 , 42. 10.1186/s41687-018-0061-6

4. Basch, E., Barbera, L., Kerrigan, C. L., & Velikova, G. (2018). Implementation of patient-reported outcomes in routine medical care. American Society of Clinical Oncology Educational Book . 10.1200/edbk_200383

5. Calvert, M., Thwaites, R., Kyte, D., & Devlin, N. (2015). Putting patient-reported outcomes on the ‘Big Data Road Map.’ Journal of the Royal Society of Medicine, 108 (8), 299–303. 10.1177/0141076815579896

6. Weldring, T., & Smith, S. M. S. (2013). Article commentary: Patient-reported outcomes (pros) and patient-reported outcome measures (PROMs). Health Services Insights . 10.4137/hsi.s11093

7. Steyerberg, E. W. (2019). Clinical prediction models. Springer . 10.1007/978-3-030-16399-0

8. Gail, M. H., Brinton, L. A., Byar, D. P., Corle, D. K., Green, S. B., Schairer, C., & Mulvihill, J. J. (1989). Projecting individualized probabilities of developing breast cancer for white females who are being examined annually. JNCI Journal of the National Cancer Institute, 81 (24), 1879–1886. 10.1093/jnci/81.24.1879

9. Vickers, A. J. (2011). Prediction models in cancer care. CA: a cancer journal for clinicians . 61 (5), 315–326. 10.3322/caac.20118

10. Wishart, G. C., Azzato, E. M., Greenberg, D. C., Rashbass, J., Kearins, O., Lawrence, G., Caldas, C., & Pharoah, P. D. (2010). PREDICT: A new UK prognostic model that predicts survival following surgery for invasive breast cancer. Breast Cancer Research, 12 (1), R1. 10.1186/bcr2464

11. Fijten, R., Wee, L., Dekker, A., & Roumen, C. (2021). Data-driven shared decision-making: A paradigm shift. Journal of Radiation Oncology Informatics, 11 (2), 4. 10.5166/jroi.11.2.1

12. Wang, X., Oldani, M. J., Zhao, X., Huang, X., & Qian, D. (2014). A review of cancer risk prediction models with genetic variants. Cancer Informatics . 10.4137/cin.s13788

13. Di Meglio, A., Havas, J., Soldato, D., Presti, D., Martin, E., Pistilli, B., Menvielle, G., Dumas, A., Charles, C., Everhard, S., Martin, A.-L., Coutant, C., Tarpin, C., Vanlemmens, L., Levy, C., Rigal, O., Delaloge, S., Lin, N. U., Ganz, P. A., … Vaz-Luis, I. (2022). Development and validation of a predictive model of severe fatigue after breast cancer diagnosis: Toward a personalized framework in survivorship care. Journal of Clinical Oncology, 40 (10), 1111–1123. 10.1200/jco.21.01252

14. Gripp, S., Moeller, S., Bölke, E., Schmitt, G., Matuschek, C., Asgari, S., Asgharzadeh, F., Roth, S., Budach, W., Franz, M., & Willers, R. (2007). Survival prediction in terminally Ill cancer patients by clinical estimates, laboratory tests, and self-rated anxiety and depression. Journal of Clinical Oncology, 25 (22), 3313–3320. 10.1200/jco.2006.10.5411

15. Groen, W. G., Naaktgeboren, W. R., Van Harten, W. H., Van Vulpen, J. K., Kool, N., Sonke, G. S., Van Der Wall, E., Velthuis, M. J., Aaronson, N. K., May, A. M., & Stuiver, M. M. (2022). Physical fitness and chemotherapy tolerance in patients with early-stage breast cancer. Medicine & Science in Sports & Exercise, 54 (4), 537–542. 10.1249/mss.0000000000002828

16. Buijs, C., De Vries, E. G. E., Mourits, M. J. E., & Willemse, P. H. B. (2008). The influence of endocrine treatments for breast cancer on health-related quality of life. Cancer Treatment Reviews, 34 (7), 640–655. 10.1016/j.ctrv.2008.04.001

17. Schapira, M. M., Lawrence, W. F., Katz, D. A., McAuliffe, T. L., & Nattinger, A. B. (2001). Effect of treatment on quality of life among men with clinically localized prostate cancer. Medical care , 243–253. SCImago. SJR — SCImago Journal & Country Rank [Portal] . Retrieved 04/09/2023 from http://www.scimagojr.com

18. Sloan, J. A., Liu, H., Satele, D. V., Puttabasavaiah, S., Kaur, J. S., Hubbard, J., Dueck, A., Stella, P. J., & Singh, J. A. (2017). Prognostic significance of baseline fatigue for overall survival: A patient-level meta-analysis of 43 oncology clinical trials with 3915 patients. Trends in Cancer Research, 12 , 97–110.

19. Lee, Y.-H., Bang, H., & Kim, D. J. (2016). How to establish clinical prediction models. Endocrinology and Metabolism, 31 (1), 38. 10.3803/enm.2016.31.1.38

20. Snell, K. I. E., Levis, B., Damen, J. A. A., Dhiman, P., Debray, T. P. A., Hooft, L., Reitsma, J. B., Moons, K. G. M., Collins, G. S., & Riley, R. D. (2023). Transparent reporting of multivariable prediction models for individual prognosis or diagnosis: Checklist for systematic reviews and meta-analyses (TRIPOD-SRMA). BMJ, 381 , e073538. 10.1136/bmj-2022-073538

21. Geersing, G. J., Bouwmeester, W., Zuithoff, P., Spijker, R., Leeflang, M., & Moons, K. (2012). Search filters for finding prognostic and diagnostic prediction studies in medline to enhance systematic reviews. PLoS ONE, 7 (2), e32844. 10.1371/journal.pone.0032844

22. Ouzzani, M., Hammady, H., Fedorowicz, Z., & Elmagarmid, A. (2016). Rayyan—A web and mobile app for systematic reviews. Systematic Reviews . 10.1186/s13643-016-0384-4

23. Collins, G. S., Reitsma, J. B., Altman, D. G., & Moons, K. G. (2015). Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD Statement. BMC Medicine, 13 , 1. 10.1186/s12916-014-0241-z

24. Wolff, R. F., Moons, K. G. M., Riley, R. D., Whiting, P. F., Westwood, M., Collins, G. S., Reitsma, J. B., Kleijnen, J., & Mallett, S. (2019). PROBAST: A tool to assess the risk of bias and applicability of prediction model studies. Annals of Internal Medicine, 170 (1), 51. 10.7326/m18-1376

25. Quintana, J. M., Anton-Ladislao, A., Lázaro, S., Gonzalez, N., Bare, M., Fernandez-de-Larrea, N., Redondo, M., Escobar, A., Sarasqueta, C., Garcia-Gutierrez, S., & Aguirre, U. (2022). Effect of comorbidities on long-term outcomes of colorectal cancer patients. European Journal of Cancer Care, 31 (2), e13561. 10.1111/ecc.13561

26. Shallwani, S. M., Simmonds, M. J., Kasymjanova, G., & Spahija, J. (2016). Quality of life, symptom status and physical performance in patients with advanced non-small cell lung cancer undergoing chemotherapy: An exploratory analysis of secondary data. Lung cancer (Amsterdam, Netherlands), 99 , 69–75. 10.1016/j.lungcan.2016.06.018

27. Yue, J., Shi, Q., Xu, T., Jeter, M., Chen, T. Y., Komaki, R., Gomez, D. R., Pan, T., Cleeland, C. S., Liao, Z., & Wang, X. S. (2018). Patient-reported lung symptoms as an early signal of impending radiation pneumonitis in patients with non-small cell lung cancer treated with chemoradiation: An observational study. Quality of Life Research, 27 (6), 1563–1570. 10.1007/s11136-018-1834-3

28. Akthar, A. S., Liao, C., Eggener, S. E., & Liauw, S. L. (2019). Patient-reported outcomes and late toxicity after postprostatectomy intensity-modulated radiation therapy. European Urology, 76 (5), 686–692. 10.1016/j.eururo.2019.05.011

29. Azad, A. D., Yilmaz, M., Bozkurt, S., Brooks, J. D., Blayney, D. W., & Hernandez-Boussard, T. (2021). Diverse patient trajectories during cytotoxic chemotherapy: Capturing longitudinal patient-reported outcomes. Cancer Medicine, 10 (17), 5783–5793. 10.1002/cam4.4124

30. Braamse, A. M. J., Yi, J. C., Visser, O. J., Heymans, M. W., van Meijel, B., Dekker, J., & Syrjala, K. L. (2016). Developing a risk prediction model for long-term physical and psychological functioning after hematopoietic cell transplantation. Biology of Blood and Marrow Transplantation, 22 (3), 549–556. 10.1016/j.bbmt.2015.11.1102

31. Casares-Magaz, O., Muren, L. P., Moiseenko, V., Petersen, S. E., Pettersson, N. J., Høyer, M., Deasy, J. O., & Thor, M. (2017). Spatial rectal dose/volume metrics predict patient-reported gastro-intestinal symptoms after radiotherapy for prostate cancer. Acta Oncologica, 56 (11), 1507–1513. 10.1080/0284186X.2017.1370130

32. Cozzarini, C., Rancati, T., Palorini, F., Avuzzi, B., Garibaldi, E., Balestrini, D., Cante, D., Munoz, F., Franco, P., Girelli, G., Sini, C., Vavassori, V., Valdagni, R., & Fiorino, C. (2017). Patient-reported urinary incontinence after radiotherapy for prostate cancer: Quantifying the dose–effect. Radiotherapy and Oncology, 125 (1), 101–106. 10.1016/j.radonc.2017.07.029

33. Jensen, N. B., Pötter, R., Spampinato, S., Fokdal, L. U., Chargari, C., Lindegaard, J. C., Schmid, M. P., Sturdza, A., Jürgenliemk-Schulz, I. M., Mahantshetty, U., & Segedin, B. (2021). Dose-volume effects and risk factors for late diarrhea in cervix cancer patients after radiochemotherapy with image guided adaptive brachytherapy in the EMBRACE I study. International Journal of Radiation Oncology Biology Physics, 109 (3), 688–700.

34. Pan, X., Levin-Epstein, R., Huang, J., Ruan, D., King, C. R., Kishan, A. U., Steinberg, M. L., & Qi, X. S. (2020). Dosimetric predictors of patient-reported toxicity after prostate stereotactic body radiotherapy: Analysis of full range of the dose-volume histogram using ensemble machine learning. Radiotherapy and Oncology: Journal of the European Society for Therapeutic Radiology and Oncology, 148 , 181–188. 10.1016/j.radonc.2020.04.013

35. Alibhai, S. M. H., Breunis, H., Matelski, J., Timilshina, N., Kundra, A., Lee, C. H., & Li, M. (2020). Age-related cytokine effects on cancer-related fatigue and quality of life in acute myeloid leukemia. Journal of Geriatric Oncology, 11 (3), 402–409. 10.1016/j.jgo.2019.04.009

36. Friis, R. B., Hjøllund, N. H., Pappot, H., Taarnhøj, G. A., Vestergaard, J. M., & Skuladottir, H. (2021). Patient-reported outcome measures used in routine care predict for survival at disease progression in patients with advanced lung cancer. Clinical Lung Cancer, 22 (2), e169–e179. 10.1016/j.cllc.2020.09.014

37. Haraldseide, L. M., Jakola, A. S., Solheim, O., & Sagberg, L. M. (2020). Does preoperative health-related quality of life predict survival in high-grade glioma patients?—A prospective study. British Journal of Neurosurgery, 34 (1), 28–34. 10.1080/02688697.2019.1698011

38. Vickers, M. M., Lee, C., Tu, D., Wheatley-Price, P., Parulekar, W., Brundage, M. D., Moore, M. J., Au, H., O’Callaghan, C. J., Jonker, D. J., Ringash, J., & Goldstein, D. (2016). Significance of baseline and change in quality of life scores in predicting clinical outcomes in an international phase III trial of advanced pancreatic cancer: NCIC CTG PA3. Pancreatology: Official Journal of the International Association of Pancreatology, 16 (6), 1106–1112. 10.1016/j.pan.2016.08.013

39. Pfob, A., Mehrara, B. J., Nelson, J. A., Wilkins, E. G., Pusic, A. L., & Sidey-Gibbons, C. (2023). Towards patient-centered decision-making in breast cancer surgery: Machine learning to predict individual patient-reported outcomes at 1-year follow-up. Annals of Surgery . 10.1097/sla.0000000000004862

40. Dess, R. T., Hartman, H. E., Aghdam, N., Jackson, W. C., Soni, P. D., Abugharib, A. E., Suy, S., Desai, N. B., Zumsteg, Z. S., Mehra, R., Morgan, T. M., Feng, F. Y., Hamstra, D. A., Schipper, M. J., Collins, S. P., & Spratt, D. E. (2018). Erectile function after stereotactic body radiotherapy for localized prostate cancer. BJU International, 121 (1), 61–68. 10.1111/bju.13962

41. Brown, S. L., Hope-Stone, L., Heimann, H., Damato, B., & Salmon, P. (2018). Predictors of anxiety and depression 2 years following treatment in uveal melanoma survivors. Psycho-Oncology, 27 (7), 1727–1734. 10.1002/pon.4715

42. Oberguggenberger, A., Meraner, V., Sztankay, M., Hilbert, A., Hubalek, M., Holzner, B., Gamper, E., Kemmler, G., Baumgartner, T., Lackinger, I., Sperner-Unterweger, B., & Mangweth-Matzek, B. (2018). Health behavior and quality of life outcome in breast cancer survivors: Prevalence rates and predictors. Clinical Breast Cancer, 18 (1), 38–44. 10.1016/j.clbc.2017.09.008

43. Misra, S., Lee, G., Korzets, Y., Wang, L., Lau, A., Koch, C. A., Croke, J., & Helou, J. (2020). Patient-reported acute fatigue in elderly breast cancer patients treated with and without regional nodal radiation. Breast Cancer Research and Treatment, 183 (2), 391–401. 10.1007/s10549-020-05781-5

44. Ljungman, L., Eriksson, L. E., Flynn, K. E., Gorman, J. R., Ståhl, O., Weinfurt, K., Wiklander, M., Lampic, C., & Wettergren, L. (2019). Sexual dysfunction and reproductive concerns in young men diagnosed with testicular cancer: An observational study. The Journal of Sexual Medicine, 16 (7), 1049–1059. 10.1016/j.jsxm.2019.05.005

45. Ha, D., & Ries, A. L. (2020). Characterization of Dyspnea in veteran lung cancer survivors following curative-intent therapy. Journal of Cardiopulmonary Rehabilitation and Prevention, 40 (2), 120–127. 10.1097/HCR.0000000000000464

46. Wang, Y., Van Dijk, L., Mohamed, A. S. R., Fuller, C. D., Zhang, X., Marai, G. E., & Canahuate, G. (2021). Predicting late symptoms of head and neck cancer treatment using LSTM and patient reported outcomes. Proceedings International Database Engineering and Applications Symposium, 2021 , 273–279. 10.1145/3472163.3472177

47. Lee, S., Deasy, J. O., Oh, J. H., Di Meglio, A., Dumas, A., Menvielle, G., Charles, C., Boyault, S., Rousseau, M., Besse, C., Thomas, E., Boland, A., Cottu, P., Tredan, O., Levy, C., Martin, A. L., Everhard, S., Ganz, P. A., Partridge, A. H., … Vaz-Luis, I. (2020). Prediction of breast cancer treatment–induced fatigue by machine learning using genome-wide association data. JNCI Cancer Spectrum . 10.1093/jncics/pkaa039

48. Révész, D., van Kuijk, S. M. J., Mols, F., van Duijnhoven, F. J. B., Winkels, R. M., Kant, I., van den Brandt, P. A., Smits, L. J., Breukink, S. O., Kampman, E., Beijer, S., Weijenberg, M. P., & Bours, M. J. L. (2022). External validation and updating of prediction models for estimating the 1-year risk of low health-related quality of life in colorectal cancer survivors. Journal of Clinical Epidemiology, 152 , 127–139. 10.1016/j.jclinepi.2022.09.019

49. Walming, S., Asplund, D., Bock, D., Gonzalez, E., Rosenberg, J., Smedh, K., & Angenete, E. (2020). Quality of life in patients with resectable rectal cancer during the first 24 months following diagnosis. Colorectal Disease: The Official Journal of the Association of Coloproctology of Great Britain and Ireland., 22 (12), 2028–2037. 10.1111/codi.15343

50. Battersby, N. J., Bouliotis, G., Emmertsen, K. J., Juul, T., Glynne-Jones, R., Branagan, G., Christensen, P., Laurberg, S., & Moran, B. J. (2018). Development and external validation of a nomogram and online tool to predict bowel dysfunction following restorative rectal cancer resection: The POLARS score. Gut, 67 (4), 688–696. 10.1136/gutjnl-2016-312695

51. Jacobs, M., Anderegg, M. C., Schoorlemmer, A., Nieboer, D., Steyerberg, E. W., Smets, E. M., Sprangers, M. A., van Berge Henegouwen, M. I., de Haes, J. C., & Klinkenbijl, J. H. (2017). Patients with oesophageal cancer report elevated distress and problems yet do not have an explicit wish for referral prior to receiving their medical treatment plan. Psycho-Oncology, 26 (4), 452–460. 10.1002/pon.4161

52. Hawkins, P. G., Lee, J. Y., Mao, Y., Li, P., Green, M., Worden, F. P., Swiecicki, P. L., Mierzwa, M. L., Spector, M. E., Schipper, M. J., & Eisbruch, A. (2018). Sparing all salivary glands with IMRT for head and neck cancer: Longitudinal study of patient-reported xerostomia and head-and-neck quality of life. Radiotherapy and Oncology: Journal of the European Society for Therapeutic Radiology and Oncology, 126 (1), 68–74. 10.1016/j.radonc.2017.08.002

53. Pfob, A., Mehrara, B. J., Nelson, J. A., Wilkins, E. G., Pusic, A. L., & Sidey-Gibbons, C. (2021). Machine learning to predict individual patient-reported outcomes at 2-year follow-up for women undergoing cancer-related mastectomy and breast reconstruction (INSPiRED-001). Breast (Edinburgh, Scotland), 60 , 111–122. 10.1016/j.breast.2021.09.009

54. Montroni, I., Ugolini, G., Saur, N. M., Rostoft, S., Spinelli, A., Van Leeuwen, B. L., De Liguori, C. N., Ghignone, F., Jaklitsch, M. T., Somasundar, P., & Garutti, A. (2022). Quality of life in older adults after major cancer surgery: The GOSAFE international study. JNCI: Journal of the National Cancer Institute, 114 (7), 969–978.

55. Fosså, S. D., Dahl, A. A., Thorsen, L., Hellesnes, R., Kiserud, C. E., Tandstad, T., Brydøy, M., Haugnes, H. S., & Myklebust, T. Å. (2022). Mortality and second cancer incidence after treatment for testicular cancer: Psychosocial health and lifestyle are modifiable prognostic factors. Journal of Clinical Oncology, 40 (23), 2588–2599. 10.1200/jco.21.02105

56. Badr, H., Sobrero, M., Chen, J., Kotz, T., Genden, E., Sikora, A. G., & Miles, B. (2019). Associations between pre-, post-, and peri-operative variables and health resource use following surgery for head and neck cancer. Oral Oncology, 90 , 102–108. 10.1016/j.oraloncology.2019.02.004

57. Beeler, W. H., Bellile, E. L., Casper, K. A., Jaworski, E., Burger, N. J., Malloy, K. M., Spector, M. E., Shuman, A. G., Rosko, A., Stucken, C. L., Chinn, S. B., Dragovic, A. F., Chapman, C. H., Owen, D., Jolly, S., Bradford, C. R., Prince, M. E. P., Worden, F. P., Jagsi, R., … Swiecicki, P. L. (2020). Patient-reported financial toxicity and adverse medical consequences in head and neck cancer. Oral Oncology, 101 , 104521. 10.1016/j.oraloncology.2019.104521

58. Hopkins, A. M., Wagner, J., Kichenadasse, G., Modi, N., Rowland, A., & Sorich, M. J. (2020). Patient-reported outcomes as a prognostic marker of survival in patients with advanced nonsmall cell lung cancer treated with immunotherapy. International Journal of Cancer, 147 (11), 3085–3089. 10.1002/ijc.33133

59. Geerse, O. P., Brandenbarg, D., Kerstjens, H. A. M., Berendsen, A. J., Duijts, S. F. A., Burger, H., Holtman, G. A., Hoekstra-Weebers, J., & Hiltermann, T. J. N. (2019). The distress thermometer as a prognostic tool for one-year survival among patients with lung cancer. Lung Cancer (Amsterdam, Netherlands), 130 , 101–107. 10.1016/j.lungcan.2019.02.008

60. Iivanainen, S., Ekstrom, J., Virtanen, H., Kataja, V. V., & Koivunen, J. P. (2021). Electronic patient-reported outcomes and machine learning in predicting immune-related adverse events of immune checkpoint inhibitor therapies. BMC Medical Informatics & Decision Making, 21 (1), 1–8. 10.1186/s12911-021-01564-0

61. Versteegh, M., van der Helm, I., Mokri, H., Oerlemans, S., Blommestein, H., & van Baal, P. (2022). Estimating quality of life decrements in oncology using time to death. Value in Health, 25 (10), 1673–1677. 10.1016/j.jval.2022.06.002

62. Roncolato, F. T., Gibbs, E., Lee, C. K., Asher, R., Davies, L. C., Gebski, V. J., Friedlander, M., Hilpert, F., Wenzel, L., Stockler, M. R., King, M., & Pujade-Lauraine, E. (2017). Quality of life predicts overall survival in women with platinum-resistant ovarian cancer: An AURELIA substudy. Annals of oncology: Official journal of the European Society for Medical Oncology, 28 (8), 1849–1855. 10.1093/annonc/mdx229

63. Huang, H., Datye, A., Fan, M., Knapp, A., Nielsen, T., Bottos, A., Paulson, J. N., Trask, P. C., & Efficace, F. (2022). Patient-reported outcomes provide prognostic information for survival in patients with diffuse large B-cell lymphoma: Analysis of 1239 patients from the GOYA study. Cancer Medicine, 11 (17), 3312–3322. 10.1002/cam4.4692

64. Badaoui, S., Shahnam, A., McKinnon, R. A., Abuhelwa, A. Y., Sorich, M. J., & Hopkins, A. M. (2022). The predictive utility of patient-reported outcomes and performance status for survival in metastatic lung cancer patients treated with chemoimmunotherapy. Translational Lung Cancer Research, 11 (3), 432.

65. Bhandari, N. R., Kamel, M. H., Kent, E. E., McAdam-Marx, C., Ounpraseuth, S. T., Tilford, J. M., & Payakachat, N. (2021). Association of health-related quality of life with overall survival in older americans with kidney cancer: A population-based cohort study. Healthcare . 10.3390/healthcare9101344

66. Atkinson, T. M., Schwartz, C. E., Goldstein, L., Garcia, I., Storfer, D. F., Li, Y., Zhang, J., Bochner, B. H., & Rapkin, B. D. (2019). Perceptions of response burden associated with completion of patient-reported outcome assessments in oncology. Value in Health, 22 (2), 225–230. 10.1016/j.jval.2018.07.875

67. Armbrust, R., Richter, R., Woopen, H., Hilpert, F., Harter, P., & Sehouli, J. (2021). Impact of health-related quality of life (HRQoL) on short-term mortality in patients with recurrent ovarian, fallopian or peritoneal carcinoma (the NOGGO-AGO QoL Prognosis-Score-Study): Results of a meta-analysis in 2209 patients. ESMO Open, 6 (2), 100081. 10.1016/j.esmoop.2021.100081

68. Astrup, G. L., Rustøen, T., Miaskowski, C., Paul, S. M., & Bjordal, K. (2015). Changes in and predictors of pain characteristics in patients with head and neck cancer undergoing radiotherapy. Pain, 156 (5), 967–979. 10.1097/j.pain.0000000000000142

69. Hansen, M. B., Nylandsted, L. R., Petersen, M. A., Adsersen, M., Rojas-Concha, L., & Groenvold, M. (2020). Patient-reported symptoms and problems at admission to specialized palliative care improved survival prediction in 30,969 cancer patients: A nationwide register-based study. Palliative Medicine, 34 (6), 795–805. 10.1177/0269216320908488

70. Heiman, J., Pavia, J., Bock, D., Haglind, E., & Olofsson Bagge, R. (2023). Sick leave and predictive factors for sick leave at 12 months after breast cancer surgery in the randomized controlled physical activity trial (PhysSURG-B). The Surgeon: Journal of the Royal Colleges of Surgeons of Edinburgh and Ireland . 10.1016/j.surge.2022.12.001

71. Kargo, A. S., Jensen, P. T., Lindemann, K., Hjøllund, N. H., Liposits, G. I., Raaschou-Jensen, N., Knudsen, B. M., Möller, S., Hansen, D. G., & Steffensen, K. D. (2021). Association of patient-reported outcomes and ovarian cancer recurrence. International journal of gynecological cancer : Official journal of the International Gynecological Cancer Society, 31 (9), 1248–1259. 10.1136/ijgc-2021-002550

72. Quintana, J. M., Antón-Ladisla, A., González, N., Lázaro, S., Baré, M., Fernández de Larrea, N., Redondo, M., Briones, E., Escobar, A., Sarasqueta, C., García-Gutierrez, S., Quintana López, J. M., Mañas, M. B., Bautista, M. R., Pérez de la Blanca, E. B., de Larrea, F., Baz, N., Eizaguirre, C. S., Martínez, A. E., … Mar, J. (2018). Outcomes of open versus laparoscopic surgery in patients with colon cancer. European Journal of Surgical Oncology, 44 (9), 1344–1353. 10.1016/j.ejso.2018.05.030

73. Quintana, J. M., Anton-Ladislao, A., Lázaro, S., Gonzalez, N., Bare, M., de Larrea, N. F., Redondo, M., Briones, E., Escobar, A., Sarasqueta, C., & Garcia-Gutierrez, S. (2018). Outcomes of open versus laparoscopic surgery in patients with rectal cancer. International Journal of Colorectal Disease, 33 (1), 99–103. 10.1007/s00384-017-2925-2

74. Quinten, C., Kenis, C., Decoster, L., Debruyne, P. R., De Groof, I., Focan, C., Cornelis, F., Verschaeve, V., Bachmann, C., Bron, D., Luce, S., Debugne, G., Van den Bulck, H., Goeminne, J. C., Schrijvers, D., Geboers, K., Petit, B., Langenaeken, C., Van Rijswijk, R., … Wildiers, H. (2020). The prognostic value of patient-reported health-related quality of life and geriatric assessment in predicting early death in 6769 older (≥70 years) patients with different cancer tumors. Journal of Geriatric Oncology, 11 (6), 926–936. 10.1016/j.jgo.2020.03.017

75. Rees, J. R., Rees, M., McNair, A. G., Odondi, L. O., Metcalfe, C., John, T., Welsh, F. K., & Blazeby, J. M. (2016). The prognostic value of patient-reported outcome data in patients with colorectal hepatic metastases who underwent surgery. Clinical Colorectal Cancer, 15 (1), 74–81.

76. Tohme, S., Sanin, G. D., Patel, V., Bress, K., Ahmed, N., Krane, A., Tsung, A., & Steel, J. L. (2020). Health-related quality of life as a prognostic factor in patients after resection of hepatic malignancies. The Journal of Surgical Research, 245 , 257–264. 10.1016/j.jss.2019.07.061

77. Trejo, M. J., Bell, M. L., Dhillon, H. M., & Vardy, J. L. (2020). Baseline quality of life is associated with survival among people with advanced lung cancer (Vol. 38). Taylor & Francis Ltd. 10.1080/07347332.2020.1765065

78. Gawryszuk, A., Bijl, H. P., van der Schaaf, A., Perdok, N., Wedman, J., Verdonck-de Leeuw, I. M., Rinkel, R. N., Steenbakkers, R., van den Hoek, J. G. M., van der Laan, H. P., & Langendijk, J. A. (2021). Relationship between videofluoroscopic and subjective (physician- and patient- rated) assessment of late swallowing dysfunction after (chemo) radiation: Results of a prospective observational study. Radiotherapy and Oncology : Journal of the European Society for Therapeutic Radiology and Oncology, 164 , 253–260. 10.1016/j.radonc.2021.09.017

79. Aamdal, E., Skovlund, E., Jacobsen, K. D., Straume, O., Kersten, C., Herlofsen, O., Karlsen, J., Hussain, I., Amundsen, A., Dalhaug, A., & Nyakas, M. (2022). Health-related quality of life in patients with advanced melanoma treated with ipilimumab: Prognostic implications and changes during treatment. ESMO Open, 7 (5), 100588.

80. Hamers, P. A. H., Wensink, G. E., van Smeden, M., Vink, G. R., Smabers, L. P., Lunenberg, R. A., Laclé, M. M., Koopman, M., May, A. M., & Roodhart, J. M. L. (2022). External validation of the colon life nomogram for predicting 12-week mortality in dutch metastatic colorectal cancer patients treated with trifluridine/tipiracil in daily practice. Cancers . 10.3390/cancers14205094

81. Pompili, C., Dalmia, S., McLennan Battleday, F., Rogers, Z., Absolom, K., Bekker, H., Franks, K., Brunelli, A., & Velikova, G. (2022). Factors influencing patient satisfaction after treatments for early-stage non-small cell lung cancer. Journal of Cancer Research and Clinical Oncology, 148 (9), 2447–2454. 10.1007/s00432-021-03795-0

82. Zhou, K., Bellanger, M., Le Lann, S., Robert, M., Frenel, J. S., & Campone, M. (2022). The predictive value of patient-reported outcomes on the impact of breast cancer treatment-related quality of life. Frontiers in Oncology, 12 , 925534. 10.3389/fonc.2022.925534

83. Efficace, F., Cottone, F., Abel, G., Niscola, P., Gaidano, G., Bonnetain, F., Anota, A., Caocci, G., Cronin, A., Fianchi, L., Breccia, M., Stauder, R., Platzbecker, U., Palumbo, G. A., Luppi, M., Invernizzi, R., Bergamaschi, M., Borin, L., Di Tucci, A. A., & Zhang, H. (2018). Patient-reported outcomes enhance the survival prediction of traditional disease risk classifications: An international study in patients with myelodysplastic syndromes. Cancer, 124 (6), 1251–1259. 10.1002/cncr.31193

84. Mackay, T. M., Latenstein, A. E. J., Sprangers, M. A. G., van der Geest, L. G., Creemers, G. J., van Dieren, S., de Groot, J. B., Groot Koerkamp, B., de Hingh, I. H., Homs, M. Y. V., de Jong, E. J. M., Molenaar, I. Q., Patijn, G. A., van de Poll-Franse, L. V., van Santvoort, H. C., de Vos-Geelen, J., Wilmink, J. W., van Eijck, C. H., Besselink, M. G., & van Laarhoven, H. W. M. (2020). Relationship between quality of life and survival in patients with pancreatic and periampullary cancer: A multicenter cohort analysis. Journal of the National Comprehensive Cancer Network: JNCCN, 18 (10), 1354–1363. 10.6004/jnccn.2020.7579

85. Mihalcik, S. A., Chipman, J. J., Sanda, M. G., Regan, M. M., Kaplan, I. D., Wagner, A. A., Crociani, C. M., & Chang, P. (2018). Predicting erectile function following external beam radiation therapy or brachytherapy for prostate cancer using EPIC-CP. Practical Radiation Oncology, 8 (6), 445–451. 10.1016/j.prro.2018.04.007

86. Brown, S. L., Fisher, P. L., Hope-Stone, L., Heimann, H., Hussain, R., & Cherry, M. G. (2022). Prediction of all-cause mortality from 24 month trajectories in patient-reported psychological, clinical and quality of life outcomes in uveal melanoma patients. Journal of Behavioral Medicine, 45 (1), 115–123.

87. van Kleef, J. J., Dijksterhuis, W. P. M., van den Boorn, H. G., Prins, M., Verhoeven, R. H. A., Gisbertz, S. S., Slingerland, M., Mohammad, N. H., Creemers, G. J., Neelis, K. J., Heisterkamp, J., Rosman, C., Ruurda, J. P., Kouwenhoven, E. A., van de Poll-Franse, L. V., van Oijen, M. G. H., Sprangers, M. A. G., & van Laarhoven, H. W. M. (2021). Prognostic value of patient-reported quality of life for survival in oesophagogastric cancer: Analysis from the population-based POCOP study. Gastric Cancer: Official Journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association, 24 (6), 1203–1212. 10.1007/s10120-021-01209-1

88. Sim, J. A., Kim, Y. A., Kim, J. H., Lee, J. M., Kim, M. S., Shim, Y. M., Zo, J. I., & Yun, Y. H. (2020). The major effects of health-related quality of life on 5-year survival prediction among lung cancer survivors: Applications of machine learning. Scientific Reports, 10 (1), 10693. 10.1038/s41598-020-67604-3

89. Bernhard, J., Dietrich, D., Glimelius, B., Bodoky, G., Scheithauer, W., & Herrmann, R. (2014). Clinical benefit response in pancreatic cancer trials revisited. Oncology Research and Treatment, 37 (1), 42–48. 10.1159/000357965

90. Dubois, D., Dhawan, R., van de Velde, H., Esseltine, D., Gupta, S., Viala, M., & de la Loge, C. (2006). Descriptive and prognostic value of patient-reported outcomes: The bortezomib experience in relapsed and refractory multiple myeloma. Journal of clinical oncology : Official journal of the American Society of Clinical Oncology, 24 (6), 976–982. 10.1200/jco.2005.04.0824

91. Badaoui, S., Kichenadasse, G., Rowland, A., Sorich, M. J., & Hopkins, A. M. (2021). Patient-reported outcomes predict progression-free survival of patients with advanced breast cancer treated with Abemaciclib. The Oncologist, 26 (7), 562–568. 10.1002/onco.13806

92. Creutzfeldt, A., Suling, A., Oechsle, K., Mehnert, A., Atanackovic, D., Kripp, M., Arnold, D., Stein, A., & Quidd, J. (2016). Integrating patient reported measures as predictive parameters into decisionmaking about palliative chemotherapy: A pilot study. BMC Palliative Care, 15 , 1–9. 10.1186/s12904-016-0101-z

93. Baekelandt, B. M., Hjermstad, M. J., Nordby, T., Fagerland, M. W., Kure, E. H., Heiberg, T., Buanes, T., & Labori, K. J. (2016). Preoperative cognitive function predicts survival in patients with resectable pancreatic ductal adenocarcinoma. HPB: The official journal of the International Hepato Pancreato Biliary Association, 18 (3), 247–254. 10.1016/j.hpb.2015.09.004

94. Röttgering, J. G., Belgers, V., De Witt Hamer, P. C., Knoop, H., Douw, L., & Klein, M. (2022). Toward unraveling the correlates of fatigue in glioma. Neuro-Oncology Advances . 10.1093/noajnl/vdac169

95. Agarwal, J. P., Chakraborty, S., Laskar, S. G., Mummudi, N., Patil, V. M., Prabhash, K., Noronha, V., Purandare, N., Joshi, A., Tandon, S., Arora, J., & Badhe, R. (2017). Prognostic value of a patient-reported functional score versus physician-reported Karnofsky performance status score in brain metastases. Ecancermedicalscience, 11 , 779. 10.3332/ecancer.2017.779

96. Howdon, D., van den Hout, W., van der Linden, Y., & Spencer, K. (2022). Replacing performance status with a simple patient-reported outcome in palliative radiotherapy prognostic modelling. Clinical and Translational Radiation Oncology, 37 , 137–144. 10.1016/j.ctro.2022.09.008

97. Tan, E., Abuhelwa, A. Y., Badaoui, S., Modi, N. D., Wiese, M. D., McKinnon, R. A., Sorich, M. J., & Hopkins, A. M. (2022). Association between patient-reported outcomes and survival in patients with advanced urothelial carcinoma treated with Atezolizumab. Bladder Cancer, 8 (1), 81–88. 10.3233/BLC-211613

98. Barney, B. J., Wang, X. S., Lu, C., Liao, Z., Johnson, V. E., Cleeland, C. S., & Mendoza, T. R. (2013). Prognostic value of patient-reported symptom interference in patients with late-stage lung cancer. Quality of Life Research, 22 (8), 2143–2150. 10.1007/s11136-013-0356-2

99. Viala, M., Bhakar, A. L., de la Loge, C., van de Velde, H., Esseltine, D., Chang, M., Dhawan, R., & Dubois, D. (2007). Patient-reported outcomes helped predict survival in multiple myeloma using partial least squares analysis. Journal of Clinical Epidemiology, 60 (7), 670–679. 10.1016/j.jclinepi.2006.10.006

100. Llewellyn, C. D., Horney, D. J., McGurk, M., Weinman, J., Herold, J., Altman, K., & Smith, H. E. (2013). Assessing the psychological predictors of benefit finding in patients with head and neck cancer. Psycho-Oncology, 22 (1), 97–105. 10.1002/pon.2065

101. Balazard, F., Bertaut, A., Bordet, É., Mulard, S., Blanc, J., Briot, N., Paux, G., Dhaini Merimeche, A., Rigal, O., Coutant, C., Fournier, M., Jouannaud, C., Soulie, P., Lerebours, F., Cottu, P. H., Tredan, O., Vanlemmens, L., Levy, C., Mouret-Reynier, M. A., … Pistilli, B. (2023). Adjuvant endocrine therapy uptake, toxicity, quality of life, and prediction of early discontinuation. Journal of the National Cancer Institute, 115 (9), 1099–1108. 10.1093/jnci/djad109

102. Baskin, A., Cowan, J. E., Braun, A., Lonergan, P. E., Mohamad, O., Washington, S. L., Zhao, S., Broering, J. M., Cooperberg, M. R., Breyer, B. N., & Carroll, P. R. (2023). Long-term complications and health-related quality of life outcomes after radical prostatectomy with or without subsequent radiation treatment for prostate cancer. Urologic Oncology: Seminars and Original Investigations, 41 (10), 429.e429-429.e414. 10.1016/j.urolonc.2023.06.003

103. Borg, M. A., O’Callaghan, M. E., Moretti, K. L., & Vincent, A. D. (2024). External validation of predictive models of sexual, urinary, bowel and hormonal function after surgery in prostate cancer subjects. BMC Urology, 24 (1), 2. 10.1186/s12894-023-01373-9

104. McGarrah, P., Hubbard, J., Novotny, P. J., Branda, M. E., Sargent, D. S., Morton, R. F., Fuchs, C. S., Benson, A. B., Williamson, S. K., Findlay, B. P., Alberts, S. R., Goldberg, R. M., & Sloan, J. A. (2023). Baseline quality of life is a strong and independent prognostic factor for overall survival in metastatic colorectal cancer. Cancer Control, 30 , 10732748231185048. 10.1177/10732748231185047

105. De Henau, M., Van Kuijk, S. M. J., Colla, C., Van Den Kerckhove, E., Van Der Hulst, R. R. W. J., & Piatkowski, A. (2023). Pressure masks for facial scar treatment after oncological reconstruction: Long-term patient satisfaction and quality of life [Article]. Facial Plastic Surgery, 40 (1), 36–45. 10.1055/a-2035-4468

106. Deutsch, T. M., Pfob, A., Brusniak, K., Riedel, F., Bauer, A., Dijkstra, T., Engler, T., Brucker, S. Y., Hartkopf, A. D., Schneeweiss, A., Sidey-Gibbons, C., & Wallwiener, M. (2023). Machine learning and patient-reported outcomes for longitudinal monitoring of disease progression in metastatic breast cancer: A multicenter, retrospective analysis. European Journal of Cancer, 188 , 111–121. 10.1016/j.ejca.2023.04.019

107. Dorr, M. C., Sewnaik, A., Andrinopoulou, E., Berzenji, D., Dronkers, E. A. C., Bernard, S. E., Hoesseini, A., Tans, L., Rizopoulos, D., Baatenburg de Jong, R. J., & Offerman, M. P. J. (2023). Longitudinal patient-reported voice quality in early-stage glottic cancer. Otolaryngology Head and Neck Surgery, 168 (6), 1463–1471. 10.1002/ohn.263

108. Dorr, M. C., Andrinopoulou, E. R., Sewnaik, A., Berzenji, D., van Hof, K. S., Dronkers, E. A. C., Bernard, S. E., Hoesseini, A., Rizopoulos, D., Baatenburg de Jong, R. J., & Offerman, M. P. J. (2024). Individualized dynamic prediction model for patient-reported voice quality in early-stage glottic cancer. Otolaryngology Head and Neck Surgery Official Journal of American Academy of Otolaryngology-Head and Neck Surgery, 170 (1), 169–178. 10.1002/ohn.479

109. Harris, J., Purssell, E., Cornelius, V., Ream, E., Jones, A., & Armes, J. (2020). Development and internal validation of a predictive risk model for anxiety after completion of treatment for early stage breast cancer. Journal of Patient-Reported Outcomes, 4 (1), 1–9. 10.1186/s41687-020-00267-w

110. Hasannejadasl, H., Roumen, C., van der Poel, H., Vanneste, B., van Roermund, J., Aben, K., Kalendralis, P., Osong, B., Kiemeney, L., Van Oort, I., Verwey, R., Hochstenbach, L., Bloemen- van Gurp, E. J., Dekker, A., & Fijten, R. R. R. (2023). Development and external validation of multivariate prediction models for erectile dysfunction in men with localized prostate cancer. PLoS ONE, 18 (3), e0276815. 10.1371/journal.pone.0276815

111. Huang, S., Tang, Y., Wu, H., Shi, Q., Tang, J., Ben, X., Zhang, D., Xie, L., Zhou, H., Chen, G., Wang, S., Gao, Z., Xie, Z., Chen, R., & Qiao, G. (2023). Early and persistent dysphagia relief predicts tumor response in esophageal squamous cell carcinoma patients treated with immunochemotherapy. Annals of Surgical Oncology, 30 (8), 5171–5181. 10.1245/s10434-023-13467-7

112. Huberts, A. S., Clarijs, M. E., Pastoor, H., van Rosmalen, M., & Koppert, L. B. (2023). Sexual well-being in patients with early-stage breast cancer at 1- and 2-year follow-up. The Journal of Sexual Medicine . 10.1093/jsxmed/qdad007

113. Lazarewicz, M. A., Wlodarczyk, D., & Johansen Reidunsdatter, R. (2023). Decision tree analyses for prediction of QoL over a one-year period in breast cancer patients: An added value of patient-reported outcomes. Cancers, 15 (9), 2474. 10.3390/cancers15092474

114. Orive, M., Barrio, I., Lázaro, S., Gonzalez, N., Bare, M., de Larrea, N. F., Redondo, M., Cortajarena, S., Bilbao, A., Aguirre, U., Sarasqueta, C., & Quintana, J. M. (2023). Five-year follow-up mortality prognostic index for colorectal patients. International Journal of Colorectal Disease, 38 (1), 64. 10.1007/s00384-023-04358-0

115. Paetkau, O., Weppler, S., Kwok, J., Quon, H. C., Gomes da Rocha, C., Smith, W., Tchistiakova, E., & Kirkby, C. (2024). Pharyngeal constrictor dose-volume histogram metrics and patient-reported dysphagia in head and neck radiotherapy. Clinical Oncology . 10.1016/j.clon.2024.01.002

116. Pleyer, L., Heibl, S., Tinchon, C., Vallet, S., Schreder, M., Melchardt, T., Stute, N., Föhrenbach Quiroz, K. T., Leisch, M., Egle, A., Scagnetti, L., Wolf, D., Beswick, R., Drost, M., Larcher-Senn, J., Grochtdreis, T., Vaisband, M., Hasenauer, J., Zaborsky, N., & Greil, R. (2023). Health-related quality of life as assessed by the EQ-5D-5L predicts outcomes of patients treated with Azacitidine—A prospective cohort study by the AGMT. Cancers, 15 (5), 1388. 10.3390/cancers15051388

117. Soda, T., Otsuka, H., Koike, S., & Okada, T. (2023). Baseline factors and surgical procedures affecting changes in lower urinary tract symptoms after robot-assisted radical prostatectomy: The impact of nerve-sparing. International Urology and Nephrology . 10.1007/s11255-023-03859-9

118. Tang, J., Wong, G., Naffouje, S., Felder, S., Sanchez, J., Dineen, S., Powers, B. D., Dessureault, S., Gurd, E., Castillo, D., & Hodul, P. (2023). A novel nomogram for early identification and intervention in colorectal cancer patients at risk for malnutrition. American Surgeon, 89 (5), 1485–1496. 10.1177/00031348211058620

119. Tournoy, K. G., Adam, V., Muylle, I., De Rijck, H., Everaert, E., Eqlimi, E., van Meerbeeck, J. P., & Vercauter, P. (2023). Health outcomes with curative and palliative therapies in real world: Role of the quality of life summary score in thoracic oncology patients. Cancers . 10.3390/cancers15153821

120. Unger, J. M., Qian, L., Redman, M. W., Tavernier, S. S., Minasian, L., Sigal, E. V., Papadimitrakopoulou, V. A., LeBlanc, M., Cleeland, C. S., Dzingle, S. A., Summers, T. J., Chao, H., Madhusudhana, S., Villaruz, L., Crawford, J., Gray, J. E., Kelly, K. L., Gandara, D. R., Bazhenova, L., … Moinpour, C. M. (2023). Quality-of-life outcomes and risk prediction for patients randomized to Nivolumab/Ipilimumab vs Nivolumab on LungMAP-S1400I. Journal of the National Cancer Institute . 10.1093/jnci/djad003

121. Xu, C., Pfob, A., Mehrara, B. J., Yin, P., Nelson, J. A., Pusic, A. L., & Sidey-Gibbons, C. (2023). Enhanced surgical decision-making tools in breast cancer: Predicting 2-year postoperative physical, sexual, and psychosocial well-being following mastectomy and breast reconstruction (INSPiRED 004). Annals of Surgical Oncology, 30 (12), 7046–7059. 10.1245/s10434-023-13971-w

122. Xu, C., Subbiah, I. M., Lu, S. C., Pfob, A., & Sidey-Gibbons, C. (2023). Machine learning models for 180-day mortality prediction of patients with advanced cancer using patient-reported symptom data. Quality of Life Research : An International Journal of Quality of Life Aspects of Treatment, Care and Rehabilitation, 32 (3), 713–727. 10.1007/s11136-022-03284-y

123. Zhang, B., Shi, H., & Wang, H. (2023). Machine learning and AI in cancer prognosis, prediction, and treatment selection: A critical approach. Journal of Multidisciplinary Healthcare, 16 , 1779–1791. 10.2147/jmdh.s410301

124. Cuocolo, R., Caruso, M., Perillo, T., Ugga, L., & Petretta, M. (2020). Machine Learning in oncology: A clinical appraisal. Cancer Letters, 481 , 55–62. 10.1016/j.canlet.2020.03.032

125. Tseng, Y. J., Wang, H. Y., Lin, T. W., Lu, J. J., Hsieh, C. H., & Liao, C. T. (2020). Development of a machine learning model for survival risk stratification of patients with advanced oral cancer. JAMA Network Open, 3 (8), e2011768. 10.1001/jamanetworkopen.2020.11768

126. Iivanainen, S., Alanko, T., Vihinen, P., Konkola, T., Ekstrom, J., Virtanen, H., & Koivunen, J. (2020). Follow-up of cancer patients receiving anti-PD-(L)1 therapy using an electronic patient-reported outcomes tool (KISS): Prospective feasibility cohort study. JMIR formative research, 4 (10), e17898. 10.2196/17898

127. Giesinger, J. M., Loth, F. L. C., Aaronson, N. K., Arraras, J. I., Caocci, G., Efficace, F., Groenvold, M., van Leeuwen, M., Petersen, M. A., Ramage, J., Tomaszewski, K. A., Young, T., & Holzner, B. (2020). Thresholds for clinical importance were established to improve interpretation of the EORTC QLQ-C30 in clinical practice and research. Journal of Clinical Epidemiology, 118 , 1–8. 10.1016/j.jclinepi.2019.10.003

128. Fedorov, V., Mannino, F., & Zhang, R. (2009). Consequences of dichotomization. Pharmaceutical Statistics, 8 (1), 50–61. 10.1002/pst.331

129. Van Houwelingen, H. C. (2007). Dynamic prediction by landmarking in event history analysis. Scandinavian Journal of Statistics, 34 (1), 70–85. 10.1111/j.1467-9469.2006.00529.x

130. Asgari, S., Khalili, D., Zayeri, F., Azizi, F., & Hadaegh, F. (2021). Dynamic prediction models improved the risk classification of type 2 diabetes compared with classical static models. Journal of Clinical Epidemiology, 140 , 33–43. 10.1016/j.jclinepi.2021.08.026

131. Spreafico, M., Hazewinkel, A.-D., Gelderblom, H., & Fiocco, M. (2024). Dynamic Prediction of Overall Survival for Patients with Osteosarcoma: A Retrospective Analysis of the EURAMOS-1 Clinical Trial Data. Current Oncology , 31 (7), 3630–3642. https://www.mdpi.com/1718-7729/31/7/267

132. Collins, G. S., Dhiman, P., Andaur Navarro, C. L., Ma, J., Hooft, L., Reitsma, J. B., Logullo, P., Beam, A. L., Peng, L., Van Calster, B., van Smeden, M., Riley, R. D., & Moons, K. G. (2021). Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence. British Medical Journal Open, 11 (7), e048008. 10.1136/bmjopen-2020-048008

133. Debray, T. P. A., Collins, G. S., Riley, R. D., Snell, K. I. E., Van Calster, B., Reitsma, J. B., Moons, K. G. M. (2023). Transparent reporting of multivariable prediction models developed or validated using clustered data (TRIPOD-Cluster): Explanation and elaboration. BMJ , 380 , e071058. 10.1136/bmj-2022-071058

134. Food and Drug Administration, (2021). Core Patient Reported Outcomes in Cancer clinical trials .

135. Chang, V. T., Thaler, H. T., Polyak, T. A., Kornblith, A. B., Lepore, J. M., & Portenoy, R. K. (1998). Quality of life and survival. Cancer, 83 (1), 173–179. 10.1002/(sici)1097-0142(19980701)83:1%3c173::aid-cncr23%3e3.0.co;2-t

136. Di Meglio, A., Havas, J., Gbenou, A. S., Martin, E., El-Mouhebb, M., Pistilli, B., Menvielle, G., Dumas, A., Everhard, S., Martin, A. L., Cottu, P. H., Lerebours, F., Coutant, C., Lesur, A., Tredan, O., Soulie, P., Vanlemmens, L., Joly, F., Delaloge, S., Ganz, P. A., André, F., Partridge, A. H., Jones, L. W., Michiels, S., Vaz-Luis, I. (2022). Dynamics of long-term patient-reported quality of life and health behaviors after adjuvant breast cancer chemotherapy. Journal of Clinical Oncology , 40 (27), 3190–3204. 10.1200/JCO.21.00277

137. Vaz-Luis, I., Di Meglio, A., Havas, J., El-Mouhebb, M., Lapidari, P., Presti, D., Soldato, D., Pistilli, B., Dumas, A., Menvielle, G., Charles, C., Everhard, S., Martin, A. L., Cottu, P. H., Lerebours, F., Coutant, C., Dauchy, S., Delaloge, S., Lin, N. U., Ganz, P. A., Partridge, A. H., André, F., Michiels, S. (2022). Long-term longitudinal patterns of patient-reported fatigue after breast cancer: A group-based trajectory analysis. Journal of Clinical Oncology , 40 (19), 2148–2162. 10.1200/JCO.21.01958

138. Jenkins, D. A., Sperrin, M., Martin, G. P., & Peek, N. (2018). Dynamic models to predict health outcomes: Current status and methodological challenges. Diagnostic and Prognostic Research . 10.1186/s41512-018-0045-2

139. Van Der Ploeg, T., Austin, P. C., & Steyerberg, E. W. (2014). Modern modelling techniques are data hungry: A simulation study for predicting dichotomous endpoints. BMC Medical Research Methodology, 14 (1), 137. 10.1186/1471-2288-14-137

140. Corless, I. B., Nicholas, P. K., & Nokes, K. M. (2001). Issues in cross-cultural quality-of-life research. Journal of Nursing Scholarship, 33 (1), 15–20. 10.1111/j.1547-5069.2001.00015.x

141. Sprangers, M. A. G. (2002). Quality-of-life assessment in oncology. Acta Oncologica, 41 (3), 229–237. 10.1080/02841860260088764

142. Krepper, D., Cesari, M., Hubel, N. J., Zelger, P., Sztankay, M. J. (2024). Machine learning models including patient-reported outcome data in oncology: a systematic literature review and analysis of their reporting quality. Journal of Patient-Reported Outcomes , 8 (1), 126. 10.1186/s41687-024-00808-7

Associated Data

Supplementary Materials

Supplementary file1 (DOCX 389 KB)

Data Availability Statement

The templates for data extraction and data extracted from the literature are available from the authors upon reasonable request.