Nursing research and practice · 2026
Study on the Current Status of Supportive Care Needs of Elderly Breast Cancer Patients and Influencing Factors.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Tian Weishuang, Gao Junxiong, Wei Tingting, Zhang Yan, Liu Xinyu, Li Xia
Аннотация
AIM: This study investigated the current status and key influencing factors of supportive care needs among elderly breast cancer patients, with a focus on identifying critical determinants through a survey and advanced machine learning techniques.
DESIGN: The cross-sectional study randomly interviewed 180 elderly breast cancer patients, and 157 valid observations were retained for analysis.
METHODS: Firstly, patients were surveyed by two questionnaires. One is for fundamental information, which includes demographics, clinical, and psychosocial variables; the other is the Chinese version of the Supportive Care Needs Survey-Short Form 34 (SCNS-SF34). And then, the questionnaires' results were transferred into a tabular dataset, with each question from the questionnaires serving as a column in the dataset. Secondly, an Extreme Gradient Boosting (XGBoost, a supervised learning algorithm) model was trained on the dataset. Fundamental features served as input variables, and the label was the total score of SCNS-SF34. Thirdly, the Shapley Additive Explanations (SHAP) framework was applied to interpret the XGBoost model by quantifying feature importance.
RESULTS: The XGBoost model demonstrated moderate predictive efficacy (R 2 = 0.58). After adopting the SHAP method on the model, we have the following findings. Fatigue severity emerged as the most significant feature of increased care needs, followed by weight, age, and educational level. Surgical interventions and low exercise frequency were associated with heightened demands, while managed chronic conditions (e.g., hypertension) and higher socioeconomic status (e.g., pension-based income) mitigated the care needs. Psychosocial factors, such as minority ethnicity and low health literacy, exacerbated unmet needs, whereas regular family support and higher education levels buffered demands.
CONCLUSION: This study highlights the multidimensional nature of supportive care needs in elderly breast cancer patients, emphasizing the interplay of physiological, treatment-related, and psychosocial factors. The findings suggest that targeted interventions, such as fatigue management, culturally sensitive care navigation, and structured support for low-literacy populations, are essential to address unmet needs. Future research should prioritize longitudinal designs and policy integration to enhance care delivery and promote health equity.
REPORTING METHOD: The study adhered to STROBE guidelines for cross-sectional studies to ensure transparent and comprehensive reporting of results.
PATIENT OR PUBLIC CONTRIBUTION: Not applicable.
DESIGN: The cross-sectional study randomly interviewed 180 elderly breast cancer patients, and 157 valid observations were retained for analysis.
METHODS: Firstly, patients were surveyed by two questionnaires. One is for fundamental information, which includes demographics, clinical, and psychosocial variables; the other is the Chinese version of the Supportive Care Needs Survey-Short Form 34 (SCNS-SF34). And then, the questionnaires' results were transferred into a tabular dataset, with each question from the questionnaires serving as a column in the dataset. Secondly, an Extreme Gradient Boosting (XGBoost, a supervised learning algorithm) model was trained on the dataset. Fundamental features served as input variables, and the label was the total score of SCNS-SF34. Thirdly, the Shapley Additive Explanations (SHAP) framework was applied to interpret the XGBoost model by quantifying feature importance.
RESULTS: The XGBoost model demonstrated moderate predictive efficacy (R 2 = 0.58). After adopting the SHAP method on the model, we have the following findings. Fatigue severity emerged as the most significant feature of increased care needs, followed by weight, age, and educational level. Surgical interventions and low exercise frequency were associated with heightened demands, while managed chronic conditions (e.g., hypertension) and higher socioeconomic status (e.g., pension-based income) mitigated the care needs. Psychosocial factors, such as minority ethnicity and low health literacy, exacerbated unmet needs, whereas regular family support and higher education levels buffered demands.
CONCLUSION: This study highlights the multidimensional nature of supportive care needs in elderly breast cancer patients, emphasizing the interplay of physiological, treatment-related, and psychosocial factors. The findings suggest that targeted interventions, such as fatigue management, culturally sensitive care navigation, and structured support for low-literacy populations, are essential to address unmet needs. Future research should prioritize longitudinal designs and policy integration to enhance care delivery and promote health equity.
REPORTING METHOD: The study adhered to STROBE guidelines for cross-sectional studies to ensure transparent and comprehensive reporting of results.
PATIENT OR PUBLIC CONTRIBUTION: Not applicable.