Journal of patient-reported outcomes · 2026
Machine learning in the development and application of patient-reported outcome measures (PROMs) for surgical patients: a systematic review.
СтатьяСистематический обзорНазвание 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.
Alanezi Tariq, Li Ben, Al-Omran Leen, Alshabanah Lina, Alkhayal Nawaf K, Verma Meena, Alrumaih Husam, Hussain Mohamad A, Mamdani Muhammad, Al-Omran Mohammed
Аннотация
BACKGROUND: Artificial intelligence (AI) and machine learning (ML) are increasingly integrated into healthcare, offering potential advancements in patient-reported outcome measures (PROMs) for surgical populations. Improved PROMs can enhance patient-centered care by accurately capturing patient experiences with minimal burden.
OBJECTIVE: In the context of surgery, where recovery trajectories vary widely, this study aims to systematically review the use of AI and ML in the development, application, and prediction capabilities of PROMs in surgical populations, with a focus on psychometric properties and the predictive accuracy of post-surgical outcomes.
METHODS: A comprehensive search of the PubMed database was conducted from inception until August 2024. Studies were included if they utilized AI or ML in the development, application, or predicting PROMs for surgical patients. Methodological quality was assessed using COSMIN and PROBAST tools, depending on study design. A qualitative synthesis of findings was performed.
RESULTS: Twenty-two studies met the inclusion criteria, with 19 rated as high quality. Six studies focused on developing computer adaptive tests (CAT) PROMs, seven on evaluating psychometric properties, and five on ML for post-surgical outcome prediction. CAT PROMs showed comparable measurement accuracy to traditional PROMs, good to excellent construct validity, and significantly reduced patient burden by reducing the length of questionnaires. ML algorithms, such as logistic regression, random forests, extreme gradient boosting, and neural networks, achieved similar predictive accuracy for post-surgical outcomes, with no single model demonstrating consistent superiority.
CONCLUSIONS: AI and ML have the potential to improve PROM utilization in surgical care by enhancing efficiency and personalization while maintaining data quality. Clinicians can use AI-driven PROMs to reduce patient burden and integrate ML models for accurate post-surgical outcome prediction, thereby optimizing patient-centered care.
OBJECTIVE: In the context of surgery, where recovery trajectories vary widely, this study aims to systematically review the use of AI and ML in the development, application, and prediction capabilities of PROMs in surgical populations, with a focus on psychometric properties and the predictive accuracy of post-surgical outcomes.
METHODS: A comprehensive search of the PubMed database was conducted from inception until August 2024. Studies were included if they utilized AI or ML in the development, application, or predicting PROMs for surgical patients. Methodological quality was assessed using COSMIN and PROBAST tools, depending on study design. A qualitative synthesis of findings was performed.
RESULTS: Twenty-two studies met the inclusion criteria, with 19 rated as high quality. Six studies focused on developing computer adaptive tests (CAT) PROMs, seven on evaluating psychometric properties, and five on ML for post-surgical outcome prediction. CAT PROMs showed comparable measurement accuracy to traditional PROMs, good to excellent construct validity, and significantly reduced patient burden by reducing the length of questionnaires. ML algorithms, such as logistic regression, random forests, extreme gradient boosting, and neural networks, achieved similar predictive accuracy for post-surgical outcomes, with no single model demonstrating consistent superiority.
CONCLUSIONS: AI and ML have the potential to improve PROM utilization in surgical care by enhancing efficiency and personalization while maintaining data quality. Clinicians can use AI-driven PROMs to reduce patient burden and integrate ML models for accurate post-surgical outcome prediction, thereby optimizing patient-centered care.