MedElevator
Войти в исследования Musculoskeletal science & practice · 2026
Automated prescription of therapeutic exercise for shoulder impingement syndrome using literature-driven rule generation architecture.
СтатьяНазвание и аннотация: Перевод в очереди
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.
Kim Jun-Hee
Аннотация
BACKGROUND: Shoulder impingement syndrome (SIS) is a common musculoskeletal disorder that requires individualized therapeutic exercise prescription. However, it is challenging to provide individualized prescriptions based on the latest evidence.
OBJECTIVES: This study aimed to develop and evaluate an automated literature-driven architecture that generates personalized therapeutic exercise prescriptions for SIS by integrating real-time clinical literature with patient-specific shoulder range of motion (ROM) data.
DESIGN: a cross-sectional secondary data analysis.
METHODS: A generative artificial intelligence (AI) model (Gemini 1.5) was used to retrieve, extract, and structure the evidence-based exercise recommendations from recent PubMed abstracts. Information linking specific shoulder ROM impairments to clinically relevant symptoms and therapeutic exercises was converted into executable decision rules. These rules were applied to anonymized shoulder ROM data from 35 patients with SIS. ROM deficits were calculated as percentage deviations from the normative values, prioritized by severity, and used to generate individualized exercise prescriptions.
RESULTS: The architecture successfully extracted six evidence-based decision rules associating distinct shoulder ROM limitations with the corresponding symptoms and targeted therapeutic exercises. When applied to patient data, the system generated personalized exercise prescriptions that reflected prioritized ROM impairments and included symptom descriptions and detailed exercise instructions based on current literature.
CONCLUSION: This study demonstrated the feasibility of the literature-driven rule generation architecture for the automated prescription of personalized therapeutic exercises for SIS. By integrating real-time clinical evidence with individual biomechanical profiles, the proposed architecture offers a scalable and adaptive framework for evidence-based rehabilitation planning and has potential applicability in other musculoskeletal conditions.
OBJECTIVES: This study aimed to develop and evaluate an automated literature-driven architecture that generates personalized therapeutic exercise prescriptions for SIS by integrating real-time clinical literature with patient-specific shoulder range of motion (ROM) data.
DESIGN: a cross-sectional secondary data analysis.
METHODS: A generative artificial intelligence (AI) model (Gemini 1.5) was used to retrieve, extract, and structure the evidence-based exercise recommendations from recent PubMed abstracts. Information linking specific shoulder ROM impairments to clinically relevant symptoms and therapeutic exercises was converted into executable decision rules. These rules were applied to anonymized shoulder ROM data from 35 patients with SIS. ROM deficits were calculated as percentage deviations from the normative values, prioritized by severity, and used to generate individualized exercise prescriptions.
RESULTS: The architecture successfully extracted six evidence-based decision rules associating distinct shoulder ROM limitations with the corresponding symptoms and targeted therapeutic exercises. When applied to patient data, the system generated personalized exercise prescriptions that reflected prioritized ROM impairments and included symptom descriptions and detailed exercise instructions based on current literature.
CONCLUSION: This study demonstrated the feasibility of the literature-driven rule generation architecture for the automated prescription of personalized therapeutic exercises for SIS. By integrating real-time clinical evidence with individual biomechanical profiles, the proposed architecture offers a scalable and adaptive framework for evidence-based rehabilitation planning and has potential applicability in other musculoskeletal conditions.