Digital health interventions are increasingly used in physical and occupational therapy to deliver home exercise programs via sensor equipped devices such as smartphones, enabling remote monitoring of adherence and performance. However, digital interventions are typically programmed as software before clinical encounters as libraries of parametrized exercise modules targeting broad patient populations. At the point of care, clinicians can only select modules and adjust a narrow set of parameters like repetitions, so patient specific needs that emerge during encounters, such as distinct movement limitations, and home environments, are rarely reflected in the software. We evaluated a digital intervention paradigm that uses large language models (LLMs) to translate clinicians' exercise prescriptions into intervention software. In a prospective single arm feasibility study with 20 licensed physical and occupational therapists and a standardized patient, clinicians created 40 individualized upper extremity programs (398 instructions) that were automatically translated into executable software. Our results show a 45% increase in the proportion of personalized prescriptions that can be implemented as software compared with a template based benchmark, with unanimous consensus among therapists on ease of use. The LLM generated software correctly delivered 99.78% (397/398) of instructions as prescribed and monitored performance with 88.4% (352/398) accuracy, with 90% (18/20) of therapists judged it safe to interact with patients, and 75% (15/20) expressed willingness to adopt it. To our knowledge, this is the first prospective evaluation of clinician directed intervention software generation with LLMs in healthcare, demonstrating feasibility and motivating larger trials to assess clinical effectiveness and safety in real patient populations.

翻译：数字健康干预在物理治疗和职业治疗中日益普及，通过配备传感器的设备（如智能手机）提供家庭运动方案，实现对患者依从性和表现的远程监测。然而，数字干预通常需在临床诊疗前预先编程为软件，形成针对广泛患者群体的参数化运动模块库。在诊疗现场，临床医生仅能选择模块并调整有限参数（如重复次数），导致诊疗过程中出现的患者特定需求（如独特的运动限制）及家庭环境因素难以在软件中体现。本研究评估了一种利用大语言模型（LLMs）将临床医生运动处方转化为干预软件的数字干预范式。在一项包含20名持证物理治疗师与职业治疗师及标准化患者的前瞻性单臂可行性研究中，临床医生创建了40个个体化上肢康复方案（共398条指令），并自动转化为可执行软件。结果显示：相较于基于模板的基准方法，可实现软件化的个性化处方比例提升45%，且治疗师一致认可其易用性。LLM生成的软件能正确执行99.78%（397/398）的处方指令，并以88.4%（352/398）的准确率监测运动表现；90%（18/20）的治疗师认为其与患者交互具有安全性，75%（15/20）表示愿意采用该技术。据我们所知，这是医疗领域首次对临床医生导向的LLM干预软件生成进行前瞻性评估，验证了其可行性，并为在真实患者群体中开展更大规模临床试验以评估临床有效性与安全性提供了依据。