Digital health interventions increasingly deliver home exercise programs via sensor-equipped devices such as smartphones, enabling remote monitoring of adherence and performance. However, current software is usually authored before clinical encounters as libraries of modules for broad impairment categories. At the point of care, clinicians can only choose from these modules and adjust a few parameters (for example, duration or repetitions). As a result, individual limitations, goals, and environmental constraints are often not reflected, limiting personalization and benefit. We propose a paradigm in which large language models (LLMs) act as constrained translators that convert clinicians' exercise prescriptions into intervention software. Clinicians remain the decision makers: they design exercises during the encounter, tailored to each patient's impairments, goals, and environment, and the LLM generates matching software. We conducted a prospective single-arm feasibility study with 20 licensed physical and occupational therapists who created 40 individualized upper extremity programs for a standardized patient; 100% of prescriptions were translated into executable software, compared with 55% under a representative template-based digital health intervention (p < 0.01). LLM-generated software correctly delivered 99.7% of instructions and monitored performance with 88.4% accuracy (95% confidence interval, 0.843-0.915). Overall, 90% of therapists judged the system safe for patient interaction and 75% expressed willingness to adopt it in practice. To our knowledge, this is the first prospective evaluation of clinician-directed intervention software generation with an LLM in health care, demonstrating feasibility and motivating larger trials in real patient populations.

翻译：数字健康干预日益通过配备传感器的设备（如智能手机）提供家庭锻炼计划，从而实现对依从性和表现的远程监测。然而，当前软件通常在临床接触前预先编写为针对广泛损伤类别的模块库。在护理点，临床医生只能从这些模块中选择并调整少数参数（例如持续时间或重复次数）。因此，个体限制、目标及环境约束往往未能体现，限制了干预的个性化与获益。我们提出一种新范式，其中大语言模型（LLMs）作为受约束的翻译器，将临床医生的锻炼处方转化为干预软件。临床医生仍是决策者：他们在诊疗过程中根据每位患者的损伤、目标和环境设计定制化锻炼方案，并由LLM生成匹配的软件。我们开展了一项前瞻性单臂可行性研究，邀请20名持证物理治疗师和作业治疗师为标准化患者创建了40个个体化上肢康复方案；100%的处方被成功转化为可执行软件，而基于代表性模板的数字健康干预转化率仅为55%（p < 0.01）。LLM生成的软件正确执行了99.7%的指令，并以88.4%的准确率（95%置信区间为0.843-0.915）监测患者表现。总体而言，90%的治疗师认为该系统与患者交互是安全的，75%表示愿意在临床实践中采用。据我们所知，这是首次在医疗保健领域对临床医生导向的大语言模型干预软件生成进行前瞻性评估，证明了其可行性，并为在真实患者群体中开展更大规模试验提供了依据。