From Therapeutic Exercise Guidelines to Adherence-Aware mHealth Systems: A Modeling Framework with Cloud and Explainable AI Support.

According to World Health Organization, regular physical activity is proven to help prevent and manage noncommunicable diseases such as heart disease, hypertension, diabetes and several cancers as well as to promote health during specific physiological or metabolic conditions such as pregnancy and obesity. In this context, therapeutic exercise guidelines have been developed to provide structured recommendations for safe and effective exercise prescription across diverse health conditions. Despite their clinical importance, these guidelines are not effectively integrated into digital health systems, as they are typically represented in a descriptive rather than computational form. Most mobile health applications support generic activity tracking without formally representing protocol-based exercise prescriptions or quantifying adherence beyond simple completion metrics. This paper proposes a modeling framework for translating Frequency-Intensity-Time-Type (FITT)-based therapeutic exercise guidelines into computable protocol structures and measurable adherence indicators. The framework introduces (i) a protocol formalization layer encoding guideline parameters as structured entities, (ii) an adherence modeling mechanism defining compliance metrics, and (iii) an explainability module combining rule-based evaluation with AI-assisted natural language generation to produce interpretable feedback. Moreover, an event-driven reference architecture is presented, forming the basis of a mobile application prototype that operationalizes the modeling framework.