Motivation for Physical Activity

The primary objective of this study is to evaluate whether adaptive, AI-delivered personalized self-efficacy-based AI coaching based on real-time physiological and performance feedback enhance indoor cycling power output during a 20-minute time trial compared to static affirmations and exercise-only control conditions.

This study aims to determine the extent to which different approaches to adapted physical activity coaching influence physical fitness, psycho-behavioral, and anthropometric parameters in patients with stabilized chronic conditions who have been referred to a Sport-Health Center by their physician. The trial includes four parallel groups, distinguishing between two program durations (3 months or 6 months) and the use or non-use of a smartwatch as a tool for monitoring activity. All participants complete 24 sessions of adapted physical activity (APA), in accordance with the standard practices of the La Musse Sport-Health Center, where the study is entirely conducted. However, the distribution of sessions differs by group: two sessions per week over three months or one session per week over six months. Randomization is stratified by age, sex, and baseline fitness level. Assessments are conducted at the following five time points: enrollment (T0), end of the 3-month program (T1), end of the 6-month program (T2), followed by follow-up at 12 months (T3) and 18 months (T4), to observe the durability of the effects after the supervised phase. The primary outcome measure is improvement in physical fitness and anthropometric parameters, objectively measured using tests recognized for their reliability (TDM6, Sit-to-Stand 30s, Timed Up and Go, Sit and Reach, grip strength, BMI, waist circumference). The secondary outcomes focus on changes in motivation toward health-related physical activity (EMAPS), perceived self-efficacy to engage in physical activity (ECS), and self-reported physical activity (IPAQ-SF), which will be collected regularly throughout the program, more frequently than in standard care. A total of 280 patients will be enrolled to ensure sufficient statistical power, taking into account an anticipated loss-to-follow-up rate over 18 months. Data collection and processing will be pseudonymized and conducted on the secure network of La Musse Hospital.