Virtual Assistant for Exercise Adherence in Older ADULTS

The objective of this study is to determine whether a virtual assistant-controlled, home-based exercise program can improve adherence to therapeutic exercise among older adults, compared with a conventional municipal program of similar dosage. Although exercise is effective for preserving function and quality of life during aging, adherence remains suboptimal. Virtual assistants may offer a scalable and acceptable solution to support sustained participation.

The study will employ a nonrandomized controlled clinical trial (quasi-experimental design) involving community-dwelling adults aged ≥60 years. Participants will be allocated to groups based on program pathway:

Experimental group (Virtual Assistant/BOT): a structured home-based exercise program (60 minutes per session, 3 sessions per week for 12 weeks), guided and monitored by a virtual assistant (BOT), including automated session delivery, reminders, and adherence tracking.

Control group (Municipal program): older adults already participating in Enguera se saludable, an onsite, instructor-led municipal program with equivalent frequency and duration (60 minutes, 3 times per week for 12 weeks). Attendance records from the municipal program will quantify adherence.

The primary outcome is exercise adherence, defined as the proportion of prescribed sessions completed during the 12-week period, with predefined adherence thresholds (e.g., ≥75% of sessions completed). Secondary outcomes include changes in muscle strength, balance, functional performance, and health-related quality of life. Additional measures will include user perceptions, usability, and satisfaction with the virtual assistant to evaluate acceptability and feasibility.

Given the nonrandomized design and the pre-existing enrollment of the control group, the study will incorporate the following methodological safeguards:

Baseline demographic and clinical characteristics (e.g., age, sex, comorbidities, prior activity level) will be comprehensively documented.

Baseline imbalances will be controlled through statistical adjustment (e.g., covariate adjustment, propensity score procedures, and sensitivity analyses) to reduce selection bias and confounding.

Exercise dosage (frequency, duration, and intervention length) will be matched across groups, or, when small discrepancies arise, dosage will be included as a covariate in the analyses.

This study is expected to contribute evidence regarding whether a virtual assistant-based exercise program represents a viable, effective, and acceptable alternative to conventional program delivery models for promoting active and healthy aging in community-dwelling older adults.

Participants in this group will complete a 12-week home-based exercise program delivered and monitored by a virtual assistant (BOT). The program consists of 60-minute sessions, three times per week, including guided instructions, automated reminders, and adherence tracking. The BOT provides real-time session support and records participation throughout the intervention.

Procedure: Exercise program

Participants in this group are individuals already enrolled in the municipal program "Enguera se saludable", which offers a face-to-face, instructor-led exercise program of the same duration and frequency (60 minutes, three times per week for 12 weeks). Attendance is recorded routinely by program instructors and will be used to assess adherence.

Procedure: Exercise program

BOT Group: Home-based exercise program delivered through a virtual assistant for 12 weeks (60 minutes, three times per week), including guided instructions and adherence monitoring.

Enguera Exercise Group: Face-to-face, instructor-led exercise sessions from the Enguera se saludable program, with the same frequency and duration (60 minutes, three times per week for 12 weeks).

Time frame: End of the 12-week intervention.

Exercise adherence will be defined as the percentage of prescribed exercise sessions completed during the 12-week intervention. A single adherence value will be calculated for each participant as:

\\text{Adherence (%) = (Sessions completed / Sessions prescribed) × 100}

Measurement method:

Virtual Assistant/BOT Group: Adherence will be recorded automatically by the virtual assistant (BOT), which logs session completion in real time.

Municipal Exercise Group: Adherence will be calculated from attendance records routinely collected in the Enguera se saludable municipal program, using the same formula (completed / prescribed × 100).

Although adherence is obtained from different data sources, the measurement itself is identical in both groups, expressed as a percentage (%).

Time frame: Baseline and 12 weeks.

Lower-limb functional performance will be assessed using the Short Physical Performance Battery (SPPB), a validated instrument for older adults. The SPPB includes three components: balance tests, gait speed, and the 5-times sit-to-stand test. Each component is scored from 0 to 4, yielding a total score from 0 to 12, with higher scores indicating better physical performance.

Unit of measurement:

SPPB total score (0-12 points).

Time frame: Baseline and 12 weeks

Moderate-to-vigorous physical activity (MVPA) will be quantified using a wrist- or hip-worn triaxial accelerometer. MVPA will be calculated according to established cut-points for older adults, expressed as minutes per day accumulated at moderate or vigorous intensity. Devices will be worn during the monitoring period, and raw acceleration data will be processed using standardized algorithms to derive daily MVPA time. A single MVPA value will be generated for each assessment period.

Unit of measurement:

Minutes/day of MVPA (moderate-to-vigorous physical activity).

Time frame: Baseline and 12 weeks

Risk of falls will be assessed using the FallSkip® system, an instrumented device that evaluates fall risk in older adults through a standardized functional protocol. The device records parameters such as reaction time, postural stability, gait acceleration/deceleration patterns, and sit-to-stand performance. These variables are integrated automatically by the device software to generate a Fall Risk Index on a 0-100 scale, with higher values indicating greater risk of falls. A single Fall Risk Index score will be obtained for each participant at every assessment time point.

Unit of measurement:

FallSkip® Fall Risk Index (0-100 points).

Time frame: 12 weeks.

User experience and usability of the virtual assistant (BOT) will be evaluated using a Visual Analog Scale (VAS), an anchored numerical scale ranging from 0 to 10, in which 0 represents the worst possible user experience/usability and 10 represents the best possible user experience/usability. Participants will rate their overall experience and perceived usability of the virtual assistant on this single-item scale. A single VAS score will be obtained for each assessment period.

Unit of measurement:

Score on the Visual Analog Scale (0-10), where higher scores indicate better user experience/usability.

Application of a Virtual Assistant to Enhance Exercise Adherence in Older Adults