Gerontechnology Acceptance in Thai Older Adult Care Facilities-Sensor Network and Machine Learning Adoption: Mixed...

Thailand is undergoing a rapid demographic transition, with an estimated 28% of the population expected to be aged 60 years or older by 2030. This shift creates an urgent demand for technology-enhanced solutions for older adults. Despite growing interest in Internet of Things (IoT) sensor networks and machine learning applications for older adult care, the patterns of technology acceptance and implementation readiness in Thai older adult care facilities remain underexplored.

This study aimed to assess the readiness and adoption patterns of sensor network and machine learning technologies among older adults and care stakeholders in Thai older adult care facilities, guided by the Gerontechnology Acceptance Model (GTAM) and Service Exchange Value Creation Logic.

A sequential explanatory mixed methods design was used. Phase 1 (quantitative) involved structured technology assessments by 12 health care technology specialists and survey administration to 120 consumer representatives (older adults, n=70; adult family members, n=50), stratified across Bangkok and Chiang Mai. Phase 2 (qualitative) comprised 20 semistructured interviews and 3 purposively selected focus groups from phase 1 participants to elaborate on the quantitative findings. The primary theoretical framework was GTAM, mapping 5 constructs (perceived usefulness, ease of use, social influence, facilitating conditions, and behavioral intention) to corresponding survey items. This study was approved by the Assumption University Institutional Review Board (AU-IRB 80/2024) and is registered under a noninterventional observational design; formal clinical trial registration was not applicable.

IoT fall detection systems received the highest clinical efficacy ratings from specialists (mean 4.5, SD 0.3 on a 5-point scale) and achieved 89% user acceptance. Artificial intelligence-driven early warning systems demonstrated the highest perceived clinical impact (mean 4.7, SD 0.2) but also the greatest implementation complexity (mean 4.2, SD 0.5). The consumer survey findings revealed that digital literacy level was the strongest predictor of behavioral adoption intention (β=.62; P<.001), with high-confidence participants showing 2.3 times higher acceptance rates than low-confidence participants. Significant geographic differences emerged: Bangkok respondents showed higher acceptance of medical IoT technologies (mean 4.3, SD 0.3; t₁₁₉=1.98; P=.05), while Chiang Mai respondents reported a stronger preference for environmental digital health solutions (mean 4.5, SD 0.3; t₁₁₉=4.12; P<.001) and elevated privacy concerns (mean 4.2, SD 0.4; P=.005). Qualitative analysis identified 5 themes: surveillance anxiety, family-mediated adoption, regional digital trust, training needs, and dignity-preserving technology design.

Smart technology integration in Thai older adult care facilities is feasible and accepted across demographic groups when implemented in phases, culturally adapted, and supported by digital literacy training. Key adoption enablers were digital confidence, family involvement, and privacy-respecting design. The GTAM-derived findings offer an evidence-based framework for deploying gerontechnology in health care contexts in developing nations. Longitudinal outcome studies are needed to validate clinical and economic projections from prior literature.