JMIR Publications

ABSTRACT

Background:

Tuberculosis (TB) remains a pressing global health challenge, especially in low-resource settings where long-term treatment and regular follow-up are essential. The integration of artificial intelligence (AI) into remote health management offers new possibilities, yet patient preferences regarding such services remain underexplored.

Objective:

This study aimed to examine TB patients’ preferences for AI-assisted remote health management services in China, identifying key service characteristics that influence their choices.

Methods:

A discrete choice experiment (DCE) was conducted among 203 TB patients in Hubei Province. Each participant completed eight choice tasks comparing hypothetical remote health service options defined by six attributes: interaction method, service provider, service frequency, service content, out-of-pocket cost, and service integration. A mixed logit model was used to estimate preferences, with further subgroup and interaction analyses to examine heterogeneity. Scenario simulations were employed to assess changes in service uptake probabilities across different configurations.

Results:

All six attributes significantly influenced patients’ choices (p < 0.05). Patients showed strong preferences for services delivered by doctors (p < 0.001), video-based interactions (p < 0.001), and comprehensive follow-up content (p < 0.001), while higher costs were associated with lower acceptance (p < 0.001). Scenario analysis demonstrated that transitioning from the baseline to the optimal configuration substantially increased the predicted uptake probability from 50.0% to 90.9%. Subgroup analysis revealed variations in preferences across gender, age, income, education, residence, and treatment status.

Conclusions:

The findings underscore the importance of integrating professional medical involvement, particularly by physicians, and delivering more comprehensive and interactive services to improve patient acceptance. These insights provide valuable guidance for the design and implementation of AI-enabled TB management strategies in resource-constrained settings, aligning technological advancement with patient-centered care.