JMIR Publications

ABSTRACT

Background:

Hypertension is a long-term medical condition. Mobile health services can help out-of-hospital patients to self-manage. However, not all management is effective, which may be because the behavior mechanism and behavior preferences of patients with various characteristics in hypertension management were unclear.

Objective:

The purpose of this study was to (1) explore patient multi-behavior engagement trails in the pathway-based hypertension self-management; (2) discover patient behavior preference patterns; (3) identify the characteristics of patients with different behavior preferences.

Methods:

This study included 863 hypertensive patients who generated 295,855 usage records in the mHealth app from December 28, 2016 to July 2, 2020. Markov Chain was used to infer the patient multi-behavior engagement trails, which contained the type, quantity, time spent, sequence, and transition probability of patient behavior. K-means algorithm was used to group patients by the normalized behavior preference features: the number of behavioral states that a patient performed in each trail. The pages in the app represented the behavior states. Chi-square tests, Z-test, analysis of variances, and Bonferroni multiple comparisons were conducted to characterize the patient behavior preference patterns.

Results:

Markov Chain analysis revealed 3 types of behavior transition (one-way transition, cycle-transition, and self-transition) and 4 trails of patient multi-behavior engagement. In perform task trail (PT-T), Patients preferred to start self-management from the states of Task BP (0.29), Task Drug (0.18), and Task Weight (0.20), and spent more time on the Task Food state (35.87s). Some patients entered the states of Task BP (0.20) and Task Drug (0.25) from the Reminder Item state. In result-oriented trail (RO-T), patients spent more energy on the Ranking state (19.66s) compared the Health Report state (13.52s). In knowledge learning trail (KL-T), there was a high probability of cycle-transition (0.47, 0.31) between the states of Knowledge List and Knowledge Content. In support acquisition trail (SA-T), there was a high probability of self-transition in the Questionnaire (0.29) state. K-means analysis discovered 3 patient behavior preference patterns: only PT-T, PT-T and KL-T, and PT-T and SA-T. There were statistically significant associations between the behavior preference pattern and gender, education level, and blood pressure (BP).

Conclusions:

This study identified the dynamic, longitudinal, and multi-dimension characteristics of patient behavior. Patients preferred to focus on BP, medications, and weight conditions, and pay attention to BP and medications using reminders. The diet management and questionnaires were complicated and difficult to implement and record. Competitive methods such as ranking were more likely to attract patients to pay attention to their own self-management states. Female patients with lower education level and poor-controlled BP were more likely to be highly involved in hypertension health education.