MHealth based patient-centered self-management reduces the burden and episodes of atrial fibrillation

Abstract

Abstract Background There is a surging development of digital technologies for screening and diagnosis of atrial fibrillation (AF), nonetheless, how these digital technologies impact AF care remains unclear. Objectives The present study aimed to investigate the impact on AF episodes and arrhythmia burden of patient-centered self-management with using smart technologies, incorporating artificial intelligence (AI), wearable and mobile health (mHealth) technology for patient-centred self-management. Methods In this cohort study, we applied AI machine-learning (ML) model predicting AF prior to 4 hours of AF occurrence, while the timely monitoring of AF episodes with photoplethysmography (PPG) technology, and further confirmation of the diagnosis of AF with single-lead ECG, was based on wearable devices. These have been developed in AF screening study (stage 1 pre-mAFA) of Mobile Health technology for improved screening and optimizing integrated care in atrial fibrillation (mAFA II programme), while mHealth supported integrated care of AF was validated to reduce clinical events (stage 2 mAFA II cluster randomized trial). In this observational cohort, the subjects were in 2 groups: (i) subjects with monitored AF but without using mAFA (Group 1); (ii) subjects with monitored AF and using smart devices and mAFA for patient-centered self-management (Group 2). Adult subjects freely downloaded the mAFA AF App, with compatible devices, and were included into the study from across China between October 26, 2018 and Dec 1, 2021. Results From 3499461 subjects involving in AF population screening, there were 5904 subjects in Group 1 (mean age 57 years, SD,15 years; 80.7%, male), while 2667 subjects in Group 2 (51, 15; 89.7% male). The diagnosis of AF episodes was confirmed by single-lead ECG recordings, and decreased among those using mAFA in Group 2 (Confirmed AF: 602 in 1st quarter, 224 in 2nd quarter, 81 in 3rd quarter, 52 in 4th quarter) (all p value for trend<0.001). AF burden was significantly reduced over time (PPG: 26% on 1st month, 19% on 12th month; ECG: 3%, 0.7%, all p<0.001), while the average probability of AF occurrences by AI ML model prediction was decreased among those using mAFA in Group 2 (65%, 57%, p<0.001). The decreasing trend of AF burden over time was not seen in subjects with detected AF without mAFA (Group 1). On multivariate analysis, AI ML model driven mAFA-based upstream risk factor control significantly reduced the changes in AF burden of both Δ 6 month (adjusted OR, 95% CI, 0.51,0.43–0.59) and Δ 12 month (0.39,0.32–0.47, all p<0.001). Conclusion mHealth-AF care increased the adherence of using smart devices for AF detection. The incorporation of smart devices and AI tools into an AF clinical care pathway, effectively reduced AF burden and detected AF episodes, through appropriate rhythm control management and upstream risk factor control. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Natural Science Foundation of China