Back

Monitoring Heart Failure Patients with Mobile Health Technologies: Outcomes from a 180-day Prospective Study

Mohapatra, S.; Issa, M.; Ivezic, V.; Doherty, R.; Marks, S.; Lan, E.; Rozett, K.; Cullen, L.; Reynolds, W.; Rocchio, R.; Fonarow, G. C.; Ong, M. K.; Speier, W.; Arnold, C.

2023-09-04 health informatics
10.1101/2023.08.30.23294869 medRxiv
Show abstract

Mobile health (mHealth) methods have grown in popularity in preventative medicine due to their convenience, cost, and ability to acquire actionable data. At the same time, the burden of many diseases has grown due to their prevalence and high rates of morbidity and mortality. To combat this burden, mHealth can be customized to improve adherence to recommended regimens and decrease doctor or hospital visits for patients and their families. Heart failure (HF) is a disease with an especially high burden for which mHealth can be used to promote adherence to advised care plans with the goal of decreasing exacerbations and their associated urgent and emergency care visits. Our study compared adherence to different mHealth monitoring regimens that used activity trackers, scales, and a mobile app with gamification features and a financial incentive. In a prospective analysis of 111 HF patients monitored for 180 days, we found that a regimen including a mobile app with a gamified financial incentive led to significantly higher adherence to activity tracker (95% vs. 72.2%, p=0.0101) and weight (87.5% vs. 69.4%, p=0.0016) monitoring compared to a regimen that included the monitoring devices alone. Our findings indicate that mobile apps with added engagement features can be useful tools to reduce temporal adherence decline and may thus increase the impact of mHealth driven interventions.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.