Back

Exploring Outcomes and Engagement Patterns for Hypertensive Patients: An Observational Analysis of the Withings Remote Patient Monitoring Program

Letzelter, P.; Vittrant, B.; Tunis, R.

2024-10-31 health informatics
10.1101/2024.10.28.24315321 medRxiv
Show abstract

BackgroundHypertension is a health issue that affects more than one billion people worldwide and can lead to severe health complications. If untreated, hypertensive crises can occur, which are medical emergencies that require immediate care. Remote Patient Monitoring (RPM) offers a transformative approach to managing hypertension by enabling continuous collection and analysis of blood pressure (BP) data. Our study focuses on Withings RPM system and analyzes the outcomes and engagement patterns of patients using RPM for hypertension management. MethodsThe study comprises 1,873 patients over 6 months who followed an RPM program and used Withings Blood Pressure Monitors. Data was analyzed using Python and R. The analysis examines patients systolic and diastolic BP over time as well as the frequency of measurements that patients took using the RPM system. ResultsThe study reveals that patients who consistently followed the program experienced significant reductions in both systolic and diastolic BP levels. Statistically significant reductions in SBP were observed in users with higher grades of hypertension over six months. The percentage of users experiencing hypertensive crises was reduced from more than 8% to less than 3% over 24 weeks. More frequent engagement with the RPM program was associated with greater BP reductions. ConclusionThese findings highlight the potential of RPM programs in helping patients manage hypertension and minimize hypertensive crises. Future research should go further to understand factors that impact patient outcomes and engagement patterns to improve the effectiveness of RPM programs.

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.