Comparison of Transdermal Optical Imaging and Conventional Handcuff Methods for Blood Pressure Screening: A Cross-Sectional Study

Introduction: Non-communicable diseases (NCDs), including cardiovascular diseases (CVDs), contribute significantly to global mortality, accounting for over 70% of deaths worldwide. Recent advancements in Transdermal Optical Imaging (TOI) technologies, such as the Lifesten app, offer innovative approaches to blood pressure measurement. This study compares the accuracy of the Lifesten app to traditional cuff-based methods for measuring blood pressure.

Methods: A cross-sectional study was conducted in Kigali, Rwanda, targeting adults aged 18–45, including high-risk individuals that were identified through social media, community outreach, and targeted advertising. Participants underwent blood pressure measurements using both the Lifesten app and a traditional hand-cuff device. Data were analyzed using SPSS software to compare the two methods.

Results: Among the 384 participants, 59.63% were male (n=229) and 40.37% were female (n=155), with the majority aged 18–27 years. The mean scores measured using the Lifesten app for systolic and diastolic pressures were 111.45 mmHg and 74.75 mmHg, respectively, compared to 116.78 mmHg and 75.71 mmHg using the traditional device, showing differences of 4.56% and 1.27%. In a subgroup of 12 hypertensive individuals, the app recorded lower systolic (114.17 mmHg) and diastolic (75.67 mmHg) readings than the traditional device (140.17 mmHg and 80.00 mmHg).The app’s systolic MAE was 11.68 mmHg (MAPE: 9.63%), while diastolic MAE was 8.66 mmHg (MAPE: 11.63%).

Conclusion: The Lifesten app demonstrated potential for hypertension screening in resource-limited settings. However, algorithm improvements are necessary to enhance its accuracy and ensure reliable clinical use.

Article file ID not found.

The authors declare no conflict of interest.

Not applicable

The datasets used in this study are openly available at [repository link] and the source code is available on GitHub at [GitHub link].

This work did not receive any external funding.