Key result
ResNet-18 deep learning model using calibrated photoplethysmography identifies hypertension with ~93% accuracy.
Why the study?
Hypertension is a primary cardiovascular risk factor where early identification is vital, leading the authors to explore deep learning on photoplethysmographic recordings with calibration intervals.
Do deep learning models using photoplethysmographic recordings and per-subject calibration accurately discriminate between normotensive and hypertensive individuals?
Do deep learning models using photoplethysmographic recordings and per-subject calibration accurately discriminate between normotensive and hypertensive individuals?
Deep learning models applied to photoplethysmographic recordings can accurately discriminate between normotensive and hypertensive states, with highest accuracy achieved when calibration measurements are closely spaced in time.
Answers are grounded in this paper and cite their sources.
Frequent calibration may enable PPG-based hypertension screening; leaves open prospective validation before clinical adoption.
Hypertension, a primary risk factor for various cardiovascular diseases, is a global health concern. Early identification and effective management of hypertensive individuals are vital for reducing associated health risks. This study explores the potential of deep learning (DL) techniques, specifically GoogLeNet, ResNet-18, and ResNet-50, for discriminating between normotensive (NTS) and hypertensive (HTS) individuals using photoplethysmographic (PPG) recordings. The research assesses the impact of calibration at different time intervals between measurements, considering intervals less than 1 h, 1-6 h, 6-24 h, and over 24 h. Results indicate that calibration is most effective when measurements are closely spaced, with an accuracy exceeding 90% in all the DL strategies tested. For calibration intervals below 1 h, ResNet-18 achieved the highest accuracy (93.32%), sensitivity (84.09%), specificity (97.30%), and F1-score (88.36%). As the time interval between calibration and test measurements increased, classification performance gradually declined. For intervals exceeding 6 h, accuracy dropped below 81% but with all models maintaining accuracy above 71% even for intervals above 24 h. This study provides valuable insights into the feasibility of using DL for hypertension risk assessment, particularly through PPG recordings. It demonstrates that closely spaced calibration measurements can lead to highly accurate classification, emphasizing the potential for real-time applications. These findings may pave the way for advanced, non-invasive, and continuous blood pressure monitoring methods that are both efficient and reliable.
No takes yet. Share an insight, caveat, or question.
Cano et al. (2023) studied Hypertension (n=69). Deep learning models (ResNet-18) with calibration vs. Calibration intervals >1h was evaluated on Accuracy of discriminating between normotensive and hypertensive individuals (93.32% accuracy). ResNet-18 deep learning models using photoplethysmographic recordings with calibration intervals below 1 hour achieved 93.32% accuracy in discriminating between normotensive and hypertensive individuals.
Synapse has enriched 10 related papers. Consider them for comparative context: