Hypertension Management via Photoplethysmography: An Ensemble Learning-Based Approach for Classification of Blood Pressure Using Fourier Synchrosqueezed Transform
Bibliographic record
Abstract
As the global prevalence of hypertension continues to rise, researchers have increasingly explored the potential of artificial intelligence (AI) for developing self-tracking blood pressure (BP) monitoring systems.An ideal approach would utilize photoplethysmography (PPG) signals, as they enable non-invasive wearable-based hypertension monitoring without reliance on cuff-based devices.This study investigated a PPG-based system for automated BP classification using an ensemble bagging technique with 200 decision trees.Given the nonstationary properties and motion artifact susceptibility of PPG signals, time-frequency (TF) analysis was conducted using Fourier Synchrosqueezed Transforms (FSST) to generate high-resolution TF representations.A set 44 features were extracted from the transformed signals, revealing the dynamic statistical properties over time.Three experimental models were trained on datasets incorporating different FSST variables.Unlike prior studies using small datasets, the models were trained on a large dataset comprising 46,572 subjectsegments across varied BP ranges, collected from the MIMIC-III intensive care database.This large dataset allowed boosting models accuracies and generalizability, achieving 100% training accuracy and 95.7% to 96.9% testing accuracy across the FSST experimental settings.The system also showed excellent results on three different classification tasksnormotension vs. hypertension, normotension vs. prehypertension, and non-hypertension vs. hypertension -with F1 scores reaching 99.1%.Moreover, the lightweight decision tree models enabled training in just minutes on this large dataset, indicating low computational complexity.Overall, this study presents an efficient PPG-based hypertension classification system.Results suggest potential for convenient clinical-grade BP monitoring beyond healthcare settings.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".