Classifying Abnormal Arterial Pulse Patterns in Cardiovascular Diseases: A Photoplethysmography and Machine Learning Approach
Bibliographic record
Abstract
In the realm of cardiovascular disease (CVD) diagnostics, the morphological changes in arterial blood pressure (ABP) attributable to various pathologies have long been recognized.This study explores the innovative intersection of photoplethysmography (PPG) signals and machine learning (ML) techniques, focusing on the classification of abnormal arterial pulse (AAP) patterns, a domain hitherto not extensively researched.The challenges of this endeavor, primarily the scarcity of clinically labeled AAP waveform datasets, are acknowledged.This scarcity stems from the difficulty in sourcing volunteers exhibiting diverse disease-related AAPs and the inherent risks associated with ABP measurement procedures.Furthermore, current guidelines do not sufficiently characterize AAP traits, limiting the application of PPG and ML in detecting ABP-related anomalies predominantly to hypertension and hypotension cases.Addressing these gaps, the present study introduces a PPG-based classification system employing k-nearest neighbors (KNN) and bagged trees (BT) algorithms.These were selected for their proficiency in modeling complex, nonlinear relationships while maintaining lower complexity levels compared to alternatives like Deep Neural Networks (DNN) or Support Vector Machines (SVM).Additionally, novel detectors have been developed for identifying key pulse wave features such as troughs and dicrotic notches, crucial for AAP pattern recognition and PPG feature extraction.The methodology encompasses a modeling process that references pathological cases known to manifest specific AAP patterns.An extensive evaluation involving 1,120 PPG and ABP signals yielded impressive accuracies of 90.9% and 91% for KNN and BT algorithms, respectively.Across 11 distinct classes, both algorithms exhibited robust performance, underscoring their potential as effective AAP detectors.These results signify an advancement over existing classifiers, particularly in generating multiple CVD-related classes with reduced complexity at both modular and instance levels.The system's capability to associate AAPs with CVDs positions it as a promising, non-invasive, and cost-effective tool for diverse applications including doctor-assisted diagnosis, remote post-surgery monitoring, nursing alerts, and personalized health management.This approach not only meets emerging healthcare needs but also mitigates the risks associated with current invasive diagnostic practices.
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".