Dual-Stream CNN-LSTM Architecture for Cuffless Blood Pressure Estimation From PPG and ECG Signals: A PulseDB Study
Bibliographic record
Abstract
Accurate and noninvasive blood pressure (BP) monitoring is essential for managing cardiovascular health, yet traditional cuff-based methods are uncomfortable and unsuitable for continuous use. Existing cuffless BP estimation techniques face limitations such as limited feature extraction capabilities, which can result in lower performance, and validation on nonstandard or small datasets, which raises concerns about generalizability. To address these challenges, we propose a novel convolutional neural network (CNN)-long short-term memory (LSTM) architecture that independently processes photoplethysmogram (PPG) and electrocardiogram (ECG) signals through separate CNN layers, enhancing morphological feature extraction. These layers are followed by a multilayer Bi-LSTM network that captures long-term temporal dependencies, improving BP prediction accuracy. Unlike prior studies, we validate our method on the PulseDB dataset, the largest publicly available dataset for BP estimation, comprising cleaned PPG, ECG, and arterial BP (ABP) waveforms from the MIMIC-III and VitalDB databases. Evaluated on data from 3027 individuals using fivefold cross-validation, our model achieved a mean absolute error (MAE) of 5.16 mmHg for systolic BP (SBP) and 3.24 mmHg for diastolic BP (DBP), with consistent performance across various age groups and genders. These results surpassed American National Standards Institute (ANSI)/Association for the Advancement of Medical Instrumentation (AAMI) standards and achieved an “A” grade by British Hypertension Society (BHS) standards, demonstrating the potential of this approach to improve patient comfort and care in diverse clinical and home environments.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".