ArtEARial: Arterial Pressure Waveform Reconstruction Using Earbud Audio
Bibliographic record
Abstract
Noninvasive retrieval of the arterial pressure waveform (APW) enables a variety of cardiovascular monitoring tasks using pulse wave analysis (PWA). This paper demonstrates a novel way of reconstructing the APW using the audio recorded by an active noise-cancelling earbud. Our key observation is that low-frequency audio recorded in the ear canal is morphologically similar to the second derivative of the APW; however, differences in sensing site and modality lead to non-trivial differences in the waveforms. Our system, called ArtEARial, combines signal processing and deep learning to overcome these differences and accurately reconstruct the pulsatile APW. Using a dataset collected from 50 healthy adults, we compare ArtEARial's reconstructed APW against the signals produced by a continuous noninvasive blood pressure monitor. We demonstrate that the signal generated by ArtEARial yields better waveform fidelity, fiducial point localization, and PWA feature extraction compared to photoplethysmography (PPG) signals collected from the finger and earlobe. While ArtEARial is primarily envisioned for use while participants are seated in a quiet space, we also show that it is able to operate in scenarios with moderate background noise.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".