Wearable health monitoring with seismocardiography and generative modeling
Bibliographic record
Abstract
Cardiovascular disease (CVD) remains a leading cause of death and disability worldwide, underscoring the critical need for early detection and continuous monitoring.Wearable technologies have emerged as a promising solution, offering non-invasive, real-time assessment of physiological signals in daily life.Among these, seismocardiography (SCG)-a technique that captures chest wall vibrations from cardiac activity using low-cost accelerometers-has the potential to enable affordable, comfortable, and continuous monitoring.However, several limitations hinder its widespread adoption.SCG signals are highly susceptible to motion artifacts during ambulatory activity, complicating their use in real-world settings.Furthermore, the scarcity of large, annotated SCG datasets limits the development and generalization of machine learning models.Compared to conventional modalities, SCG remains underutilized for extracting detailed cardiac features or supporting clinical use.This thesis aims to address these limitations and advance the utility of SCG for wearable cardiac monitoring by improving signal robustness, mitigating data scarcity, and demonstrating its functional relevance across diverse applications.NIBP, ICG, and PPG, respectively.This result demonstrates the feasibility of using a single motion sensor to estimate rich, multimodal cardiac information, offering a simplified and scalable alternative to traditional multi-sensor systems.Finally, we explore the use of synthetic SCG data to improve cross-domain pulmonary hypertension (PH) detection.We leverage generative models and introduce a dataset selection method to optimize the composition of synthetic and real training data.Our approach improves the out-of-distribution PH detection performance, increasing the area under the ROC curve from 0.51 to 0.86.These results highlight the potential of generative SCG modelling in a clinically relevant scenario with limited training data.Collectively, these contributions advance SCG as a viable and scalable modality for wearable cardiac monitoring.By improving signal robustness, addressing data scarcity, enabling multimodal estimation, and demonstrating clinical relevance, this work expands the role of SCG in both research and real-world applications.iii RESUME cardiographie vibratoire 6 axes : ECG, cardiographie d'impédance (ICG), photopléthysmographie (PPG) et pression artérielle non invasive (NIBP).Nous montrons que les signaux reconstruits correspondent fidèlement aux signaux de référence, avec des corrélations médianes de 0,808, 0,907, 0,833 et 0,929 pour l'ECG, la NIBP, l'ICG et la PPG respectivement.Cela montre qu'un capteur inertiel unique peut estimer des signaux cardiaques multimodaux riches, offrant une alternative simplifiée aux systèmes multisenseurs.Enfin, nous explorons l'utilisation de SCG synthétique pour améliorer la détection de l'hypertension pulmonaire (HP) en situation de changement de domaine.Nous exploitons des modèles génératifs et introduisons une méthode de sélection de données pour optimiser la composition des données d'entraînement synthétiques et réelles.Notre approche améliore la performance de détection de l'HP hors distribution, augmentant l'aire sous la courbe ROC de 0,51 à 0,86.Ces résultats mettent en évidence le potentiel du modélisation générative SCG dans un scénario cliniquement pertinent avec peu de données d'entraînement.Collectivement, ces contributions font progresser la SCG en tant que modalité viable et scalable pour la surveillance cardiaque portable.En améliorant la robustesse du signal, en répondant à la rareté des données, en permettant l'estimation multimodale et en démontrant sa pertinence clinique, ce travail étend le rôle de la SCG à la fois dans la recherche et dans les applications pratiques.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".