Using apple watch ECG data for heart rate variability monitoring and stress prediction: A pilot study
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Stress is an increasingly prevalent mental health condition that can have serious effects on human health. The development of stress prediction tools would greatly benefit public health by allowing policy initiatives and early stress-reducing interventions. The advent of mobile health technologies including smartphones and smartwatches has made it possible to collect objective, real-time, and continuous health data. We sought to pilot the collection of heart rate variability data from the Apple Watch electrocardiograph (ECG) sensor and apply machine learning techniques to develop a stress prediction tool. Random Forest (RF) and Support Vector Machines (SVM) were used to model stress based on ECG measurements and stress questionnaire data collected from 33 study participants. Data were stratified into socio-demographic classes to further explore our prediction model. Overall, the RF model performed slightly better than SVM, with results having an accuracy within the low end of state-of-the-art. Our models showed specificity in their capacity to assess "no stress" states but were less successful at capturing "stress" states. Overall, the results presented here suggest that, with further development and refinement, Apple Watch ECG sensor data could be used to develop a stress prediction tool. A wearable device capable of continuous, real-time stress monitoring would enable individuals to respond early to changes in their mental health. Furthermore, large-scale data collection from such devices would inform public health initiatives and policies.
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.
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 | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.000 |
| 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 it