Application of a mobile health data platform for public health surveillance: A case study in stress monitoring and prediction
Bibliographic record
Abstract
Background: Public health surveillance involves the collection, analysis and dissemination of data to improve population health. The main sources of data for public health decision-making are surveys, typically comprised of self-report which may be subject to biases, costs and delays. To complement subjective data, objective measures from sensors could potentially be used. Specifically, advancements in personal mobile and wearable technologies enable the collection of real-time and continuous health data. Objective: In this context, the goal of this work is to apply a mobile health platform (MHP) that extracts health data from the Apple Health repository to collect data in daily-life scenarios and use it for the prediction of stress, a major public health issue. Methods: A pilot study was conducted with 45 participants over 2 weeks, using the MHP to collect stress-related data from Apple Health and perceived stress self-reports. Apple, Withings and Empatica devices were distributed to participants and collected a wide range of data, including heart rate, sleep, blood pressure, temperature, and weight. These were used to train random forests and support vector machines. The SMOTE technique was used to handle imbalanced datasets. Results: Accuracy and f1-macro scores were in line with state-of-the-art models for stress prediction above 60% for the majority of analyses and samples analysed. Apple Watch sleep features were particularly good predictors, with most models with these data achieving results around 70%. Conclusions: A system such as the MHP could be used for public health data collection, complementing traditional self-reporting methods when possible. The data collected with the system was promising for monitoring and predicting stress in a population.
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 | 0.005 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".