0795 IMPORTANCE OF SLEEP DATA IN PREDICTING NEXT-DAY STRESS, HAPPINESS, AND HEALTH IN COLLEGE STUDENTS
Bibliographic record
Abstract
Perceived wellbeing, as measured by self-reported health, stress, and happiness, has a number of important clinical health consequences. The ability to model and predict these measures could therefore be immensely beneficial in the treatment and prevention of mental illness. However, predicting self-reported health, stress, and happiness is a difficult problem often requiring large, multi-modal datasets. We show that the accuracy for predicting next-day wellbeing is improved when including simple sleep features. Data from 144 college students were collected during a 30-day study. Participants wore two sensors to collect actigraphy and physiology data, installed a data logger on their smartphone, and filled out online surveys. Participants self-reported daily on three wellbeing measures (stress - calm; sad - happy; sick - healthy) using a visual analog scale (later scored 0 to 100). The top and bottom 40% of scores were assigned positive and negative labels, respectively. A hierarchical bayes machine learning algorithm was trained to predict each next-day wellbeing label on two data sets: (1) including self-reported sleep features (e.g., self-reported sleep latency, bedtime, and wake time), and (2) discarding sleep features. Both data sets include approximately 20 features computed from wearable sensors, phone, and online surveys. In total, 2,769 days of data were used. Without including the sleep features, hold-out test accuracies for stress, happiness, and healthy were 79.62%, 78.24%, 83.55%, respectively. When including sleep features, the accuracies were improved for the stress and happy predictions to 80.67%, 80.40%, respectively; however the healthy prediction accuracy worsened slightly to 83.12%. Using McNemar’s test we find that including sleep features does not significantly improve the classifiers for the stress or healthy prediction, but does significantly improve the classifier for the happy prediction (p<0.15). The inclusion of sleep features improved the prediction of next-data self-reported stress/calm and happy/sad metric of individuals above a classifier using features from smartphones and wearables. Future studies of personalized prediction of happy/sad and stress/calm ought to consider including self-reported sleep features in order to improve prediction. MIT Media Lab Consortium, NIH (R01GM105018, K24HL105664), Samsung Electronics, and Canada’s NSERC program.
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 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 | 0.002 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".