Key takeaway
Using smartphone and wearable data from 479 people with major depressive disorder, at least 8 days (range 2-12) in a 14-day window were needed to calculate most of 21 features reliably. Some features, such as sleep onset time, tracked depression scores better across people than within a person, while others, such as wakefulness after sleep onset, did the reverse. The abstract reports no prediction accuracy.
Study design
Research article
Reading basis
Published abstract
Reading focus
Design & applicability
The research question
Depression is often missed or treated late, partly because people recall symptoms poorly and symptoms fluctuate. Passive data from phones and wearables could allow continuous monitoring, but results have been mixed. The authors addressed three challenges: how much missing data is acceptable, whether features track differences between people or changes within a person, and how differently depression shows up in behavior across people.
Who and how
Retrospective analysis of smartphone and wearable data from 479 participants with major depressive disorder. Twenty-one features capturing mobility, sleep and smartphone use were extracted. The effect of the number of available days on feature quality was assessed with the intraclass correlation coefficient and Bland-Altman analysis. Relationships with the 8-item Patient Health Questionnaire (PHQ-8), measured every 14 days, were examined with individual-mean correlation, repeated measures correlation and a linear mixed effects model. Participants were then clustered by their behavioral difference between high-PHQ-8 (depression) and low-PHQ-8 (no depression) periods using a Gaussian mixture model.
What it found
The authors’ reported results. Read each estimate with its population and uncertainty.
- 1Reliable calculation of most features in the 14-day window needed at least 8 days of data (range 2-12).
- 2Sleep onset time correlated better with PHQ-8 scores cross-sectionally (between people) than longitudinally (within a person).
- 3Wakefulness after sleep onset correlated well with PHQ-8 scores longitudinally but worse cross-sectionally.
- 4Participants separated into 3 distinct clusters according to how their behavior differed between periods of depression and periods without depression.
Limits & uncertainty
- 1The abstract gives no correlation values, prediction accuracy or sample sizes for the clusters, so it cannot be judged how well these features can actually predict depression severity.
- 2Everyone in the dataset had major depressive disorder, so the results say little about screening people without a diagnosis.
- 3The PHQ-8 was measured only every 14 days and is a self-report questionnaire, so the link with daily behavior features is coarse.
- 4This reading is based on the abstract only.
What to take from it
Passive phone and wearable measures of sleep and mobility may help follow depression symptoms, but the readings need enough days of data, and some signals reflect differences between people more than changes within one person. They are not a diagnostic test. Mood concerns or changes in sleep that persist deserve a conversation with a clinician.
Reading your own data
If you track sleep onset time, time awake after sleep onset, and activity with a wearable, look at your own multi-week trends against your own baseline on the same device, since several days are needed for a stable average. Pair it with a brief mood check-in, and share patterns with your care team rather than using the numbers to self-diagnose.
How to read this evidence
The index does not establish a precise design. Read the methods before making causal claims; check population, comparator, outcomes and uncertainty in the source.
Authors’ structured abstract English
The attributed English abstract is reproduced under the recorded open licence. It is source material, not a MoveVitals interpretation. The prepared analysis above separates the authors’ findings from our interpretation.
Background
Major depressive disorder (MDD) affects millions of people worldwide, but timely treatment is not often received owing in part to inaccurate subjective recall and variability in the symptom course. Objective and frequent MDD monitoring can improve subjective recall and help to guide treatment selection. Attempts have been made, with varying degrees of success, to explore the relationship between the measures of depression and passive digital phenotypes (features) extracted from smartphones and wearables devices to remotely and continuously monitor changes in symptomatology. However, a number of challenges exist for the analysis of these data. These include maintaining participant engagement over extended time periods and therefore understanding what constitutes an acceptable threshold of missing data; distinguishing between the cross-sectional and longitudinal relationships for different features to determine their utility in tracking within-individual longitudinal variation or screening individuals at high risk; and understanding the heterogeneity with which depression manifests itself in behavioral patterns quantified by the passive features.
Objective
We aimed to address these 3 challenges to inform future work in stratified analyses.
Methods
Using smartphone and wearable data collected from 479 participants with MDD, we extracted 21 features capturing mobility, sleep, and smartphone use. We investigated the impact of the number of days of available data on feature quality using the intraclass correlation coefficient and Bland-Altman analysis. We then examined the nature of the correlation between the 8-item Patient Health Questionnaire (PHQ-8) depression scale (measured every 14 days) and the features using the individual-mean correlation, repeated measures correlation, and linear mixed effects model. Furthermore, we stratified the participants based on their behavioral difference, quantified by the features, between periods of high (depression) and low (no depression) PHQ-8 scores using the Gaussian mixture model.
Results
We demonstrated that at least 8 (range 2-12) days were needed for reliable calculation of most of the features in the 14-day time window. We observed that features such as sleep onset time correlated better with PHQ-8 scores cross-sectionally than longitudinally, whereas features such as wakefulness after sleep onset correlated well with PHQ-8 longitudinally but worse cross-sectionally. Finally, we found that participants could be separated into 3 distinct clusters according to their behavioral difference between periods of depression and periods of no depression.
Conclusions
This work contributes to our understanding of how these mobile health-derived features are associated with depression symptom severity to inform future work in stratified analyses.
Sources & attribution
Challenges in Using mHealth Data From Smartphones and Wearable Devices to Predict Depression Symptom Severity: Retrospective Analysis.
Sun S, Folarin AA, Zhang Y, Cummins N, Garcia-Dias R, Stewart C, Ranjan Y, Rashid Z, Conde P, Laiou P, Sankesara H, Matcham F, Leightley D, White KM, Oetzmann C, Ivan A, Lamers F, Siddi S, Simblett S, Nica R, Rintala A, Mohr DC, Myin-Germeys I, Wykes T, Haro JM, Penninx BWJH, Vairavan S, Narayan VA, Annas P, Hotopf M, Dobson RJB, RADAR-CNS Consortium.
Journal of medical Internet research · 2023-08-14
DOI: 10.2196/45233 ↗PubMed · 37578823 ↗Europe PMC · Recorded licence: cc by ↗Abstract © the original authors, reproduced under the recorded open licence. Translations support reading; use the English record to check terminology and numerical results. Our methodological interpretation is separate from the authors’ conclusions.
MoveVitals editorial interpretation · educational content · no individual clinical review recorded
Sources checked 2026-11-01
Practical guides
Read in context
Activity–stroke and heart attack curves differ by accelerometer processing method
Among 90,237 UK Biobank adults free of cardiovascular disease at baseline, followed until December 2022 for 1,298 strokes and 2,031 myocardial infarctions, the shape of the link between moderate-vigorous physical activity (MVPA) and each outcome depended on how the accelerometer data were processed. For stroke, hazard fell in a straight line only with the machine-learning metric; for myocardial infarction, two metrics gave a curved decline and activity counts a straight one. The abstract gives no hazard ratios, so it shows that methods disagree, not which one is right, and the findings are observational associations.
Preventive Medicine
Smartwatch data as forensic evidence: heart rate is best validated, the rest uneven
A systematic review and meta-analysis of studies on smartwatches from four major brands, framed around digital forensics, found that heart rate was both the most studied and the most accurate measure. Step count, distance, energy expenditure, activity classification and sleep were less consistently validated, and results varied by brand, protocol and reporting. The abstract gives no pooled numbers, and most studies were run in healthy people in laboratories, so it cannot say how a particular watch performs for a particular person in daily life.
Forensic Science International
Activity trackers: about 1,800 more steps a day, but small effects on other outcomes
An umbrella review of 39 systematic reviews and meta-analyses, covering 163,992 participants, found that activity trackers were associated with more physical activity (SMD 0.3–0.6), equating to about 1,800 extra steps and 40 minutes more walking per day, and with a bodyweight reduction of about 1 kg. Effects on blood pressure, cholesterol, glycosylated haemoglobin, quality of life and pain were typically small and often non-significant. The abstract does not say what else came with the trackers in these programs or how much the reviews overlap, so the gains cannot be credited to the device alone.
The Lancet Digital Health
Seven sleep trackers: good at spotting sleep, weak on wake and sleep stages
In a sleep laboratory, 34 healthy young adults wore a subset of seven consumer sleep trackers for three nights. Against polysomnography every device detected sleep very well (sensitivity 0.93 or higher) but caught wake poorly (specificity 0.18–0.54), and five of the seven matched or beat research actigraphy (specificity 0.39). Sleep-stage estimates were inconsistent, and the participants were healthy adults aged 18 to 35 in a fixed 8-hour bed window, with each device tested in only 11 to 20 of them, so the results say little about people with sleep problems.
Sleep

