{
  "id": 2877,
  "url": "https://nnemf.org/research/2877-the-relationship-between-mobile-phone-location-sensor-data",
  "title": "The relationship between mobile phone location sensor data and depressive symptom severity.",
  "authors": [
    "Sohrab Saeb",
    "Emily G Lattie",
    "Stephen M Schueller",
    "Konrad P Kording",
    "David C Mohr"
  ],
  "journal": "PeerJ",
  "year": "2016",
  "doi": "10.7717/peerj.2537",
  "pmid": "28344895",
  "abstract": "BACKGROUND: Smartphones offer the hope that depression can be detected using passively collected data from the phone sensors. The aim of this study was to replicate and extend previous work using geographic location (GPS) sensors to identify depressive symptom severity. METHODS: We used a dataset collected from 48 college students over a 10-week period, which included GPS phone sensor data and the Patient Health Questionnaire 9-item (PHQ-9) to evaluate depressive symptom severity at baseline and end-of-study. GPS features were calculated over the entire study, for weekdays and weekends, and in 2-week blocks. RESULTS: The results of this study replicated our previous findings that a number of GPS features, including location variance, entropy, and circadian movement, were significantly correlated with PHQ-9 scores ('s ranging from -0.43 to -0.46, -values < .05). We also found that these relationships were stronger when GPS features were calculated from weekend, compared to weekday, data. Although the correlation between baseline PHQ-9 scores with 2-week GPS features diminished as we moved further from baseline, correlations with the end-of-study scores remained significant regardless of the time point used to calculate the features. DISCUSSION: Our findings were consistent with past research demonstrating that GPS features may be an important and reliable predictor of depressive symptom severity. The varying strength of these relationships on weekends and weekdays suggests the role of weekend/weekday as a moderating variable. The finding that GPS features predict depressive symptom severity up to 10 weeks prior to assessment suggests that GPS features may have the potential as early warning signals of depression.",
  "effect": "unclear",
  "evidence": "low",
  "extraction": {
    "studyType": "cohort",
    "studyTypeLabel": "cohort",
    "effectDirection": "unclear",
    "evidenceLabel": "Low",
    "population": "48 college students",
    "sampleSize": "48",
    "exposure": "mobile phone · 10-week period",
    "confidencePct": "74",
    "peerReviewed": "yes",
    "mainFindings": "In 48 college students followed for 10 weeks, several GPS-derived features (e.g., location variance, entropy, circadian movement) were significantly correlated with PHQ-9 depressive symptom severity scores (r values approximately -0.43 to -0.46; p < .05). Associations were reported as stronger for weekend-derived GPS features than weekday-derived features, and correlations with end-of-study PHQ-9 scores remained significant across different 2-week feature windows.",
    "outcomes": [
      "Depressive symptom severity (PHQ-9)",
      "Correlation of GPS-derived mobility features with PHQ-9 scores"
    ],
    "limitations": [
      "Small sample size (48 participants)",
      "Observational/correlational design (cannot infer causality)",
      "Population limited to college students"
    ],
    "keywords": [
      "smartphone",
      "mobile phone",
      "GPS",
      "location sensor",
      "passive sensing",
      "digital phenotyping",
      "depression",
      "PHQ-9",
      "college students",
      "circadian movement",
      "entropy",
      "location variance"
    ],
    "hubs": [],
    "raw": "{\n  \"study_type\": \"cohort\",\n  \"exposure\": {\n    \"band\": null,\n    \"source\": \"mobile phone\",\n    \"frequency_mhz\": null,\n    \"sar_wkg\": null,\n    \"duration\": \"10-week period\"\n  },\n  \"population\": \"48 college students\",\n  \"sample_size\": 48,\n  \"outcomes\": [\n    \"Depressive symptom severity (PHQ-9)\",\n    \"Correlation of GPS-derived mobility features with PHQ-9 scores\"\n  ],\n  \"main_findings\": \"In 48 college students followed for 10 weeks, several GPS-derived features (e.g., location variance, entropy, circadian movement) were significantly correlated with PHQ-9 depressive symptom severity scores (r values approximately -0.43 to -0.46; p < .05). Associations were reported as stronger for weekend-derived GPS features than weekday-derived features, and correlations with end-of-study PHQ-9 scores remained significant across different 2-week feature windows.\",\n  \"effect_direction\": \"unclear\",\n  \"limitations\": [\n    \"Small sample size (48 participants)\",\n    \"Observational/correlational design (cannot infer causality)\",\n    \"Population limited to college students\"\n  ],\n  \"evidence_strength\": \"low\",\n  \"confidence\": 0.74,\n  \"peer_reviewed_likely\": \"yes\",\n  \"keywords\": [\n    \"smartphone\",\n    \"mobile phone\",\n    \"GPS\",\n    \"location sensor\",\n    \"passive sensing\",\n    \"digital phenotyping\",\n    \"depression\",\n    \"PHQ-9\",\n    \"college students\",\n    \"circadian movement\",\n    \"entropy\",\n    \"location variance\"\n  ],\n  \"suggested_hubs\": []\n}"
  },
  "synthesis": null,
  "synthesisStatus": "pending",
  "originalHref": "https://pubmed.ncbi.nlm.nih.gov/28344895/",
  "sourceUrl": "https://rfsafe.org/mel/paper.php?id=2877",
  "updated": "2026-02-13 06:54:30"
}