{
  "id": 7917638,
  "title": "Tracking visits to public points of interest can inform community health measures",
  "url": "https://urgent.news/2026/09/17/tracking-visits-to-public-points-of-interest-can-inform-community",
  "topic": "science",
  "section": "Science",
  "published": "2026-09-17T01:20:02.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-09-tracking-community-health.html"
  },
  "original_language": "en",
  "account": "This study highlights how tracking anonymous cellphone users' visits to public places can enhance community health predictions. By adding place visitation data to a population health model, researchers from Penn State College of Earth and Mineral Sciences found an average 7.5% improvement in predictive accuracy for factors like depression and binge drinking. Geographic data from millions of anonymous users revealed that daily activity patterns at the neighborhood level could better predict health outcomes than traditional demographic and social statistics alone. Place visitation data had the most significant impact on models for depression and binge drinking, improving predictive capabilities by 38.8% in urban areas and 48.9% in rural areas. For urban areas, frequent visits to drinking places were linked to higher binge drinking and depression rates, while visits to bowling centers, amusement parks, religious organizations, limited-service restaurants, and malls were associated with lower binge drinking rates. In rural areas, visits to standalone casinos and convenience stores were linked to higher binge drinking prevalence, while visits to general stores, limited-service restaurants, and gas stations had lower binge drinking rates. The study emphasizes that while the findings reveal associations, they do not establish causation. Researchers suggest that using similar data from smart wearables could also help predict health outcomes and human mobility patterns.",
  "summary": "It's not so much where people live, but where they frequently spend their time, that can provide useful information for predicting community health measures. A team led by geographers in the Penn State College of Earth and Mineral Sciences found that adding place visitation data—geographic data points collected from millions of anonymous cellphone users with GPS-enabled devices—to a population…",
  "key_points": [],
  "editors_take": "This development suggests that incorporating location data into community health models can significantly improve predictive accuracy, especially in urban and rural areas, and for issues like depression and binge drinking.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}