{
  "id": 19133087,
  "title": "AI predicts PTSD risk based on stories about what brought patients to the emergency room",
  "url": "https://urgent.news/2026/11/09/ai-predicts-ptsd-risk-based-on-stories-about-what-brought-patients-to",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-09T10:00:01.000Z",
  "source": {
    "name": "Medical Xpress",
    "slug": "medical-xpress",
    "url": "https://medicalxpress.com/news/2026-11-ai-ptsd-based-stories-brought.html"
  },
  "original_language": "en",
  "account": "A new study reveals an AI tool called PREVIA that can predict the risk of posttraumatic stress disorder (PTSD) in patients based on their narratives about their injuries leading to emergency room visits. Led by researchers at NYU Langone Health, the study found that PREVIA correctly identified over 95.4% of at-risk patients among 145 emergency department (ED) cases. This AI tool outperformed an ED clinician specializing in PTSD, who correctly identified 89% of the cases. PREVIA was developed using generative AI, which analyzes language patterns in patients' descriptions of their trauma to identify risk factors. The tool consists of three layers that scan for symptoms during the initial trauma, during the ED visit, and weigh risk and protective factors. The final layer combines these assessments with demographic information to produce a risk score and plain-language explanation. PREVIA could provide an early opportunity for timely care, as the first month after trauma is a critical window for finding those at risk for PTSD. This study, published in Nature Communications, demonstrates the potential of AI to detect PTSD risk early and improve patient outcomes.",
  "summary": "An AI tool can analyze patients' narratives about injuries that sent them to the emergency room to predict who will later develop posttraumatic stress disorder (PTSD), a new study found.",
  "key_points": [],
  "editors_take": null,
  "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."
}