Using AI on health record notes to find loneliness and suicide risk in older adults
Official title: Integrating Loneliness and Social Isolation Insights into Late-Life Suicide Risk Prediction Through the Digital Phenotyping of Electronic Health Records
Funded at Emory University · NIH-11231275 · Data updated 2026-11-12
This project uses artificial intelligence to read doctors' notes and medical records to spot loneliness and help reduce suicide risk for older adults.
Quick facts
| Grant type | R21 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Emory University NIH-funded |
| Lab location | 1 site (Atlanta, United States) |
| Project start | November 13, 2024 |
| Project end | October 31, 2026 |
| Funding year | 2026 |
| Award (this year) | $199,024 |
| NIH project number | 5R21MH139049-02 |
| Project ID | NIH-11231275 on NIH RePORTER |
Who could benefit from this research
✓Could help
Ideal participants are older adults who receive care in the participating health system, especially those who report or show signs of loneliness or social isolation in their medical records.
✕Less likely to help
People who are younger, who do not get care within the participating health system, or whose records do not include narrative notes about social circumstances are unlikely to benefit directly.
What this research studies
You would be part of work that looks at the words and notes clinicians write in electronic health records to find clues about loneliness and social isolation. The team will apply modern, explainable AI and language-model tools to pull out narrative signs that standard billing codes miss. They will link those signals with visit patterns and other health data to improve predictions of suicide risk in later life. The goal is to create clear, usable risk markers that clinicians could use to offer help sooner.
Why it matters
Potential benefit: If successful, this could help clinicians identify isolated older adults earlier and offer timely support or interventions to lower suicide risk.
How similar studies have gone: Prior work using NLP on records has shown promise for predicting suicide risk, but combining detailed loneliness signals with modern language models and interpretable AI is relatively new.
Where this research is happening
-
Emory University
Atlanta, United States Active
Researchers
- Principal investigator: Bozkurt, Selen — Emory University
- Study coordinator: Bozkurt, Selen
Related research
Other NIH-funded projects on the same topics.
-
Using digital health records to predict suicide risk in older adults based on loneliness and social isolation.
This study is looking at how feeling lonely or isolated can make older adults more likely to think about suicide, and it uses advanced technology to better spot those at risk so they can get help sooner.
-
How isolation and COVID-19 affected suicide risk in youth
This project looks at how social isolation during the COVID-19 era may influence suicide risk among people aged 21 and younger.
-
How social connections and loneliness affect thinking in older adults
A study of how feeling lonely and actually having few social contacts influence thinking skills and risk of dementia in older adults.
-
Trajectories of loneliness and social isolation in older adults with HIV who use methamphetamine
This study follows older adults living with HIV who use methamphetamine to understand how loneliness and isolation change over time and relate to health care use and wellbeing.
-
Understanding how social isolation and loneliness affect brain health in Alzheimer’s risk
This research looks at how feeling isolated or lonely and the social environment might influence brain changes related to Alzheimer’s disease in adults.
-
Social factors and brain health: how loneliness and social support affect stroke risk and recovery
Researchers will study how social isolation and lack of support influence brain injury, stroke risk, and recovery in people over 21, using long-term data from large population studies.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.