# Improving Suicide Prediction using NLP-Extracted Social Determinants of Health

> **NIH NIH R01** · UNIVERSITY OF MASSACHUSETTS LOWELL · 2022 · $740,228

## Abstract

Improving Suicide Prediction using NLP-Extracted Social Determinants of Health
Suicide is among the leading causes of death worldwide and among United States Veterans in
particular. Current methods of risk assessment are limited in their ability to accurately identify
patients who are at the highest risk of suicide. The overarching goal of this proposal is to
strengthen suicide prediction efforts by gaining a more granular understanding of the
association between social determinants of health and suicide risk.
Social determinants of health (SDH) refer to the conditions in which people are born, live, work,
and age. A number of SDH are known risk factors for suicide. While SDH could be obtained
from the structured EHR data, their scope is limited. A recent study has shown that EHR notes
contain about 90 times more information about SDH than the structured data. To address this
gap, we propose a stepwise approach that leverages the power of EHR and new computational
methdologies to explore associations between natural language processing extracted SDH and
suicide ideation, attempt and death. This approach is critical to the development of next-
generation suicide prevention tools.

## Key facts

- **NIH application ID:** 10428629
- **Project number:** 5R01MH125027-03
- **Recipient organization:** UNIVERSITY OF MASSACHUSETTS LOWELL
- **Principal Investigator:** HONG YU
- **Activity code:** R01 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2022
- **Award amount:** $740,228
- **Award type:** 5
- **Project period:** 2020-09-01 → 2024-06-30

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10428629

## Citation

> US National Institutes of Health, RePORTER application 10428629, Improving Suicide Prediction using NLP-Extracted Social Determinants of Health (5R01MH125027-03). Retrieved via AI Analytics 2026-05-23 from https://api.ai-analytics.org/grant/nih/10428629. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*