Insights from a Scoping Review of Machine Learning Models Predicting Suicide in Military and Veteran Populations 4219

Tuesday, October 28, 2025

1:30 PM - 2:30 PM

Location: ROOM: Private Dining Room #6 >>> DIRECTIONS Third Floor >>> From the Main Elevator Bank, proceed right and then right again after the stairs. PDR #6 is located at the end of the corridor on the left.

Presenter(s)

Huaijin Xu, PhD Candidate (she/her/hers)

Graduate Research Assistant
University of Illinois at Urbana-Champaign
Champaign, IL, United States

Slides Slides
Kortney Wilcher

PhD Student
University of Illinois Urbana-Champaign
Urbana, IL, United States
XG

Xiaotian Gao

Assistant Professor
Baylor College of Medicine
Houston, Texas, United States
Quinn Ham

Undergraduate Research Assistant: Health Promotion and Rehabilitation Lab
University of Illinois: Urbana-Champaign
Champaign, IL, United States
Md Refat Uz Zaman Sajib (he/him/his)

Graduate Research Assistant
Department of Health & Kinesiology, College of Applied Health Sciences, University of Illinois Urbana-Champaign
Urbana, IL, United States
Mojtaba Khaliji

Graduate Research Assistant
University of Illinois Urbana-Champaign
Urbana, IL, United States
Chung-Yi Chiu, CRC, LPC

Associate Professor
University of Illinois Urbana-Champaign
Urbana, Illinois, United States

Let's leverage machine learning to serve our military members and veterans for better health and national security.

Learning Objectives:

Identify key machine learning techniques, such as Random Forest and Natural Language Processing, used in predicting suicide among U.S. military personnel and veterans, and understand their performance and application in recent studies.
Analyze the gaps in current research, including the lack of longitudinal designs, external validation, and underexplored predictors like childhood trauma and weapon possession, to inform future studies.
Apply insights from machine learning models to develop data-driven strategies for early identification and targeted interventions for suicide prevention in clinical settings.