Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Hands-on Education to Increase Comfort and Knowledge Utilizing In-Check<sup>TM</sup> Inhaler Training Device in Medical Trainees.

Journal of primary care & community health·2026
Same author

Readmission and mortality outcomes with subsequent follow-up hemoglobin checks in general medical patients with hospital-acquired anemia.

Postgraduate medicine·2026
Same author

A scheduling intervention to increase video visits in family medicine.

Journal of telemedicine and telecare·2026
Same author

Comparison of Emergency Department Attendance After Emergency Care Recommendations from Nurse and Online eHealth Self-Triage.

Telemedicine journal and e-health : the official journal of the American Telemedicine Association·2026
Same author

The role of hyperbaric oxygen therapy for treating spinal cord injury: Mechanisms, considerations, and research outcomes.

eNeurologicalSci·2026
Same author

Prostate Screening.

Journal of primary care & community health·2026

Related Experiment Video

Updated: Jul 1, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Building a Natural Language Processing Artificial Intelligence to Predict Suicide-Related Events Based on Patient

Archis R Bhandarkar1, Namrata Arya2, Keldon K Lin2

  • 1Mayo Clinic Alix School of Medicine, Rochester, MN.

Mayo Clinic Proceedings. Digital Health
|April 10, 2025
PubMed
Summary
This summary is machine-generated.

An artificial intelligence model using natural language processing can predict 30-day suicide-related events (SRE) from patient portal messages. Sentiment analysis within messages proved more effective than keyword frequency for predicting SRE.

More Related Videos

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
04:19

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

Published on: May 10, 2022

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

Related Experiment Videos

Last Updated: Jul 1, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis
04:19

A Computer-Based Platform for Aiding Clinicians in Eating Disorder Analysis and Diagnosis

Published on: May 10, 2022

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Computational Linguistics
  • Mental Health Informatics

Background:

  • Patient portal messages offer a rich source of data for understanding patient well-being.
  • Predicting suicide-related events (SRE) is crucial for timely intervention.
  • Existing methods for SRE prediction may not fully leverage unstructured patient communication.

Purpose of the Study:

  • To develop and evaluate a natural language processing (NLP) artificial intelligence (AI) model for predicting 30-day suicide-related events (SRE).
  • To assess the utility of patient portal message features, including sentiment and metadata, in SRE prediction.

Main Methods:

  • A dataset of 840 patient portal messages (420 with and 420 without a 30-day SRE) was analyzed.
  • Features extracted included keyword frequencies, message metadata, and sentiment scores.
  • A neural network machine learning model was trained and evaluated using the extracted features.

Main Results:

  • The NLP-AI model achieved an area under the receiver operating curve of 0.710, with 56.0% sensitivity and 69.0% specificity.
  • Messages associated with SREs exhibited lower mean sentiment scores, higher word counts, and different punctuation usage compared to control messages.
  • Sentiment analysis was a more significant predictor of SREs than individual word frequencies.

Conclusions:

  • An NLP-AI model can predict 30-day SREs from patient portal messages with performance comparable to established suicide assessment tools.
  • The overall tone and sentiment of patient messages are critical indicators for predicting SREs.
  • This approach demonstrates the potential of leveraging routine clinical communication for mental health risk assessment.