• Education
    • Higher Education
    • Scholarships & Grants
    • Online Learning
    • School Reforms
    • Research & Innovation
  • Lifestyle
    • Travel
    • Food & Drink
    • Fashion & Beauty
    • Home & Living
    • Relationships & Family
  • Technology & Startups
    • Software & Apps
    • Startup Success Stories
    • Startups & Innovations
    • Tech Regulations
    • Venture Capital
    • Artificial Intelligence
    • Cybersecurity
    • Emerging Technologies
    • Gadgets & Devices
    • Industry Analysis
  • About us
  • Contact
  • Advertise with Us
  • Privacy & Policy
Today Headline
  • Home
  • World News
    • Us & Canada
    • Europe
    • Asia
    • Africa
    • Middle East
  • Politics
    • Elections
    • Political Parties
    • Government Policies
    • International Relations
    • Legislative News
  • Business & Finance
    • Market Trends
    • Stock Market
    • Entrepreneurship
    • Corporate News
    • Economic Policies
  • Science & Environment
    • Space Exploration
    • Climate Change
    • Wildlife & Conservation
    • Environmental Policies
    • Medical Research
  • Health
    • Public Health
    • Mental Health
    • Medical Breakthroughs
    • Fitness & Nutrition
    • Pandemic Updates
  • Sports
    • Football
    • Basketball
    • Tennis
    • Olympics
    • Motorsport
  • Entertainment
    • Movies
    • Music
    • TV & Streaming
    • Celebrity News
    • Awards & Festivals
  • Crime & Justice
    • Court Cases
    • Cybercrime
    • Policing
    • Criminal Investigations
    • Legal Reforms
No Result
View All Result
  • Home
  • World News
    • Us & Canada
    • Europe
    • Asia
    • Africa
    • Middle East
  • Politics
    • Elections
    • Political Parties
    • Government Policies
    • International Relations
    • Legislative News
  • Business & Finance
    • Market Trends
    • Stock Market
    • Entrepreneurship
    • Corporate News
    • Economic Policies
  • Science & Environment
    • Space Exploration
    • Climate Change
    • Wildlife & Conservation
    • Environmental Policies
    • Medical Research
  • Health
    • Public Health
    • Mental Health
    • Medical Breakthroughs
    • Fitness & Nutrition
    • Pandemic Updates
  • Sports
    • Football
    • Basketball
    • Tennis
    • Olympics
    • Motorsport
  • Entertainment
    • Movies
    • Music
    • TV & Streaming
    • Celebrity News
    • Awards & Festivals
  • Crime & Justice
    • Court Cases
    • Cybercrime
    • Policing
    • Criminal Investigations
    • Legal Reforms
No Result
View All Result
Today Headline
No Result
View All Result
Home Science & Environment Medical Research

AI models are skilled at identifying appropriate responses to suicidal thoughts

March 12, 2025
in Medical Research
Reading Time: 4 mins read
A A
0
suicide
8
SHARES
17
VIEWS
Share on FacebookShare on Twitter


suicide
Credit: CC0 Public Domain

Two artificial intelligence platforms are nearly on par with—or sometimes surpass—mental health professionals in evaluating appropriate responses to people who exhibit suicidal thoughts, according to a new RAND study.

The work is published in the Journal of Medical Internet Research.

Though the researchers did not evaluate these models’ direct interactions with suicidal individuals, the findings underscore the importance of safe design and rigorous testing, and may provide lessons for those developing tools such as mental health apps built on AI.

The study used a standard assessment tool to test the knowledge of three major, large language models—ChatGPT by OpenAI, Claude by Anthropic and Gemini by Google. The project is among the first to gauge the knowledge of AI tools on suicide.

The assessment is designed to evaluate an individual’s knowledge about what constitutes appropriate responses to a series of statements that might be made by someone who is experiencing suicidal ideation.

Researchers had each of the large language models respond to the assessment tool, comparing the scores of the AI models against previous studies that assessed the knowledge of groups such as K–12 teachers, master’s-level psychology students, and practicing mental health professionals.

All three AI models showed a consistent tendency to overrate the appropriateness of clinician responses to suicidal thoughts, suggesting room for improvement in their calibration. However, the overall performance of ChatGPT and Claude proved comparable to that of professional counselors, nurses and psychiatrists as assessed during other studies.

“In evaluating appropriate interactions with individuals expressing suicidal ideation, we found these large language models can be surprisingly discerning,” said Ryan McBain, the study’s lead author and a senior policy researcher at RAND, a nonprofit research organization. “However, the bias of these models to rate responses as more appropriate than they are—at least according to clinical experts—indicates they should be further improved.”

Suicide is one of the leading causes of death among individuals under the age of 50 in the U.S., with the rate of suicide growing sharply in recent years.

Large language models have drawn widespread attention as a potential vehicle for helping or harming individuals who are depressed and at risk of suicide. The models are designed to interpret and generate human-like text responses to written and spoken queries, and they include broad health applications.

To assess the knowledge of the three large language models, researchers used an assessment known as the Suicidal Ideation Response Inventory (SIRI-2) that poses 24 hypothetical scenarios in which a patient exhibits depressive symptoms and suicidal ideation, followed by possible clinician responses.

The final score produced by Gemini was roughly equivalent to past scores produced by K-12 school staff prior to suicide intervention skills training. The final score produced by ChatGPT was closer to those exhibited by doctoral students in clinical psychology or master’s-level counselors. Claude exhibited the strongest performance, surpassing scores observed even among individuals who recently completed suicide intervention skills training, as well as scores from studies with psychiatrists and other mental health professionals.

“Our goal is to help policymakers and tech developers recognize both the promise and the limitations of using large language models in mental health,” McBain said. “We are pressure testing a benchmark that could be used by tech platforms building mental health care, which would be especially impactful in communities that have limited resources. But caution is essential—these AI models aren’t replacements for crisis lines or professional care.”

Researchers say that future studies should include directly studying how AI tools respond to questions that might be posted by people who are having suicidal ideation or are experiencing another type of mental health crisis.

Other authors of the study are Jonathan H Cantor, Li Ang Zhang, Aaron Kofner, Joshua Breslau and Bradley Stein, all of RAND; Olesya Baker, Fang Zhang and Hao Yu, all of the Harvard School of Medicine; Alyssa Halbisen of the Harvard Pilgrim Health Care Institute; and Ateev Mehrotra of the Brown University School of Public Health.

More information:
Ryan K McBain et al, Competency of Large Language Models in Evaluating Appropriate Responses to Suicidal Ideation: Comparative Study, Journal of Medical Internet Research (2025). DOI: 10.2196/67891

Provided by
RAND Corporation


Citation:
AI models are skilled at identifying appropriate responses to suicidal thoughts (2025, March 12)
retrieved 12 March 2025
from https://medicalxpress.com/news/2025-03-ai-skilled-responses-suicidal-thoughts.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.



suicide
Credit: CC0 Public Domain

Two artificial intelligence platforms are nearly on par with—or sometimes surpass—mental health professionals in evaluating appropriate responses to people who exhibit suicidal thoughts, according to a new RAND study.

The work is published in the Journal of Medical Internet Research.

Though the researchers did not evaluate these models’ direct interactions with suicidal individuals, the findings underscore the importance of safe design and rigorous testing, and may provide lessons for those developing tools such as mental health apps built on AI.

The study used a standard assessment tool to test the knowledge of three major, large language models—ChatGPT by OpenAI, Claude by Anthropic and Gemini by Google. The project is among the first to gauge the knowledge of AI tools on suicide.

The assessment is designed to evaluate an individual’s knowledge about what constitutes appropriate responses to a series of statements that might be made by someone who is experiencing suicidal ideation.

Researchers had each of the large language models respond to the assessment tool, comparing the scores of the AI models against previous studies that assessed the knowledge of groups such as K–12 teachers, master’s-level psychology students, and practicing mental health professionals.

All three AI models showed a consistent tendency to overrate the appropriateness of clinician responses to suicidal thoughts, suggesting room for improvement in their calibration. However, the overall performance of ChatGPT and Claude proved comparable to that of professional counselors, nurses and psychiatrists as assessed during other studies.

“In evaluating appropriate interactions with individuals expressing suicidal ideation, we found these large language models can be surprisingly discerning,” said Ryan McBain, the study’s lead author and a senior policy researcher at RAND, a nonprofit research organization. “However, the bias of these models to rate responses as more appropriate than they are—at least according to clinical experts—indicates they should be further improved.”

Suicide is one of the leading causes of death among individuals under the age of 50 in the U.S., with the rate of suicide growing sharply in recent years.

Large language models have drawn widespread attention as a potential vehicle for helping or harming individuals who are depressed and at risk of suicide. The models are designed to interpret and generate human-like text responses to written and spoken queries, and they include broad health applications.

To assess the knowledge of the three large language models, researchers used an assessment known as the Suicidal Ideation Response Inventory (SIRI-2) that poses 24 hypothetical scenarios in which a patient exhibits depressive symptoms and suicidal ideation, followed by possible clinician responses.

The final score produced by Gemini was roughly equivalent to past scores produced by K-12 school staff prior to suicide intervention skills training. The final score produced by ChatGPT was closer to those exhibited by doctoral students in clinical psychology or master’s-level counselors. Claude exhibited the strongest performance, surpassing scores observed even among individuals who recently completed suicide intervention skills training, as well as scores from studies with psychiatrists and other mental health professionals.

“Our goal is to help policymakers and tech developers recognize both the promise and the limitations of using large language models in mental health,” McBain said. “We are pressure testing a benchmark that could be used by tech platforms building mental health care, which would be especially impactful in communities that have limited resources. But caution is essential—these AI models aren’t replacements for crisis lines or professional care.”

Researchers say that future studies should include directly studying how AI tools respond to questions that might be posted by people who are having suicidal ideation or are experiencing another type of mental health crisis.

Other authors of the study are Jonathan H Cantor, Li Ang Zhang, Aaron Kofner, Joshua Breslau and Bradley Stein, all of RAND; Olesya Baker, Fang Zhang and Hao Yu, all of the Harvard School of Medicine; Alyssa Halbisen of the Harvard Pilgrim Health Care Institute; and Ateev Mehrotra of the Brown University School of Public Health.

More information:
Ryan K McBain et al, Competency of Large Language Models in Evaluating Appropriate Responses to Suicidal Ideation: Comparative Study, Journal of Medical Internet Research (2025). DOI: 10.2196/67891

Provided by
RAND Corporation


Citation:
AI models are skilled at identifying appropriate responses to suicidal thoughts (2025, March 12)
retrieved 12 March 2025
from https://medicalxpress.com/news/2025-03-ai-skilled-responses-suicidal-thoughts.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.


Tags: Health ResearchHealth Research NewsHealth ScienceMedicine ResearchMedicine Research NewsMedicine Science
Previous Post

Trump says he feels ‘very badly’ for fired federal workers but ‘many of them don’t work at all’

Next Post

Could Mars’ red color have formed under wet conditions?

Related Posts

Autism and ADHD have distinct brain connectivity signatures, study finds

Autism and ADHD have distinct brain connectivity signatures, study finds

May 31, 2025
8

Journalists Draw Link Between Internet Dead Zones, Threatened Medicaid Cuts, and Health

May 31, 2025
8
Next Post
Mars

Could Mars’ red color have formed under wet conditions?

  • Trending
  • Comments
  • Latest
Family calls for change after B.C. nurse dies by suicide after attacks on the job

Family calls for change after B.C. nurse dies by suicide after attacks on the job

April 2, 2025
Pioneering 3D printing project shares successes

Product reduces TPH levels to non-hazardous status

November 27, 2024

Hospital Mergers Fail to Deliver Better Care or Lower Costs, Study Finds todayheadline

December 31, 2024

Police ID man who died after Corso Italia fight

December 23, 2024
Harris tells supporters 'never give up' and urges peaceful transfer of power

Harris tells supporters ‘never give up’ and urges peaceful transfer of power

0
Des Moines Man Accused Of Shooting Ex-Girlfriend's Mother

Des Moines Man Accused Of Shooting Ex-Girlfriend’s Mother

0

Trump ‘looks forward’ to White House meeting with Biden

0
Catholic voters were critical to Donald Trump’s blowout victory: ‘Harris snubbed us’

Catholic voters were critical to Donald Trump’s blowout victory: ‘Harris snubbed us’

0
Egypt Independent

South Korea is voting for a new president after six months of political chaos. Here’s what to know

June 1, 2025
Copy Link

PSG win first Champions League by utterly humiliating Inter Milan

June 1, 2025
Customer interacts with AI system.

Prediction: This Artificial Intelligence (AI) Stock Could Be the Next Great Value Play todayheadline

June 1, 2025

What is the best cruise brand? todayheadline

June 1, 2025

Recent News

Egypt Independent

South Korea is voting for a new president after six months of political chaos. Here’s what to know

June 1, 2025
2
Copy Link

PSG win first Champions League by utterly humiliating Inter Milan

June 1, 2025
3
Customer interacts with AI system.

Prediction: This Artificial Intelligence (AI) Stock Could Be the Next Great Value Play todayheadline

June 1, 2025
4

What is the best cruise brand? todayheadline

June 1, 2025
4

TodayHeadline is a dynamic news website dedicated to delivering up-to-date and comprehensive news coverage from around the globe.

Follow Us

Browse by Category

  • Africa
  • Asia
  • Basketball
  • Business & Finance
  • Climate Change
  • Crime & Justice
  • Cybersecurity
  • Economic Policies
  • Elections
  • Entertainment
  • Entrepreneurship
  • Environmental Policies
  • Europe
  • Football
  • Gadgets & Devices
  • Health
  • Medical Research
  • Mental Health
  • Middle East
  • Motorsport
  • Olympics
  • Politics
  • Public Health
  • Relationships & Family
  • Science & Environment
  • Software & Apps
  • Space Exploration
  • Sports
  • Stock Market
  • Technology & Startups
  • Tennis
  • Travel
  • Uncategorized
  • Us & Canada
  • Wildlife & Conservation
  • World News

Recent News

Egypt Independent

South Korea is voting for a new president after six months of political chaos. Here’s what to know

June 1, 2025
Copy Link

PSG win first Champions League by utterly humiliating Inter Milan

June 1, 2025
  • Education
  • Lifestyle
  • Technology & Startups
  • About us
  • Contact
  • Advertise with Us
  • Privacy & Policy

© 2024 Todayheadline.co

Welcome Back!

OR

Login to your account below

Forgotten Password?

Retrieve your password

Please enter your username or email address to reset your password.

Log In
No Result
View All Result
  • Business & Finance
  • Corporate News
  • Economic Policies
  • Entrepreneurship
  • Market Trends
  • Crime & Justice
  • Court Cases
  • Criminal Investigations
  • Cybercrime
  • Legal Reforms
  • Policing
  • Education
  • Higher Education
  • Online Learning
  • Entertainment
  • Awards & Festivals
  • Celebrity News
  • Movies
  • Music
  • Health
  • Fitness & Nutrition
  • Medical Breakthroughs
  • Mental Health
  • Pandemic Updates
  • Lifestyle
  • Fashion & Beauty
  • Food & Drink
  • Home & Living
  • Politics
  • Elections
  • Government Policies
  • International Relations
  • Legislative News
  • Political Parties
  • Africa
  • Asia
  • Europe
  • Middle East
  • Artificial Intelligence
  • Cybersecurity
  • Emerging Technologies
  • Gadgets & Devices
  • Industry Analysis
  • Basketball
  • Football
  • Motorsport
  • Olympics
  • Climate Change
  • Environmental Policies
  • Medical Research
  • Science & Environment
  • Space Exploration
  • Wildlife & Conservation
  • Sports
  • Tennis
  • Technology & Startups
  • Software & Apps
  • Startup Success Stories
  • Startups & Innovations
  • Tech Regulations
  • Venture Capital
  • Uncategorized
  • World News
  • Us & Canada
  • Public Health
  • Relationships & Family
  • Travel
  • Research & Innovation
  • Scholarships & Grants
  • School Reforms
  • Stock Market
  • TV & Streaming
  • Advertise with Us
  • Privacy & Policy
  • About us
  • Contact

© 2024 Todayheadline.co