Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide Prevention

Artificial Intelligence (AI)-based systems have been proposed to aid Mental Health Professionals (MHPs) in various tasks, including the prevention of suicide by identifying Suicidal Ideation (SI). However, these systems may lack transparency and thereby create mistrust among MHPs. Explainable Artifi...

Full description

Saved in:
Bibliographic Details
Main Authors: Adonias Caetano de Oliveira, Joao Pedro Cavalcanti Azevedo, Livia Ruback, Rayele Moreira, Silmar Silva Teixeira, Ariel Soares Teles
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10945851/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850185216110362624
author Adonias Caetano de Oliveira
Joao Pedro Cavalcanti Azevedo
Livia Ruback
Rayele Moreira
Silmar Silva Teixeira
Ariel Soares Teles
author_facet Adonias Caetano de Oliveira
Joao Pedro Cavalcanti Azevedo
Livia Ruback
Rayele Moreira
Silmar Silva Teixeira
Ariel Soares Teles
author_sort Adonias Caetano de Oliveira
collection DOAJ
description Artificial Intelligence (AI)-based systems have been proposed to aid Mental Health Professionals (MHPs) in various tasks, including the prevention of suicide by identifying Suicidal Ideation (SI). However, these systems may lack transparency and thereby create mistrust among MHPs. Explainable Artificial Intelligence (XAI) methods can elucidate how features influence system predictions, aiding MHPs in understanding them. This exploratory study aims to investigate how MHPs’ trust is influenced by AI explanations (educational intervention and XAI methods) and other factors (professional background, knowledge of AI and computing, and reported system misclassification). We conducted an experiment using Boamente, an AI-powered clinical decision support system designed to assist MHPs in suicide prevention. Boamente identifies SI in Brazilian Portuguese texts typed on smartphones by leveraging a Large Language Model (LLM) for analysis. The results demonstrate that professional background, knowledge of AI and computing, and educational intervention had no statistically significant effect on trust. In contrast, trust was affected by factors such as LLM prediction explanations, the quality of explanations, and reported misclassification. Therefore, providing prediction explanations to understand the inner workings of AI models led MHPs to be more critical in relation to predictions, while there was an overtrust on MHPs when no explanations were provided. Furthermore, disagreement with LLM classifications and perceptions of system vulnerabilities also affected trust.
format Article
id doaj-art-a77aae1dd810498b89ea935bb65752b8
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a77aae1dd810498b89ea935bb65752b82025-08-20T02:16:49ZengIEEEIEEE Access2169-35362025-01-0113609876100510.1109/ACCESS.2025.355624510945851Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide PreventionAdonias Caetano de Oliveira0https://orcid.org/0000-0002-5643-2916Joao Pedro Cavalcanti Azevedo1https://orcid.org/0009-0003-2035-6872Livia Ruback2https://orcid.org/0000-0001-5000-2280Rayele Moreira3https://orcid.org/0000-0002-4480-732XSilmar Silva Teixeira4https://orcid.org/0000-0002-9240-1228Ariel Soares Teles5https://orcid.org/0000-0002-0840-3870Programa de Pós-Graduação em Biotecnologia (PPGBiotec), Universidade Federal do Delta do Parnaíba, Parnaíba, BrazilPrograma de Pós-graduação em Ciência da Computação (PPGCC), Universidade Federal do Maranhão, São Luís, BrazilFaculdade de Tecnologia (FT), Universidade Estadual de Campinas, Campinas, BrazilPrograma de Pós-Graduação em Biotecnologia (PPGBiotec), Universidade Federal do Delta do Parnaíba, Parnaíba, BrazilPrograma de Pós-Graduação em Biotecnologia (PPGBiotec), Universidade Federal do Delta do Parnaíba, Parnaíba, BrazilPrograma de Pós-Graduação em Biotecnologia (PPGBiotec), Universidade Federal do Delta do Parnaíba, Parnaíba, BrazilArtificial Intelligence (AI)-based systems have been proposed to aid Mental Health Professionals (MHPs) in various tasks, including the prevention of suicide by identifying Suicidal Ideation (SI). However, these systems may lack transparency and thereby create mistrust among MHPs. Explainable Artificial Intelligence (XAI) methods can elucidate how features influence system predictions, aiding MHPs in understanding them. This exploratory study aims to investigate how MHPs’ trust is influenced by AI explanations (educational intervention and XAI methods) and other factors (professional background, knowledge of AI and computing, and reported system misclassification). We conducted an experiment using Boamente, an AI-powered clinical decision support system designed to assist MHPs in suicide prevention. Boamente identifies SI in Brazilian Portuguese texts typed on smartphones by leveraging a Large Language Model (LLM) for analysis. The results demonstrate that professional background, knowledge of AI and computing, and educational intervention had no statistically significant effect on trust. In contrast, trust was affected by factors such as LLM prediction explanations, the quality of explanations, and reported misclassification. Therefore, providing prediction explanations to understand the inner workings of AI models led MHPs to be more critical in relation to predictions, while there was an overtrust on MHPs when no explanations were provided. Furthermore, disagreement with LLM classifications and perceptions of system vulnerabilities also affected trust.https://ieeexplore.ieee.org/document/10945851/Explainable artificial intelligencetrustmedical AImental healthsuicidedigital phenotyping
spellingShingle Adonias Caetano de Oliveira
Joao Pedro Cavalcanti Azevedo
Livia Ruback
Rayele Moreira
Silmar Silva Teixeira
Ariel Soares Teles
Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide Prevention
IEEE Access
Explainable artificial intelligence
trust
medical AI
mental health
suicide
digital phenotyping
title Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide Prevention
title_full Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide Prevention
title_fullStr Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide Prevention
title_full_unstemmed Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide Prevention
title_short Effect of Explainable Artificial Intelligence on Trust of Mental Health Professionals in an AI-Based System for Suicide Prevention
title_sort effect of explainable artificial intelligence on trust of mental health professionals in an ai based system for suicide prevention
topic Explainable artificial intelligence
trust
medical AI
mental health
suicide
digital phenotyping
url https://ieeexplore.ieee.org/document/10945851/
work_keys_str_mv AT adoniascaetanodeoliveira effectofexplainableartificialintelligenceontrustofmentalhealthprofessionalsinanaibasedsystemforsuicideprevention
AT joaopedrocavalcantiazevedo effectofexplainableartificialintelligenceontrustofmentalhealthprofessionalsinanaibasedsystemforsuicideprevention
AT liviaruback effectofexplainableartificialintelligenceontrustofmentalhealthprofessionalsinanaibasedsystemforsuicideprevention
AT rayelemoreira effectofexplainableartificialintelligenceontrustofmentalhealthprofessionalsinanaibasedsystemforsuicideprevention
AT silmarsilvateixeira effectofexplainableartificialintelligenceontrustofmentalhealthprofessionalsinanaibasedsystemforsuicideprevention
AT arielsoaresteles effectofexplainableartificialintelligenceontrustofmentalhealthprofessionalsinanaibasedsystemforsuicideprevention