2024
DOI: 10.1136/fmch-2023-002583
|View full text |Cite
|
Sign up to set email alerts
|

Assessing prognosis in depression: comparing perspectives of AI models, mental health professionals and the general public

Zohar Elyoseph,
Inbar Levkovich,
Shiri Shinan-Altman

Abstract: BackgroundArtificial intelligence (AI) has rapidly permeated various sectors, including healthcare, highlighting its potential to facilitate mental health assessments. This study explores the underexplored domain of AI’s role in evaluating prognosis and long-term outcomes in depressive disorders, offering insights into how AI large language models (LLMs) compare with human perspectives.MethodsUsing case vignettes, we conducted a comparative analysis involving different LLMs (ChatGPT-3.5, ChatGPT-4, Claude and … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
5
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
8
1

Relationship

2
7

Authors

Journals

citations
Cited by 28 publications
(6 citation statements)
references
References 59 publications
1
5
0
Order By: Relevance
“…This finding corroborates and is congruent with prior empirical findings [19,21]. Taken in concert, these findings elucidate the multifaceted mentalizing capabilities of ChatGPT-4, span visual and textual modalities, and reinforce previous findings about the potential of LLMs in performing tasks in the mental health field [19,21,[30][31][32][33][34][35][36][37]. Additionally, although its nascent visual emotion recognition abilities are noteworthy, its competencies in textual mentalization remain unparalleled, a testament to its foundational architecture rooted in NLP.…”
Section: Principal Findingssupporting
confidence: 88%
“…This finding corroborates and is congruent with prior empirical findings [19,21]. Taken in concert, these findings elucidate the multifaceted mentalizing capabilities of ChatGPT-4, span visual and textual modalities, and reinforce previous findings about the potential of LLMs in performing tasks in the mental health field [19,21,[30][31][32][33][34][35][36][37]. Additionally, although its nascent visual emotion recognition abilities are noteworthy, its competencies in textual mentalization remain unparalleled, a testament to its foundational architecture rooted in NLP.…”
Section: Principal Findingssupporting
confidence: 88%
“…Subsequent screening based on titles and abstracts led to the exclusion of 255 papers, primarily due to their irrelevance or lack of discussion on LLMs, leaving 33 articles for full-text evaluation. Upon detailed examination, 16 studies were found to meet our inclusion criteria and were thus selected for the final review (22)(23)(24)(25)(26)(27)(28)(29)(30)(31)(32)(33)(34)(35)(36)(37). The process of study selection and the results at each stage are comprehensively illustrated in Figure 2, the PRISMA flowchart.…”
Section: Search Results and Study Selectionmentioning
confidence: 99%
“…The study revealed notable differences in long-term outcome predictions. AI models, including ChatGPT, showed variability in prognostic outlooks, with ChatGPT-3.5 often presenting a more pessimistic view compared to other AI models and human evaluation ( 36 ).…”
Section: Resultsmentioning
confidence: 99%
“…Since the release of GAI systems, numerous studies have been conducted regarding their applications in the field of mental health [ 2 7-10 22 34 48-53 undefined undefined undefined undefined undefined undefined undefined undefined ]. However, the current research seeks to examine the entry of this technology from a broader perspective, particularly focusing on its potential impact on psychotherapy.…”
Section: Discussionmentioning
confidence: 99%