Academic Journal
Προβολή σε EDS

Assessing the Need for Mental Health Support From Free-Text Responses: Development and Validation of Language-Based Assessments in Adults With Internalizing Symptoms.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Assessing the Need for Mental Health Support From Free-Text Responses: Development and Validation of Language-Based Assessments in Adults With Internalizing Symptoms.
Συγγραφείς: Wiebel C; Department of Psychology, Lund University, Box 213, Allhelgona Kyrkogata 16A, 16B, 18A, 18B och 18C, Lund, Skåne, 22350, Sweden, +46 46 222 00 00.; School of Management, Technical University of Munich, Heilbronn, Baden-Württemberg, Germany., Eijsbroek VC; Department of Psychology, Lund University, Box 213, Allhelgona Kyrkogata 16A, 16B, 18A, 18B och 18C, Lund, Skåne, 22350, Sweden, +46 46 222 00 00., Varadarajan V; Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, United States., Kjell K; Department of Psychology, Lund University, Box 213, Allhelgona Kyrkogata 16A, 16B, 18A, 18B och 18C, Lund, Skåne, 22350, Sweden, +46 46 222 00 00., Schwartz HA; College of Connected Computing, Vanderbilt University, Nashville, TN, United States., Kjell O; Department of Psychology, Lund University, Box 213, Allhelgona Kyrkogata 16A, 16B, 18A, 18B och 18C, Lund, Skåne, 22350, Sweden, +46 46 222 00 00.; College of Connected Computing, Vanderbilt University, Nashville, TN, United States.
Πηγή: JMIR mental health [JMIR Ment Health] 2026 Sep 25; Vol. 13, pp. e105460. Date of Electronic Publication: 2026 Sep 25.
Τύπος έκδοσης: Journal Article; Validation Study
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: JMIR Publications Inc Country of Publication: Canada NLM ID: 101658926 Publication Model: Electronic Cited Medium: Internet ISSN: 2368-7959 (Electronic) Linking ISSN: 23687959 NLM ISO Abbreviation: JMIR Ment Health Subsets: MEDLINE
Imprint Name(s): Original Publication: Toronto : JMIR Publications Inc., [2014]-
Ιατρικοί όροι (MeSH): Depression*/diagnosis , Anxiety*/diagnosis , Natural Language Processing*, Humans ; Adult ; Female ; Male ; Middle Aged ; Large Language Models ; Machine Learning ; Reproducibility of Results ; Young Adult
Περίληψη: Background: Machine learning and natural language processing have demonstrated significant potential for mental health assessment: describing your mental health in your own words can offer a more ecologically valid approach than traditional rating scales. However, most models focus on specific diagnoses, conditions, or symptoms, which may prematurely assign labels and potentially reinforce stigma in the context of early-stage mental health screening.
Objective: This study develops a language-based assessment model that assesses the need for mental health support based on probed natural language and validates it against best-estimate assessments from multiple experienced psychotherapists.
Methods: We analyzed an enriched online sample (n=600 for development and n=212 for validation), in which about half reported experiencing internalizing symptoms (depression or anxiety). Participants described their mental health using open-ended responses regarding (1) mental health, (2) suicidal thoughts, (3) medical history, and (4) depression. The responses were converted into contextual word embeddings using a large language model and entered as predictors in a ridge regression using nested cross-validation. Two to three experienced psychotherapists assessed each participant's need for mental health support on a scale from 1 (no support needed) to 5 (potential crisis). Their assessments were based on longitudinal clinical data (natural language, validated scales, clinical interview, sociodemographics, and clinical history) and were averaged into a best-estimate assessment for model validation. We used the Sequential Evaluation With Model Preregistration framework, which separates model development from validation in a held-out set to support robust estimations and generalizability.
Results: The language-based assessments closely aligned with the best-estimate assessments (r=0.82) and showed strong correlations with established clinical rating scales for depression (Patient Health Questionnaire-9), anxiety (Generalized Anxiety Disorder 7-Item Scale), stress (Perceived Stress Scale 10), and suicidality (Inventory of Depression and Anxiety Symptoms; r=0.62-0.77). Language-based visualizations of topics and word embeddings showed that low need for support assessments was associated with mentioning well-being and good health, while high assessments were related to depression, anxiety, and suicidality.
Conclusions: This study demonstrates that natural language responses analyzed through large language models and machine learning can be used to assess individuals' need for mental health support in close alignment with best-estimate assessments from experienced psychotherapists. Using less than 5 minutes of respondent time, this approach offers a practical tool for early-stage mental health screening in both clinical and self-guided screening contexts.
(© Clara Wiebel, Veerle C Eijsbroek, Vasudha Varadarajan, Katarina Kjell, H Andrew Schwartz, Oscar Kjell. Originally published in JMIR Mental Health (https://mental.jmir.org).)
References: J Ment Health. 2010 Aug;19(4):318-27. (PMID: 20636112)
Transl Psychiatry. 2023 Oct 6;13(1):309. (PMID: 37798296)
Curr Psychiatry Rep. 2018 Sep 17;20(11):95. (PMID: 30221308)
Science. 2024 Jan 12;383(6679):164-167. (PMID: 38207039)
J Lang Soc Psychol. 2021 Jan;40(1):21-41. (PMID: 34413563)
J Nerv Ment Dis. 2010 Apr;198(4):280-5. (PMID: 20386257)
Front Psychiatry. 2022 May 24;13:801301. (PMID: 35686182)
BMC Psychiatry. 2020 Jun 12;20(1):297. (PMID: 32532225)
Proc Natl Acad Sci U S A. 2024 Sep 24;121(39):e2321321121. (PMID: 39284070)
Psychol Bull. 1955 Jul;52(4):281-302. (PMID: 13245896)
Can J Psychiatry. 2005 Feb;50(2):87-94. (PMID: 15807224)
J Pers Assess. 2021 Mar-Apr;103(2):183-194. (PMID: 32167788)
Arch Intern Med. 2006 May 22;166(10):1092-7. (PMID: 16717171)
Suicide Life Threat Behav. 2018 Oct;48(5):531-543. (PMID: 28678380)
J Psychopathol Clin Sci. 2023 Nov;132(8):972-983. (PMID: 37471025)
PLoS Med. 2022 Feb 15;19(2):e1003901. (PMID: 35167593)
Psychol Med. 2015 Jan;45(1):11-27. (PMID: 24569086)
J Abnorm Psychol. 2017 May;126(4):454-477. (PMID: 28333488)
Annu Rev Psychol. 2003;54:547-77. (PMID: 12185209)
Front Psychiatry. 2023 Jun 12;14:1143175. (PMID: 37377466)
Assessment. 2026 Sep;33(6):927-953. (PMID: 40974258)
Npj Ment Health Res. 2025 Jul 8;4(1):28. (PMID: 40629100)
J Clin Epidemiol. 2009 Aug;62(8):797-806. (PMID: 19447581)
Psychol Med. 2014 Dec;44(16):3361-3. (PMID: 24998511)
Clin Psychol Rev. 2023 Apr;101:102272. (PMID: 37001469)
J Health Soc Behav. 1983 Dec;24(4):385-96. (PMID: 6668417)
Psychiatry Res. 2024 May;335:115854. (PMID: 38554496)
Sci Rep. 2022 Mar 10;12(1):3918. (PMID: 35273198)
J Pers Assess. 1985 Feb;49(1):71-5. (PMID: 16367493)
Clin Psychol Sci. 2016 Mar;4(2):239-253. (PMID: 31289695)
J Affect Disord. 2024 Apr 1;350:255-263. (PMID: 38224742)
J Abnorm Psychol. 1991 Aug;100(3):316-36. (PMID: 1918611)
Am J Psychol. 1987 Fall-Winter;100(3-4):441-71. (PMID: 3322052)
JMIR Ment Health. 2024 May 16;11:e57234. (PMID: 38771256)
J Affect Disord. 2022 Apr 15;303:273-285. (PMID: 35176342)
Am Psychol. 2001 Mar;56(3):218-26. (PMID: 11315248)
Proc Natl Acad Sci U S A. 2024 Apr 2;121(14):e2319837121. (PMID: 38530887)
Community Ment Health J. 2021 Apr;57(3):470-481. (PMID: 32617737)
Psychol Assess. 2007 Sep;19(3):253-68. (PMID: 17845118)
Psychol Methods. 2023 Dec;28(6):1478-1498. (PMID: 37126041)
Compr Psychiatry. 1983 Sep-Oct;24(5):399-411. (PMID: 6354575)
J Clin Epidemiol. 2007 Jan;60(1):34-42. (PMID: 17161752)
Compr Psychiatry. 2025 Aug;141:152603. (PMID: 40479924)
JAMA Psychiatry. 2026 Apr 1;83(4):399-403. (PMID: 41405895)
Nat Hum Behav. 2024 Oct;8(10):1877-1889. (PMID: 39438680)
JAMA Intern Med. 2018 Nov 1;178(11):1544-1547. (PMID: 30128552)
J Affect Disord. 2026 Jan 15;393(Pt A):120299. (PMID: 40935255)
Nat Commun. 2020 Sep 10;11(1):4525. (PMID: 32913209)
Depress Anxiety. 2022 Dec;39(12):794-804. (PMID: 36281621)
Psychiatry Res. 2024 Mar;333:115667. (PMID: 38290286)
Proc Natl Acad Sci U S A. 2022 Mar 29;119(13):e2114737119. (PMID: 35316132)
PLoS Med. 2013 Oct;10(10):e1001531. (PMID: 24143138)
Soc Psychiatry Psychiatr Epidemiol. 2000 Sep;35(9):427-35. (PMID: 11089671)
Psychol Med. 2023 Dec;53(16):7504-7511. (PMID: 37681273)
Proc Natl Acad Sci U S A. 2018 Oct 30;115(44):11203-11208. (PMID: 30322910)
Arch Gen Psychiatry. 1963 Oct;9:324-33. (PMID: 14045261)
J Gen Intern Med. 2001 Sep;16(9):606-13. (PMID: 11556941)
Am J Public Health. 1997 Jul;87(7):1136-43. (PMID: 9240103)
Psychol Methods. 2019 Feb;24(1):92-115. (PMID: 29963879)
Nat Hum Behav. 2026 Jul;10(7):1182-1186. (PMID: 42265331)
Contributed Indexing: Keywords: AI; best-estimate assessments; language-based assessments; large language models; machine learning; mental health support; natural language processing
Entry Date(s): Date Created: 20260928 Date Completed: 20260928 Latest Revision: 20260930
Update Code: 20260930
PubMed Central ID: PMC13617639
DOI: 10.2196/105460
PMID: 42803493
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:2368-7959
DOI:10.2196/105460