Treffer: Machine Learning and Natural Language Processing in Mental Health: Systematic Review.

Title:
Machine Learning and Natural Language Processing in Mental Health: Systematic Review.
Authors:
Le Glaz A; URCI Mental Health Department, Brest Medical University Hospital, Brest, France., Haralambous Y; IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238, Brest, France., Kim-Dufor DH; URCI Mental Health Department, Brest Medical University Hospital, Brest, France., Lenca P; IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238, Brest, France., Billot R; IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238, Brest, France., Ryan TC; Department of Mental Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, United States., Marsh J; Fordham University Graduate School of Social Service, New York, NY, United States., DeVylder J; Fordham University Graduate School of Social Service, New York, NY, United States., Walter M; URCI Mental Health Department, Brest Medical University Hospital, Brest, France.; EA 7479 SPURBO, Université de Bretagne Occidentale, Brest, France., Berrouiguet S; URCI Mental Health Department, Brest Medical University Hospital, Brest, France.; IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238, Brest, France.; EA 7479 SPURBO, Université de Bretagne Occidentale, Brest, France.; LaTIM, INSERM, UMR 1101, Brest, France., Lemey C; URCI Mental Health Department, Brest Medical University Hospital, Brest, France.; IMT Atlantique, Lab-STICC, UMR CNRS 6285, F-29238, Brest, France.; EA 7479 SPURBO, Université de Bretagne Occidentale, Brest, France.
Source:
Journal of medical Internet research [J Med Internet Res] 2021 May 04; Vol. 23 (5), pp. e15708. Date of Electronic Publication: 2021 May 04.
Publication Type:
Journal Article; Meta-Analysis; Research Support, Non-U.S. Gov't; Systematic Review
Language:
English
Journal Info:
Publisher: JMIR Publications Country of Publication: Canada NLM ID: 100959882 Publication Model: Electronic Cited Medium: Internet ISSN: 1438-8871 (Electronic) Linking ISSN: 14388871 NLM ISO Abbreviation: J Med Internet Res Subsets: MEDLINE
Imprint Name(s):
Publication: <2011- > : Toronto : JMIR Publications
Original Publication: [Pittsburgh, PA? : s.n., 1999-
MeSH Terms:
Artificial Intelligence* , Natural Language Processing*, Data Management ; Humans ; Machine Learning ; Mental Health
References:
J Biomed Inform. 2017 Nov;75S:S62-S70. (PMID: 28455151)
Am J Psychiatry. 2015 Apr;172(4):363-72. (PMID: 25827034)
Front Psychiatry. 2018 Dec 03;9:650. (PMID: 30559686)
Int J Methods Psychiatr Res. 2017 Jun;26(2):. (PMID: 27634457)
JAMA. 2016 Feb 9;315(6):551-2. (PMID: 26864406)
JMIR Public Health Surveill. 2017 Jun 13;3(2):e35. (PMID: 28611016)
AMIA Annu Symp Proc. 2014 Nov 14;2014:729-38. (PMID: 25954379)
J Biomed Inform. 2017 Nov;75S:S94-S104. (PMID: 28571784)
Stud Health Technol Inform. 2019 Aug 21;264:40-44. (PMID: 31437881)
Diabetes Metab. 2019 Sep;45(4):322-329. (PMID: 30243616)
J Nucl Med. 2017 Mar;58(3):357-358. (PMID: 28153954)
Assessment. 2017 Mar;24(2):157-172. (PMID: 26358713)
Eur J Epidemiol. 2019 Feb;34(2):153-162. (PMID: 30535584)
IEEE J Biomed Health Inform. 2017 Sep;21(5):1449-1459. (PMID: 27542187)
Internet Interv. 2017 Oct 10;10:39-46. (PMID: 30135751)
Internet Interv. 2018 Jul 19;13:105-107. (PMID: 30206524)
AMA J Ethics. 2018 Sep 1;20(9):E804-811. (PMID: 30242810)
J Med Internet Res. 2017 Feb 28;19(2):e48. (PMID: 28246066)
J Med Syst. 2017 Apr;41(4):69. (PMID: 28285459)
Stud Health Technol Inform. 2019 Aug 21;264:50-54. (PMID: 31437883)
Biomed Inform Insights. 2018 Aug 27;10:1178222618792860. (PMID: 30158822)
Behav Res Methods. 2017 Jun;49(3):835-852. (PMID: 27338931)
J Biomed Inform. 2017 Nov;75S:S120-S128. (PMID: 28694118)
Psychol Med. 2019 Jul;49(9):1426-1448. (PMID: 30744717)
Am J Psychiatry. 2010 Jul;167(7):748-51. (PMID: 20595427)
Ann Intern Med. 2018 Jul 3;169(1):44-46. (PMID: 29710098)
J Biomed Inform. 2017 Nov;75S:S149-S159. (PMID: 28822857)
Proc IEEE ACM Int Conf Adv Soc Netw Anal Min. 2017 Jul-Aug;2017:1191-1198. (PMID: 29707701)
J Biomed Inform. 2017 Nov;75S:S138-S148. (PMID: 28606869)
Autism Res. 2016 Aug;9(8):846-53. (PMID: 26613541)
J Subst Abuse Treat. 2016 Jun;65:43-50. (PMID: 26944234)
Psychol Med. 2012 Jan;42(1):41-50. (PMID: 21682950)
Front Psychiatry. 2018 Apr 30;9:135. (PMID: 29760666)
Circulation. 2015 Nov 17;132(20):1920-30. (PMID: 26572668)
BMJ. 2015 Jan 02;350:g7647. (PMID: 25555855)
Stroke Vasc Neurol. 2017 Jun 21;2(4):230-243. (PMID: 29507784)
PLoS One. 2015 Aug 14;10(8):e0134208. (PMID: 26273830)
Stud Health Technol Inform. 2019 Aug 21;264:1056-1060. (PMID: 31438086)
PLoS One. 2019 Feb 6;14(2):e0210575. (PMID: 30726237)
J Biomed Inform. 2018 Oct;86:49-58. (PMID: 30118855)
J Autism Dev Disord. 2020 Jan;50(1):162-170. (PMID: 31571066)
J Med Internet Res. 2017 Jun 29;19(6):e228. (PMID: 28663166)
PLoS One. 2019 Feb 19;14(2):e0211116. (PMID: 30779800)
Suicide Life Threat Behav. 2016 Apr;46(2):154-9. (PMID: 26252868)
J Affect Disord. 2020 Jan 1;260:366-371. (PMID: 31539672)
JAMA Netw Open. 2019 Jun 5;2(6):e195627. (PMID: 31199445)
J Clin Psychiatry. 2016 Jun;77(6):e711-8. (PMID: 27035768)
J Biomed Inform. 2015 Dec;58 Suppl:S158-S163. (PMID: 26362344)
Comput Struct Biotechnol J. 2014 Nov 15;13:8-17. (PMID: 25750696)
World Psychiatry. 2018 Feb;17(1):67-75. (PMID: 29352548)
Adm Policy Ment Health. 2013 Jul;40(4):311-8. (PMID: 22535469)
BMJ Open. 2015 May 21;5(5):e007504. (PMID: 25998036)
Stud Health Technol Inform. 2015;216:736-40. (PMID: 26262149)
Comput Math Methods Med. 2016;2016:8708434. (PMID: 27752278)
Int J Med Inform. 2015 Dec;84(12):1057-64. (PMID: 26456569)
J Med Syst. 2019 May 28;43(7):204. (PMID: 31139933)
Am J Public Health. 2017 Jan;107(1):e1-e8. (PMID: 27854532)
J Am Med Inform Assoc. 2011 Dec;18 Suppl 1:i144-9. (PMID: 21946242)
Int J Eat Disord. 2018 Jul;51(7):656-667. (PMID: 29746710)
Int J Eat Disord. 2019 Oct;52(10):1150-1156. (PMID: 31381168)
Mol Syst Biol. 2016 Jul 29;12(7):878. (PMID: 27474269)
Heliyon. 2019 Jun 10;5(6):e01802. (PMID: 31211254)
J Biomed Inform. 2011 Aug;44(4):509-18. (PMID: 21292030)
Artif Intell Med. 2016 Jan;66:53-62. (PMID: 26616420)
J Med Internet Res. 2013 Aug 28;15(8):e184. (PMID: 23985172)
J Med Internet Res. 2018 Nov 07;20(11):e10497. (PMID: 30404767)
Acta Neurol Scand. 2020 May;141(5):388-396. (PMID: 31889296)
Cancer Inform. 2007 Feb 11;2:59-77. (PMID: 19458758)
Alcohol. 2020 May;84:49-55. (PMID: 31574300)
Sci Rep. 2018 May 9;8(1):7426. (PMID: 29743531)
J Psychopharmacol. 2015 Jun;29(6):669-77. (PMID: 25922420)
BMJ Open. 2019 Nov 4;9(11):e030355. (PMID: 31685502)
Rev Psiquiatr Salud Ment (Engl Ed). 2019 Jul - Sep;12(3):187-195. (PMID: 29941228)
Cortex. 2014 Jun;55:43-60. (PMID: 23332818)
JAMA Psychiatry. 2019 Jun 1;76(6):642-651. (PMID: 30865249)
BMJ Open. 2015 Sep 07;5(9):e007619. (PMID: 26346872)
Psychol Med. 2020 Oct;50(13):2221-2229. (PMID: 31544723)
J Biomed Inform. 2017 Nov;75S:S112-S119. (PMID: 28602906)
Acta Psychiatr Scand. 2019 Aug;140(2):147-157. (PMID: 31209866)
J Am Med Inform Assoc. 2019 Mar 1;26(3):254-261. (PMID: 30602031)
J Biomed Inform. 2017 Nov;75S:S71-S84. (PMID: 28576748)
AMIA Annu Symp Proc. 2015 Nov 05;2015:2063-72. (PMID: 26958306)
JMIR Ment Health. 2019 May 07;6(5):e9766. (PMID: 31066693)
Adm Policy Ment Health. 2018 Jul;45(4):519-529. (PMID: 29450781)
J Med Toxicol. 2017 Dec;13(4):278-286. (PMID: 28831738)
Front Psychiatry. 2017 Sep 29;8:192. (PMID: 29038651)
Artif Intell Med. 2014 Jun;61(2):89-96. (PMID: 24813116)
J Healthc Eng. 2019 Nov 3;2019:4253641. (PMID: 31814951)
Schizophr Res. 2014 Nov;159(2-3):533-8. (PMID: 25261880)
Eur Psychiatry. 2019 Apr;57:58-60. (PMID: 30677549)
NPJ Schizophr. 2015 Aug 26;1:15030. (PMID: 27336038)
Contributed Indexing:
Keywords: artificial intelligence; data mining; machine learning; mental health; natural language processing; psychiatry
Entry Date(s):
Date Created: 20210504 Date Completed: 20211001 Latest Revision: 20250623
Update Code:
20250623
PubMed Central ID:
PMC8132982
DOI:
10.2196/15708
PMID:
33944788
Database:
MEDLINE

Weitere Informationen

Background: Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining.
Objective: The primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice.
Methods: This systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed.
Results: A total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform.
Conclusions: Machine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients' daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.
(©Aziliz Le Glaz, Yannis Haralambous, Deok-Hee Kim-Dufor, Philippe Lenca, Romain Billot, Taylor C Ryan, Jonathan Marsh, Jordan DeVylder, Michel Walter, Sofian Berrouiguet, Christophe Lemey. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 04.05.2021.)