000 04469naa a22005417i 4500
001 UMUN-OA-20261005-AI-028
003 local
005 20261005174825.0
006 m o d
007 cr||||||||||||
008 261005s2023 xx o u000 0 eng d
024 7 _a10.1038/s41398-023-02592-2
_2doi
035 _a(local)OpenAlex:W4387393037
040 _alocal
_beng
_clocal
041 0 _aeng
100 0 _aMatteo Malgaroli
_eauthor.
245 1 0 _aNatural language processing for mental health interventions: a systematic review and research framework /
_cMatteo Malgaroli; Thomas D. Hull; James M. Zech [and others].
264 1 _a[Place of publication not identified] :
_bNature Publishing Group,
_c2023.
300 _a1 online resource (1 article).
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
500 _aPublication type: Review article.
500 _aLinked open-access copy: published version.
506 0 _aOpen access; no subscription required for the linked open-access version.
_fUnrestricted online access
_2star
520 3 _aNeuropsychiatric disorders pose a high societal cost, but their treatment is hindered by lack of objective outcomes and fidelity metrics. AI technologies and specifically Natural Language Processing (NLP) have emerged as tools to study mental health interventions (MHI) at the level of their constituent conversations. However, NLP's potential to address clinical and research challenges remains unclear. We therefore conducted a pre-registered systematic review of NLP-MHI studies using PRISMA guidelines (osf.io/s52jh) to evaluate their models, clinical applications, and to identify biases and gaps. Candidate studies (n = 19,756), including peer-reviewed AI conference manuscripts, were collected up to January 2023 through PubMed, PsycINFO, Scopus, Google Scholar, and ArXiv. A total of 102 articles were included to investigate their computational characteristics (NLP algorithms, audio features, machine learning pipelines, outcome metrics), clinical characteristics (clinical ground truths, study samples, clinical focus), and limitations. Results indicate a rapid growth of NLP MHI studies since 2019, characterized by increased sample sizes and use of large language models. Digital health platforms were the largest providers of MHI data. Ground truth for supervised learning models was based on clinician ratings (n = 31), patient self-report (n = 29) and annotations by raters (n = 26). Text-based features contributed more to model accuracy than audio markers. Patients' clinical presentation (n = 34), response to intervention (n = 11), intervention monitoring (n = 20), providers' characteristics (n = 12), relational dynamics (n = 14), and data preparation (n = 4) were commonly investigated clinical categories. Limitations of reviewed studies included lack of linguistic diversity, limited reproducibility, and population bias. A research framework is developed and validated (NLPxMHI) to assist computational and clinical researchers in addressing the remaining gaps in applying NLP to MHI, with the goal of improving clinical utility, data access, and fairness.
540 _aCreative Commons Attribution. See the linked licence for the applicable terms.
_uhttps://creativecommons.org/licenses/by/4.0/
546 _aIn English.
588 0 _aDescription generated from OpenAlex bibliographic metadata retrieved on 5 October 2026; full text linked from the source.
590 _aCourse allocation: B. Sc. Artificial Intelligence.
650 4 _anatural language processing
650 4 _amental health interventions
650 4 _aneuropsychiatric disorders
650 4 _alarge language models
650 4 _adigital health platforms
650 4 _aaudio features
653 _aB. Sc. Artificial Intelligence
653 _aUMUN open access collection
653 _anatural language processing
655 4 _aReview articles.
700 0 _aThomas D. Hull
_eauthor.
700 0 _aJames M. Zech
_eauthor.
700 0 _aTim Althoff
_eauthor.
773 0 _tTranslational Psychiatry
_gVol. 13, no. 1, (2023), pages/article 309
_x2158-3188
856 4 0 _uhttps://europepmc.org/articles/PMC10556019
_yRead open-access publication
_zOpen access.
_70
884 _aCourse selection and automated MARC21 enrichment from OpenAlex metadata.
_g20261005
_khttps://openalex.org/W4387393037
_qlocal
942 _n0
999 _c585
_d585