Machine Learning in Mental Health: A Systematic Review of the HCI Literature to Support the Development of Effective and Implementable ML Systems
The DOI matches its Crossref record; 217 of the 217 references it cites were found in a registry or an index.
Abstract
High prevalence of mental illness and the need for effective mental health care, combined with recent advances in AI, has led to an increase in explorations of how the field of machine learning (ML) can assist in the detection, diagnosis and treatment of mental health problems. ML techniques can potentially offer new routes for learning patterns of human behavior; identifying mental health symptoms and risk factors; developing predictions about disease progression; and personalizing and optimizing therapies. Despite the potential opportunities for using ML within mental health, this is an emerging research area, and the development of effective ML-enabled applications that are implementable in practice is bound up with an array of complex, interwoven challenges. Aiming to guide future research and identify new directions for advancing development in this important domain, this article presents an introduction to, and a systematic review of, current ML work regarding psycho-socially based mental health conditions from the computing and HCI literature. A quantitative synthesis and qualitative narrative review of 54 papers that were included in the analysis surfaced common trends, gaps, and challenges in this space. Discussing our findings, we (i) reflect on the current state-of-the-art of ML work for mental health, (ii) provide concrete suggestions for a stronger integration of human-centered and multi-disciplinary approaches in research and development, and (iii) invite more consideration of the potentially far-reaching personal, social, and ethical implications that ML models and interventions can have, if they are to find widespread, successful adoption in real-world mental health contexts.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“a growing body of research is beginning to demonstrate the importance of user-centered design for work on ML tools [57,122].”
From Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty (2021) · cites this paper as [122]
In the citing paper
“suicide prediction algorithms' false positives could result in an individual being wrongly detained by a health service [43], whilst false negatives could mean an otherwise preventable suicide is missed [40].”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [43]
In the citing paper
“Regarding ML models, the majority of related literature has applied some kind of supervised learning, such as logistic regression or SVMs, which cannot capture nonlinear combinations of features.”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [158]
Citations
Cites
Items 201–217 of 217
A semantic framework for intelligent matchmaking for clinical trial eligibility criteria
Lee, Y., Krishnamoorthy, S., & Dinakarpandian, D. (2013) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/2508037.2508052 · Cited by 6 · cited 1×
“Further excluded were papers that described ML research outside a specific focus on mental health (n = 16 [21, 26, 32, 43, 75, 81, 88, 114, 118, 120, 160, 167, 200, 208, 215, 221]); or that otherwise did not fit thematically (n = 20 [11, 14, 18, 29, 30, 36, 55, 87, 101, 107, 110, 113, 138, 143, 147, 174, 178, 194, 197…”
BackgroundSymptomatic Diagnosis and Prognosis of Psychiatric Disorders through Personal Gadgets
Jain, V., & Agarwal, P. (2017) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3027063.3048417 · Cited by 6 · cited 1×
“1924583 [82] Vidhi Jain and Prakhar Agarwal.”
Spatio-temporal optical flow statistics (STOFS) for activity classification
Jagadeesh, V., Karthikeyan, S., & Manjunath, B. S. (2010) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/1924559.1924583 · Cited by 5 · cited 1×
“Further excluded were papers that described ML research outside a specific focus on mental health (n = 16 [21, 26, 32, 43, 75, 81, 88, 114, 118, 120, 160, 167, 200, 208, 215, 221]); or that otherwise did not fit thematically (n = 20 [11, 14, 18, 29, 30, 36, 55, 87, 101, 107, 110, 113, 138, 143, 147, 174, 178, 194, 197…”
BackgroundTextual prediction of attitudes towards mental health
Mensah, P. K. (2015) · International Journal of Knowledge Engineering and Data Mining · doi:10.1504/ijkedm.2015.074076 · Cited by 5
Extrapolating Expected Accuracies for Large Multi-Class ProblemsPreprint
ZhengCharles, AchantaRakesh, & BenjaminiYuval (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.09713 · Cited by 5
Pfeffer, L., Ide, D. C., Stewart, C. V., & Plenz, D. (2004) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2004.1311759 · Cited by 5 · cited 1×
“Papers were excluded if they described topics of neuroscience, neurobiology or neurological conditions – including cell structure, cortex and (f)MRI research (n = 22 [3, 54, 59, 72, 92, 94, 95, 96, 98, 103, 108, 115, 117, 131, 146, 180, 183, 185, 195, 199, 214, 220]), and in one case epilepsy [5].”
BackgroundObservation Time vs. Performance in Digital Phenotyping
Quisel, T., Lee, W.-N., & Foschini, L. (2017) · doi:10.1145/3089341.3089347 · Cited by 4 · cited 10×
“Here, success of newly developed models is primarily reported through performance measures of the ‘accuracy of the (best) classifier’ or ‘robustness of clustering’ [2, 4, 6, 23, 27, 33, 44, 45, 50, 57, 61, 62, 63, 64, 67, 86, 89, 112, 122, 128, 133, 134, 135, 136, 139, 141, 144, 145, 152, 153, 155, 165, 168, 176, 177,…”
BackgroundMethodInfluentialA feature-based selection technique for reduction of large scale data
Chauhan, R., & Kaur, H. (2017) · International Journal of Data Analysis Techniques and Strategies · doi:10.1504/ijdats.2017.10007626 · Cited by 4 · cited 1×
“Further excluded were papers that described ML research outside a specific focus on mental health (n = 16 [21, 26, 32, 43, 75, 81, 88, 114, 118, 120, 160, 167, 200, 208, 215, 221]); or that otherwise did not fit thematically (n = 20 [11, 14, 18, 29, 30, 36, 55, 87, 101, 107, 110, 113, 138, 143, 147, 174, 178, 194, 197…”
BackgroundApplication of data mining for young children education using emotion information
Yue, L., Zhang, C., Tian, C., Zhao, X., Zhang, R., & Ji, Y. (2018) · International Conference on Data Science and Information Technology (DSIT) · doi:10.1145/3239283.3239321 · Cited by 4 · cited 1×
“Further excluded were papers that described ML research outside a specific focus on mental health (n = 16 [21, 26, 32, 43, 75, 81, 88, 114, 118, 120, 160, 167, 200, 208, 215, 221]); or that otherwise did not fit thematically (n = 20 [11, 14, 18, 29, 30, 36, 55, 87, 101, 107, 110, 113, 138, 143, 147, 174, 178, 194, 197…”
BackgroundWilbourne, P. L., Dexter, G., & Shoup, D. (2018) · International Conference on Pervasive Computing Technologies for Healthcare · doi:10.1145/3240925.3240932 · Cited by 4 · cited 7×
“[205] use ML tools to aid human coaches of a text chat-based app called Silby(4) to assess the quality and help improve their coaching response in real-time.”
BackgroundMethodInfluentialCell Responsiveness in Macaque Superior Temporal Polysensory Area Measured by Temporal Discriminants
Turner, J. A., Anderson, K. C., & Siegel, R. M. (2003) · Neural Computation · doi:10.1162/089976603322297296 · Cited by 3 · cited 1×
“Papers were excluded if they described topics of neuroscience, neurobiology or neurological conditions – including cell structure, cortex and (f)MRI research (n = 22 [3, 54, 59, 72, 92, 94, 95, 96, 98, 103, 108, 115, 117, 131, 146, 180, 183, 185, 195, 199, 214, 220]), and in one case epilepsy [5].”
BackgroundKotlar, A., & Wingo, T. S. (2018) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3233547.3233666 · Cited by 3 · cited 1×
“Papers were excluded if they described topics of neuroscience, neurobiology or neurological conditions – including cell structure, cortex and (f)MRI research (n = 22 [3, 54, 59, 72, 92, 94, 95, 96, 98, 103, 108, 115, 117, 131, 146, 180, 183, 185, 195, 199, 214, 220]), and in one case epilepsy [5].”
BackgroundMikelsons, G., Mehrotra, A., Musolesi, M., & Shadbolt, N. (2019) · doi:10.1145/3325426.3329948 · Cited by 3 · cited 1×
“Further excluded were papers that described ML research outside a specific focus on mental health (n = 16 [21, 26, 32, 43, 75, 81, 88, 114, 118, 120, 160, 167, 200, 208, 215, 221]); or that otherwise did not fit thematically (n = 20 [11, 14, 18, 29, 30, 36, 55, 87, 101, 107, 110, 113, 138, 143, 147, 174, 178, 194, 197…”
BackgroundKasmiran, K. A., Zomaya, A. Y., Mazari, A. A., & Garsia, R. J. (2010) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2010.6042686 · Cited by 2 · cited 1×
“Further excluded were papers that described ML research outside a specific focus on mental health (n = 16 [21, 26, 32, 43, 75, 81, 88, 114, 118, 120, 160, 167, 200, 208, 215, 221]); or that otherwise did not fit thematically (n = 20 [11, 14, 18, 29, 30, 36, 55, 87, 101, 107, 110, 113, 138, 143, 147, 174, 178, 194, 197…”
BackgroundMulti-Atlas Based Early Prediction of Post-Traumatic Stress Disorder
Yu, Y., Wang, Q., Hu, H., Su, S., & Wang, Z. (2018) · International Symposium on Image Computing and Digital Medicine (ISICDM) · doi:10.1145/3285996.3286012 · Cited by 1
Passive Detection of Perceived Stress Using Location-driven Sensing Technologies at Scale (demo)
Zakaria, C., Lee, Y., & Balan, R. K. (2019) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3307334.3328574 · Cited by 1 · cited 13×
“The remaining records primarily captured data from individuals who were described as ‘normal users’, ‘healthy subjects’, ‘students’ or ‘older adults’ [44, 67, 139, 140, 153, 168, 179, 193, 201, 217, 218, 222], or for whom data was sampled from public social media (n = 8, plus 1 record that also includes a diagnostic s…”
BackgroundMethodInfluential(2018) · ACM eBooks · doi:10.1145/3107990.3107991 · Cited by 1
Research works printed but not linked: 15
- American Psychiatry Association . 2019. Diagnostic and Statistical Manual of Mental Disorders (DSM--5). Last retrieved 7 th July 2019 from https://www.psychiatry.org/psychiatrists/practice/dsm. American Psychiatry Association. 2019. Diagnostic and Statistical Manual of Mental Disorders (DSM--5). Last retrieved 7 th July 2019 from https://www.psychiatry.org/psychiatrists/practice/dsm.
- Leo Breiman and Adele Cutler . 2007. Random Forests-Classification Description. Department of Statistics , University of California , Berkeley. Leo Breiman and Adele Cutler. 2007. Random Forests-Classification Description. Department of Statistics, University of California, Berkeley.
- Moustapha M. Cisse , Yossi Adi , Natalia Neverova , and Joseph Keshet . 2017 . Houdini: Fooling deep structured visual and speech recognition mossdels with adversarial examples . In Proceedings of the s Neural Information Processing Systems (NIPS’17) . 6977--6987. Moustapha M. Cisse, Yossi Adi, Natalia Neverova, and Joseph Keshet. 2017. Houdini: Fooling deep structured visual and speech recognition mossdels with adversarial examples. In Proceedings of the s Neural Information Processing Systems (NIPS’17). 6977--6987.
- Jason A. Colquitt , and Jessica B . Rodell . 2015 . Measuring justice and fairness. In Oxford Handbook of Justice in the Workplace. Vol. 187 , Oxford University Press , 202. Jason A. Colquitt, and Jessica B. Rodell. 2015. Measuring justice and fairness. In Oxford Handbook of Justice in the Workplace. Vol. 187, Oxford University Press, 202.
- Emad N. Eskandar and Barry J. Richmond. 1991. Decoding of neuronal signals in visual pattern recognition . In Proceedings of the 4th International Conference on Neural Information Processing Systems (NIPS’91) . J. E. Moody, S. J. Hanson, and R. P. Lippmann (Eds.), Morgan Kaufmann Publishers Inc., San Francisco, CA, 356--363. Emad N. Eskandar and Barry J. Richmond. 1991. Decoding of neuronal signals in visual pattern recognition. In Proceedings of the 4th International Conference on Neural Information Processing Systems (NIPS’91). J. E. Moody, S. J. Hanson, and R. P. Lippmann (Eds.), Morgan Kaufmann Publishers Inc., San Francisco, CA, 356--363.
- 10.5555/1343031.1343035 · doi:10.5555/1343031.1343035
- Natasha Jaques , Sara Taylor , Ehimwenma Nosakhare , Akane Sano , and Rosalind Picard . 2016 . Multi-task learning for predicting health, stress, and happiness . In Proceedings of the NIPS Workshop on Machine Learning for Healthcare. Last Retrieved 14th September 2019 from https://pdfs.semanticscholar.org/b228/7a406985980515d5cc63e9b37fb17c5186f8.pdf. Natasha Jaques, Sara Taylor, Ehimwenma Nosakhare, Akane Sano, and Rosalind Picard. 2016. Multi-task learning for predicting health, stress, and happiness. In Proceedings of the NIPS Workshop on Machine Learning for Healthcare. Last Retrieved 14th September 2019 from https://pdfs.semanticscholar.org/b228/7a406985980515d5cc63e9b37fb17c5186f8.pdf.
- Maria Madsen , and Shirley Gregor . 2000 . Measuring human-computer trust . In Proceedings of the 11th Australasian Conference on Information Systems. Vol. 53 , 6--8. Maria Madsen, and Shirley Gregor. 2000. Measuring human-computer trust. In Proceedings of the 11th Australasian Conference on Information Systems. Vol. 53, 6--8.
- Sharon Oviatt Björn Schuller Philip R. Cohen Daniel Sonntag Gerasimos Potamianos and Antonio Krüger (Eds.). 2018. The Handbook of Multimodal-Multisensor Interfaces. ACM and Morgan 8 Claypool xvii--xix. DOI:https://doi.org/10.1145/3107990.3107991 · DOI
- 10.5555/1827616.1827621 · doi:10.5555/1827616.1827621
- 10.1300/j017v16n02_05 · doi:10.1300/j017v16n02_05
- 10.5555/1572306.1572327 · doi:10.5555/1572306.1572327
- Koustuv Saha , Benjamin Sugar , John Torous , Bruno Abrahao , Emre Kıcıman , and Munmun De Choudhury . 2019 . A social media study on the effects of psychiatric medication use . In Proceedings of the International AAAI Conference on Web and Social Media 13 , 1 (2019), 440--451. DOI:https://wvvw.aaai.org/ojs/index.php/ICWSM/article/view/3242 Koustuv Saha, Benjamin Sugar, John Torous, Bruno Abrahao, Emre Kıcıman, and Munmun De Choudhury. 2019. A social media study on the effects of psychiatric medication use. In Proceedings of the International AAAI Conference on Web and Social Media 13, 1 (2019), 440--451. DOI:https://wvvw.aaai.org/ojs/index.php/ICWSM/article/view/3242
- Oliver Theobald . 2017. Machine Learning for Absolute Beginners. A Plain English Introduction . Scatterplot Press . Oliver Theobald. 2017. Machine Learning for Absolute Beginners. A Plain English Introduction. Scatterplot Press.
- Frank W. Weathers , Brett T. Litz , Debra S. Herman , Jennifer A. Huska , and Terence M. Keane . 1993. The PTSD checklist (PCL): Reliability, validity, and diagnostic utility . In Proceedings of the Annual Convention of the International Society for Traumatic Stress Studies. Vol. 462 . Frank W. Weathers, Brett T. Litz, Debra S. Herman, Jennifer A. Huska, and Terence M. Keane. 1993. The PTSD checklist (PCL): Reliability, validity, and diagnostic utility. In Proceedings of the Annual Convention of the International Society for Traumatic Stress Studies. Vol. 462.
Cited by
Torous, J., Bucci, S., Bell, I. H., Kessing, L. V., Faurholt‐Jepsen, M., Whelan, P., Carvalho, A. F., Keshavan, M., Linardon, J., & Firth, J. (2021) · World Psychiatry · doi:10.1002/wps.20883 · Cited by 1,199
Remote patient monitoring using artificial intelligence: Current state, applications, and challenges
Shaik, T., Tao, X., Higgins, N., Li, L., Gururajan, R., Zhou, X., & Acharya, U. R. (2023) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1485 · Cited by 515
The Pile: An 800GB Dataset of Diverse Text for Language Modeling
Gao, L., Biderman, S., Black, S., Golding, L., Hoppe, T., Foster, C., Phang, J., He, H., Thite, A., Nabeshima, N., et al. (2021) · arXiv · doi:10.48550/arxiv.2101.00027 · Cited by 492
Technology Acceptance in Mobile Health: Scoping Review of Definitions, Models, and Measurement
Nadal, C., Sas, C., & Doherty, G. (2020) · Journal of Medical Internet Research · doi:10.2196/17256 · Cited by 320
Self-citationUncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Bhatt, U., Antorán, J., Zhang, Y., Liao, Q. V., Sattigeri, P., Fogliato, R., Melançon, G., Krishnan, R., Stanley, J., Tickoo, O., et al. (2021) · Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3461702.3462571 · Cited by 300
“, [81, 173]).”
Metadata
- Authors
- Thieme, A., Belgrave, D., & Doherty, G.
- Affiliations
- Microsoft Research (United Kingdom) (GB)
- Trinity College Dublin (IE)
- Venue
- ACM Transactions on Computer-Human Interaction
- Published
- 2020-08-17
- Volume
- 27
- Issue
- 5
- Pages
- 1-53
- ISSN
- 1073-0516 (ISSN-L)
- 1557-7325
- OpenAlex
- W3042379185
- Cited by
- 406
- References
- 217
- Citations by year
- 2026: 53 · 2025: 91 · 2024: 82 · 2023: 63 · 2022: 82 · 2021: 29 · 2020: 6
- FWCI
- 40.78
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Computer-Human Interaction (publishedVersion)
- Funders
- Adapt Centre and Marie Sklodowska-Curie (722022)
- SFI (13/RC/2106)
- Topics
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Physical Sciences › Computer Science › Artificial Intelligence › Emotion and Mood Recognition
- Social Sciences › Psychology › Social Psychology › Mental Health via Writing
- Keywords
- mental disorder detection, psychiatric diagnosis, personalized treatment, behavioral pattern recognition, mental health risk factors, disease progression prediction, human-centered design, interdisciplinary research, ethical implications of AI, clinical implementation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.