Stigma, biomarkers, and algorithmic bias: recommendations for precision behavioral health with artificial intelligence
Open accessThe DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index.
Abstract
Effective implementation of artificial intelligence in behavioral healthcare delivery depends on overcoming challenges that are pronounced in this domain. Self and social stigma contribute to under-reported symptoms, and under-coding worsens ascertainment. Health disparities contribute to algorithmic bias. Lack of reliable biological and clinical markers hinders model development, and model explainability challenges impede trust among users. In this perspective, we describe these challenges and discuss design and implementation recommendations to overcome them in intelligent systems for behavioral and mental health.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Trust may be lost when AI have many false positive or negative results [41], are perceived to be incompetent [30], or make use of public data in a disrespectful way [37].”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [41]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Economic factors (e.g.different billing rates for specific groups) could also influence what and how information is collected in healthcare [41].”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [41]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Another bias related to interactions is the feedback loop [80]. This occurs when clinicians accept AI recommendations even if they are incorrect, leading the algorithm to relearn and perpetuate the same mistakes.”
From Fairness of artificial intelligence in healthcare: review and recommendations (2024) · cites this paper as [80]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“If such data is used for predictions, these algorithms could simply exacerbate existing disparities [40,41].”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [41]
The cited source says what the claim attributes to it.
In the citing paper
“People are more likely to report behavioural symptoms to digital agents than humans”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [41]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
Computing Machinery and Intelligence (1950)
Turing, A. (2004) · The Essential Turing · doi:10.1093/oso/9780198250791.003.0017 · Cited by 6,118
Neural Networks and the Bias/Variance Dilemma
Geman, S., Bienenstock, E., & Doursat, R. (1992) · Neural Computation · doi:10.1162/neco.1992.4.1.1 · Cited by 3,578 · cited 1×
“43 A rich literature in AI includes representational and procedural bias in the interest of generalizing algorithmic learning beyond “strict consistency with individual instances.””
Background(2019) · Cited by 2,637
Box, G. E. P. (1976) · Journal of the American Statistical Association · doi:10.1080/01621459.1976.10480949 · Cited by 2,114 · cited 1×
“69 In 2019, we might amend that statement to say, “All models are wrong, some are useful, some might be dangerous.””
BackgroundShandler, R. (2019) · Journal of Cyber Policy · doi:10.1080/23738871.2019.1637914 · Cited by 2,092
Risk Prediction Models for Hospital Readmission: A Systematic Review
Kansagara, D., Englander, H., Salanitro, A., Kagen, D., Theobald, C., Freeman, M., & Kripalani, S. (2011) · JAMA · doi:10.1001/jama.2011.1515 · Cited by 1,707
Social determinants of mental health
Allen, J., Balfour, R., Bell, R., & Marmot, M. (2014) · International Review of Psychiatry · doi:10.3109/09540261.2014.928270 · Cited by 1,411
Automated Identification of Diabetic Retinopathy Using Deep Learning
Gargeya, R., & Leng, T. (2017) · Ophthalmology · doi:10.1016/j.ophtha.2017.02.008 · Cited by 1,362
Research works printed but not linked: 13
- Corrigan PW, Kleinlein P. The Impact of Mental Illness Stigma. In P. W. Corrigan ed. On the stigma of mental illness: Practical strategies for research and social change. Washington, DC, US: American Psychological Association; 2005:11–44.
- Choi E, Bahadori MT, Sun J, Kulas J, Schuetz A, Stewart W. Retain: An interpretable predictive model for healthcare using reverse time attention mechanism. In Advances in Neural Information Processing Systems, 2016: 3504–3512.
- Mikolov T, Sutskever I, Chen K, et al Distributed representations of words and phrases and their compositionality In: Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2. Curran Associates Inc; 2013: 3111– 19; Lake Tahoe, CA. http://dl.acm.org/citation.cfm? id=2999792.2999959. Accessed July 22, 2019.
- Baeza-Yates R. Data and algorithmic bias in the web In: Proceedings of the 8th ACM Conference on Web Science. ACM; 2016: 1; Hannover, Germany.
- Danks D, London AJ. Algorithmic bias in autonomous systems In: IJCAI. 2017: 4691– 97.
- Hajian S, Bonchi F, Castillo C. Algorithmic bias: from discrimination discovery to fairness-aware data mining In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY: ACM; 2016: 2125– 26.
- Lambrecht A, Tucker CE. Algorithmic bias? An empirical study into apparent gender-based discrimination in the display of STEM career ads. Management Science; 2019; 65 (7): 2947– 3448.
- Niculescu-Mizil A, Caruana R. Predicting good probabilities with supervised learning In: Proceedings of the 22nd International Conference on Machine Learning. New York, NY: ACM; 2005: 625– 32.
- Gunning D, Aha D. DARPA's Explainable Artificial Intelligence (XAI) Program. AI Magazine, 2019; 40 (2): 44–58.
- Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, Pedreschi D. A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 2019; 51 (5): 93
- Chen I, Johansson FD, Sontag D. Why is my classifier discriminatory? In: Bengio S, Wallach H, Larochelle H, et al, eds. Advances in Neural Information Processing Systems 31. Curran Associates, Inc; 2018: 3539– 50; Montreal, Canada. http://papers.nips.cc/paper/7613-why-is-my-classifier-discriminatory.pdf. Accessed March 5, 2019.
- Goodman KW, Cushman R, Miller RA. Ethics in Biomedical and Health Informatics: Users, Standards, and Outcomes. In: Shortliffe EH and Cimino JJ, eds. Biomedical Informatics—Computer Applications in Health Care and Biomedicine. New York: Springer; 2014: 329– 53.
- Kaplan B, Ranchordás S. Alzheimer's and m-Health: Regulatory, Privacy, and Ethical Considerations. In: Hayre CM, Muller DJ, and Scherer MH, eds. Everyday Technologies in Healthcare. 1 ed. Boca Raton, FL: CRC Press, 2019: 31– 52.
Cited by
Items 101–139 of 139
(2024) · Pesci Egyetemi Archivum (University of Pécs) · doi:10.15170/4ffisc-ktk-2024 · Cited by 1
Ayim, A., Dassah, Z., Sopaal, A., Amoako, E., & Addy, A. (2025) · Ghana Journal of Nursing and Midwifery. · doi:10.69600/gjnmid.2024.v01.i04.140-170 · Cited by 2
Applying analytics to sociodemographic disparities in mental health
Baird, A. M., & Xia, Y. (2025) · Nature Mental Health · doi:10.1038/s44220-024-00359-2 · Cited by 4
Matos, A. G. M. (2022) · EthAIca · doi:10.56294/ai202220 · Cited by 8
Rassismusforschung III: Rassismus in Strukturen und Praxisfeldern
Rassismusmonitor, N. D. U. (2025) · Gesellschaft der Unterschiede · doi:10.14361/9783839467527 · Cited by 1
Galli, F., New, K. J., & Grech, M. (2023) · Mental Health Global Challenges Journal · doi:10.56508/mhgcj.v6i1.163 · Cited by 1
Delgado, C. F., Ferretti, M. T., & Carnevale, A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13681-8.00012-6 · Cited by 2
Análise de predições de atendimentos na saúde em Florianópolis
Weber, L., Lourenço, L. A., Brehm, M. K., Pereira, P. M., & Ramos, V. F. C. (2024) · Journal of Health Informatics · doi:10.59681/2175-4411.v16.iespecial.2024.1338 · Cited by 1
Empowering Epidemiology with Life-Based Ethics: A Study of the Exposome and Exposomics
Safarlou, C. W. (2025) · Utrecht University Repository (Utrecht University) · doi:10.33540/2831 · Cited by 1
Rubeis, G. (2024) · The International library of ethics, law and technology · doi:10.1007/978-3-031-55744-6_5
Human Resource Development Dimensions of Health AI Implementation in Selected Africa Countries
Sopaal, A., Amoako, E., Ayim, A., Dassah, Z., & Mensah, G. A. (2025) · Ghana Journal of Nursing and Midwifery. · doi:10.69600/gjnmid.2024.v01.i04.198-228 · Cited by 1
Kählig, M., Wendt, K., Hickmann, E., & Schlieter, H. (2024) · Gemeinschaften in Neuen Medien · doi:10.25368/2025.342
Towards Human-Centered Digital Health Interventions
Kostick, K. M., & Storch, E. A. (2025) · Psychiatric Clinics of North America · doi:10.1016/j.psc.2025.10.004
Interpretability of Deep Learning Models for Time-Series Clinical Data
Nayebi Nodoushan, A., & Nayebi Nodoushan, A. (2023) · UA Campus Repository (The University of Arizona)
How Can I ‘Speak’ to Earn Your Trust: Impact of Voice on Trust in Mental Healthcare
Xian, C., & Xu, D. (. (2025) · Journal of the Association for Information Systems
Herencia del sesgo: influencia de los sesgos de la Inteligencia Artificial en las decisiones humanas
Vicente Holgado, L. (2024) · Basque Digital Memory (Vital Foundation) · Cited by 1
Exploring User Acceptance of AI Chatbots in Mental Health Support
Mendes, M. M. (2025) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)
Artificial intelligence and digital control: navigating the future of laser dentistry
Pinheiro, A. L. B. (2025) · LASER THERAPY · doi:10.4081/ltj.2025.431
An Overview of AI and Data Science in South Africa
Olaokun, T. T., Nkuna, J., & Pradhan, A. (2025) · IEEE International Conference on Industrial Engineering and Engineering Management (IEEM) · doi:10.1109/ieem63636.2025.11357831
“It is essential to consider these issues to ensure AI technologies are relevant and practical for the local context [41].”
Precision Psychiatry in the Age of AI: Early Detection and Personalized Treatment of Mood Disorders
Verma, M., & Beg, M. J. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-1325-2.ch004
Souligne, N., & Subbian, V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.16450
“…significantly shape the quality of healthcare data but that these societal inequities that become embedded in the data used to train these models can lead to significant model performance biases along demographic lines that may perpetuate or even reinforce these systemic inequities 3,4,5,6,7 .”
Self-citationRubeis, G. (2026) · Springer eBooks · doi:10.1007/978-3-032-14301-3_5
Explainable Artificial Intelligence for Early Disease Prediction in Public Health Systems
OSENI, P. A., & Omiko, D. O. (2026) · International Journal of Scientific Research in Science Engineering and Technology · doi:10.32628/ijsrset2613312
Mapping the role of artificial intelligence in health-related stigma: a scoping review
Song, T., Jamieson, J., Akahori, W., Meng, H., Wang, S., & Lee, Y.-C. (2026) · npj Digital Medicine · doi:10.1038/s41746-026-02832-x · Cited by 1
“Clear reporting of labeling criteria, transparency about annotation processes, and engagement with people who have lived experience of stigmatized conditions are needed to ensure conceptual validity and ethical sensitivity 59,106,107 .”
The impact of policy shifts on mental health innovation, accessibility, and ethical considerations
Ebo, T. O., Osho, D., Ebo, D. M., Egbon, E., Okesanya, O. J., & Olawade, D. B. (2026) · Journal of Global Health Science · doi:10.35500/jghs.2026.8.e15
HarmoniqMind: AI-Powered Mental Equilibrium and Relationship Optimizer
Thilagam, T., Ram, S. K., & Karn, S. (2026) · International Conference on Computational Intelligence and Communication Networks (CICN) · doi:10.1109/cicn70047.2026.11594214
“Walsh et al. [18] further emphasized algorithmic bias risks in behavioral health prediction systems and recommended fairness-aware modeling strategies.”
FairSelect: A Systematic Evaluation of Multi-Level and Intersectional Algorithmic FairnessPreprint
Souligne, N., Mixton-Garcia, I., & Subbian, V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.08953
“Comprehensive reviews have documented common sources of bias arising from data collection practices, measurement processes, and modeling assumptions, highlighting the importance of understanding sociotechnical drivers of inequity in predictive modeling [2,29,30,31].”
Self-citationSabri, O., & Alabdali, S. A. (2026) · Healthcare · doi:10.3390/healthcare14162506
“In addition, the emergence of generative AI and large language models has introduced new governance challenges related to clinical safety, liability, data privacy, hallucinations, and algorithmic bias, which are not fully addressed by existing frameworks [24–27].”
Precision medicine for mood disorders in the big data era
Joshi, A. A., Franklin, C., Bray, M. J. C., Adams, R. J., Li, K., Taylor, J., Goes, F. S., Zandi, P., & Potash, J. B. (2026) · International Review of Psychiatry · doi:10.1080/09540261.2026.2717216
Alhalawany, R. M., Khatatbeh, Y. M., & Jawkhab, A. A. (2026) · Healthcare · doi:10.3390/healthcare14172721
“These limitations highlight the need for a comprehensive synthesis of evidence that can critically integrate clinical, educational and governance perspectives in a single analytical framework [3,7,8,10,15].”
InfluentialKaligis, F., Rizqina, A. R., Pramatirta, B., Purba, N. V. T., & Widyaputri, F. N. (2026) · Behavioral Sciences · doi:10.3390/bs16091622
“Moreover, the performance of the algorithm itself heavily depends on the quality and diversity of data they trained on, meaning that bias even in AI cannot be disregarded (Thakkar et al., 2024; Walsh et al., 2020).”
Prakash, P., & Reddy, K. J. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-9109-0.ch011
Navigating the AI-Driven Healthcare Era: A Review of Key Developments
Khan, M., & Sherani, A. M. K. (2024) · BULLET : Jurnal Multidisiplin Ilmu
Butorac, I., McNaney, R., Seguin, J. P., Northam, J. C., Yap, M. B. H., & Carter, A. (2026) · Frontiers in Digital Health · doi:10.3389/fdgth.2026.1941307
Rossom, R. C., Johnson, E. A., Papini, S., Shortreed, S. M., Coleman, K. J., Ziebell, R. A., Ahmedani, B. K., Lynch, F. L., Beck, A. L., Daida, Y. G., et al. (2026) · Psychiatric Services · doi:10.1176/appi.ps.20250697
Ahmad, N., Diyali, C., & Guite, N. (2026) · Adolescencia e Saude · doi:10.67440/ahj.vi.2809
Kasoka, K. (2026) · Medicine Health Care and Philosophy · doi:10.1007/s11019-026-10418-3
Metadata
- Authors
- Walsh, C. G., Chaudhry, B., Dua, P., Goodman, K. W., Kaplan, B., Kavuluru, R., Solomonides, A., & Subbian, V.
- Affiliations
- Vanderbilt University Medical Center (US)
- University of Louisiana at Lafayette (US)
- Louisiana Tech University (US)
- University of Miami (US)
- Yale University (US)
- University of Kentucky (US)
- Endeavor Health (US)
- University of Arizona (US)
- Corresponding author
- Walsh, Colin G
- ORCID
- Venue
- JAMIA Open
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-01-22
- Volume
- 3
- Issue
- 1
- Pages
- 9-15
- ISSN
- 2574-2531 (ISSN-L)
- PMC
- PMC7309258
- OpenAlex
- W3001779409
- Cited by
- 118
- References
- 67
- Citations by year
- 2026: 14 · 2025: 24 · 2024: 28 · 2023: 23 · 2022: 19 · 2021: 6 · 2020: 4
- FWCI
- 3.83
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- JAMIA Open (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Funders
- National Institute of General Medical Sciences (# W81XWH-10-2-0181, R01 MH116269-01)
- National Institutes of Health (#P20 GM103424-17)
- U.S. National Center for Advancing Translational Sciences (#UL1TR001998)
- National Science Foundation (#1838745)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- algorithmic bias, stigma, self-stigma, social stigma, biomarkers, health disparities, model explainability, mental health, symptom underreporting, intelligent systems
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.