Algorithmic fairness in precision psychiatry: analysis of prediction models in individuals at clinical high risk for psychosis.

Şahin, Derya; Kambeitz-Ilankovic, Lana; Wood, Stephen; Dwyer, Dominic; Upthegrove, Rachel; Salokangas, Raimo; Borgwardt, Stefan; Brambilla, Paolo; Meisenzahl, Eva; Ruhrmann, Stephan; Schultze-Lutter, Frauke; Lencer, Rebekka; Bertolino, Alessandro; Pantelis, Christos; Koutsouleris, Nikolaos; Kambeitz, Joseph (2024). Algorithmic fairness in precision psychiatry: analysis of prediction models in individuals at clinical high risk for psychosis. The British journal of psychiatry, 224(2), pp. 55-65. Cambridge University Press 10.1192/bjp.2023.141

[img] Text
algorithmic-fairness-in-precision-psychiatry-analysis-of-prediction-models-in-individuals-at-clinical-high-risk-for-psychosis.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.
Author holds Copyright

Download (448kB)

BACKGROUND

Computational models offer promising potential for personalised treatment of psychiatric diseases. For their clinical deployment, fairness must be evaluated alongside accuracy. Fairness requires predictive models to not unfairly disadvantage specific demographic groups. Failure to assess model fairness prior to use risks perpetuating healthcare inequalities. Despite its importance, empirical investigation of fairness in predictive models for psychiatry remains scarce.

AIMS

To evaluate fairness in prediction models for development of psychosis and functional outcome.

METHOD

Using data from the PRONIA study, we examined fairness in 13 published models for prediction of transition to psychosis (n = 11) and functional outcome (n = 2) in people at clinical high risk for psychosis or with recent-onset depression. Using accuracy equality, predictive parity, false-positive error rate balance and false-negative error rate balance, we evaluated relevant fairness aspects for the demographic attributes 'gender' and 'educational attainment' and compared them with the fairness of clinicians' judgements.

RESULTS

Our findings indicate systematic bias towards assigning less favourable outcomes to individuals with lower educational attainment in both prediction models and clinicians' judgements, resulting in higher false-positive rates in 7 of 11 models for transition to psychosis. Interestingly, the bias patterns observed in algorithmic predictions were not significantly more pronounced than those in clinicians' predictions.

CONCLUSIONS

Educational bias was present in algorithmic and clinicians' predictions, assuming more favourable outcomes for individuals with higher educational level (years of education). This bias might lead to increased stigma and psychosocial burden in patients with lower educational attainment and suboptimal psychosis prevention in those with higher educational attainment.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > University Psychiatric Services > University Hospital of Child and Adolescent Psychiatry and Psychotherapy > Research Division
04 Faculty of Medicine > University Psychiatric Services > University Hospital of Child and Adolescent Psychiatry and Psychotherapy

UniBE Contributor:

Schultze-Lutter, Frauke

Subjects:

600 Technology > 610 Medicine & health

ISSN:

1472-1465

Publisher:

Cambridge University Press

Language:

English

Submitter:

Pubmed Import

Date Deposited:

08 Nov 2023 16:21

Last Modified:

25 Jan 2024 00:14

Publisher DOI:

10.1192/bjp.2023.141

PubMed ID:

37936347

Uncontrolled Keywords:

Ethics psychotic disorders/schizophrenia risk assessment schizophrenia stigma and discrimination

BORIS DOI:

10.48350/188685

URI:

https://boris.unibe.ch/id/eprint/188685

Actions (login required)

Edit item Edit item
Provide Feedback