Algorithmic fairness in precision psychiatry: analysis of prediction models in individuals at clinical high risk for psychosis
Year: 2023
Type: article
Abstract: 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: = 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.
DOI: 10.1192/bjp.2023.141
Authors: Derya Şahin, Lana Kambeitz-Ilankovic, Stephen Wood, Dominic Dwyer, Rachel Upthegrove, Raimo Salokangas, Stefan Borgwardt, Paolo Brambilla, Eva Meisenzahl, Stephan Ruhrmann, Frauke Schultze-Lutter, Rebekka Lencer, Alessandro Bertolino, Christos Pantelis, Nikolaos Koutsouleris, Joseph Kambeitz, for the PRONIA Study Group
Institutions: University of Cologne, University Hospital Cologne, Ludwig-Maximilians-Universität München, The University of Melbourne, Orygen, Birmingham Women’s and Children’s NHS Foundation Trust, University of Birmingham, University of Turku, University of Basel, Universitäre Psychiatrische Kliniken Basel, University of Lübeck, University of Milan, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Heinrich Heine University Düsseldorf, University of Bern, Universitas Airlangga, University of Münster, University of Bari Aldo Moro, Melbourne Health, King's College London, Max Planck Institute of Psychiatry
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: bronze
Funders: Universität Basel, University of Bern, Università degli Studi di Milano, Birmingham Women's and Children's NHS Foundation Trust, University of Cambridge, King's College London, European Commission, Deutsche Forschungsgemeinschaft, Universität zu Lübeck, Westfälische Wilhelms-Universität Münster, Universita degli Studi di Bari Aldo Moro, Turun Yliopisto, Universität zu Köln, Universitas Airlangga, Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico, Institute of Psychiatry, Psychology and Neuroscience, King’s College London
OpenAlex ID: W4388498236