Fairness and bias correction in machine learning for depression prediction across four study populations

Scientific Reports, vol. 14, pp. 7848

Abstract

A significant level of stigma and inequality exists in mental healthcare, especially in under-served populations. Inequalities are reflected in the data collected for scientific purposes. When not properly accounted for, machine learning (ML) models learned from data can reinforce these structural inequalities or biases. Here, we present a systematic study of bias in ML models designed to predict depression in four different case studies covering different countries and populations. We find that standard ML approaches regularly present biased behaviors. We also show that mitigation techniques, both standard and our own post-hoc method, can be effective in reducing the level of unfair bias. There is no one best ML model for depression prediction that provides equality of outcomes. This emphasizes the importance of analyzing fairness during model selection and transparent reporting about the impact of debiasing interventions. Finally, we also identify positive habits and open challenges that practitioners could follow to enhance fairness in their models.

Authors 7

1. Vien Ngoc Dang corresponding

   Universitat de Barcelona

   Affiliation as printed

   Departament de Matemàtiques i Informàtica, Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain. dangn@ub.edu

   Departament de Matemàtiques i Informàtica, Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain

2. Anna Cascarano

   Universitat de Barcelona

   Affiliation as printed

   Departament de Matemàtiques i Informàtica, Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain

3. Rosa H. Mulder

   Erasmus MC

   Affiliation as printed

   Department of Child and Adolescent Psychiatry/Psychology, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands

   The Generation R Study Group, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands

4. Charlotte A. M. Cecil Aachen Molecular Epidemiology Department of Biomedical Data Sciences

   Leiden University Medical Center · Erasmus MC

   Affiliation as printed

   Department of Child and Adolescent Psychiatry/Psychology, Erasmus MC, University Medical Center Rotterdam, Rotterdam, The Netherlands

   Department of Epidemiology, Erasmus MC, Rotterdam,University Medical Center Rotterdam, Rotterdam, The Netherlands

   Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands

5. María A. Zuluaga

   EURECOM

   Affiliation as printed

   Data Science Department, EURECOM, Biot, France

6. Jerónimo Hernández-González

   Universitat de Girona

   Affiliation as printed

   Departament d'Informàtica, Matemàtica Aplicada i Estadística, Universitat de Girona, Girona, Spain

7. Karim Lekadir

   Institució Catalana de Recerca i Estudis Avançats · Universitat de Barcelona

   Affiliation as printed

   Departament de Matemàtiques i Informàtica, Facultat de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, Spain

   Institució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Spain