Predicting Opioid Use Outcomes in Minoritized Communities

TL;DR

This study uses machine learning to predict opioid use outcomes in minoritized communities, highlighting the importance of representative data to avoid biases and improve prediction accuracy for diverse populations.

Contribution

It demonstrates the impact of training data composition on model accuracy for opioid use predictions in minoritized groups, emphasizing the need for inclusive datasets.

Findings

Models trained on diverse data predict outcomes accurately.

Models trained only on majority groups perform poorly on minoritized groups.

Biases due to cultural and systemic factors affect prediction accuracy.

Abstract

Machine learning algorithms can sometimes exacerbate health disparities based on ethnicity, gender, and other factors. There has been limited work at exploring potential biases within algorithms deployed on a small scale, and/or within minoritized communities. Understanding the nature of potential biases may improve the prediction of various health outcomes. As a case study, we used data from a sample of 539 young adults from minoritized communities who engaged in nonmedical use of prescription opioids and/or heroin. We addressed the indicated issues through the following contributions: 1) Using machine learning techniques, we predicted a range of opioid use outcomes for participants in our dataset; 2) We assessed if algorithms trained only on a majority sub-sample (e.g., Non-Hispanic/Latino, male), could accurately predict opioid use outcomes for a minoritized sub-sample (e.g., Latino, female). Results indicated that models trained on a random sample of our data could predict a range of opioid use outcomes with high precision. However, we noted a decrease in precision when we trained our models on data from a majority sub-sample, and tested these models on a minoritized sub-sample. We posit that a range of cultural factors and systemic forms of discrimination are not captured by data from majority sub-samples. Broadly, for predictions to be valid, models should be trained on data that includes adequate representation of the groups of people about whom predictions will be made. Stakeholders may utilize our findings to mitigate biases in models for predicting opioid use outcomes within minoritized communities.