Annals of Internal Medicine· 2018Q1
Ensuring Fairness in Machine Learning to Advance Health Equity
- 1,194citations
- Q1SCImago
- 2018year
Short summary
Machine learning models can exacerbate health disparities by learning from biased historical data, but can be proactively designed using principles of distributive justice to advance health equity.
AI-generated from the title and abstract; the full text is not read.
Key points
- Machine learning models can harm protected groups by learning from historically biased data, leading to incorrect predictions or resource withholding.
- Model design, data biases, and interactions with clinicians/patients can worsen healthcare disparities.
- Proactive design of machine learning systems is needed to advance health equity.
- Technical implementations of distributive justice (equality in outcomes, performance, resource allocation) should be incorporated into model design, deployment, and evaluation.
AI-generated from the title and abstract; the full text is not read.
Abstract
Machine learning is used increasingly in clinical care to improve diagnosis, treatment selection, and health system efficiency. Because machine-learning models learn from historically collected data, populations that have experienced human and structural biases in the past-called protected groups-are vulnerable to harm by incorrect predictions or withholding of resources. This article describes how model design, biases in data, and the interactions of model predictions with clinicians and patients may exacerbate health care disparities. Rather than simply guarding against these harms passively, machine-learning systems should be used proactively to advance health equity. For that goal to be achieved, principles of distributive justice must be incorporated into model design, deployment, and evaluation. The article describes several technical implementations of distributive justice-specifically those that ensure equality in patient outcomes, performance, and resource allocation-and guides clinicians as to when they should prioritize each principle. Machine learning is providing increasingly sophisticated decision support and population-level monitoring, and it should encode principles of justice to ensure that models benefit all patients.
The authors' abstract, as published at the source. Annals of Internal Medicine, 2018 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Health Informatics
Health InformaticsMedicine