Fairness Definitions and Metrics in Deep Reinforcement Learning for Drug Discovery in Healthcare: A Rapid Evidence Review

2026-06-01

AI Summary

This study addresses fairness issues in deep reinforcement learning (DRL) for de novo molecular design, which often arise from data biases, suboptimal reward function design, and inadequate evaluation protocols, leading to inequitable generation outcomes across disease domains and chemical scaffolds. The work presents the first systematic framework defining and evaluating fairness in DRL-based molecular generation, distinguishing between outcome fairness and distributional fairness, and elucidating their relationships with data partitioning strategies and reward mechanisms. Drawing on PRISMA-guided multi-source literature analysis, the authors propose quantifiable fairness metrics tailored to oncological and non-oncological indications—including disease subtypes—identify key determinants of fairness disparities, and thereby establish a theoretical foundation and practical guidelines for developing trustworthy and equitable DRL-driven drug discovery pipelines.

Abstract

Deep reinforcement learning (DRL) is increasingly applied to de novo molecular design, but choices in data, rewards, and evaluation can yield uneven performance across disease areas and chemotypes. Despite this, there is no concise synthesis of how fairness is defined, measured, and tested in DRL-based drug discovery. In this rapid evidence review, we synthesize fairness definitions and metrics for DRL-driven molecule generation in healthcare. We focus on three questions: (i) how dataset composition and split strategies, especially scaffold versus random splits, affect evaluation and distribution shift; (ii) how reward design (e.g., QED, docking, toxicity, synthetic accessibility) can create or mitigate bias, with emphasis on cancer targets; and (iii) which measurable metrics best capture fairness. This includes parity across cancer versus non-cancer indications and across cancer subtypes. It also includes distributional balance in key physicochemical descriptors, scaffold/chemotype diversity, groupwise validity, toxicity, and synthetic accessibility. From 2017 onward, we searched major biomedical, computer science, and engineering literature databases and used arXiv for horizon scanning. Records were screened using PRISMA-style procedures and analyzed via content coding to link reported parity outcomes to dataset and reward choices. Our review provides a concise set of fairness definitions and metrics for DRL molecule generation. It offers practical guidance for reporting distribution parity and outcome parity. It also summarizes how dataset and reward choices relate to observed parity effects and identifies open gaps relevant to trustworthy, cancer-relevant DRL generation.

Problem

• fairness
• deep reinforcement learning
• drug discovery
• healthcare
• molecular design

Innovation

• fairness metrics
• deep reinforcement learning
• molecular design
• dataset bias
• reward design