Step-by-Step Guidance to Differential Anemia Diagnosis with Real-World Data and Deep Reinforcement Learning

Lillian Muyama, Estelle Lu, Geoffrey Cheminet, Jacques Pouchot, Bastien Rance +3 more
12/3/2024
cs.LG

No official code found. Best implementation: lilly-muyama/RWD-Anemia-Diagnostic-Pathways (1 star, MIT, last commit 2024-09-05).

Abstract

Clinical diagnostic guidelines outline the key questions to answer to reach a diagnosis. Inspired by guidelines, we aim to develop a model that learns from electronic health records to determine the optimal sequence of actions for accurate diagnosis. Focusing on anemia and its sub-types, we employ deep reinforcement learning (DRL) algorithms and evaluate their performance on both a synthetic dataset, which is based on expert-defined diagnostic pathways, and a real-world dataset. We investigate the performance of these algorithms across various scenarios. Our experimental results demonstrate that DRL algorithms perform competitively with state-of-the-art methods while offering the significant advantage of progressively generating pathways to the suggested diagnosis, providing a transparent decision-making process that can guide and explain diagnostic reasoning.

View on arXivView PDF

Code Implementations(1)

lilly-muyama/RWD-Anemia-Diagnostic-PathwaysCommunity100%
MIT
11HTML, PythonAug 28, 20242 years agoMIT

Similar Papers

Extracting Diagnosis Pathways from Electronic Health Records Using Deep Reinforcement Learning

96% match2023

Prompting Large Language Models for Supporting the Differential Diagnosis of Anemia

85% match2024

Deep Reinforcement Learning for Cost-Effective Medical Diagnosis

82% match1 repo142023

DDxT: Deep Generative Transformer Models for Differential Diagnosis

81% match1 repo32023

Deep Reinforcement Learning for Personalized Diagnostic Decision Pathways Using Electronic Health Records: A Comparative Study on Anemia and Systemic Lupus Erythematosus

81% match1 repo12024

Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning

80% match1 repo312025

Cite this paper

@article{muyama2024stepbystep,
  title  = {Step-by-Step Guidance to Differential Anemia Diagnosis with Real-World Data and Deep Reinforcement Learning},
  author = {Lillian Muyama and Estelle Lu and Geoffrey Cheminet and Jacques Pouchot and Bastien Rance and Anne-Isabelle Tropeano and Antoine Neuraz and Adrien Coulet},
  year   = {2024},
  eprint = {2412.02273},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2412.02273v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2412.02273.svg)](https://codeofpaper.com/paper/2412.02273)

Discussion