RDmaster: A novel phenotype-oriented dialogue system supporting differential diagnosis of rare disease

Jian Yang; Liqi Shu; Mingyu Han; Jiarong Pan; Lihua Chen; Tianming Yuan; Linhua Tan; Qiang Shu; Huilong Duan; Haomin Li

doi:10.1016/j.compbiomed.2024.107924

RDmaster: A novel phenotype-oriented dialogue system supporting differential diagnosis of rare disease

Comput Biol Med. 2024 Feb:169:107924. doi: 10.1016/j.compbiomed.2024.107924. Epub 2024 Jan 2.

Authors

Jian Yang¹, Liqi Shu², Mingyu Han³, Jiarong Pan³, Lihua Chen³, Tianming Yuan³, Linhua Tan⁴, Qiang Shu⁵, Huilong Duan⁶, Haomin Li⁷

Affiliations

¹ Clinical Data Center, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Zhejiang, China; The College of Biomedical Engineering and Instrument Science, Zhejiang University, Zhejiang, China.
² Rhode Island Hospital, Warren Alpert Medical School of Brown University, Rhode Island, USA.
³ Neonatal Department, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Zhejiang, China.
⁴ Surgical Intensive Care Unit, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Zhejiang, China.
⁵ Clinical Data Center, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Zhejiang, China.
⁶ The College of Biomedical Engineering and Instrument Science, Zhejiang University, Zhejiang, China.
⁷ Clinical Data Center, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Zhejiang, China. Electronic address: hmli@zju.edu.cn.

PMID: 38181610
DOI: 10.1016/j.compbiomed.2024.107924

Abstract

Background: Clinicians often lack the necessary expertise to differentially diagnose multiple underlying rare diseases (RDs) due to their complex and overlapping clinical features, leading to misdiagnoses and delayed treatments. The aim of this study is to develop a novel electronic differential diagnostic support system for RDs.

Method: Through integrating two Bayesian diagnostic methods, a candidate list was generated with enhance clinical interpretability for the further Q&A based differential diagnosis (DDX). To achieve an efficient Q&A dialogue strategy, we introduce a novel metric named the adaptive information gain and Gini index (AIGGI) to evaluate the expected gain of interrogated phenotypes within real-time diagnostic states.

Results: This DDX tool called RDmaster has been implemented as a web-based platform (http://rdmaster.nbscn.org/). A diagnostic trial involving 238 published RD patients revealed that RDmaster outperformed existing RD diagnostic tools, as well as ChatGPT, and was shown to enhance the diagnostic accuracy through its Q&A system.

Conclusions: The RDmaster offers an effective multi-omics differential diagnostic technique and outperforms existing tools and popular large language models, particularly enhancing differential diagnosis in collecting diagnostically beneficial phenotypes.

Keywords: Differential diagnosis; Electronic differential diagnostic support system; Human phenotype ontology; Phenomic and genomic diagnostics; Rare disease.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Bayes Theorem
Diagnosis, Differential
Dichlorodiphenyl Dichloroethylene*
Humans
Phenotype
Rare Diseases* / diagnosis
Rare Diseases* / genetics

Substances

Dichlorodiphenyl Dichloroethylene