PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendation

Abstract Background Current phenotype-based diagnostic tools often struggle with accurate disease prioritization due to incomplete phenotypic data and the complexity of rare disease presentations. Additionally, they lack the ability to generate patient-centered clinical insights or recommend further...

Full description

Saved in:
Bibliographic Details
Main Authors: Baole Wen, Sheng Shi, Yi Long, Yanan Dang, Weidong Tian
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Genome Medicine
Subjects:
Online Access:https://doi.org/10.1186/s13073-025-01496-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434300103000064
author Baole Wen
Sheng Shi
Yi Long
Yanan Dang
Weidong Tian
author_facet Baole Wen
Sheng Shi
Yi Long
Yanan Dang
Weidong Tian
author_sort Baole Wen
collection DOAJ
description Abstract Background Current phenotype-based diagnostic tools often struggle with accurate disease prioritization due to incomplete phenotypic data and the complexity of rare disease presentations. Additionally, they lack the ability to generate patient-centered clinical insights or recommend further symptoms for differential diagnosis. Methods We developed PhenoDP, a deep learning-based toolkit with three modules: Summarizer, Ranker, and Recommender. The Summarizer fine-tuned a distilled large language model to create clinical summaries from a patient’s Human Phenotype Ontology (HPO) terms. The Ranker prioritizes diseases by combining information content-based, phi-based, and semantic-based similarity measures. The Recommender employs contrastive learning to recommend additional HPO terms for enhanced diagnostic accuracy. Results PhenoDP’s Summarizer produces more clinically coherent and patient-centered summaries than the general-purpose language model FlanT5. The Ranker achieves state-of-the-art diagnostic performance, consistently outperforming existing phenotype-based methods across both simulated and real-world datasets. The Recommender also outperformed GPT-4o and PhenoTips in improving diagnostic accuracy when its suggested terms were incorporated into different ranking pipelines. Conclusions PhenoDP enhances Mendelian disease diagnosis through deep learning, offering precise summarization, ranking, and symptom recommendation. Its superior performance and open-source design make it a valuable clinical tool, with potential to accelerate diagnosis and improve patient outcomes. PhenoDP is freely available at https://github.com/TianLab-Bioinfo/PhenoDP .
format Article
id doaj-art-b120da21ebdf47a39c48c582d2940f2e
institution Kabale University
issn 1756-994X
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series Genome Medicine
spelling doaj-art-b120da21ebdf47a39c48c582d2940f2e2025-08-20T03:26:43ZengBMCGenome Medicine1756-994X2025-06-0117112010.1186/s13073-025-01496-8PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendationBaole Wen0Sheng Shi1Yi Long2Yanan Dang3Weidong Tian4State Key Laboratory of Genetics and Development of Complex Phenotypes, Department of Computational Biology, School of Life Sciences, Fudan UniversityState Key Laboratory of Genetics and Development of Complex Phenotypes, Department of Computational Biology, School of Life Sciences, Fudan UniversitySchool of Medicine, Nankai UniversityState Key Laboratory of Genetics and Development of Complex Phenotypes, Department of Computational Biology, School of Life Sciences, Fudan UniversityState Key Laboratory of Genetics and Development of Complex Phenotypes, Department of Computational Biology, School of Life Sciences, Fudan UniversityAbstract Background Current phenotype-based diagnostic tools often struggle with accurate disease prioritization due to incomplete phenotypic data and the complexity of rare disease presentations. Additionally, they lack the ability to generate patient-centered clinical insights or recommend further symptoms for differential diagnosis. Methods We developed PhenoDP, a deep learning-based toolkit with three modules: Summarizer, Ranker, and Recommender. The Summarizer fine-tuned a distilled large language model to create clinical summaries from a patient’s Human Phenotype Ontology (HPO) terms. The Ranker prioritizes diseases by combining information content-based, phi-based, and semantic-based similarity measures. The Recommender employs contrastive learning to recommend additional HPO terms for enhanced diagnostic accuracy. Results PhenoDP’s Summarizer produces more clinically coherent and patient-centered summaries than the general-purpose language model FlanT5. The Ranker achieves state-of-the-art diagnostic performance, consistently outperforming existing phenotype-based methods across both simulated and real-world datasets. The Recommender also outperformed GPT-4o and PhenoTips in improving diagnostic accuracy when its suggested terms were incorporated into different ranking pipelines. Conclusions PhenoDP enhances Mendelian disease diagnosis through deep learning, offering precise summarization, ranking, and symptom recommendation. Its superior performance and open-source design make it a valuable clinical tool, with potential to accelerate diagnosis and improve patient outcomes. PhenoDP is freely available at https://github.com/TianLab-Bioinfo/PhenoDP .https://doi.org/10.1186/s13073-025-01496-8Phenotype-driven diagnosisMendelian diseaseLarge language modelsHuman Phenotype OntologyDisease rankingClinical summarization
spellingShingle Baole Wen
Sheng Shi
Yi Long
Yanan Dang
Weidong Tian
PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendation
Genome Medicine
Phenotype-driven diagnosis
Mendelian disease
Large language models
Human Phenotype Ontology
Disease ranking
Clinical summarization
title PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendation
title_full PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendation
title_fullStr PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendation
title_full_unstemmed PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendation
title_short PhenoDP: leveraging deep learning for phenotype-based case reporting, disease ranking, and symptom recommendation
title_sort phenodp leveraging deep learning for phenotype based case reporting disease ranking and symptom recommendation
topic Phenotype-driven diagnosis
Mendelian disease
Large language models
Human Phenotype Ontology
Disease ranking
Clinical summarization
url https://doi.org/10.1186/s13073-025-01496-8
work_keys_str_mv AT baolewen phenodpleveragingdeeplearningforphenotypebasedcasereportingdiseaserankingandsymptomrecommendation
AT shengshi phenodpleveragingdeeplearningforphenotypebasedcasereportingdiseaserankingandsymptomrecommendation
AT yilong phenodpleveragingdeeplearningforphenotypebasedcasereportingdiseaserankingandsymptomrecommendation
AT yanandang phenodpleveragingdeeplearningforphenotypebasedcasereportingdiseaserankingandsymptomrecommendation
AT weidongtian phenodpleveragingdeeplearningforphenotypebasedcasereportingdiseaserankingandsymptomrecommendation