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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |