Application of machine learning in constructing a diagnostic model for neonatal biliary atresia
ML models demonstrate high diagnostic accuracy for BA in neonates, with GGT, PLT counts, and acholic stools as pivotal predictors. This approach may enable earlier BA identification and intervention during the neonatal period.
Authors
- Peize Wang
- Dayan Sun (ORCID: https://orcid.org/0000-0003-0087-9230)
- Kaiyun Hua
- Junmin Liao
- Jie Sun (ORCID: https://orcid.org/0000-0002-1201-7550)
- Yichao Gu
- Dingding Wang (ORCID: https://orcid.org/0000-0001-5250-3011)
- Shuangshuang Li (ORCID: https://orcid.org/0000-0002-5885-3706)
- Yong Zhao (ORCID: https://orcid.org/0009-0005-5074-1346)
- Jinshi Huang (ORCID: https://orcid.org/0009-0007-8674-9184)
- Yuyan Jin
- Yanan Zhang (ORCID: https://orcid.org/0009-0007-7580-2293)
Institutions
- Capital Medical University (CN)
- Beijing Children’s Hospital (CN)
Publication Details
- Journal
- Pediatric Investigation
- Published
- 2025-05-05
- DOI
- https://doi.org/10.1002/ped4.70009
- Primary Topic
- Pediatric Hepatobiliary Diseases and Treatments
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Capital Medical University