Development and validation of machine learning-based diagnostic models using blood transcriptomics for early childhood diabetes prediction
This study establishes the feasibility of integrating peripheral blood transcriptomic profiling with machine learning for early pediatric T1DM prediction. The identified transcriptomic signatures and validated predictive models provide a foundation for developing clinically translatable, non-invasive diagnostic tools. These findings support the implementation of precision medicine approaches for childhood diabetes prevention and warrant validation in larger, multi-center cohorts to assess generalizability and clinical utility.
Authors
- H.L. Zhuang (ORCID: https://orcid.org/0009-0001-3635-6290)
- Pan Liu (ORCID: https://orcid.org/0009-0006-8544-3725)
- Xin Huang (ORCID: https://orcid.org/0000-0002-4081-9024)
- Weiming Xie
- Lizhong Guo (ORCID: https://orcid.org/0000-0002-1938-2649)
- Siyu Gao (ORCID: https://orcid.org/0000-0002-9434-5979)
- Di Ouyang
Institutions
- Nanjing University of Chinese Medicine (CN)
- Guangxi Medical University (CN)
- Xuzhou Medical College (CN)
- Yulin Normal University (CN)
- Guangxi Yuchai Machinery Group (China) (CN)
- Second People’s Hospital of Huai’an (CN)
- Yulin Orthopedics Hospital of Chinese and Western Medicine (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-07-16
- DOI
- https://doi.org/10.3389/fmed.2025.1636214
- Citations
- 1
- Primary Topic
- Hyperglycemia and glycemic control in critically ill and hospitalized patients
- Type
- article
- Field-Weighted Citation Impact
- 1.29
Funders
- Yulin Science and Technology Bureau