From deep learning discovery to clinical validation: a new composite marker predicts mortality in type 2 diabetes
In this nationally representative cohort, ln[ALP × Scr] showed a J-shaped association with all-cause mortality. These findings highlight the potential utility of ln[ALP × Scr] as a simple, noninvasive biomarker for mortality risk assessment in individuals with diabetes. This study also illustrates the value of integrating AI-based feature selection with traditional epidemiologic modeling to enhance long-term mortality risk stratification and inform public health strategies.
Authors
- Fan Yang (ORCID: https://orcid.org/0000-0003-4676-3778)
- Liu Ji (ORCID: https://orcid.org/0000-0002-4233-4821)
- Jian Wu (ORCID: https://orcid.org/0000-0002-3394-1507)
- Guanghua Chen (ORCID: https://orcid.org/0000-0002-5820-2719)
- Dawei Yang (ORCID: https://orcid.org/0000-0002-5392-1896)
- Xiao Tong (ORCID: https://orcid.org/0000-0003-3892-2118)
- Youqi Zhang
Institutions
- Department of Health (CN)
- Harbin Medical University (CN)
- Fourth Affiliated Hospital of Harbin Medical University (CN)
- Second Affiliated Hospital of Harbin Medical University (CN)
Publication Details
- Journal
- Cardiovascular Diabetology – Endocrinology Reports
- Published
- 2025-09-02
- DOI
- https://doi.org/10.1186/s40842-025-00229-5
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 2.94
Funders
- Harbin Medical University
- Second Affiliated Hospital of Harbin Medical University
- National Natural Science Foundation of China
- Chinese Academy of Sciences
- Natural Science Foundation of Heilongjiang Province