{"entity": "publication", "iuid": "d117bf1507994111b505447bb73e92f3", "timestamp": "2026-09-30T22:58:41.282Z", "links": {"self": {"href": "https://publications-affiliated.scilifelab.se/publication/d117bf1507994111b505447bb73e92f3.json"}, "display": {"href": "https://publications-affiliated.scilifelab.se/publication/d117bf1507994111b505447bb73e92f3"}}, "title": "A deep learning-derived digital biomarker of dysglycemia and its association with genetic risk of type 2 diabetes.", "authors": [{"family": "Shao", "given": "Jian", "initials": "J"}, {"family": "Pan", "given": "Ying", "initials": "Y"}, {"family": "Xue", "given": "Jingnan", "initials": "J"}, {"family": "Pan", "given": "Haonan", "initials": "H"}, {"family": "Wang", "given": "Jing", "initials": "J"}, {"family": "Li", "given": "Shaoyun", "initials": "S"}, {"family": "Nie", "given": "Zedong", "initials": "Z"}, {"family": "Li", "given": "Yuefei", "initials": "Y"}, {"family": "Tian", "given": "Zijian", "initials": "Z"}, {"family": "Zhao", "given": "Yu", "initials": "Y"}, {"family": "Feng", "given": "Huyi", "initials": "H"}, {"family": "Zhou", "given": "Kaixin", "initials": "K"}], "type": "journal article", "published": "2025-12-02", "journal": {"title": "NPJ Metab Health Dis", "issn": "2948-2828", "volume": "3", "issue": "1", "pages": "46", "issn-l": null}, "abstract": "Type 2 diabetes is a global health burden driven by genetic and environmental factors. Continuous glucose monitoring (CGM) can effectively guide lifestyle interventions in non-diabetic. However, predefined CGM metrics fail to fully capture the dysglycemic information contained in the high-dimensional time-series CGM data. This study employed deep learning to learn dysglycemia features from CGM data associated with diabetes and derived a digital biomarker of dysglycemia, validated against traditional dysglycemic biomarkers and diabetes polygenic risk score (PRS). Output of the deep learning model, called the deep learning-score, was significantly associated with multiple existing dysglycemic biomarkers and PRS of diabetes (P = 0.007). Moreover, existing CGM metrics were not associated with prevalent diabetes after adjusting for the deep learning-score, while the deep learning-score remained significantly associated with prevalent diabetes (P < 0.001) in a regression analysis. This digital biomarker demonstrated potential for providing dynamic feedback on dysglycemia and improving long-term intervention adherence.", "doi": "10.1038/s44324-025-00089-8", "pmid": "41331126", "labels": [], "xrefs": [{"db": "pmc", "key": "PMC12672723"}, {"db": "pii", "key": "10.1038/s44324-025-00089-8"}], "notes": [], "created": "2026-09-23T15:55:39.694Z", "modified": "2026-09-23T15:55:39.722Z"}