Academic Journal
Performance of machine learning-based prediction models for hypoglycemia in Chinese patients with diabetes: A systematic review and meta-analysis.
| Τίτλος: | Performance of machine learning-based prediction models for hypoglycemia in Chinese patients with diabetes: A systematic review and meta-analysis. |
|---|---|
| Συγγραφείς: | Yan J; Department of General Practice, the People's Hospital of Leshan, Leshan, China., Song Y; Department of General Practice, the People's Hospital of Leshan, Leshan, China., Du Y; Department of General Practice, the People's Hospital of Leshan, Leshan, China., Li F; Department of General Practice, the People's Hospital of Leshan, Leshan, China. |
| Πηγή: | PloS one [PLoS One] 2026 Sep 22; Vol. 21 (9), pp. e0358876. Date of Electronic Publication: 2026 Sep 22 (Print Publication: 2026). |
| Τύπος έκδοσης: | Journal Article; Systematic Review; Meta-Analysis |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Public Library of Science Country of Publication: United States NLM ID: 101285081 Publication Model: eCollection Cited Medium: Internet ISSN: 1932-6203 (Electronic) Linking ISSN: 19326203 NLM ISO Abbreviation: PLoS One Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: San Francisco, CA : Public Library of Science |
| Ιατρικοί όροι (MeSH): | Hypoglycemia*/diagnosis , Hypoglycemia*/epidemiology , Boosting Machine Learning Algorithms* , Diabetes Mellitus*, China/epidemiology ; Humans ; Classification Algorithms ; Predictive Learning Models ; Random Forest ; ROC Curve ; East Asian People |
| Περίληψη: | Objectives: This study aimed to systematically evaluate the predictive performance of machine learning (ML)-based models for predicting hypoglycemia in Chinese patients with diabetes. Methods: We systematically searched PubMed, Embase, Web of Science, the Cochrane Library, CINAHL, CNKI, and Wanfang databases from inception to February 2026. Eligible studies focused on the development or validation of ML-based models for predicting hypoglycemia in Chinese patients with diabetes. Study selection and data extraction were performed independently by two reviewers. Information on study characteristics, modeling approaches, predictors, validation methods, and model performance was collected. The area under the receiver operating characteristic curve (AUC) was synthesized using a random-effects model. Study quality was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Results: A total of 13 studies were included, and the pooled prevalence of hypoglycemia was 25% (95% CI: 17%-33%). The overall pooled area under the receiver operating characteristic curve (AUC) was 0.90 (95% CI: 0.87-0.93). Subgroup analyses by modeling algorithms showed pooled AUCs of 0.89 for extreme gradient boosting (XGBoost), 0.88 for random forest (RF), 0.85 for support vector machine (SVM), 0.84 for Light Gradient Boosting Machine (LightGBM), 0.83 for logistic regression (LR), and 0.81 for decision tree (DT) models. Common predictors included age, insulin use, body mass index, HbA1c, creatinine, and history of hypoglycemia. Conclusion: We attempted to provide a comprehensive overview of machine learning-based prediction models for hypoglycemia in patients with diabetes. Research in this field remains at an early stage, although several models with good discriminatory performance have been reported. Methodological limitations and insufficient validation were observed in many studies. Concerns regarding model robustness and interpretability also exist. More efforts to develop reliable and interpretable models and to promote their application in clinical practice for early risk identification are needed. (Copyright: © 2026 Yan et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.) |
| Competing Interests: | The authors have declared that no competing interests exist. |
| References: | Curr Diab Rep. 2021 Dec 13;21(12):61. (PMID: 34902070) JAMA. 2018 Jan 23;319(4):388-396. (PMID: 29362800) J Matern Fetal Neonatal Med. 2024 Dec;37(1):2388171. (PMID: 39107137) Front Endocrinol (Lausanne). 2026 Jan 07;16:1685969. (PMID: 41573194) Int J Mol Sci. 2023 May 27;24(11):. (PMID: 37298308) Digit Health. 2022 Oct 17;8:20552076221129712. (PMID: 36276186) J Diabetes. 2015 Mar;7(2):166-73. (PMID: 24809622) Am J Med. 2020 Aug;133(8):895-900. (PMID: 32325045) BMJ. 2017 Jan 5;356:i6460. (PMID: 28057641) Front Endocrinol (Lausanne). 2025 Sep 17;16:1634358. (PMID: 41040859) JMIR Med Inform. 2023 Nov 20;11:e47833. (PMID: 37983072) Lancet Public Health. 2024 Dec;9(12):e1089-e1097. (PMID: 39579774) Anesthesiology. 2024 Jan 1;140(1):85-101. (PMID: 37944114) Diabetes Res Clin Pract. 2025 Dec;230:112993. (PMID: 41213360) Nature. 2026 Feb;650(8103):978-986. (PMID: 41535468) PLoS Med. 2024 Apr 12;21(4):e1004369. (PMID: 38607977) Can J Diabetes. 2015 Dec;39 Suppl 5:S155-9. (PMID: 26654859) J Clin Endocrinol Metab. 2022 May 17;107(6):e2221-e2236. (PMID: 35094087) Ann Intern Med. 2019 Jan 1;170(1):51-58. (PMID: 30596875) Nurs Open. 2024 Oct;11(10):e70055. (PMID: 39363560) AJPM Focus. 2024 Feb 24;3(3):100215. (PMID: 38638940) Sci Rep. 2020 Jan 13;10(1):170. (PMID: 31932608) J Diabetes Sci Technol. 2023 Nov;17(6):1470-1481. (PMID: 37864340) Diabetes Ther. 2023 Jun;14(6):953-965. (PMID: 37052842) Cardiovasc Diabetol. 2023 Sep 25;22(1):259. (PMID: 37749579) Nephrology (Carlton). 2021 Dec;26(12):939-947. (PMID: 34138495) Diabetologia. 2021 May;64(5):963-970. (PMID: 33550443) Worldviews Evid Based Nurs. 2022 Oct;19(5):426-427. (PMID: 35842743) BMC Endocr Disord. 2025 Nov 22;25(1):291. (PMID: 41275263) Nat Metab. 2025 Jan;7(1):16-34. (PMID: 39809974) Lancet Diabetes Endocrinol. 2019 May;7(5):385-396. (PMID: 30926258) Prim Care Diabetes. 2025 Dec;19(6):658-666. (PMID: 41006077) Geriatr Nurs. 2025 May-Jun;63:1-7. (PMID: 40081096) J Diabetes Sci Technol. 2025 Sep;19(5):1353-1361. (PMID: 38445628) JCO Clin Cancer Inform. 2021 Sep;5:1015-1023. (PMID: 34591602) BMJ. 1997 Sep 13;315(7109):629-34. (PMID: 9310563) PLoS Med. 2014 Oct 14;11(10):e1001744. (PMID: 25314315) Sci Rep. 2025 Apr 14;15(1):12808. (PMID: 40229548) Diabetes Res Clin Pract. 2022 Jan;183:109119. (PMID: 34879977) JMIR Med Inform. 2024 May 24;12:e56909. (PMID: 38801705) JMIR Med Inform. 2022 Jun 16;10(6):e36958. (PMID: 35708754) Nutr Res. 2024 Jul;127:123-132. (PMID: 38943730) Diabet Med. 2019 Apr;36(4):434-443. (PMID: 30653706) |
| Entry Date(s): | Date Created: 20260922 Date Completed: 20260922 Latest Revision: 20260924 |
| Update Code: | 20260924 |
| PubMed Central ID: | PMC13596806 |
| DOI: | 10.1371/journal.pone.0358876 |
| PMID: | 42771639 |
| Βάση Δεδομένων: | MEDLINE |
καταχωρήστε σχόλιο πρώτοι!