EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning‐Based Risk Stratification for Metabolic Dysfunction Severity Among Diabetic Patients With Established MASLD: Distinguishing Normal‐Weight From Overweight Individuals

Yuelan Yin iD, Sa Ke iD, Yilin Liu iD, Xiaoling Wang iD, Qing Xue iD, Weining Sun iD

Journal of Diabetes Research · 2026-01 · 2026 (1)

DOI: 10.1155/jdr/4207980 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Diabetes Research, online erschienen am 15.04.2026. Verfasst von Yuelan Yin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Practice, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China, sysu.edu.cn. Hauptthemen laut MEDLINE: Overweight, Non-alcoholic Fatty Liver Disease, Machine Learning, Diabetes Mellitus. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To rank biochemical and clinical features that distinguish normal‐weight (BMI 18–24 kg/m 2 ) from overweight diabetics already carrying a discharge diagnosis of metabolic dysfunction‐associated steatotic liver disease (MASLD), and to build a parsimonious model that can flag lean individuals at highest risk of advanced metabolic complications.

Methods

This study collected a total of 3524 samples from hospitalized patients with diabetes and nonalcoholic fatty liver disease (NAFLD), with 54 NAFLD features serving as the original dataset. After data preprocessing, 2624 samples and 52 NAFLD features were screened from the original dataset to form the final dataset for model input. Among these, 1848 patients were labeled as Class 0 (BMI > 24 kg/m 2 ), and 776 patients were labeled as Class 1 (BMI between 18 and 24 kg/m 2 ). Data visualization and exploratory data analysis were performed using t‐SNE and heat maps. A five‐fold cross‐validation with 10 repetitions was employed for model optimization. The predictive model was evaluated using a confusion matrix. Three optimal predictive models with the smallest error were established: random forest, logistic regression, and gradient boosting. The top 30 feature variables were ultimately selected. An independent dataset containing 699 cases was used for external validation.

Results

Uric acid, vitamin D, hemoglobin, and creatine kinase are the most significant features in normal‐weight diabetes patients with MASLD. Gradient boosting was considered the best model; the average area under the ROC curve (AUC) was 0.733 (95% CI: 0.7089–0.7578).

Conclusion

Gradient boosting is the optimal predictive model, which can assist healthcare professionals in risk assessment and management for diabetic MASLD patients with normal BMI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

OverweightNon-alcoholic Fatty Liver DiseaseMachine LearningDiabetes MellitusHumansFemaleMaleMiddle AgedRisk AssessmentPredictive Learning ModelsBody Mass IndexBoosting Machine Learning AlgorithmsSeverity of Illness IndexAdultRisk FactorsRandom ForestAgedClassification AlgorithmsLogistic ModelsBody WeightPrediction Algorithms

Stichwörter der Autor:innen

fatty liverlean MASLDmachine learningmetabolic dysfunction-associated steatotic liver disease (MASLD)predictive models

Autor:innen und Institutionen

  • Department of General Practice, The Fifth Affiliated Hospital of Sun Yat-sen University, Zhuhai, China, sysu.edu.cn.
  • Department of Endocrinology, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, China, xinhuamed.com.cn.

ORCID-Profile: Yuelan Yin, Sa Ke, Yilin Liu, Xiaoling Wang, Qing Xue, Weining Sun

Zitieren

APA

Yin, Y., Ke, S., Liu, Y., Wang, X., Xue, Q., & Sun, W. (2026). Machine Learning‐Based Risk Stratification for Metabolic Dysfunction Severity Among Diabetic Patients With Established MASLD: Distinguishing Normal‐Weight From Overweight Individuals. Journal of Diabetes Research, 2026(1). https://doi.org/10.1155/jdr/4207980

Vancouver

Yin Y, Ke S, Liu Y, Wang X, Xue Q, Sun W. Machine Learning‐Based Risk Stratification for Metabolic Dysfunction Severity Among Diabetic Patients With Established MASLD: Distinguishing Normal‐Weight From Overweight Individuals. Journal of Diabetes Research. 2026;2026(1). doi:10.1155/jdr/4207980

BibTeX
@article{Yin2026,
  author = {Yin, Yuelan and Ke, Sa and Liu, Yilin and Wang, Xiaoling and Xue, Qing and Sun, Weining},
  title = {Machine Learning‐Based Risk Stratification for Metabolic Dysfunction Severity Among Diabetic Patients With Established MASLD: Distinguishing Normal‐Weight From Overweight Individuals},
  journal = {Journal of Diabetes Research},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/jdr/4207980}
}
Kostenlos starten →