Identification of key metabolic indicators associated with the comorbidity of ischemic stroke and diabetes mellitus using an optimal interpretable clinlabomics model
Identifikation wichtiger metabolischer Indikatoren bei der Komorbidität von ischämischem Schlaganfall und Diabetes mellitus mit einem interpretierbaren Clinlabomics-Modell
Frontiers in Cardiovascular Medicine · 24.06.2026 · 13
DOI: 10.3389/fcvm.2026.1874711 ↗Auf einen Blick
Bei 2.587 Patient:innen mit ischämischem Schlaganfall wurden metabolische Marker für die Komorbidität mit Diabetes mellitus untersucht. Das rpart-Modell zeigte die beste Vorhersageleistung.
Fragestellung
Welche metabolischen Indikatoren sind mit der Komorbidität von ischämischem Schlaganfall und Diabetes mellitus assoziiert, und wie gut sagt ein Clinlabomics-Modell diese Konstellation vorher?
Methode
Retrospektive Analyse von 2.587 IS-Patient:innen; 16 metabolische Indikatoren; logistische Regression, RCS, LASSO und 11 ML-Algorithmen; 7:3-Split plus 406 Patient:innen zur zeitlichen Validierung.
Ergebnisse
12 Indikatoren waren in der multivariaten Regression assoziiert. TyG: OR 4,76 (95 %-KI 4,01–5,64); AIP: OR 3,60 (95 %-KI 2,74–4,72). Das rpart-Modell erreichte AUC 0,910; Test 0,839; zeitliche Validierung 0,873.
Schlussfolgerung der Autor:innen
Die Studie identifizierte 9 Kandidaten für metabolische Biomarker der IS-DM-Komorbidität. Das mit rpart etablierte Clinlabomics-Modell zeigte eine sehr gute Leistung zur Identifikation der IS-DM-Population.
Kernaussagen
- TyG und AIP waren deutlich mit IS-DM assoziiert
- rpart erzielte die beste Modellleistung
- HbA1c/HDL-C war das wichtigste Feature in der SHAP-Analyse
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Cardiovascular Medicine, online erschienen am 24.06.2026. Verfasst von Yao Jiang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Laboratory Medicine, Suining Central Hospital, Suining, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Diabetes mellitus, Schlaganfall
Abstract (Originalsprache)
Background
To identify candidate metabolic biomarkers and establish a Clinlabomics model for early precise screening of ischemic stroke (IS) with diabetes mellitus (DM) comorbidity population.
Methods
A total of 2,587 IS patients were retrospectively enrolled and classified into IS-DM comorbidity and IS-only groups. A total of 16 metabolic indicators were collected, and candidate indicators were identified using univariate and multivariate logistic regression along with restricted cubic spline (RCS) analysis. The dataset was randomly split into training and test sets at a 7:3 ratio, and an additional 406 patients constituted a temporal validation set. Clinlabomics models were constructed using 11 machine learning (ML) algorithms. Model performance was evaluated using F1-score, accuracy (ACC) and area under the curve (AUC) to select the optimal algorithm, and SHapley Additive exPlanations (SHAP) analysis was performed to quantify feature contributions.
Results
Multivariate logistic regression showed that 12 metabolic indicators were closely associated with IS-DM comorbidity. Notably, the triglyceride glucose (TyG) index (OR = 4.76, 95% CI: 4.01–5.64, P < 0.001) and atherogenic index of plasma (AIP) (OR = 3.60, 95% CI: 2.74–4.72, P < 0.001) were significantly associated with an increased risk of IS-DM comorbidity. RCS revealed non-linear associations between 9 indicators and comorbidity. Least Absolute Shrinkage and Selection Operator (LASSO) analysis identified 16 feature variables, and the recursive partitioning and regression trees (rpart) algorithm model achieved the best performance, with ACC, F1-score, AUC, sensitivity, and specificity of 0.885, 0.818, 0.910, 78%, and 94%, respectively. The AUC values in the training, test and temporal validation sets were 0.910 (95% CI: 0.894–0.926), 0.839 (95% CI: 0.807–0.871) and 0.873 (95% CI: 0.831–0.915), respectively. SHAP analysis suggested that glycated hemoglobin A1c (HbA1c)/high-density lipoprotein cholesterol (HDL-C) was the most important feature. Finally, 9 candidate metabolic biomarkers for comorbidity were identified, including TyG, uric acid (UA), total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), AIP, atherogenic coefficient (AC), Castelli's risk index I (CRI-I), Castelli's risk index II (CRI-II), and HbA1c/HDL-C.
Conclusions
This study successfully identified 9 candidate metabolic indicators of IS-DM comorbidity. The Clinlabomics model established by rpart algorithm presents excellent performance in identifying the IS-DM population.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Clinical Laboratory Medicine, Suining Central Hospital, Suining, China.
- Department of Cerebrovascular Disease, Suining Central Hospital, Suining, China.
- Faculty of Medical Technology, Shaanxi University of Chinese Medicine, Xi'an, China.
- Department of Neurosurgery, Suining Central Hospital, Suining, China.
Zitieren
APA
Jiang, Y., Qian, A., Chen, S., Wu, Q., Xu, H., Zheng, C., Zhang, F., Xing, W., & He, J. (2026). Identification of key metabolic indicators associated with the comorbidity of ischemic stroke and diabetes mellitus using an optimal interpretable clinlabomics model. Frontiers in Cardiovascular Medicine, 13. https://doi.org/10.3389/fcvm.2026.1874711
Vancouver
Jiang Y, Qian A, Chen S, Wu Q, Xu H, Zheng C, et al. Identification of key metabolic indicators associated with the comorbidity of ischemic stroke and diabetes mellitus using an optimal interpretable clinlabomics model. Frontiers in Cardiovascular Medicine. 2026;13. doi:10.3389/fcvm.2026.1874711
BibTeX
@article{Jiang2026,
author = {Jiang, Yao and Qian, Ao and Chen, Shu and Wu, Qian and Xu, Hao and Zheng, Chang and Zhang, Fengyu and Xing, Wenli and He, Jimin},
title = {Identification of key metabolic indicators associated with the comorbidity of ischemic stroke and diabetes mellitus using an optimal interpretable clinlabomics model},
journal = {Frontiers in Cardiovascular Medicine},
year = {2026},
volume = {13},
doi = {10.3389/fcvm.2026.1874711}
}
EUVIMED