[Prediction Model of Systemic Lupus Erythematosus Based on Machine Learning Algorithms].

Authors

Jin Zhang, Tai-Qiang Zhao, Juan Zhang

Published in

Zhongguo shi yan xue ye xue za zhi. Volume 34. Issue 4. Pages 1085-1091.

Abstract

To establish disease prediction models using 6 distinct machines learning algorithms, and to screen diagnostic markers for systemic lupus erythematosus(SLE) by detecting platelet aggregation rates via platelet aggregation assays and comparing their differences between SLE patients and healthy controls.
A cross-sectional study design was adopted, retrospective data were gathered from 123 female patients diagnosed with SLE who attended Sichuan Provincial People's Hospital between July 2022 and July 2025, alongside data from 64 female healthy controls. Platelet aggregation rates induced by four agonists, including adenosine diphosphate(ADP), arachidonic acid(AA), epinephrine(EPI) and collagen(COL), were quantified by optical transmission turbidimetry. Six diagnostic models for SLE were further established, and their diagnostic efficiencies were evaluated.
Due to missing data, the valid sample size was 121 among the 123 patients with SLE. The multivariate logistic regression analysis revealed that both AA and ADP serve as independent risk factors for patients with SLE(P<0.05). Among the evaluated predictive models, the XGBoost model exhibited the highest area under the curve(AUC=0.984, 95%CI : 0.969-1.000). Furthermore, the DCA curve indicated that the XGBoost model provided the greatest net benefit across the examined threshold probabilities. Feature importance assessment within the XGBoost framework identified AA as the most significant predictor of SLE, followed sequentially by COL, ADP, and EPI.
The diagnostic model for SLE patients, developed utilizing the XGBoost algorithm, exhibits a robust predictive performance. When integrated with clinical features, this model has the potential to enhance diagnostic accuracy and efficiency, thereby presenting significant value for clinical application.

PMID:
42802447
Bibliographic data and abstract were imported from PubMed on 28 Sep 2026.

Read full publication at:
Please sign in to see all details.

Stats

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.