Interpretable machine learning model for predicting the prognosis of antibody positive autoimmune encephalitis patients
Journal of Affective Disorders · 2025-01 · 369 · 352-363
DOI: 10.1016/j.jad.2024.10.010 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Affective Disorders, 2025-01. Verfasst von Junshuang Guo und 5 weiteren Autor:innen. Beteiligte Einrichtung: Neuro-Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China; Department of Immunology, Schoo…. Hauptthemen laut MEDLINE: Encephalitis, Machine Learning. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Health Commission of Henan Province.
Abstract (Originalsprache)
OBJECTIVE: The objective was to utilize nine machine learning (ML) methods to predict the prognosis of antibody positive autoimmune encephalitis (AE) patients. METHODS: The encephalitis data from the Global Burden of Disease (GBD) study is analyzed to reflect the disease burden of encephalitis. This study included 187 patients with AE. 121 patients as training set and 67 patients as validation set. Decision trees (DT), random forest (RF), extreme gradient boosting (XGBoost), k-nearest neighbor (KNN), support vector machine (SVM), naive bayes (NB), neural network (NN), light gradient boosting machine (LGBM), and logistic regression (LR) are ML methods used to construct predictive models. The constructed models were validated for discrimination, calibration and clinical applicability using validation set data. Shapley additive explanation (SHAP) analysis was used to explain the model. RESULTS: The number of encephalitis worldwide deaths, incidence and prevalence is increasing every year from 2010 to 2021. The training set included 121 patients with AE. Univariate analysis and LASSO screening identified six variables. The results of constructing models using 9 ML methods showed RF had the highest accuracy (0.860), followed by XGBoost (0.826), with F1 scores of 0.844 and 0.807, respectively. Validation set data showed good discrimination, calibration and clinical applicability of the model. The SHAP values of infection, CSF monocyte percentage, and prealbumin were 0.906, 0.790, and 0.644, respectively. LIMITATIONS: As a rare disease, the sample size of this study is relatively small. CONCLUSION: The model constructed using RF and XGBoost has good performance, good discrimination, calibration, clinical applicability, and interpretability.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Neuro-Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China; Department of Immunology, School of Basic Medical Science, Central South University, Changsha City, H…
- Neuro-Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China.
- Neuro-Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China. Electronic address: miaowang7211@126.com.
Förderung
- Health Commission of Henan Province
Zitieren
APA
Guo, J., Dong, R., Zhang, R., Yang, F., Wang, Y., & Miao, W. (2025). Interpretable machine learning model for predicting the prognosis of antibody positive autoimmune encephalitis patients. Journal of Affective Disorders, 369, 352-363. https://doi.org/10.1016/j.jad.2024.10.010
Vancouver
Guo J, Dong R, Zhang R, Yang F, Wang Y, Miao W. Interpretable machine learning model for predicting the prognosis of antibody positive autoimmune encephalitis patients. Journal of Affective Disorders. 2025;369:352-363. doi:10.1016/j.jad.2024.10.010
BibTeX
@article{Guo2025,
author = {Guo, Junshuang and Dong, Ruirui and Zhang, Ruike and Yang, Fan and Wang, Yating and Miao, Wang},
title = {Interpretable machine learning model for predicting the prognosis of antibody positive autoimmune encephalitis patients},
journal = {Journal of Affective Disorders},
year = {2025},
volume = {369},
pages = {352--363},
doi = {10.1016/j.jad.2024.10.010}
}
EUVIMED