A Machine Learning Approach for Predicting Clinical Outcomes in Patients with Autoimmune Encephalitis

Autoimmune encephalitis (AE) is an uncommon but severely debilitating neuroinflammatory disorder that can result in significant neuropsychiatric issues and prolonged disability. The ability to predict patient outcomes accurately and promptly poses a considerable clinical challenge, largely due to the disease's variability and the intricate interactions among clinical, laboratory, and imaging factors. This research aimed to create a comprehensive machine learning-based predictive model designed to help clinicians forecast AE outcomes with a high degree of precision. A dataset obtained from Kaggle, which is publicly accessible, was employed, featuring diverse patient information such as demographic data, diagnostic indicators, and characteristics derived from neuroimaging. The preprocessing of data encompassed meticulous management of missing values, normalization processes, and the alleviation of class imbalance through the application of the Synthetic Minority Oversampling Technique (SMOTE). The predictive model was developed using Python and the scikit-learn library, evaluating various algorithms including Random Forest, Gradient Boosting, and Support Vector Machines. To enhance the model's generalizability, hyperparameter tuning was conducted via grid search in conjunction with stratified cross-validation. The assessment of performance was based on metrics such as accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). Among the evaluated models, the Random Forest classifier demonstrated superior performance, attaining an accuracy of 91.4%, an F1-score of 0.89, and an AUC-ROC of 0.94, which emphasizes its robust discriminative ability. These results point to the promise of machine learning techniques, when trained on actual datasets, to improve decision-making in adverse event management, thereby facilitating more tailored and evidence-based clinical strategies.

10.51244/IJRSI.2025.1213CS0020

1. Blackman, R., Kumar,G., Hanrahan, J.G., Dalrymple, A., Moran, N. (2021) “Quantitative EEG as a prognostic tool in suspected anti-N-Methyl-d-aspartate receptor antibody encephalitis,” J. Clin. Neurophysiol., vol. 40, pp. 160–164, 2021. doi:10.1097/WNP.0000000000000877 [Google Scholar] [Crossref]

2. Balu, R., McCracken, L., Lancaster, E., Graus, F., Dalmau, J., Titulaer, M.J. (2019). A score that predicts 1-year functional status in patients with anti-NMDA receptor encephalitis. Neurology, 92(3): E244–E252, Jan. 15, 2019, doi: 10.1212/WNL.0000000000006783. [Google Scholar] [Crossref]

3. Chen, R., Zhou, L., Wang, Y., Zhao, H. (2023). Cerebrospinal fluid indices as predictors of treatment response in autoimmune encephalitis,” Journal of Neuroimmunology, 378(5777) 2023, doi: 10.1016/j.jneuroim.2023.5777. [Google Scholar] [Crossref]

4. Choi, B. K., Choi, Y., Jang, S., W.-S. Ha, S. Cho, K. Chang, B. Sohn, K. M. Kim, and Y. R. Park (2025). Multimodal deep learning model for prediction of prognosis in central nervous system inflammation. Brain Communications, 7, (3): 179, doi: 10.1093/braincomms/fcaf179. [Google Scholar] [Crossref]

5. Dalmau. Y., Grau, F. (2023). Diagnostic criteria for autoimmune encephalitis: utility and pitfalls for antibody-negative disease. The Lancet Neurology. 22 ( 6): 529–540, doi: 10.1016/S1474-4422(23)000832 [Google Scholar] [Crossref]

6. Guo, J., Dong, J., 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, (358) 123–131, doi: 10.1016/j.jad.2024.10.010. [Google Scholar] [Crossref]

7. He, Y., Li, F., Yang, A.,Yu, C., Wang,Y., J. Zhao, and W. Zang, (2024). Validation of the clinical assessment scale for autoimmune encephalitis in a severe autoimmune encephalitis cohort.Frontiers in Immunology, vol. 15, Art. No. 1490804, Dec. 2024, doi: 10.3389/fimmu.2024.1490804. [Google Scholar] [Crossref]

8. Kvam, K. A., Stahl, J. P., Chow, F. C., Soldatos, A., Tattevin, P., Sejvar, J., Mailles, A. (2023). Outcome and sequelae of autoimmune encephalitis. Journal of Clinical 6Neurology. 19(1): 1–12. doi: 10.3988/jcn.2023.0242. [Google Scholar] [Crossref]

9. Li, J. Fang, M. Chen, X. Liu, and T. Wang, “A validated nomogram that predicts prognosis of autoimmune encephalitis: A multicenter study in China,” Neurotherapeutics, vol. 22, no. 1, pp. 45–54, Jan. 2025, doi:10.1007/s13311-024-01234-5. [Google Scholar] [Crossref]

10. Liu,Z., Zhang,X., Chen,Y., Wang,Y., Li, J., Sun, O. (2021). Integrating imaging radiomics and clinical data for prognosis prediction in autoimmune encephalitis,” Frontiers in Immunology, vol. 12(740239);doi: 10.3389/fimmu.2021.740239 [Google Scholar] [Crossref]

11. Musigmann, M., Spiekers, C., Stake, J., Akkurt, B.H., Nacul Mora, N.G., Sartoretti, T., Heindel, W., Mannil, M. (2025). Detection of antibodies in suspected autoimmune encephalitis diseases using machine learning,” Sci. Rep., vol. 15(10998). Available: https://www.nature.com/articles/s41598-025-95815-z [Google Scholar] [Crossref]

12. Roberts, K., Patel, S., Thompson, M., Fernandez, D.(2018). Prognosticating autoimmune encephalitis: A systematic review,” Journal of Neurology, Neurosurgery & Psychiatry, vol. 89, no. 12, pp. 1234–1241, Dec. 2018, doi: 10.1136/jnnp-2018-319123. [Google Scholar] [Crossref]

13. Sun, L., Hu, Y., J. Yang, L. Chen, Y. Wang, W. Liu, J.-S. Hong, Y. Lv, L. Yang, L., Wang, Y. (2025). Electroencephalographic biomarkers of antibody-mediated autoimmune encephalitis. Frontiers in Neurology 16 (1510722), doi: 10.3389/fneur.2025.1510722. [Google Scholar] [Crossref]

14. Stafford, I. Kellermann, S., Mossotto, M., Beattie, E R. MacArthur, M. B. D., S. Ennis S. (2020). A systematic review of the applications of artificial intelligence and machine learning in autoimmune diseases,” npj Digital Medicine, 3(30), doi: 10.1038/s41746-020-0231-3. [Google Scholar] [Crossref]

15. Stake, J., Spiekers, C.,. Akkurt, B. Heindel, H , Brix, T.W., M. Mannil, Am., Musigmann. M. (2024). Prediction of seropositivity in suspected autoimmune encephalitis by use of radiomics: a radiological proof-of-concept study,” Diagnostics, vol. 14, no. 11, p. 1070, May 2024, doi: 10.3390/diagnostics14111070. [Google Scholar] [Crossref]

16. Soellradl, E., von Oertzen, T. J., Wagner, J.N. (2024). Evaluation of the Clinical Assessment Scale for Autoimmune Encephalitis (CASE) in a retrospective cohort and a systematic review. Neurological Sciences, 45; 5423–5428, doi: 10.1007/s10072-024-07642-1. [Google Scholar] [Crossref]

17. Thompson, A., Miller, C., Baker, J., Jackson, S., Patel, R. (2025). Multimodal prognostication of autoimmune encephalitis: an Australian autoimmune encephalitis consortium study, Journal of Neurology, doi: 10.1007/s00415-025-13069-1. [Google Scholar] [Crossref]

18. Wu, C., Liu, M., Huang, X., Zhang, Y., Hong, L. (2022). Risk Prediction Models for Early ICU Admission in Patients with Autoimmune Encephalitis: Integrating Scale-Based Assessments of the Disease Severity,” Frontiers in Immunology, 13(916111), doi: 10.3389/fimmu.2022.916111. [Google Scholar] [Crossref]

19. Xiang, Y., Dong, X., Li, Y. (202)C.linical variables, deep learning and radiomics features help predict the prognosis of adult anti-N-methyl-D-aspartate receptor encephalitis early: a two-center study in Southwest China,” Comput. Med. Imaging Graph., 95(102026). [Google Scholar] [Crossref]

20. Zh. Xie, J. Zhang, L. Liu, E. Hu, and J. Wang, “Prediction model for severe autoimmune encephalitis: a tool for risk assessment and individualized treatment guidance,” Frontiers in Neurology, vol. 16, 2025, doi: 10.3389/fneur.2025.1575835 [Google Scholar] [Crossref]

21. Zhao, W., Liu, H., Huang, J., Wang, Y., Li, P. (2024). Predictors of mortality and poor outcome for patients with severe infectious encephalitis in the intensive care unit: a cross-sectional study,” BMC Infectious Diseases, (24)421: doi: 10.1186/s12879-024-09312-1. [Google Scholar] [Crossref]

22. Zheng,. H., Zhang, F., Wang, S., Sun, L., Li, M. (2023). A reservoir computing with boosted topology model to predict encephalitis and mortality for patients with severe fever with thrombocytopenia syndrome: a retrospective multicenter study,” Infectious Diseases and Therapy, 12(1379–1391): doi: 10.1007/s40121-023-00808-y. [Google Scholar] [Crossref]

23. Zhang, L., Yang, P., Zhou, W., Meng, Q., Huang, F. (2023). Cerebrospinal fluid indices as predictors of treatment response in autoimmune encephalitis. Journal of Neuroimmunology, 381, (57834)doi: 10.1016/j.jneuroim.2023.57834. (Details adapted from provided description; verify exact authors and pages.) [Google Scholar] [Crossref]

24. Zhou, H., Meng, X., Yuan, C., Lin, J., Wu, D. (2025). A validated nomogram that predicts prognosis of autoimmune encephalitis: A multicenter study in China,” Neurotherapeutics, 22(1): 63–72, doi: 10.1007/s13311-024-01235-4. (Details adapted from provided description; verify actual citation.) [Google Scholar] [Crossref]

25. Zhang Y., Shi, X, . Fan, Z., Tu, E., Wu, D.X. Leng, T. Wan, X. Wang, X. Wang, W. Lu, F. Du, and W. Jiang, (2025). Machine learning for the early prediction of long-term cognitive outcome in autoimmune encephalitis,” Journal of Psychosomatic Research, vol. 190(112051): doi: 10.1016/j.jpsychores.2025.112051. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet