Deep Learning-Based Diagnostic Support for Complex Autoimmune Syndromes: A Multi-label Classification Study
Main Article Content
Abstract
Autoimmune conditions frequently show similar clinical signs and symptoms, making it difficult to accurately diagnose when there are coexisting conditions. This study proposes a computational framework that aims to simultaneously predict multiple autoimmune labels using routine clinical data and advanced serological tests. The study examined 13,812 patients with 79 diagnostic features, including hematologic tests, inflammatory tests, and specific autoantibodies. The study trained a multi-layer perceptron (MLP) to predict autoimmune conditions such as Systemic Lupus Erythematosus (SLE), Rheumatoid Arthritis, and Graves' Disease. The model achieved strong performance, with validation F1 scores starting at 0.4723 and near-perfect Area Under the Curve (AUC) values ranging from 0.98 to 1.00 for all categories. The 79-parameter approach was highly effective in describing the autoimmunity “mosaic” and identifying polyautoimmunity with high precision compared to contemporary models that use fewer autoantibodies. The study shows that Multi-Label Multi-Layer Perceptron (ML-MLP) are able to process different types of data from lab tests and provide high utility diagnostic support for complex and overlapping autoimmune conditions.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1] Y. Shoenfeld and D. A. Isenberg, “The mosaic of autoimmunity.,” Immunol. Today, vol. 10, no. 4, pp. 123–126, Apr. 1989, doi: 10.1016/0167-5699(89)90245-4.
[2] L. A. Dourmishev, “Overlap Syndromes in Autoimmune Connective Tissue Diseases,” Acta Medica Bulg., vol. 51, no. 3, pp. 63–69, 2024, doi: 10.2478/amb-2024-0044.
[3] M. Rojas et al., “New insights into the taxonomy of autoimmune diseases based on polyautoimmunity,” J. Autoimmun., vol. 126, p. 102780, 2022, doi: 10.1016/j.jaut.2021.102780.
[4] M. Rojas et al., “Autoimmunity is a hallmark of post-COVID syndrome,” J. Transl. Med., vol. 20, no. 1, p. 129, 2022, doi: 10.1186/s12967-022-03328-4.
[5] M. Y. Choi et al., “Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes,” Ann. Rheum. Dis., vol. 82, no. 7, pp. 927–936, Jul. 2023, doi: 10.1136/ard-2022-223808.
[6] M. Y. Choi et al., “1704 Identifying clusters of longitudinal autoantibody profiles associated with systemic lupus erythematosus disease outcomes,” Lupus Sci. Med., vol. 8, no. Suppl 2, Nov. 2021, doi: 10.1136/lupus-2021-lupus21century.99.
[7] Y. Ding et al., “Calculation of Similarity Between 26 Autoimmune Diseases Based on Three Measurements Including Network, Function, and Semantics,” Front. Genet., vol. Volume 12, 2021, doi: 10.3389/fgene.2021.758041.
[8] G. Gomez, Y. Cheng, K. Nita, M. Hausmann, and C. Fischer, “B-146 A Machine Learning Algorithm Based on a 15-Autoantibody Profile by a Novel Fully Automated Multiplexed Microarray Immunoassay for the Diagnosis of Autoimmune Connective Tissue Diseases,” Clin. Chem., vol. 71, no. Supplement_1, p. hvaf086.540, Oct. 2025, doi: 10.1093/clinchem/hvaf086.540.
[9] J. Höppner et al., “Comprehensive autoantibody profiles in systemic sclerosis: Clinical cluster analysis,” Front. Immunol., vol. Volume 13, 2023, doi: 10.3389/fimmu.2022.1045523.
[10] A. Ragheb, “Comprehensive Autoimmune Disorder Dataset,” 2024, Kaggle. doi: 10.34740/kaggle/dsv/9807734.
[11] G. Cafaro et al., “Autoantibody status according to multiparametric assay accurately estimates connective tissue disease classification and identifies clinically relevant disease clusters.,” RMD open, vol. 9, no. 3, Sep. 2023, doi: 10.1136/rmdopen-2023-003365.
[12] I. Cavazzana et al., “Systemic Sclerosis-Specific Antibodies: Novel and Classical Biomarkers,” Clin. Rev. Allergy Immunol., vol. 64, no. 3, pp. 412–430, 2023, doi: 10.1007/s12016-022-08946-w.