Machine Learning–Based Prediction of Autoimmune Diseases in Primary Care

Abstract

Objective: Autoimmune diseases are complex disorders with varied clinical manifestations, and their diagnosis often requires specialized tests not readily available in primary care. This study aimed to design and assessed machine learning (ML) algorithms capable of identifying potential cases of autoimmune diseases by using routinely available, low-cost clinical and laboratory parameters. Materials and Methods: A total of 1650 individuals from four family health centers were retrospectively evaluated. Commonly used primary care tests—including complete blood count, biochemical markers, metabolic indices, and anthropometric variables—were incorporated. Five ML approaches (Random Forest, Extreme Gradient Boosting (XGBoost), Support Vector Machine, Logistic Regression, and Deep Learning) were implemented and compared. To improve interpretability, SHapley Additive Explanations (SHAP) were employed to determine the relative importance of predictors. Results: XGBoost demonstrated the highest performance (Accuracy: 0.77, AUC: 0.83, F1 score: 0.77), whereas Random Forest and Deep Learning achieved moderately high accuracy. SHAP interpretation revealed that sex, systolic blood pressure, mean platelet volume, monocyte levels, triglyceride-glucose, waist-to-height ratio, and neutrophil-tolymphocyte ratio were the most impactful predictors. Conclusion: ML models using routinely available measures may support risk stratification for autoimmune diseases in primary care. SHAP improves transparency; however, external and prospective validation is needed before clinical use.

Keywords

• Artificial intelligence
• autoimmune disease
• diagnostic prediction
• machine learning
• primary health care

References

1. 1. Taha SI, Samaan SF, Ibrahim RA, Moustafa NM, El-Sehsah EM, Youssef MK. Can complete blood count picture tell us more about the activity of rheumatological diseases? Clin Med Insights Arthritis Musculoskelet Disord 2022; 15: 11795441221089182. google scholar
2. 2. Rose NR. Prediction and prevention of autoimmune disease in the 21st century: a review and preview. Am J Epidemiol 2016; 183(5): 403–6. google scholar
3. 3. Mormile I, Osman M, Rossi FW. Editorial: Prognostic and predictive factors in autoimmune connective tissue disorders. Front Immunol 2024; 15: 1465572. google scholar
4. 4. Chen T, Guestrin C. XGBoost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016 Aug 13–17; San Francisco, CA, USA. New York: ACM; 2016. pp.785–94. google scholar
5. 5. Manning C. Artificial Intelligence Definitions. Stanford University Human-Centered Artificial Intelligence (serial online) 2020 (cited 2025 Mar 18). Available from: URL: https://hai.stanford.edu/sites/default/files/2020-09/AI-Definitions-HAI.pdf google scholar
6. 6. Galozzi P, Basso D, Plebani M, Padoan A. Artificial intelligence and laboratory data in rheumatic diseases. Clin Chim Acta 2023; 546: 117388. google scholar
7. 7. Yoshihara A, Yoshimura Noh J, Inoue K, Taguchi J, Hata K, Aizawa T, et al. Prediction model of Graves' disease in general clinical practice based on complete blood count and biochemistry profile. Endocr J 2022; 69(9): 1091-100. google scholar
8. 8. Kay J, Upchurch KS. ACR/EULAR 2010 rheumatoid arthritis classification criteria. Rheumatology (Oxford) 2012; 51(6): vi5–9. google scholar

9. 9. Sherlock ME, Benchimol EI. Classification of Inflammatory Bowel Disease in Children. Mamula P, Grossman AB, Baldassano RN, Kelsen JR, Markowitz JE, editors. Pediatric Inflammatory Bowel Disease. 3rd ed. New York: Springer International Publishing; 2017.p.181–91. google scholar
10. 10. International Study Group for Behcet's Disease. Criteria for diagnosis of Behcet's disease. Lancet 1990; 335(8697): 1078–80. google scholar
11. 11. Breiman L. Random forests. Mach Learn 2001; 45: 5–32. google scholar
12. 12. Cortes C, Vapnik V. Support-vector networks. Mach Learn 1995; 20: 273–97. google scholar
13. 13. Hosmer DW, Lemeshow S, Sturdivant RX. Applied Logistic Regression. 3rd ed. Hoboken, NJ: John Wiley & Sons; 2013. google scholar
14. 14. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521(7553): 436–44. google scholar
15. 15. Al-Azzawi SM, Deif MA, Attar H, Amer A. Hyperparameter optimization of regression model for electrical load forecasting during the COVID-19 pandemic lockdown period. J Intell Fuzzy Syst 2023; 16(4): 239–53. google scholar
16. 16. Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006; 27: 861–74. google scholar
17. 17. Grinsztajn L, Oyallon E, Varoquaux G. Why do tree-based models still outperform deep learning on typical tabular data? In: Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS 2022); 2022 Nov 28–Dec 9; New Orleans, USA. Red Hook, NY: Curran Associates, Inc.; 2022. pp.507–20. google scholar
18. 18. Shickel B, Tighe PJ, Bihorac A, Rashidi P. Deep EHR: a survey of recent advances in deep learning techniques for electronic health record (EHR) analysis. IEEE J Biomed Health Inform 2017; 22(5): 1589–604. google scholar
19. 19. Sitompul LR, Nababan AA, Manihuruk ML, Ponsen WA, Supriyandi S, Setyawan A, et al. Comparison of XGBoost, Random Forest, and Logistic Regression algorithms in stroke disease classification. Sinkron J Dan Penelit Tek Inform 2025; 9(2): 957–68. google scholar
20. 20. Yaşar Ş, Çolak C. A proposed model can classify the COVID-19 pandemic based on the laboratory test results. J Cogn Syst 2020; 5(2): 60–3. google scholar
21. 21. Abbasoğulları EG, Günay FB. Using and Comparing Different Machine Learning Methods for Thalassemia Disease Prediction. Karadeniz Fen Bilim Derg 2024; 14(4): 1990–2007. google scholar
22. 22. Fairweather D, Frisancho-Kiss S, Rose NR. Sex differences in autoimmune disease from a pathological perspective. Am J Pathol 2008; 173(3): 600–9. google scholar
23. 23. Ngo ST, Steyn FJ, McCombe PA. Gender differences in autoimmune disease. Front Neuroendocrinol 2014; 35(5): 347–69. google scholar
24. 24. Weyand CM, Goronzy JJ. Aging of the immune system: mechanisms and therapeutic targets. Ann Am Thorac Soc 2016; 13 Suppl 5: S422–8. google scholar
25. 25. Versini M, Jeandel PY, Rosenthal E, Shoenfeld Y. Obesity in autoimmune diseases: not a passive bystander. Autoimmun Rev 2014; 13(9): 981–1000. google scholar
26. 26. García-González C, Baker JF. The effects of inflammation and treatment on adiposity, obesity, and sarcopenia in patients with autoimmune rheumatic disease. Curr Treatm Opt Rheumatol 2025; 11: 5. google scholar
27. 27. Szekanecz Z, Koch AE. Vascular involvement in rheumatic diseases: 'vascular rheumatology'. Arthritis Res Ther 2008; 10(5): 224. google scholar
28. 28. Conrad N, Verbeke G, Molenberghs G, Goetschalckx L, Callender T, Cambridge G, et al. Autoimmune diseases and cardiovascular risk: a population-based study on 19 autoimmune diseases and 12 cardiovascular diseases in 22 million individuals in the UK. Lancet 2022; 400(10354): 733–43. google scholar
29. 29. Toms TE, Panoulas VF, Kitas GD. Dyslipidaemia in rheumatological autoimmune diseases. Open Cardiovasc Med J 2011; 5: 64-75. google scholar
30. 30. Fietta P, Delsante G, Zini E, Zanatta E, Valentini G. Hematologic manifestations of connective autoimmune diseases. Clin Exp Rheumatol 2009; 27(1): 140-54. google scholar
31. 31. Erre GL, Paliogiannis P, Castagna F, Mangoni AA, Carru C, Passiu G, et al. Meta-analysis of neutrophil-to-lymphocyte and platelet-to-lymphocyte ratio in rheumatoid arthritis. Eur J Clin Invest 2019; 49(1): e13037. google scholar
32. 32. Moreno-Torres V, Castejón R, Mellor-Pita S, Tutor-Ureta P, Durán-Del Campo P, MartínezUrbistondo M, et al. Usefulness of the hemogram as a measure of clinical and serological activity in systemic lupus erythematosus. J Transl Autoimmun 2022; 5: 100157. google scholar
33. 33. Schmoeller D, Picarelli MM, Paz Munhoz T, Poli de Figueiredo CE, Staub HL. Mean platelet volume and immature platelet fraction in autoimmune disorders. Front Med 2017; 4: 146. google scholar
34. 34. Yorulmaz A, Yildiz H, Akpinar U, Yalcin B. Systemic immune-inflammation index (SII) predicts increased severity in psoriasis and psoriatic arthritis. Curr Health Sci J 2020; 46(4): 352-7. google scholar
35. 35. Zhai YJ, Lin CY,Li JB, Qiu HN, Wu F, Wang YL, et al. Mediating role of triglyceride-glucose index and its derivatives in the relationship between central obesity and Hashimoto thyroiditis in type 2 diabetes. Lipids Health Dis 2024; 23(1): 411. google scholar
36. 36. Huang D, Ma R, Zhong X, Jiang Y, Lu J, Li Y, et al. Positive association between different triglyceride glucose index-related indicators and psoriasis: evidence from NHANES. Front Immunol 2023; 14: 1325557. google scholar
37. 37. Contreras-Haro B, Hernandez-Gonzalez SO, Gonzalez-Lopez L, Espinel-Bermudez MC, Garcia-Benavides L, Perez-Guerrero E, et al. Fasting triglycerides and glucose index: a useful screening test for assessing insulin resistance in patients diagnosed with rheumatoid arthritis and systemic lupus erythematosus. Diabetol Metab Syndr 2019; 11: 95. google scholar