Machine Learning-Based Analysis of Serum Interleukin-39 and Interleukin-40 Levels - Diagnostic Differentiation of Rheumatoid Arthritis and Systemic Lupus Erythematosus

Q: What was the study objective regarding IL-39 and IL-40?

To evaluate the diagnostic utility of serum IL-39 and IL-40 levels for differentiating rheumatoid arthritis from systemic lupus erythematosus using machine learning algorithms.

Q: Which machine learning models were tested?

Logistic regression, random forest, decision tree, and support vector machine were applied to previously published serum IL-39 and IL-40 datasets.

Q: What performance did the random forest model achieve?

It achieved 92.4% accuracy and an AUC of 0.95.

Sep 28, 2026

Uploaded by kopisore

Rheumatoid arthritis and systemic lupus erythematosus are severe autoimmune disorders marked by immune dysregulation and systemic inflammation, yet their diagnosis remains difficult because clinical features overlap. A study evaluated whether serum interleukin-39 and interleukin-40 levels improve differentiation between RA and SLE using multiple machine learning models. Data from 66 RA and 66 SLE patients were analyzed with logistic regression, random forest, decision tree, and support vector machine. The random forest model showed 92.4% accuracy and AUC 0.95. Feature importance indicated IL-39 and IL-40 contributed 58% and 42% to classification performance.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages6

Reading Time15 min

AccessFree to download

Abstract

Objective

Methods

Results

Conclusions

Keywords

Introduction

DOI: 10.4274/MMJ.galenos.2025.95690 Original Article Medeni Med J 2025;40:235-240 Machine Learning-Based Analysis of Serum Interleukin-39 and Interleukin-40 Levels for Differentiating Rheumatoid Arthritis and Systemic Lupus Erythematosus Romatoid Artrit ve Sistemik Lupus Eritematozusun Ayırt Edilmesi için Serum İnterlökin-39 ve İnterlökin-40 Düzeylerinin Makine Öğrenimi Temelli Analizi Inas K. SHARQUIE1, Faiq Isho GORIAL2, Zahraa Adnan AL-GHURAIBAWI3, Amal Mahdi AL RUBAYE4 1University of Baghdad Faculty of Medicine, Department of Microbiology and Immunology, Baghdad, Iraq 2University of Baghdad Faculty of Medicine, Department of Medicine, Baghdad, Iraq 3Iraqi National Cancer Research Center, University of Baghdad, Baghdad, Iraq 4Diyala Health Directorate, Baqubah General Hospital, Educational Laboratories, Baqubah, Iraq ABSTRACT Objective: Rheumatoid arthritis (RA) and systemic lupus erythematosus (SLE) are both severe autoimmune diseases characterised by immune dysregulation and systemic inflammation. Despite advances in diagnostic tools, distinguishing RA from SLE remains challenging due to overlapping clinical manifestations. Emerging evidence highlights the potential roles of novel cytokines, such as interleukin-39 [(IL)-39] and IL-40, in autoimmune pathogenesis. This study aimed to evaluate the diagnostic utility of serum levels of IL-39 and IL-40 for differentiating RA from SLE using several machine learning (ML) algorithms. Methods: Data from 66 patients with RA and 66 patients with SLE were analysed using previously published serum IL-39 and IL-40 datasets. ML algorithms, namely logistic regression, random forest, decision tree, and support vector machine, were applied. Model performance was evaluated using sensitivity, accuracy, specificity, and area under the receiver operating characteristic curve. Results: SLE patients exhibited significantly higher serum IL-39 and IL- 40 levels than those of RA patients (p<0 . 001) . The random forest model achieved an accuracy of 92.4% and an AUC of 0.95. Feature importance analysis revealed that IL-39 and IL-40 contributed 58% and 42%, respectively to the classification performance. Conclusions: ML models based on IL-39 and IL-40 serum levels can effectively differentiate RA from SLE. The findings suggest that integrating artificial intelligence-based analytical approaches with novel cytokine biomarkers may enhance diagnostic precision and support differential diagnosis in autoimmune diseases. Keywords: Rheumatoid arthritis, systemic lupus erythematosus, interleukin-39, interleukin-40, machine learning, biomarkers ÖZ Amaç: Romatoid artrit (RA) ve sistemik lupus eritematozus (SLE), bağışıklık düzensizliği ve sistemik enflamasyon ile karakterize edilen ciddi otoimmün hastalıklardır. Tanı araçlarındaki gelişmelere rağmen klinik belirtilerin birbiriyle örtüşmesi nedeniyle RA'yı SLE'den ayırtetmek hala zordur. Ortaya çıkan kanıtlar, interlökin-39 [(IL)-39] ve IL-40 gibi yeni sitokinlerin otoimmün patogenezdeki potansiyel rollerini vurgulamaktadır. Bu çalışma, çeşitli makine öğrenimi (ML) algoritmaları kullanarak RA ile SLE’yi ayırt etmek için serum IL-39 ve IL-40 düzeylerinin tanısal yararını değerlendirmeyi amaçlamıştır. Yöntemler: RA’lı 66 hasta ve SLE’li 66 hastadan elde edilen veriler, daha önce yayınlanmış serum IL-39 ve IL-40 veri setleri kullanılarakanaliz edilmiştir. Lojistik regresyon, rastgele orman, karar ağacı ve destek vektör makinesi gibi ML algoritmaları uygulandı. Model performansı, duyarlılık, doğruluk, özgüllük ve alıcı işletim karakteristikeğrisi altındaki alan kullanılarak değerlendirildi. Bulgular: SLE hastaları, RA hastalarına göre anlamlı olarak dahayüksek serum IL-39 ve IL-40 düzeyleri sergiledi (p<0,001) . Rastgele orman modeli %92,4 doğruluk ve 0,95 AUC elde etti. Özellik önem analizi, IL- 39 ve IL-40’ın sınıflandırma performansına sırasıyla %58 ve %42 katkıdabulunduğunu ortaya koydu. Sonuçlar: IL-39 ve IL-40 serum düz

FAQs

What was the study objective regarding IL-39 and IL-40?

To evaluate the diagnostic utility of serum IL-39 and IL-40 levels for differentiating rheumatoid arthritis from systemic lupus erythematosus using machine learning algorithms.

Which machine learning models were tested?

Logistic regression, random forest, decision tree, and support vector machine were applied to previously published serum IL-39 and IL-40 datasets.

What performance did the random forest model achieve?

It achieved 92.4% accuracy and an AUC of 0.95.

Sep 28, 2026

Uploaded by kopisore