Predicting major organ complications in primary Sjögren’s disease using a machine learning ensemble strategy: a dual-center retrospective clinical study - Report - MDSpire

Predicting major organ complications in primary Sjögren’s disease using a machine learning ensemble strategy: a dual-center retrospective clinical study

  • By

  • Wenqi Xia

  • Jiayun Wu

  • Jingyu Zhang

  • Yuening Kang

  • Yuling Chen

  • Ruyi Liao

  • Xiaomin Li

  • Ya Wen

  • Shenghui Wen

  • Fanxuan Meng

  • Huifen Liu

  • Zhiyang He

  • Jieruo Gu

  • Ou Jin

  • Yong Ren

  • Qing Lv

  • May 29, 2026

  • 0 min

Share

Clinical Report: Utilizing a Machine Learning Ensemble Approach to Anticipate Major Organ Complications in Primary Sjögren’s Disease

Overview

This study developed a machine learning ensemble model to predict major organ complications in patients with primary Sjögren’s disease (SjD). The model demonstrated moderate performance with an AUC of 0.725 and identified complement C3 and immunoglobulin G as significant predictors of complication risk.

Background

Primary Sjögren’s disease is a systemic autoimmune condition that can lead to severe complications affecting major organs, significantly impacting patient prognosis and quality of life. Early identification of patients at risk for these complications is crucial for timely intervention and management. Current methods for risk stratification are limited, highlighting the need for innovative approaches such as machine learning to enhance predictive capabilities.

Data Highlights

MetricValue
AUC0.725
Accuracy71%
Negative Predictive Value79%

Key Findings

  • The ensemble model outperformed individual machine learning algorithms in predicting major organ complications.
  • Complement C3 and immunoglobulin G were identified as the most important predictors of complication risk.
  • Low levels of complement C3 and high levels of immunoglobulin G were significantly associated with increased risk of complications.
  • The model achieved an accuracy of 71% and a negative predictive value of 79% on the test set.
  • Further validation and optimization of the model are necessary before clinical implementation.

Clinical Implications

The findings suggest that machine learning models can assist in early identification of high-risk patients with primary Sjögren’s disease. Incorporating routine clinical variables into predictive models may enhance risk stratification and guide clinical decision-making.

Conclusion

The study presents a promising machine learning approach for predicting major organ complications in primary Sjögren’s disease. However, further validation is essential to confirm its clinical utility.

Related Resources & Content

  1. npj Digital Medicine, 2025 -- A multi-criterion feature integration framework for accurate diagnosis of Sjögren’s disease using routine laboratory tests
  2. Clinical Rheumatology, 2025 -- Utilizing Artificial Intelligence to Forecast Organ Involvement in Sjogren’s Syndrome Through Whole-Slide Imaging of Labial Gland Biopsies
  3. Frontiers in Medicine, 2026 -- Increased lymphoma risk in patients with systemic manifestations of Sjögren’s disease: a population-based study
  4. British Society for Rheumatology guideline on management of adult and juvenile onset Sjögren disease - PMC, 2024
  5. Clinical Practice Guideline for Evaluation and Management of Peripheral Nervous System Manifestations in Sjögren's Disease - PubMed, 2025
  6. Ophthalmology Management — WHEN Dry Eye Isn’t Just DRY EYE
  7. Novartis announces both ianalumab Phase III clinical trials met primary endpoint in patients with Sjögren's disease
  8. 2025 ACR Abstract Released! Exciting Data from Telitacicept's Phase III Clinical Study in Sjögren's Syndrome in China
  9. British Society for Rheumatology guideline on management of adult and juvenile onset Sjögren disease - PMC
  10. Clinical Practice Guideline for Evaluation and Management of Peripheral Nervous System Manifestations in Sjögren's Disease - PubMed
  11. Prevalence of Interstitial Lung Disease in Patients with Primary Sjogren’s Syndrome: A Systematic Review and Meta-analysis of Observational Studies: Prevalence of Interstitial Lung Disease in Patients with Primary Sjogren’s Syndrome - PMC
  12. Artificial intelligence-based prediction of organ involvement in Sjogren’s syndrome using labial gland biopsy whole-slide images | Clinical Rheumatology | Springer Nature Link

Original Source(s)

Predicting major organ complications in primary Sjögren’s disease using a machine learning ensemble strategy: a dual-center retrospective clinical study

  • by Wenqi Xia, Jiayun Wu, Jingyu Zhang, Yuening Kang, Yuling Chen, Ruyi Liao, Xiaomin Li, Ya Wen, Shenghui Wen, Fanxuan Meng, Huifen Liu, Zhiyang He, Jieruo Gu, Ou Jin, Yong Ren, Qing Lv

  • May 29, 2026

Related Content

Sleep-related problems among patients with rheumatoid arthritis in the World Health Organization Eastern Mediterranean region: a systematic review and meta-analysis

Peripheral CD4+ naïve T cell remodeling and MMP1-associated inflammatory signatures in acute gouty arthritis

Sandwich strategy for the treatment of kyphosis with scoliosis and bilateral hip ankylosis in ankylosing spondylitis: a case report