Systemic lupus erythematosus damage risk index (SLE-DRI): a simple machine learning-based tool for identifying patients at risk for early organ damage.
Panagiotis Garantziotis, Dionysis Nikolopoulos, Spyridon Katechis, Alp Temiz, Danae-Mona Nöthling, Christina Adamichou, Christina Bergmann, Prodromos Sidiropoulos, Georg Schett, Antonis Fanouriakis, Dimitrios T Boumpas, George Bertsias
{"title":"Systemic lupus erythematosus damage risk index (SLE-DRI): a simple machine learning-based tool for identifying patients at risk for early organ damage.","authors":"Panagiotis Garantziotis, Dionysis Nikolopoulos, Spyridon Katechis, Alp Temiz, Danae-Mona Nöthling, Christina Adamichou, Christina Bergmann, Prodromos Sidiropoulos, Georg Schett, Antonis Fanouriakis, Dimitrios T Boumpas, George Bertsias","doi":"10.1136/rmdopen-2025-006009","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Organ damage is a key determinant of poor prognosis and increased mortality in systemic lupus erythematosus (SLE). However, no validated clinical tools for predicting damage accumulation currently exist. We sought to develop a machine learning-based model to predict early organ damage in patients with SLE.</p><p><strong>Methods: </strong>Classification criteria (American College of Rheumatology (ACR)-1997, Systemic Lupus International Collaborating Clinics (SLICC)-2012, European League Against Rheumatism (EULAR)/ACR-2019) and non-criteria features of a cohort of 914 patients with SLE were analysed to predict damage (defined as SLICC/ACR Damage Index (SDI)) within 5 years since diagnosis. Feature selection and model construction were performed using the least absolute shrinkage and selection operator-logistic regression (LASSO-LR). The best model in 10-fold cross-validation was tested in an external cohort (n=50).</p><p><strong>Results: </strong>A LASSO-LR model incorporating 16 criteria and non-criteria features predicted early organ damage with area under the receiver operating characteristic curve (AUC) values of 0.80 (95% CI 0.74 to 0.87) and 0.86 (95% CI 0.76 to 0.97) in the derivation and external validation cohorts, respectively, outperforming the ACR-1997 (AUC 0.70; 95% CI 0.62 to 0.78), SLICC-2012 (AUC 0.74; 95% CI 0.66 to 0.81) and EULAR/ACR-2019 (AUC 0.70; 95% CI 0.63 to 0.78) classification systems. Features most strongly associated with damage included the SLICC-2012 neurological disorder, EULAR/ACR-2019 class III/IV lupus nephritis and among non-criteria manifestations, myocarditis and interstitial lung disease. Operating the model as a binary classifier (early damage versus no damage), it demonstrated high specificity (0.90, 95% CI 0.78 to 0.95). The model can be converted to a simplified scoring system, with a threshold of ≥3 achieving an AUC of 0.86 (95% CI 0.75 to 0.96).</p><p><strong>Conclusion: </strong>We developed and validated a clinician-friendly model for early organ damage prediction in SLE, facilitating risk stratification.</p>","PeriodicalId":21396,"journal":{"name":"RMD Open","volume":"11 3","pages":""},"PeriodicalIF":4.7000,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"RMD Open","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/rmdopen-2025-006009","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RHEUMATOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: Organ damage is a key determinant of poor prognosis and increased mortality in systemic lupus erythematosus (SLE). However, no validated clinical tools for predicting damage accumulation currently exist. We sought to develop a machine learning-based model to predict early organ damage in patients with SLE.
Methods: Classification criteria (American College of Rheumatology (ACR)-1997, Systemic Lupus International Collaborating Clinics (SLICC)-2012, European League Against Rheumatism (EULAR)/ACR-2019) and non-criteria features of a cohort of 914 patients with SLE were analysed to predict damage (defined as SLICC/ACR Damage Index (SDI)) within 5 years since diagnosis. Feature selection and model construction were performed using the least absolute shrinkage and selection operator-logistic regression (LASSO-LR). The best model in 10-fold cross-validation was tested in an external cohort (n=50).
Results: A LASSO-LR model incorporating 16 criteria and non-criteria features predicted early organ damage with area under the receiver operating characteristic curve (AUC) values of 0.80 (95% CI 0.74 to 0.87) and 0.86 (95% CI 0.76 to 0.97) in the derivation and external validation cohorts, respectively, outperforming the ACR-1997 (AUC 0.70; 95% CI 0.62 to 0.78), SLICC-2012 (AUC 0.74; 95% CI 0.66 to 0.81) and EULAR/ACR-2019 (AUC 0.70; 95% CI 0.63 to 0.78) classification systems. Features most strongly associated with damage included the SLICC-2012 neurological disorder, EULAR/ACR-2019 class III/IV lupus nephritis and among non-criteria manifestations, myocarditis and interstitial lung disease. Operating the model as a binary classifier (early damage versus no damage), it demonstrated high specificity (0.90, 95% CI 0.78 to 0.95). The model can be converted to a simplified scoring system, with a threshold of ≥3 achieving an AUC of 0.86 (95% CI 0.75 to 0.96).
Conclusion: We developed and validated a clinician-friendly model for early organ damage prediction in SLE, facilitating risk stratification.
目的：器官损害是系统性红斑狼疮（SLE）预后不良和死亡率增加的关键决定因素。然而，目前还没有有效的临床工具来预测损伤的累积。我们试图开发一种基于机器学习的模型来预测SLE患者的早期器官损伤。方法：分析914例SLE患者的分类标准(美国风湿病学会(ACR)-1997，系统性狼疮国际合作诊所（SLICC)-2012，欧洲抗风湿病联盟(EULAR)/ACR-2019）和非标准特征，以预测诊断后5年内的损害（定义为SLICC/ACR损害指数（SDI））。使用最小绝对收缩和选择算子-逻辑回归（LASSO-LR）进行特征选择和模型构建。在外部队列（n=50）中测试了10倍交叉验证的最佳模型。结果：包含16个标准和非标准特征的LASSO-LR模型在衍生和外部验证队列中预测早期器官损害的受者工作特征曲线下面积（AUC）分别为0.80 （95% CI 0.74至0.87）和0.86 (95% CI 0.76至0.97)，优于ACR-1997 (AUC 0.70; 95% CI 0.62至0.78),SLICC-2012 （AUC 0.74; 95% CI 0.66至0.81）和EULAR/ACR-2019 （AUC 0.70; 95% CI 0.63至0.78）分类系统。与损害最密切相关的特征包括SLICC-2012神经系统疾病、EULAR/ACR-2019 III/IV级狼疮性肾炎以及非标准表现、心肌炎和间质性肺疾病。将该模型作为二元分类器（早期损伤与无损伤），它显示出高特异性（0.90,95% CI 0.78至0.95）。该模型可以转换为简化的评分系统，阈值≥3的AUC为0.86 （95% CI为0.75至0.96）。结论：我们开发并验证了一个临床友好的SLE早期器官损伤预测模型，促进了风险分层。
期刊介绍：
RMD Open publishes high quality peer-reviewed original research covering the full spectrum of musculoskeletal disorders, rheumatism and connective tissue diseases, including osteoporosis, spine and rehabilitation. Clinical and epidemiological research, basic and translational medicine, interesting clinical cases, and smaller studies that add to the literature are all considered.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
