{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T17:21:25Z","timestamp":1790702485363,"version":"4.1.0"},"reference-count":26,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Systemic lupus erythematosus (SLE) is a chronic disease characterized by a broad spectrum of involved organs, including neurological, renal, and vascular domains, with disease activity manifesting through unpredictable patterns that vary across individuals and over time, making the prediction of activity events particularly challenging.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This paper proposes a hierarchical machine learning model to predict a 12-month SLE activity, defined as the occurrence of at least one event among SLE hospitalization, new organ-involved domain, and neurological, renal, or vascular manifestation within the following year. At each patient\u2019s visit, the model considers all the features at the current time point, the information about the patient\u2019s clinical history, and about its last 12 months, to predict the outcome for the next 12 months.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The study cohort consists of 262 patients with at least an outpatient visit and an SLE admission from 2012 to 2020, at the Italian Gemelli Hospital, comprising a retrospective longitudinal dataset of 5962 contacts. The data include demographics, laboratory, clinical features (eg, domain involvements and manifestations), treatments, and pathways (eg, contact types as outpatients, hospitalizations, day hospitals, and visit frequency). The variables consider 3 time ranges: features about the current contact and the last 12 months, and the previous patient\u2019s clinical history. The main model was developed by testing different machine learning approaches within a cross-validation setup. The predicted probability outputs were used in a risk stratification analysis, identifying 3 groups of predictions: strong, moderate, and mild. Mild samples were then passed through a second cascade model. The integration of the main model (applied to strong and moderate samples) with the cascade model (applied to mild contacts) forms our final hierarchical model.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n The hierarchical model, resulting from the ensemble of the main random forest and cascade decision tree, demonstrated enhanced performance, increasing the area under the receiver operating characteristic curve from 0.696 (95% CI 0.672\u20100.719) in the original main model to 0.743 (95% CI 0.717-0.769), particularly for specific patient characteristics. Through the application of explainable artificial intelligence methods, we also identified the key features that significantly influence the model\u2019s predictions. Among the 185 collected features, 15 emerged as the most impactful, including age at contact, response to therapy modifications, abnormal laboratory tests, and clinical manifestations. This analysis plays a crucial role in enhancing model transparency, which is essential for fostering the adoption of artificial intelligence in health care settings.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Our study introduces an explainable and reliable tool for predicting 1-year SLE activity, supporting physicians with an advanced decision-support system to improve patient management. The model identifies key features that may help characterize patient phenotypes, enabling personalized treatment plans and better outcomes. In addition, the methodology can be generalized for predictive analytics in other chronic autoimmune diseases.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/70200","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T20:43:53Z","timestamp":1755895433000},"page":"e70200-e70200","source":"Crossref","is-referenced-by-count":8,"title":["Prediction of 1-Year Activity in Systemic Lupus Erythematosus: Hierarchical Machine Learning Approach"],"prefix":"10.2196","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3319-7211","authenticated-orcid":false,"given":"Livia","family":"Lilli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4352-332X","authenticated-orcid":false,"given":"Laura","family":"Antenucci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3131-0939","authenticated-orcid":false,"given":"Augusta","family":"Ortolan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4837-447X","authenticated-orcid":false,"given":"Silvia Laura","family":"Bosello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2765-5935","authenticated-orcid":false,"given":"Stefano","family":"Patarnello","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6415-7267","authenticated-orcid":false,"given":"Carlotta","family":"Masciocchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1455-3884","authenticated-orcid":false,"given":"Marco","family":"Gorini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0965-7710","authenticated-orcid":false,"given":"Gabriella","family":"Castellino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4687-0709","authenticated-orcid":false,"given":"Alfredo","family":"Cesario","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5347-0060","authenticated-orcid":false,"given":"Maria Antonietta","family":"D'Agostino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8366-1474","authenticated-orcid":false,"given":"Jacopo","family":"Lenkowicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1136\/ard-2023-224762","article-title":"EULAR recommendations for the management of systemic lupus erythematosus: 2023 update","volume":"83","author":"Fanouriakis","journal-title":"Ann Rheum Dis"},{"issue":"5","key":"R2","doi-asserted-by":"publisher","first-page":"103294","DOI":"10.1016\/j.autrev.2023.103294","article-title":"Current state and completeness of reporting clinical prediction models using machine learning in systemic lupus erythematosus: a systematic review","volume":"22","author":"Mungu\u00eda-Realpozo","journal-title":"Autoimmun Rev"},{"issue":"2","key":"R3","doi-asserted-by":"publisher","DOI":"10.1136\/rmdopen-2021-001586","article-title":"Validation of a machine learning approach to estimate Systemic Lupus Erythematosus Disease Activity Index score categories and application in a real-world dataset","volume":"7","author":"Alves","journal-title":"RMD Open"},{"issue":"9","key":"R4","doi-asserted-by":"publisher","first-page":"4291","DOI":"10.1093\/rheumatology\/keab003","article-title":"Algorithm for calculating high disease activity in SLE","volume":"60","author":"Hoi","journal-title":"Rheumatology (Sunnyvale)"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2021.103892","article-title":"A novel hierarchical machine learning model for hospital-acquired venous thromboembolism risk assessment among multiple-departments","volume":"122","author":"Ma","journal-title":"J Biomed Inform"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106159","article-title":"A hierarchical machine learning model based on Glioblastoma patients\u2019 clinical, biomedical, and image data to analyze their treatment plans","volume":"150","author":"Ershadi","journal-title":"Comput Biol Med"},{"key":"R7","unstructured":"Lundberg S Lee SI . A unified approach to interpreting model predictions. arXiv. Preprint posted online on 2017. URL: https:\/\/arxiv.org\/abs\/1705.07874 [Accessed 14-08-2025] [doi: 10.48550\/arXiv.1705.07874]"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","journal-title":"Nat Mach Intell"},{"issue":"10","key":"R9","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/s41551-018-0304-0","article-title":"Explainable machine-learning predictions for the prevention of hypoxaemia during surgery","volume":"2","author":"Lundberg","journal-title":"Nat Biomed Eng"},{"issue":"2","key":"R10","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.semarthrit.2021.02.005","article-title":"Comprehensive disease control in systemic lupus erythematosus","volume":"51","author":"Ceccarelli","journal-title":"Semin Arthritis Rheum"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2018.08.029","article-title":"Predicting hospital readmission for lupus patients: An RNN-LSTM-based deep-learning methodology","volume":"101","author":"Reddy","journal-title":"Comput Biol Med"},{"issue":"3","key":"R12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0174200","article-title":"Prediction of chronic damage in systemic lupus erythematosus by using machine-learning models","volume":"12","author":"Ceccarelli","journal-title":"PLoS ONE"},{"issue":"2","key":"R13","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1159\/000513566","article-title":"Machine learning for prediction and risk stratification of lupus nephritis renal flare","volume":"52","author":"Chen","journal-title":"Am J Nephrol"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.1016\/j.semarthrit.2024.152507","article-title":"Modelling long-term outcomes for patients with systemic lupus erythematosus","volume":"68","author":"Touma","journal-title":"Semin Arthritis Rheum"},{"issue":"10","key":"R15","doi-asserted-by":"publisher","first-page":"1640","DOI":"10.1002\/acr.24612","article-title":"Prevalence and associated factors of electrocardiogram abnormalities in patients with systemic lupus erythematosus: a machine learning study","volume":"74","author":"Hu","journal-title":"Arthritis Care Res (Hoboken)"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-021-00284-5","article-title":"Machine learning approaches for the genomic prediction of rheumatoid arthritis and systemic lupus erythematosus","volume":"14","author":"Chung","journal-title":"BioData Min"},{"issue":"12","key":"R17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0207926","article-title":"Biomarkers of erosive arthritis in systemic lupus erythematosus: application of machine learning models","volume":"13","author":"Ceccarelli","journal-title":"PLoS ONE"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-28611-7","article-title":"Lupus nephritis pathology prediction with clinical indices","volume":"8","author":"Tang","journal-title":"Sci Rep"},{"issue":"4","key":"R19","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1177\/23969873241253366","article-title":"Artificial intelligence to predict individualized outcome of acute ischemic stroke patients: The SIBILLA project","volume":"9","author":"Caliandro","journal-title":"Eur Stroke J"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.2196\/53058","article-title":"Risk prediction of emergency department visits in patients with lung cancer using machine learning: retrospective observational study","volume":"11","author":"Lee","journal-title":"JMIR Med Inform"},{"key":"R21","unstructured":"Shap\/shap. GitHub. URL: https:\/\/github.com\/shap\/shap [Accessed 05-08-2025]"},{"key":"R22","doi-asserted-by":"crossref","unstructured":"Lilli L Bosello SL Antenucci L et al. A comprehensive natural language processing pipeline for the chronic lupus disease. In: Digital Health and Informatics Innovations for Sustainable Health Care Systems. IOS Press; 2024:909-913. [doi: 10.3233\/SHTI240559] [Medline: 39176940]","DOI":"10.3233\/SHTI240559"},{"issue":"3","key":"R23","doi-asserted-by":"publisher","DOI":"10.1093\/rap\/rkab061","article-title":"Disease severity, flares and treatment patterns in adults with systemic lupus erythematosus in the UK: a real-world observational retrospective cohort analysis","volume":"5","author":"Langham","journal-title":"Rheumatol Adv Pract"},{"key":"R24","unstructured":"Pedregosa F Varoquaux G Gramfort A et al. Scikit-learn: machine learning in python. arXiv. Preprint posted online on 2012. URL: https:\/\/arxiv.org\/abs\/1201.0490 [Accessed 14-08-2025] [doi: 10.48550\/arXiv.1201.0490]"},{"issue":"12","key":"R25","doi-asserted-by":"publisher","first-page":"3845","DOI":"10.1007\/s11255-024-04105-6","article-title":"Risk factors of disease activity and renal damage in patients with systemic lupus erythematosus","volume":"56","author":"Feng","journal-title":"Int Urol Nephrol"},{"issue":"8","key":"R26","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.3899\/jrheum.091028","article-title":"Serum albumin as a marker for disease activity in patients with systemic lupus erythematosus","volume":"37","author":"Yip","journal-title":"J Rheumatol"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e70200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:58:44Z","timestamp":1782842324000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2025\/1\/e70200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"references-count":26,"URL":"https:\/\/doi.org\/10.2196\/70200","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,22]]},"article-number":"v9i1e70200"}}