The clinical heterogeneity of systemic lupus erythematosus exceeds the resolution of conventional disease activity instruments. Artificial intelligence offers the analytical infrastructure to engage with this complexity, yet the translation of AI models into clinical practice remains limited.
Methods
This review critically appraises the current evidence for AI applications across the SLE clinical workflow, including computational phenotyping, diagnosis, disease activity monitoring, organ-specific predictive modelling, and treatment personalization. Studies were evaluated for external validation, prospective testing, algorithmic fairness, explainability, and regulatory status.
Findings
AI applications across the SLE clinical workflow show uneven methodological maturity. Diagnostic and monitoring tools include the SLERPI index, with multinational external validation, and an LSTM flare-prediction model (C-index 0.897). Treatment personalization is anchored by serum IgA2 anti-dsDNA, the only SLE response biomarker validated across independent trials, and by multi-stain deep learning on renal biopsies (AUC 0.84, three external centers). Predictive modelling for organ-specific manifestations has progressed unevenly: cardiovascular risk stratification (SLECRISK) and a multicenter thrombocytopenia model are the most mature, while neuropsychiatric, gastrointestinal, and ocular applications remain single-center proofs of concept. External validation is the exception across SLE prediction models, no AI tool has received regulatory clearance, and populations most affected by SLE remain underrepresented in training data.
Conclusions
AI demonstrates genuine analytical capability in SLE but the translation gap is defined by insufficient validation, limited explainability, and absent equity evidence. Closing it will require fewer published models and more validated tools, optimization for clinical impact rather than discrimination alone, and demonstration of performance equity across the demographic spectrum of the disease.
YaungKNYeoJGKumarP, et al.Artificial intelligence and high-dimensional technologies in the theragnosis of systemic lupus erythematosus. Lancet Rheumatol2023; 5: e151–e165. https://doi.org/10.1016/S2665-9913(23)00010-3
4.
Munguía-RealpozoPEtchegaray-MoralesIMendoza-PintoC, et al.Current state and completeness of reporting clinical prediction models using machine learning in systemic lupus erythematosus: a systematic review. Autoimmun Rev2023; 22: 103294. https://doi.org/10.1016/j.autrev.2023.103294
5.
KingsmoreKMLipskyPE. Recent advances in the use of machine learning and artificial intelligence to improve diagnosis, predict flares, and enrich clinical trials in lupus. Curr Opin Rheumatol2022; 34: 374–381. https://doi.org/10.1097/BOR.0000000000000902
6.
KasireddyHRLa RosaPSDemekeD, et al.A scoping review of machine learning applications for diagnosis, classification, and prognosis in lupus nephritis. Kidney2026. https://doi.org/10.34067/KID.0000001196, Epub ahead of print 18.
7.
LanataCMParanjpeINitithamJ, et al.A phenotypic and genomics approach in a multi-ethnic cohort to subtype systemic lupus erythematosus. Nat Commun2019; 10: 3902. https://doi.org/10.1038/s41467-019-11845-y
8.
ThanouAJupeEPurushothamanM, et al.Clinical disease activity and flare in SLE: current concepts and novel biomarkers. J Autoimmun2021; 119: 102615. https://doi.org/10.1016/j.jaut.2021.102615
9.
Toro-DomínguezDMartorell-MarugánJMartinez-BuenoM, et al.Scoring personalized molecular portraits identify systemic lupus erythematosus subtypes and predict individualized drug responses, symptomatology and disease progression. Briefings Bioinf2022; 23: bbac332. https://doi.org/10.1093/bib/bbac332
10.
BoselloSLOrtolanALanzoL, et al.Identification of clinical phenotypes and disease trajectories in SLE using AI through a natural language processing framework. Rheumatology2026; 65: keag035. https://doi.org/10.1093/rheumatology/keag035
11.
PerezRKGordonMGSubramaniamM, et al.Single-cell RNA-Seq reveals cell type-specific molecular and genetic associations to lupus. Science2022; 376: eabf1970. https://doi.org/10.1126/science.abf1970
12.
AdamichouCGenitsaridiINikolopoulosD, et al.Lupus or not? SLE risk probability index (SLERPI): a simple, clinician-friendly machine learning-based model to assist the diagnosis of systemic lupus erythematosus. Ann Rheum Dis2021; 80: 758–766. https://doi.org/10.1136/annrheumdis-2020-219069
13.
ZhangLLuWYanD, et al.Systemic lupus erythematosus risk probability index: ready for routine use? Results from a Chinese cohort. Lupus Sci Med2023; 10: e000988. https://doi.org/10.1136/lupus-2023-000988
14.
HammamNElsamanAAbualfadlE, et al.Performance of the systemic lupus erythematosus risk probability index (SLERPI) in the Egyptian college of rheumatology (ECR) study cohort. Clin Rheumatol2025; 44: 207–215. https://doi.org/10.1007/s10067-024-07210-0
15.
Celis-AndradeMRojasMRodríguezY, et al.Performance of the systemic lupus erythematosus risk probability index (SLERPI) in a cohort of Colombian population. Clin Rheumatol2024; 43: 3313–3322. https://doi.org/10.1007/s10067-024-07108-x
16.
MurraySGAvatiASchmajukG, et al.Automated and flexible identification of complex disease: building a model for systemic lupus erythematosus using noisy labeling. J Am Med Inform Assoc2019; 26: 61–65. https://doi.org/10.1093/jamia/ocy154
17.
SwerdelJNRamcharranDHardinJ. Using a data-driven approach for the development and evaluation of phenotype algorithms for systemic lupus erythematosus. PLoS One2023; 18: e0281929. https://doi.org/10.1371/journal.pone.0281929
18.
WangHJiangLXiaoY, et al.HERC5, IFI6, IFIT3, and OASL as potential diagnostic biomarkers for systemic lupus erythematosus: an integrated bioinformatics, machine learning and clinical validation. Clin Rheumatol2026; 45: 875–889. https://doi.org/10.1007/s10067-025-07880-4
19.
MunroeMEBlankenshipDDeFreeseD, et al.A flare risk index informed by select immune mediators in systemic lupus erythematosus. Arthritis Rheumatol2023; 75: 723–735. https://doi.org/10.1002/art.42389
20.
HuangSChenYSongY, et al.Deep learning model to predict lupus nephritis renal flare based on dynamic multivariable time-series data. BMJ Open2024; 14: e071821. https://doi.org/10.1136/bmjopen-2023-071821
21.
JupeERPurushothamanMWangB, et al.Impact of a digital platform and flare risk blood biomarker index on lupus: a study protocol design for evaluating self efficacy and disease management. Contemporary Clinical Trials Communications2025; 45: 101471. https://doi.org/10.1016/j.conctc.2025.101471
22.
JupeERLushingtonGHPurushothamanM, et al.Tracking of systemic lupus erythematosus (SLE) longitudinally using biosensor and patient-reported data: a report on the fully decentralized Mobile study to measure and predict lupus disease activity using digital signals-the OASIS study. BioTech (Basel)2023; 12: 62. https://doi.org/10.3390/biotech12040062
23.
MormileIBrussinoLCanonicaGW, et al.The LUNET project: developing the Italian systemic erythematous lupus network. J Clin Med2025; 14: 6197. https://doi.org/10.3390/jcm14176197
YeeCFarewellVIsenbergDA, et al.Revised British isles lupus assessment group 2004 index: a reliable tool for assessment of systemic lupus erythematosus activity. Arthritis Rheum2006; 54: 3300–3305. https://doi.org/10.1002/art.22162
26.
Parra SánchezARVan VollenhovenRFMorandEF, et al.Targeting DORIS remission and LLDAS in SLE: a review. Rheumatol Ther2023; 10: 1459–1477. https://doi.org/10.1007/s40744-023-00601-w
27.
ChengCLiBLiJ, et al.Multi-stain deep learning prediction model of treatment response in lupus nephritis based on renal histopathology. Kidney Int2025; 107: 714–727. https://doi.org/10.1016/j.kint.2024.12.007
ZhengZZhangXDingJ, et al.Deep learning-based artificial intelligence system for automatic assessment of glomerular pathological findings in lupus nephritis. Diagnostics2021; 11: 1983. https://doi.org/10.3390/diagnostics11111983
30.
FavaABuyonJMagderL, et al.Urine proteomic signatures of histological class, activity, chronicity, and treatment response in lupus nephritis. JCI Insight2024; 9: e172569. https://doi.org/10.1172/jci.insight.172569
LiQYangZChenK, et al.Human-multimodal deep learning collaboration in ‘precise’ diagnosis of lupus erythematosus subtypes and similar skin diseases. J Eur Acad Dermatol Venereol2024; 38: 2268–2279. https://doi.org/10.1111/jdv.20031
34.
DaneshjouRVodrahalliKNovoaRA, et al.Disparities in dermatology AI performance on a diverse, curated clinical image set. Sci Adv2022; 8: eabq6147. https://doi.org/10.1126/sciadv.abq6147
ChoiMYGuanHYoshidaK, et al.Personalizing cardiovascular risk prediction for patients with systemic lupus erythematosus. Semin Arthritis Rheum2024; 67: 152468. https://doi.org/10.1016/j.semarthrit.2024.152468
37.
WeberBNBieryDWPetranovicM, et al.Prevalence and prognostic value of incidentally detected coronary artery calcium using artificial intelligence among individuals with immune-mediated inflammatory diseases. JACC, Cardiovasc Imaging2026; 19: 64–75. https://doi.org/10.1016/j.jcmg.2025.08.020
38.
IngleseFKimMSteup-BeekmanGM, et al.MRI-based classification of neuropsychiatric systemic lupus erythematosus patients with self-supervised contrastive learning. Front Neurosci2022; 16: 695888. https://doi.org/10.3389/fnins.2022.695888
39.
LiYGeZZhangZ, et al.Broad learning enhanced 1H-MRS for early diagnosis of neuropsychiatric systemic lupus erythematosus. Comput Math Methods Med2020; 2020: 8874521. https://doi.org/10.1155/2020/8874521
40.
ZhangYJiangNDuanX, et al.Risk prediction of new-onset thrombocytopenia in patients with systemic lupus erythematosus: a multicenter prospective cohort study based on Chinese SLE treatment and research group (CSTAR) registry. Arthritis Res Ther2024; 26: 229. https://doi.org/10.1186/s13075-024-03460-0
41.
ZhangWHuangGLinJ, et al.Predictive model of risk and severity of enteritis in systemic lupus erythematosus. Lupus2022; 31: 1226–1236. https://doi.org/10.1177/09612033221110743
42.
FekrazadSHassanzadehGSalehiMA, et al.Optical coherence tomography angiography measurements in systemic lupus erythematosus: a systematic review and meta-analysis. Surv Ophthalmol2024; 69: 743–755. https://doi.org/10.1016/j.survophthal.2024.04.007
43.
MengLChenLZhangC, et al.Quantitative assessment of retinal vasculature changes in systemic lupus erythematosus using wide-field OCTA and the correlation with disease activity. Front Immunol2024; 15: 1340224. https://doi.org/10.3389/fimmu.2024.1340224
Woodward-CourtPHoggJLeeT, et al.Deep learning algorithm for the diagnosis and prediction of hydroxychloroquine retinopathy: an international, multi-institutional study. Ophthalmol Retina2025; 9: 1140–1148. https://doi.org/10.1016/j.oret.2025.06.003
46.
MoysidouG-SGarantziotisPSentisG, et al.Molecular basis for the disease-modifying effects of belimumab in systemic lupus erythematosus and molecular predictors of early response: blood transcriptome analysis implicates the innate immunity and DNA damage response pathways. Ann Rheum Dis2025; 84: 262–273. https://doi.org/10.1136/ard-2024-226051
47.
GarantziotisPMoysidouGSKapsalaN, et al.Transcriptome analysis to decipher the molecular underpinnings of response to treatment in systemic lupus erythematosus. RMD Open2025; 11: e005050. https://doi.org/10.1136/rmdopen-2024-005050
48.
ShipaMSantosLRNguyenDX, et al.Identification of biomarkers to stratify response to B-cell-targeted therapies in systemic lupus erythematosus: an exploratory analysis of a randomised controlled trial. Lancet Rheumatol2023; 5: e24–e35. https://doi.org/10.1016/S2665-9913(22)00332-0
49.
McCluskeyDShipaMRAChowdhuryK, et al.IgA2+ B cells and IgA2 anti-dsDNA antibodies are selectively targeted by belimumab after rituximab therapy in systemic lupus erythematosus. Cell Rep Med2025; 6: 102247. https://doi.org/10.1016/j.xcrm.2025.102247
50.
MorandEFFurieRTanakaY, et al.Trial of anifrolumab in active systemic lupus erythematosus. N Engl J Med2020; 382: 211–221. https://doi.org/10.1056/NEJMoa1912196
51.
Munguía-RealpozoPMendoza-PintoCEtchegaray-MoralesI, et al.Evaluating large language models as a supplementary patient information resource on antimalarial use in systemic lupus erythematosus. Lupus2025; 34: 374–380. https://doi.org/10.1177/09612033251324501
52.
SimsSRowseyKHemmerichC, et al.Systematic review of inequitable population representation in systemic lupus erythematosus clinical trials. Arthritis Care Res2025; 77: 1323–1331. https://doi.org/10.1002/acr.25576
53.
NairMSvedbergPLarssonI, et al.A comprehensive overview of barriers and strategies for AI implementation in healthcare: mixed-method design. PLoS One2024; 19: e0305949. https://doi.org/10.1371/journal.pone.0305949
54.
LiYYaoLLeeYA, et al.A fair machine learning model to predict flares of systemic lupus erythematosus. JAMIA Open2025; 8: ooaf072. https://doi.org/10.1093/jamiaopen/ooaf072
55.
MuehlematterUJDaniorePVokingerKN. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015–20): a comparative analysis. Lancet Digit Health2021; 3: e195–e203. https://doi.org/10.1016/S2589-7500(20)30292-2
