Objective Neuropsychiatric systemic lupus erythematosus (NPSLE) is linked to increased morbidity, mortality, and adverse health-related quality of life. Early disease, a history of NPSLE, antiphospholipid antibody positivity, and high disease activity are considered risk factors for NPSLE. However, there is currently no clinical tool for predicting neuropsychiatric flares. We aimed to assess the effectiveness of machine learning (ML) in predicting NPSLE flares within a large cohort of patients with active SLE, yet no active severe NPSLE.

Methods We analysed data from five phase III trials (BLISS-52, BLISS-76, BLISS-NEA, BLISS-SC, and EMBRACE) after excluding patients with baseline neuropsychiatric British Isles Lupus Assessment Group (BILAG) score A (N=3638). Neuropsychiatric flares were defined as a transition from BILAG score C, D, or E to score A or B, or from score B to score A in the neuropsychiatric domain of the classic BILAG index throughout a 52-week long follow-up. After constructing panels of variables based on knowledge, we employed ML to develop predictive models utilising the least absolute shrinkage and selection operator (LASSO) and logistic regression. A stratified split was applied to partition the study population into a training (70%; N=2547), and a test set (30%; N=1091). The training set was used in model development while the internal validation was developed by a 10-fold cross validation. The test set was used for validating the built model.

Results A total of 105 SLE patients (2.89%) experienced a neuropsychiatric flare during follow-up. Knowledge-driven feature selection included a history of NPSLE, disease duration, anticardiolipin positivity, clinical Systemic Lupus Erythematosus Disease Activity Index 2000 (SLEDAI-2K), sex, age, and the use of antimalarials. Both classifiers demonstrated comparable performance, with an AUC of 0.80 and 0.80, sensitivity of 0.61 and 0.61, and specificity of 0.83 and 0.82, respectively.

Conclusions The integration of traditional risk factors for NPSLE into ML-based models can predict neuropsychiatric involvement in SLE with high specificity and modest sensitivity. We herein propose a pragmatic, robust, and highly accurate prediction tool forecasting neuropsychiatric flares in SLE patients. The utilisation of this ML-based tool holds promising prospects for improving patient care and outcomes in real-world settings.

Conflicts of Interest IP has received research funding and/or honoraria from Amgen, AstraZeneca, Aurinia, Bristol Myers Squibb, Elli Lilly, Gilead, GlaxoSmithKline, Janssen, Novartis, Otsuka, and Roche. The other authors declare that they have no conflicts of interest related to this work. The funders had no role in the design of the study, the analyses or interpretation of data, or the writing of the manuscript.