Lupus nephritis (LN) is a major cause of renal morbidity in SLE patients. To address the need for earlier and more individualized risk identification, we developed a computational engine incorporating longitudinal phenotype trajectories, treatment burden, and traditional biomarkers into a unified risk-scoring framework. The engine was retrospectively validated across a synthetic longitudinal cohort of 377 SLE patients, outputting a continuous composite score (0–100) and a four-tier risk classification: Low / Moderate / High / Critical. At the Moderate+ screening threshold, the engine achieved 100% sensitivity and 100% NPV within 90 days of confirmed LN diagnosis — meaning zero missed progressors. These findings suggest that this computational engine can identify patients approaching lupus nephritis up to 90 days before diagnosis, giving clinicians a critical window to intervene early, triage high-risk patients, and initiate nephrology referrals sooner.
Read MoreThis study sought to identify an optimal panel of immune mediators to distinguish SLE patients with active versus low/quiescent disease and refine the Lupus Disease Activity Index (L-DAI). Using plasma immune mediators and serum autoantibody specificities from classified SLE patients, we applied random forest modeling to determine the most informative analytes. A refined panel of 9 immune mediators, including IFN-α, significantly differentiated SLE patients with active versus low disease activity, with strong correlation to clinical disease activity scores (hSLEDAI). The L-DAI demonstrated a large effect size and strong discriminatory performance (AUC=0.795). The findings support the use of a sensitive, objective biomarker surrogate for clinical disease activity in SLE, with the potential to improve disease management and prevent organ damage.
Read MoreThe decentralized OASIS study analyzed smartwatch biometric data and patient-reported outcomes from 532 SLE participants. A 94-feature regression model achieved significant correlation (R²=0.75) predicting self-reported flares, supporting proactive clinical screening.
Read MoreThis study combined natural language processing of medical records with patient biometric and self-reported data. Strong correlations identified 24 metrics predicting physician assessments, supporting AI-augmented remote lupus management strategies.
Read MoreThis prospective study evaluated aiSLE® MGMT engagement platform in SLE patients across five US practices. Participants showed improved quality-of-life metrics, reduced fatigue, and decreased physician-reported disease activity, demonstrating comprehensive care management benefits.
Read MoreThis study used a virtual/digital program to recruit at-risk individuals via online screening and sequential telehealth evaluations, classifying 18% with SLE in a mean of 371 days—shortening typical diagnosis time from 5-7 years—demonstrating potential for remote, accurate lupus assessment.
Read MoreThis study developed a Lupus Disease Activity Immune Index integrating 32 soluble mediators weighted by autoantibody burden, successfully distinguishing active from low disease activity, correlating with SLEDAI scores, and identifying renal involvement to guide objective SLE management.
Read MoreThis study refined a Lupus Disease Activity Immune Index using 12 prioritized soluble mediators and autoantibody breadth, significantly distinguishing low versus active SLE, correlating with hSLEDAI, and identifying renal involvement, supporting objective, treat-to-target disease monitoring in practice
Read MoreThis study refined a blood-based Lupus Disease Activity Immune Index using nine key soluble mediators and autoantibody breadth, accurately distinguishing active from low/quiescent SLE and correlating with hSLEDAI, supporting objective, treat-to-target monitoring in clinical practice.
Read MoreThis study refined a blood-based Lupus Disease Activity Immune Index(L-DAI) using 33 soluble mediators and autoantibody breadth with machine learning, accurately distinguishing active from low SLE activity and offering clinically actionable, objective augmentation to traditional scoring systems
Read MoreThis study assessed the parallel use of L-FRI and L-DAI to assess simultaneous risk of future disease flare and concurrent disease activity to guide therapy. Results showed that combined assessment best identified imminent flares and concurent disease activity, supporting early intervention and clinical trial utility.
Read MoreThis study evaluated the association between both L-DAI and hSLEDAI and patient reported quality of life (HRQol). Higher biomarker-derived disease activity scores correlate with lower patient-reported quality of life, validating L-DAI and hSLEDAI as effective lupus monitoring tools.
Read MoreThis study evaluated L-FRI and L-DAI in parallel to determine the risk of future flare and concurrent disease activity. Simultaneous assessment improves identification of lupus patients with concurrent active disease and imminent flare risk.
Read MoreThis study assessed whether select Patient-reported outcomes enhance flare and disease activity indexes (L-DAI & L-FRI). Results showed PRO domains improves prediction and screening performance in lupus, supporting integration into SLE management
Read MoreThis study validated the utility of the flare risk index. 11 immune mediators shows strong predictive power for lupus flares, including differentiation of mild-moderate and severe flare risk.
Read MoreThis study evaluated whether immune mediators predicts lupus flares. Using plasma samples and machine learning algorithm, 31 mediators ditinguished pre-flare from stable state. A refined lupus flare prediction index achieved high sensitivity and specificity supporting its use as a predictive tool for early flare detection and lupus management.
Read More