Photo Credit: Cesare Ferrari

The following is a summary of “Lasso-derived model for early prediction of systemic sclerosis based on vasculopathy assessment: a population-based cohort study,” published in the March 2025 issue of Rheumatology International by Lei et al. 

Researchers conducted a retrospective study to analyze vascular lesions in systemic sclerosis (SSc) and develop an early diagnostic model, identifying vasculopathy markers like nailfold capillaroscopy score and digital artery flow as key predictors. 

They recruited 111 participants (45 healthy, 66 with SSc, mean age 49.75 ± 12.902 years) and compared age, sex, blood pressure, hand grip strength, skin thickness, vascular index, skin blood flow, and nailfold microcirculation. Lasso regression was applied for variable selection, and a binary logistic regression model assessed diagnostic differences based on vascular injury. Model performance was evaluated using receiver operating characteristic (ROC) and calibration curve analyses to determine the optimal cutoff value. 

The results showed that Lasso regression identified 10 key variables from 37 microcirculation parameters, including age, left hand grip strength, left peak systolic velocity (PSV), right PSV, right resistance index (RI), ischemic perfusion (IPU), ischemic reperfusion perfusion (IRPU), post-occlusive reactive hyperemia baseline (PORH BL), loop top length, and nailfold video-capillaroscopy (NVC) score. NVC (≥5.35, AUC = 0.845, SEN = 0.74, SPE = 0.87), PSV (≥11.38, AUC = 0.838, SEN = 0.82, SPE = 0.73), IRPU (≥111.3, AUC = 0.831, SEN = 0.61, SPE = 0.91), and grip (≥22.8, AUC = 0.781, SEN = 0.79, SPE = 0.62) had high diagnostic value for SSc. The binary logistic regression model showed better interpretability and outperformed the scleroderma pattern model, with an AUC of 0.929 (95% CI: 0.883–0.974). 

Investigators identified nailfold video-capillaroscopy score, grip strength, and peak systolic flow velocity of the proper palmar digital artery as key predictors of systemic sclerosis events. 

Source: link.springer.com/article/10.1007/s00296-025-05835-1