Construction and internal cohort verification of clinical-imaging-based nomogram for early diagnosis in Takayasu arteritis

Back to news list

Source: Frontiers Medicine

Original: https://www.frontiersin.org/articles/10.3389/fmed.2026.1743349...

Published: 2026-02-03T00:00:00Z

Takayasu's arteritis (TAK) is a chronic vasculitis of the large vessels that is difficult to diagnose at an early stage[2]. A research team developed and validated a new nomogram model that combines clinical data, conventional imaging and radiomic features to improve the early diagnosis of TAK[2]. The study included 356 patients divided into a training set (249 patients) and a validation set (107 patients)[2]. The model identified independent predictors of early stage TAK including intermittent limb claudication, vascular murmur, elevated erythrocyte sedimentation rate (ESR) and C-reactive protein (CRP)[2]. The nomogram model achieved an area under the ROC curve (AUC) of 0.767 in the training set and 0.733 in the validation set, indicating good predictive accuracy[2]. The researchers concluded that this model can provide an individualized and non-invasive risk assessment for the early diagnosis of TAK and support clinical decision-making[2].