Clinical diagnostic model for predicting indolent or aggressive lymphoma based on clinical information and ultrasound features of superficial lymph nodes

Abstract

Purpose

The aim of this study was to develop a diagnostic model for predicting indolent lymphoma or aggressive lymphoma using clinical information and ultrasound characteristics of superficial lymph nodes.

Method

Patients with confirmed pathological lymphoma subtypes who had undergone ultrasound and contrast-enhanced ultrasound examinations were enrolled. Clinical and ultrasound imaging features were retrospectively analysed and compared to the pathological results, which were considered the gold standard for diagnosis. Two diagnostic models were developed: a clinical model (Model-C) using clinical data only, and a combined model (Model-US) integrating ultrasound features into the clinical model. The efficacy of these models in differentiating between indolent and aggressive lymphoma was compared.

Results

In total, 236 consecutive patients were enrolled, including 78 patients with indolent lymphomas and 158 patients with aggressive lymphomas. Receiver operating characteristic (ROC) curve analysis revealed that the areas under the curves of Model-C and Model-US were 0.78 (95 % confidence interval: 0.72–0.84) and 0.87 (95 % confidence interval: 0.82–0.92), respectively (p < 0.001). Model-US was further evaluated for calibration and is presented as a nomogram.

Conclusions

The diagnostic model incorporated clinical and ultrasound characteristics and offered a noninvasive method for assessing lymphoma with good discrimination and calibration.