Methodological Issue in “Development of an Ultrasound Prediction Model to Discriminate between Malignant and Benign Liver Lesions”

We read with interest the article by Shen et al. (2020) published recently. The aim of the authors was to discriminate between malignant and benign liver lesions. They evaluated the ultrasound features of the target lesions in 266 patients and established a prediction model using a logistic regression algorithm. To evaluate model performance, discrimination and calibration were used. They described that, given its high diagnostic specificity, sensitivity and accuracy, the ultrasound prediction model has potential for use as a diagnostic tool in early detection of malignant tumors of the liver and in reduction of unnecessary biopsies to a great extent.

Source: Ultrasound in Medicine and Biology - August 7, 2020 Category: Radiology Authors: Sahar Souri Pilangorgi, Soodeh Shahsavari Tags: Letter to the Editor Source Type: research