Back to Journals » Cancer Management and Research » Volume 13

Nomogram Based on Ultrasonography and Clinical Features for Predicting Malignancy in Soft Tissue Tumors

Authors Wu M, Hu Y, Ren A, Peng X, Ma Q, Mao C, Hang J, Li A

Received 11 December 2020

Accepted for publication 9 February 2021

Published 2 March 2021 Volume 2021:13 Pages 2143—2152

DOI https://doi.org/10.2147/CMAR.S296972

Checked for plagiarism Yes

Review by Single anonymous peer review

Peer reviewer comments 4

Editor who approved publication: Dr Eileen O'Reilly


Mengjie Wu,1 Yu Hu,1 Anjing Ren,2 Xiaojing Peng,1 Qian Ma,1 Cuilian Mao,1 Jing Hang,1 Ao Li1

1Department of Ultrasound, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, Jiangsu, People’s Republic of China; 2Department of Oncology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, Jiangsu, People’s Republic of China

Correspondence: Ao Li
The First Affiliated Hospital of Nanjing Medical University, 300, Guangzhou Road, Nanjing, 210029, Jiangsu, People’s Republic of China
Tel +86-15205159458
Email [email protected]

Purpose: The objective of this study was to establish a predictive nomogram based on ultrasound (US) and clinical features for patients with soft tissue tumors (STTs).
Patients and Methods: A total of 260 patients with STTs were enrolled in this retrospective study and were divided into a training cohort (n=200, including 110 malignant and 90 benign masses) and a validation cohort (n=60, including 30 malignant and 30 benign masses). Multivariate analysis was performed by binary logistic regression analysis to determine the significant factors predictive of malignancy. A simple nomogram was established based on these independent risk factors including US and clinical features. The predictive accuracy and discriminative ability of the nomogram were measured by the calibration curve and the concordance index (C-index).
Results: The nomogram, comprising US features (maximum diameter, margin and vascular density) and clinical features (sex, age, and duration of disease), showed a favorable performance for predicting malignancy, with a sensitivity of 88.2% and a specificity of 78.7%. The calibration curve for malignancy probability in the training cohort showed good agreement between the nomogram predictions and actual observations. The C-indexes of the training cohort and validation cohort for predicting malignancy were 0.89 (95% CI: 0.85– 0.94) and 0.83 (95% CI: 0.73– 0.94), respectively.
Conclusion: The nomogram based on US and clinical features could be a simple, intuitive and reliable tool to individually predict malignancy in patients with STTs.

Keywords: soft tissue tumors, ultrasonography, malignancy, predictive model, nomogram

Creative Commons License This work is published and licensed by Dove Medical Press Limited. The full terms of this license are available at https://www.dovepress.com/terms.php and incorporate the Creative Commons Attribution - Non Commercial (unported, v3.0) License. By accessing the work you hereby accept the Terms. Non-commercial uses of the work are permitted without any further permission from Dove Medical Press Limited, provided the work is properly attributed. For permission for commercial use of this work, please see paragraphs 4.2 and 5 of our Terms.

Download Article [PDF]  View Full Text [HTML][Machine readable]