Predicting malignancy of pulmonary ground-glass nodules and their invasiveness by random forest

Xueyan Mei; Rui Wang; Wenjia Yang; Fangfei Qian; Xiaodan Ye; Li Zhu; Qunhui Chen; Baohui Han; Timothy Deyer; Jingyi Zeng; Xiaomeng Dong; Wen Gao; Wentao Fang

doi:10.21037/jtd.2018.01.88

Predicting malignancy of pulmonary ground-glass nodules and their invasiveness by random forest

J Thorac Dis. 2018 Jan;10(1):458-463. doi: 10.21037/jtd.2018.01.88.

Authors

Xueyan Mei¹, Rui Wang², Wenjia Yang³, Fangfei Qian³, Xiaodan Ye⁴, Li Zhu⁴, Qunhui Chen⁴, Baohui Han³, Timothy Deyer^{5

6}, Jingyi Zeng⁷, Xiaomeng Dong⁸, Wen Gao², Wentao Fang²

Affiliations

¹ Department of Applied Biomedical Engineering, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, USA.
² Department of Thoracic Surgery, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai 200030, China.
³ Department of Pulmonary Medicine, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai 200030, China.
⁴ Department of Radiology, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai 200030, China.
⁵ East River Medical Imaging, New York, NY, USA.
⁶ Department of Radiology, Weill Cornell Medicine, New York, NY, USA.
⁷ Department of Statistics, University of Illinois at Urbana-Champaign, Champaign, IL, USA.
⁸ Department of Data Science Analytics, University of Oklahoma, Norman, OK, USA.

Abstract

Background: The purpose of this study was to develop a predictive model that could accurately predict the malignancy of the pulmonary ground-glass nodules (GGNs) and the invasiveness of the malignant GGNs.

Methods: The authors built two binary classification models that could predict the malignancy of the pulmonary GGNs and the invasiveness of the malignant GGNs.

Results: Results of our developed model showed random forest could achieve 95.1% accuracy to predict the malignancy of GGNs and 83.0% accuracy to predict the invasiveness of the malignant GGNs.

Conclusions: The malignancy and invasiveness of pulmonary GGNs could be predicted by random forest.

Keywords: Ground-glass nodule (GGN); random forest.