Development and Validation of Machine Learning-based Model for the Prediction of Malignancy in Multiple Pulmonary Nodules: Analysis from Multicentric Cohorts

被引：32

作者：

Chen, Kezhong ^{[1
]}

Nie, Yuntao ^{[1
]}

Park, Samina ^{[2
]}

Zhang, Kai ^{[1
]}

Zhang, Yangming ^{[3
]}

Liu, Yuan ^{[4
]}

Hui, Bengang ^{[5
]}

Zhou, Lixin ^{[1
]}

Wang, Xun ^{[1
]}

Qi, Qingyi ^{[6
]}

Li, Hao ^{[1
]}

Kang, Guannan ^{[1
]}

Huang, Yuqing ^{[7
]}

Chen, Yingtai ^{[8
]}

Liu, Jiabao ^{[9
]}

Cui, Jian ^{[10
]}

Li, Mingru ^{[11
]}

Park, In Kyu ^{[2
]}

Kang, Chang Hyun ^{[2
]}

Shen, Haifeng ^{[1
]}

Yang, Yingshun ^{[7
]}

Guan, Tian ^{[1
]}

Zhang, Yaxiao ^{[9
]}

Yang, Fan ^{[1
]}

Kim, Young Tae ^{[2
]}

Wang, Jun ^{[1
]}

机构：

[1] Peking Univ Peoples Hosp, Dept Thorac Surg, Beijing, Peoples R China

[2] Seoul Natl Univ, Seoul Natl Univ Hosp, Dept Thorac & Cardiovasc Surg, Coll Med, Seoul, South Korea

[3] Chinese Acad Sci, Shenzhen Inst Adv Technol, Inst Synthet Biol, Shenzhen, Peoples R China

[4] Peking Univ, Beijing Natl Lab Mol Sci, Coll Chem & Mol Engn,Minist Educ, Synthet & Funct Biomol Ctr,Key Lab Bioorgan Chem, Beijing, Peoples R China

[5] Air Force Med Univ, Tangdu Hosp, Dept Thorac Surg, Xian, Peoples R China

[6] Peking Univ Peoples Hosp, Dept Radiol, Beijing, Peoples R China

[7] Beijing Haidian Hosp, Dept Thorac Surg, Beijing, Peoples R China

[8] Beijing Aerosp Gen Hosp, Dept Thorac Surg, Beijing, Peoples R China

[9] First Hosp Shijiazhuang, Dept Thorac Surg, Shijiazhuang, Hebei, Peoples R China

[10] Beijing Chuiyangliu Hosp, Dept Thorac Surg, Beijing, Peoples R China

[11] Aerosp 731 Hosp, Dept Thorac Surg, Beijing, Peoples R China

来源：

CLINICAL CANCER RESEARCH | 2021年 / 27卷 / 08期

关键词：

LUNG-CANCER; PROBABILITY; PERFORMANCE; MANAGEMENT;

D O I：

10.1158/1078-0432.CCR-20-4007

中图分类号：

R73 [肿瘤学];

学科分类号：

100214 ;

摘要：

Purpose: Nodule evaluation is challenging and critical to diagnose multiple pulmonary nodules (MPNs). We aimed to develop and validate a machine learning-based model to estimate the malignant probability of MPNs to guide decision-making. Experimental Design: Aboosted ensemble algorithm (XGBoost) was used to predict malignancy using the clinicoradiologic variables of 1,739 nodules from 520 patients with MPNs at a Chinese center. The model (PKU-M model) was trained using 10-fold cross-validation in which hyperparameters were selected and fine-tuned. The model was validated and compared with solitary pulmonary nodule (SPN) models, clinicians, and a computer-aided diagnosis (CADx) system in an independent transnational cohort and a prospective multicentric cohort. Results: The PKU-M model showed excellent discrimination [area under the curve; AUC (95% confidence interval (95% CI)), 0.909 (0.854-0.946)] and calibration (Brier score, 0.122) in the development cohort. External validation (583 nodules) revealed that the AUC of the PKU-M model was 0.890 (0.859-0.916), higher than those of the Brock model [0.806 (0.771-0.838)], PKU model [0.780 (0.743-0.817)], Mayo model [0.739 (0.697-0.776)], and VA model [0.682 (0.640-0.722)]. Prospective comparison (200 nodules) showed that the AUC of the PKU-M model [0.871 (0.815-0.915)] was higher than that of surgeons [0.790 (0.711-0.852), 0.741 (0.662-0.804), and 0.727 (0.650-0.788)], radiologist [0.748 (0.671-0.814)], and the CADx system[0.757 (0.682-0.818)]. Furthermore, themodel outperformed the clinicians with an increase of 14.3% in sensitivity and 7.8% in specificity. Conclusions: After its development using machine learning algorithms, validation using transnational multicentric cohorts, and prospective comparison with clinicians and the CADx system, this novel prediction model for MPNs presented solid performance as a convenient reference to help decision-making.

引用

页码：2255 / 2265

页数：11

共 36 条

[11] UK Lung Cancer RCT Pilot Screening Trial: baseline findings from the screening arm provide evidence for the potential implementation of lung cancer screening [J].

Field, J. K. ;

Duffy, S. W. ;

Baldwin, D. R. ;

Whynes, D. K. ;

Devaraj, A. ;

Brain, K. E. ;

Eisen, T. ;

Gosney, J. ;

Green, B. A. ;

Holemans, J. A. ;

Kavanagh, T. ;

Kerr, K. M. ;

Ledson, M. ;

Lifford, K. J. ;

McRonald, F. E. ;

Nair, A. ;

Page, R. D. ;

Parmar, M. K. B. ;

Rassl, D. M. ;

Rintoul, R. C. ;

Screaton, N. J. ;

Wald, N. J. ;

Weller, D. ;

Williamson, P. R. ;

Yadegarfar, G. ;

Hansell, D. M. .

THORAX, 2016, 71 (02) :161-170

[12] Estimation of the Youden index and its associated cutoff point [J].

Fluss, R ;

Faraggi, D ;

Reiser, B .

BIOMETRICAL JOURNAL, 2005, 47 (04) :458-472

[13] Utility of Maximum Standard Uptake Value as a Predictor for Differentiating the Invasiveness of T1 Stage Pulmonary Adenocarcinoma [J].

Fu, Lilan ;

Alam, Mohammed Shah ;

Ren, Yunyan ;

Guan, Wei ;

Wu, Hubing ;

Wang, Quanshi ;

Han, Yanjiang ;

Zhou, Wenlan ;

Li, Hongsheng ;

Wang, Zhen .

CLINICAL LUNG CANCER, 2018, 19 (03) :221-229

[14] A clinical model to estimate the pretest probability of lung cancer in patients with solitary pulmonary nodules [J].

Gould, Michael K. ;

Ananth, Lakshmi ;

Barnett, Paul G. .

CHEST, 2007, 131 (02) :383-388

[15] Evaluation of Individuals With Pulmonary Nodules: When Is It Lung Cancer? Diagnosis and Management of Lung Cancer, 3rd ed: American College of Chest Physicians Evidence-Based Clinical Practice Guidelines [J].

Gould, Michael K. ;

Donington, Jessica ;

Lynch, William R. ;

Mazzone, Peter J. ;

Midthun, David E. ;

Naidich, David P. ;

Wiener, Renda Soylemez .

CHEST, 2013, 143 (05) :E93-E120

[16] Detection of lung cancer through low-dose CT screening (NELSON): a prespecifi ed analysis of screening test performance and interval cancers [J].

Horeweg, Nanda ;

Scholten, Ernst Th ;

de Jong, Pim A. ;

van der Aalst, Carlijn M. ;

Weenink, Carla ;

Lammers, Jan-Willem J. ;

Nackaerts, Kristiaan ;

Vliegenthart, Rozemarijn ;

ten Haaf, Kevin ;

Yousaf-Khan, Uraujh A. ;

Heuvelmans, Marjolein A. ;

Thunnissen, Erik ;

Oudkerk, Matthijs ;

Mali, Willem ;

de Koning, Harry J. .

LANCET ONCOLOGY, 2014, 15 (12) :1342-1350

[17] Machine learning applications in cancer prognosis and prediction [J].

Kourou, Konstantina ;

Exarchos, Themis P. ;

Exarchos, Konstantinos P. ;

Karamouzis, Michalis V. ;

Fotiadis, Dimitrios I. .

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL, 2015, 13 :8-17

[18] Impact of Video-Assisted Thoracoscopic Surgery on Benign Resections for Solitary Pulmonary Nodules [J].

Kuo, Elbert ;

Bharat, Ankit ;

Bontumasi, Nicholas ;

Sanchez, Czarina ;

Zoole, Jennifer Bell ;

Patterson, G. Alexander ;

Meyers, Bryan F. .

ANNALS OF THORACIC SURGERY, 2012, 93 (01) :266-273

[19] Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images [J].

Li, Wei ;

Cao, Peng ;

Zhao, Dazhe ;

Wang, Junbo .

COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2016, 2016

[20] Development and Validation of a Clinical Prediction Model to Estimate the Probability of Malignancy in Solitary Pulmonary Nodules in Chinese People [J].

Li, Yun ;

Chen, Ke-Zhong ;

Wang, Jun .

CLINICAL LUNG CANCER, 2011, 12 (05) :313-319

← 1 2 3 4 →