Development and Validation of a Deep Learning Model for Non–Small Cell Lung Cancer Survival

IMPORTANCE: There is a lack of studies exploring the performance of a deep learning survival neural network in non–small cell lung cancer (NSCLC). OBJECTIVES: To compare the performances of DeepSurv, a deep learning survival neural network with a tumor, node, and metastasis staging system in the prediction of survival and test the reliability of individual treatment recommendations provided by the deep learning survival neural network. DESIGN, SETTING, AND PARTICIPANTS: In this population-based cohort study, a deep learning–based algorithm was developed and validated using consecutive cases of newly diagnosed stages I to IV NSCLC between January 2010 and December 2015 in a Surveillance, Epidemiology, and End Results database. A total of 127 features, including patient characteristics, tumor stage, and treatment strategies, were assessed for analysis. The algorithm was externally validated on an independent test cohort, comprising 1182 patients with stage I to III NSCLC diagnosed between January 2009 and December 2013 in Shanghai Pulmonary Hospital. Analysis began January 2018 and ended June 2019. MAIN OUTCOMES AND MEASURES: The deep learning survival neural network model was compared with the tumor, node, and metastasis staging system for lung cancer–specific survival. The C statistic was used to assess the performance of models. A user-friendly interface was provided to facilitate the survival predictions and treatment recommendations of the deep learning survival neural network model. RESULTS: Of 17 322 patients with NSCLC included in the study, 13 361 (77.1%) were white and the median (interquartile range) age was 68 (61-74) years. The majority of tumors were stage I disease (10 273 [59.3%]) and adenocarcinoma (11 985 [69.2%]). The median (interquartile range) follow-up time was 24 (10-43) months. There were 3119 patients who had lung cancer–related death during the follow-up period. The deep learning survival neural network model showed more promising results in the prediction of lung cancer–specific survival than the tumor, node, and metastasis stage on the test data set (C statistic = 0.739 vs 0.706). The population who received the recommended treatments had superior survival rates than those who received treatments not recommended (hazard ratio, 2.99; 95% CI, 2.49-3.59; P < .001), which was verified by propensity score–matched groups. The deep learning survival neural network model visualization was realized by a user-friendly graphic interface. CONCLUSIONS AND RELEVANCE: The deep learning survival neural network model shows potential benefits in prognostic evaluation and treatment recommendation with respect to lung cancer–specific survival. This novel analytical approach may provide reliable individual survival information and treatment recommendations.