AUTHOR=Zhang Dongrui , Lu Baohua , Liang Bowen , Li Bo , Wang Ziyu , Gu Meng , Jia Wei , Pan Yuanming 

TITLE=Interpretable deep learning survival predictive tool for small cell lung cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 13 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1162181

DOI=10.3389/fonc.2023.1162181

ISSN=2234-943X

ABSTRACT=Background: Small cell lung cancer (SCLC) is an aggressive and almost universally lethal neoplasm. There is no accurate predictive method for its prognosis. Artificial intelligence deep learning may bring new hope.
Methods: By searching the Surveillance, Epidemiology, and End Results database (SEER), 21,093 patients’ clinical data were eventually included. Data then were divided into two groups (train dataset/ test dataset). Train dataset (diagnosed in 2010-2014, N=17296) was utilized to conduct deep learning survival model, validated by itself and test dataset (diagnosed in 2015, N=3797) in parallel. According to clinical experience, age, sex, tumor site, T, N, M, stage (7th American Joint Committee on Cancer TNM stage), tumor size, surgery, chemotherapy, radiotherapy and history of malignancy were chosen as predictive clinical features. C-index was the main indicator to evaluate model performance.
Results: The predictive model had a 0.7181 C-index (95% confidence intervals, CIs, 0.7174-0.7187) in train dataset and 0.7208 C-index (95% CIs, 0.7202-0.7215) in test dataset. These indicated that it had a reliable predictive value on OS for SCLC, so then it was packaged as a Windows software and free for doctors, researchers and patients to use.
Conclusions: Interpretable deep learning survival predictive tool for small cell lung cancer developed by this study had a reliable predictive value on their overall survival. More biomarkers may help improve the prognostic predictive performance of small cell lung cancer.