(Learn more about this study)
Initial CDAS Request Approval
Oct 24, 2023
A Machine Learning Model to Identify Patients at Risk for Developing Small cell lung cancer
Lung cancer is a leading cause of cancer-related death globally. Early detection is crucial for improving patient outcomes. While low-dose CT (LDCT) screening has shown promise, a substantial portion of lung cancer patients do not meet the current screening criteria. The PLCOm2012 model, based on traditional statistical methods, has demonstrated effectiveness in identifying individuals at risk for lung cancer. This study aims to employ machine learning techniques to develop a novel risk model for predicting small cell lung cancer (SCLC) risk using the PLCO lung dataset. The study will assess the performance of this machine learning model by comparing its accuracy in lung cancer detection with the SEER model. Additionally, the study will explore whether combining the machine learning model with SEER data can further enhance the accuracy of lung cancer detection. Summary, this research seeks to advance the prediction of SCLC risk by utilizing machine learning methods, evaluate the model's performance against the SEER model, and potentially improve the accuracy of early SCLC detection for better patient outcomes.
Aim 1: To develop a machine learning based risk model that would predict for SCLC risk in the PLCO lung dataset. Compare detection of lung cancer with the SEER model. Further identify if combining with SEER data would enhance the accuracy of lung cancer detection.
Aim 2: To validate the deep learning risk based model in an external dataset: hospital cohort, and compare with SEER model.
Dr. Jianya,Zhou, The First Affiliated Hospital, School of Medicine, Zhejiang University