Skip to Main Content

An official website of the United States government

Development of a Nodule Risk Calculator using NLST Data

Principal Investigator
Name
Christopher Towe
Degrees
MD
Institution
University Hospitals
Position Title
Associate Professor
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-1086
Initial CDAS Request Approval
Jun 15, 2023
Title
Development of a Nodule Risk Calculator using NLST Data
Summary
We propose to extract data from the "participant database" and "Spiral CT Abnormalities" to identify risk factors and nodule characteristics, respectively. The extracted data will be used to develop a risk model using multiple methods, including logistic regression and machine learning techniques. The goal is to create a tool that can accurately predict the risk of lung nodules, thereby aiding in early detection and treatment of lung cancer.
Aims

Data Extraction: Extract relevant data from the "participant database" and "Spiral CT Abnormalities" of the National Lung Screening Trial (NLST). This data will include risk factors and nodule characteristics that are essential for the development of the nodule risk calculator.

Risk Model Development: Develop a comprehensive risk model using multiple methods, including logistic regression and machine learning techniques. The model will be designed to accurately predict the risk of lung nodules based on the extracted data.

Risk Calculator Creation: Use the developed risk model to create a user-friendly nodule risk calculator. This tool will provide healthcare professionals and patients with an easy-to-use method for assessing lung nodule risk.

Model Validation: Validate the accuracy and reliability of the risk model and the nodule risk calculator using a subset of the NLST data. This will ensure that the tool is reliable and can accurately predict lung nodule risk.

Collaborators

Kunaal Sarnaik - Univeristy Hospitals
Aria Bassiri - University Hospitals