# Translating Molecular and Clinical Data to Population Lung Cancer Risk Assessment > **NIH NIH U19** · BAYLOR COLLEGE OF MEDICINE · 2021 · $496,067 ## Abstract Project Summary Lung cancer continues to be the most common cancer and reduction of lung cancer related death is a global priority. The National Lung Screening Trial (NLST) reported that the low-dose computed tomography (LDCT) screening reduced the lung cancer mortality by 20%, with a trade-off of more than 95% of false positive results. This underlined our need for a much improved risk prediction model and higher screening efficiency to balance the benefits and potential harms. Although there have been substantial efforts in establishing lung cancer risk prediction models, none have taken all aspects into account and the joint performance of all predictors remains unknown. For those with CT nodules, currently there is a wide range of clinical protocols on how they are managed, from watchful waiting to invasive diagnostic procedures. With the usage of LDCT scans rapidly growing following the NLST report, there is an urgent need to address the issues of (i) who should be recommended for screening and (ii) what to do when a nodule is found. Our research team is in the unique position to conduct this much needed work as we have already established extensive resources for the data elements needed being the lead investigators of the three lung cancer consortia (International Lung Cancer Consortium, Transdisciplinary Research in Cancer of Lung, and Lung Cancer Cohort Consortium), and have established collaborations with the lung cancer CT screening programs in the US, Canada and Europe. The overall goal of this project is to translate the epidemiological, molecular and clinical data into lung cancer risk assessment and to improve nodule assessment. Specifically, we will (i) establish an integrated risk prediction model to identify individuals at high risk of lung cancer, combining personal health and exposure history, targeted molecular and genomic profile and lung function data based lung cancer CT screening populations in US, Canada and Europe based on a total of 950 CT-detected lung cancer patients from cohorts of 46,057 screening individuals; and (ii) establish a comprehensive nodule assessment models for individuals with LDCT-detected non-calcified pulmonary nodules based on both 2 dimensional-based and 3D volume and radiomics-based probability models. We will compare the model performance with the existing classification system such as Lung-RADS and conduct net benefit and decision curve analysis to assess their clinical usefulness. These models will be very valuable for the general public, clinicians, researchers and health administrators. It will increase the efficiency of lung cancer LDCT screening, and reduce unnecessary workup (and patient anxiety) for those who were found to have LDCT-detected pulmonary non-calcified nodules. The impact of this project will be wide-spread in our community. ## Key facts - **NIH application ID:** 10135969 - **Project number:** 5U19CA203654-05 - **Recipient organization:** BAYLOR COLLEGE OF MEDICINE - **Principal Investigator:** Rayjean J. Hung - **Activity code:** U19 (R01, R21, SBIR, etc.) - **Funding institute:** NIH - **Fiscal year:** 2021 - **Award amount:** $496,067 - **Award type:** 5 - **Project period:** 2017-08-01 → 2023-03-31 ## Primary source NIH RePORTER: https://reporter.nih.gov/project-details/10135969 ## Citation > US National Institutes of Health, RePORTER application 10135969, Translating Molecular and Clinical Data to Population Lung Cancer Risk Assessment (5U19CA203654-05). Retrieved via AI Analytics 2026-05-22 from https://api.ai-analytics.org/grant/nih/10135969. Licensed CC0. --- *[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*