Leveraging Large Language Models to Identify Lung Cancer Patients with Unregistered World Trade Center Disaster
Julia Nancy Lo Cascio1, Nicholas Mourikis, Chinyere J Okpara
1From the NYU Grossman Long Island School of Medicine (GLISOM), Mineola, New York (J.N.L.C., N.M.); NYU Grossman School of Medicine (GSOM), New York, New York (C.J.O., R.B., F.H.); Department of Medicine, Division of Occupational Medicine, NYU GLISOM, Mineola, New York (M.W.); and Department of Medicine, NYU GLISOM, Mineola, New York (J.G.S., M.R.).
Objective:
Leveraging large language models, we identified an unregistered subpopulation of individuals with World Trade Center-related exposure and lung cancer who were not previously captured in registries, and assessed how this exposure impacted patients' disease course.
Methods:
Associations between exposure type and smoking history, cancer stage, mutation status, disease progression, and survival were statistically analyzed.
Results:
The highest proportion of never-smokers was observed among residents, compared with First Responders and Commuters (19% and 24%; P = 0.005). Residents had more than twice the risk of disease progression (Hazard Ratio (HR) = 2.14, P = 0.008) and an elevated risk of death (HR = 2.43, P = 0.03). Only EGFR mutations were significantly associated with exposure type ( P = 0.01).
Conclusions:
This work highlights that large language model can capture a greater population of World Trade Center survivors, including genetics.