Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster Display session

180P - Assessment of an artificial intelligence (AI) solution to support a lung nodule program

Date

28 Mar 2025

Session

Poster Display session

Presenters

K. Adam Lee

Citation

Journal of Thoracic Oncology (2025) 20 (3): S121-S122. 10.1016/S1556-0864(25)00632-X

Authors

K..A. Lee, J. Dubois, L. Silas

Author affiliations

  • Jupiter Medical Center, Jupiter/US

Resources

This content is available to ESMO members and event participants.

Abstract 180P

Background

The aim of the study was to assess the impact of integrating an AI solution into our lung nodule program on clinic volumes, patient management, and outcomes.

Methods

We integrated and FDA-cleared AI solution for automated patient identification, tracking and risk stratification into our lung nodule clinic. The AI solution analysed all CT radiology reports and automatically identified the ones with reported lung nodules. Identified patients were contacted by a dedicated nurse navigator and followed. Additionally, the AI solution offered a malignancy score to help risk stratify the lung nodule during clinical evaluation. The number of new nodule patients visiting the clinic, the number of biopsies and surgeries performed, and the numbers of lung cancers diagnosed was compared before and after implementation of the AI tool. For confirmed cancer patients, we compared the stage distribution at diagnosis before and after integration of the AI into our nodule program.

Results

Throughout the 4.5 months after AI implementation, 16.9 new patients per month were seen in our nodule clinic, compared to 12.4 in the same period a year earlier, prior to AI use. The number of invasive diagnostic procedures (biopsies and surgeries) performed on these patients per month increased from 5.8 before AI to 7.6 with AI. Of the 16 confirmed lung cancer patients, 10 (63%)were diagnosed in Stage I with the AI, compared to 7 out of 14 (50%) before AI implementation. The full stage distribution is presented in table.

Table 180P
StageBefore AI%With AI%
I7501063
II32116
III0000
IV321213
Unknown17319
Total1416

Conclusions

The Integration of an AI-based automatic identification and risk stratification tool for lung nodule patients into our nodule clinic led to higher patient volumes and helped treat lung cancer patients at early stages, where patients have the greatest chance of long-term survival.

Legal entity responsible for the study

K.A. Lee.

Funding

Has not received any funding.

Disclosure

K.A. Lee: Financial Interests, Personal, Speaker’s Bureau: AstraZeneca. All other authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.