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

289P - Early lung cancer detection using artificial intelligence on chest X-rays: The budget impact of implementing incidental pulmonary nodule detection

Date

28 Mar 2025

Session

Poster Display session

Presenters

Bert Sloof

Citation

Journal of Thoracic Oncology (2025) 20 (3): S163-S180. 10.1016/S1556-0864(25)00632-X

Authors

B. Sloof1, B. Dirodi2, A. Saha3

Author affiliations

  • 1 UMCG - University Medical Center Groningen, Groningen/NL
  • 2 AstraZeneca Plc, Baar/CH
  • 3 AstraZeneca Sdn. Bhd., Petaling Jaya/MY

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 289P

Background

Lung cancer can be treated curatively when diagnosed in the earlier stages. However, the symptoms are not commonly recognized by patients, resulting in late-stage diagnosis where survival rates are low. In low and middle income countries (LMICs) rates of lung cancer are increasing and improved methods of early detection are required to limit the burden of lung cancer. qXR® is an artificial intelligence (AI) software developed for the detection of abnormalities such as lung nodules on chest X-rays, currently the most commonly requested diagnostic test. The use of incidental pulmonary nodule detection could result in additional early-stage lung cancer diagnoses, requiring fewer resources compared to treatment in the late stages.

Methods

This study aimed to determine the impact of implementing AI at a population level for incidental pulmonary nodule detection on the budget of the healthcare system in Vietnam. A budget impact model with a time horizon of five years was developed, which compared the implementation of qXR to the current diagnostic process. A decision-tree design was used to determine the number of patients identified by qXR and their stage at diagnosis, while the national incidence and stage distribution are used for the current diagnostic process.

Results

The model predicts that the implementation of qXR results in 3,155 additional lung cancer diagnoses and 4,742 premature deaths prevented. While the additional diagnoses result in additional expenditures in the first year after implementation, the shift to early stages produce savings in subsequent years.

Conclusions

After five years the savings have counteracted the initial additional expenditures, making the implementation of qXR a costneutral intervention in Vietnam. In the future, this model will be used to assess the budget impact of qXR in other countries.

Legal entity responsible for the study

Qure.ai.

Funding

AstraZeneca Plc.

Disclosure

All 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.