Optimizing lung cancer detection with the power of AI

Leveraging opportunity in the incidental pulmonary finding

Amid the chaos of emergency department (ED) visits, a remarkable opportunity quietly presents itself. Studies show that approximately thirty percent of all chest CT scans contain one or more pulmonary nodules, unexpected discoveries that can lead to early lung cancer detection.^[2] While not all incidental pulmonary nodules signify lung cancer, statistics show that early identification can significantly increase the chances of survival and improved long-term outcomes.^[3] Additionally, chest CT is frequently used in the ED and has been reported to be performed in 15.8 percent of ED visits.^[4]

However, in a study evaluating the use of chest CT in the ED, researchers found that CT imaging of the chest identified significantly more clinically relevant findings that affected clinical decision-making than those from other imaging modalities that were used. The study revealed lung cancer as one of the predominant malignancies identified with low-dose CT in the patient sample, at 32.4 percent of the total.^[5] While the use of advanced imaging techniques such as CT in the ED has been scrutinized, their underutilization may lead to missed diagnoses. ^[6]

Advancing AI applications in lung cancer detection

AI applications in healthcare have experienced successful implementations across several clinical areas, such as disease detection, diagnosis, and risk stratification. According to research, AI can play an important role in the imaging inspection, histopathology examination, and genomics inspection of lung cancers. This heterogeneity makes it one of the best fields for AI application.^[7] Optellum, a lung health company, is helping to revolutionize lung cancer detection by using AI to identify cancerous nodules earlier and to provide patients with the chance of being treated earlier.

The Optellum Virtual Nodule Clinic AI is trained using multiple databases of CT scans of patients’ lungs, as well as the eventual diagnoses from many healthcare systems in the UK, US, and Europe, to differentiate between malignant and benign lung nodules. Using a proprietary algorithm, Optellum’s system applies neural network analytics to turn a standard CT scan into a Lung Cancer Prediction score from one to ten, with ten indicating the highest risk of malignancy for each nodule. The scoring process takes mere seconds. The score represents a personalized risk of malignancy.

Using this AI application, clinicians are empowered to drive presymptomatic early diagnosis for someone who undergoes a CT scan for any reason.

Collaborating for broad impact

Advances in CT technology have driven its widespread adoption in many clinical areas. Specifically, CT scans have become indispensable in assessing patients quickly and accurately in the ED, empowering clinicians to make critical decisions swiftly. The potential from the millions of high-quality CT scans already being performed across healthcare created an opportunity to forge a new path. Utilizing Optellum’s solution to identify and analyze incidental pulmonary lung nodules found with high-quality, detailed CT images can enable clinicians the ability to characterize, assess, and communicate patient risk so that patients can get the follow-up care they need, which is often left unaddressed^.[8]  This innovative frontier led Optellum and GE HealthCare to create a collaboration with the goal of making a global impact on lung cancer detection and care. Together, they aim to make the AI algorithm available in healthcare facilities. It's a strategic move that helps to transform the landscape of lung cancer detection.

By making the AI tool accessible with widespread CT scanners, this partnership not only enhances early detection but also extends the reach of improved care to a broader population, even beyond just those at higher risk. It's a pivotal step towards realizing the full potential of CT and AI in improving lung cancer detection.

Unlocking a promising future for lung cancer patients

In the face of a silent epidemic, innovation and collaboration have unlocked new possibilities for earlier lung cancer detection. With AI-powered assistance and the widespread availability and utilization of CT imaging, hope can be revitalized for lung cancer patients.

Disclaimer

Not all products or features are available in all geographies. Check with your local GE HealthCare representative for availability in your country.

References

[1] https://www.lung.org/media/press-releases/state-of-lung-cancer-2022. Accessed November 8, 2023.

[2] https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5809217. Accessed November 7, 2023.

[3] Lung cancer CT scans have already saved more than 10,000 US lives. HealthDay. Published March 31, 2022. https://consumer.healthday.com/b-3-31-lung-cancer-ct-scans-have-already-saved-more-than-10000-u-s-lives-2657058255.html. Accessed November 7, 2023.

[4] Fatihoglu, E., Aydin, S., Gokharman, F. D., Ece, B., & Kosar, P. N. (2016). X-ray Use in Chest Imaging in Emergency Department on the Basis of Cost and Effectiveness. Academic Radiology, 23(10), 1239-1245. https://doi.org/10.1016/j.acra.2016.05.008

[5] Sylvester PJ, Stewart J, Schoeffler A, Aalberg J, Hunold KM, Caterino JM, Bischof JJ. Utility of Emergency Department Chest Imaging in Patients with Cancer: A Descriptive Study. J Emerg Med. 2020 Sep;59(3):396-402. doi: 10.1016/j.jemermed.2020.05.007. Epub 2020 Jun 24. PMID: 32593580; PMCID: PMC7606423.

[6] Tung M, Sharma R, Hinson JS, Nothelle S, Pannikottu J, Segal JB. Factors associated with imaging overuse in the emergency department: A systematic review. Am J Emerg Med. 2018 Feb;36(2):301-309. doi: 10.1016/j.ajem.2017.10.049. Epub 2017 Oct 25. PMID: 29100783; PMCID: PMC5815889.

[7] Chiu HY, Chao HS, Chen YM. Application of artificial intelligence in lung cancer. Cancers. March 8, 2022;14(6):1370. doi: 10.3390/cancers14061370.

[8] https://karger.com/res/article/101/11/1024/829093/Incidental-Pulmonary-Nodules-What-Do-We-Know-in