Artificial Intelligence: Can It Save Lives, Hospitals and Lung Screening?

BACKGROUND Early detection is essential in lung cancer survival. Lung screening or incidental detection on unrelated imaging holds the most promise for early detection. With the large volume of imaging performed today, management of incidental pulmonary nodules can be difficult. We hypothesized an artificial intelligence (AI) tool could reliably read all imaging reports, detect and effectively triage indeterminant pulmonary nodules without adding additional personnel, helping save lives. METHODS An incidental lung nodule clinic (ILNC) was created utilizing AI and an existing nurse practitioner. Over 26 months, the software read all radiology reports visualizing any lung tissue. Nodules greater than 3 mm and considered indeterminant by the nurse practitioner were referred to the ILNC. Benign nodules in high-risk patients were offered entry into the lung screening program. RESULTS 502,632 imaging reports were analyzed, 22,136 (4.4%) had positive findings. 11,797 (2.3%) lacked follow up data. 911 (7.7%) were verified lost with 518 (4.4%) referred to the ILNC. 393 had benign nodules and accepted enrollment in the lung screening program. Mean age of enrolled patients was 61 and 53% were male. Workup included 499 diagnostic computed tomography scans, 39 positron emission tomography scans, and 27 biopsies which identified 15 total malignancies (2.9%) with 14 Lung cancers (8 stage I, 4 stage III and 2 stage IV). Treatment included 5 lobectomies and 4 stereotactic body radiation therapy. Financials were favorable. CONCLUSIONS AI software can supplement practitioners, help diagnose lung cancer earlier, save lives and generate value-based revenue for the hospital.