Clinical Impact and Generalizability of a Computer-Assisted Diagnostic Tool to Risk-Stratify Lung Nodules With CT.
- Department of Medical Imaging, University of Saskatchewan, Saskatoon, Canada; Scientific Director of the National Medical Imaging Clinic in Saskatoon.
- Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, Washington.
- Department of Medical Imaging, University of Saskatchewan, Saskatoon, Canada.
- RevealDx, Seattle, Washington.
- Professor and Vice Chair, Department of Diagnostic Radiology, University of Maryland School of Medicine; Chief of Radiology and Nuclear Medicine for the Veterans Affairs Maryland Healthcare System; and Fellow of the American College of Radiology.
- Department of Medical Imaging, University of Saskatchewan, Saskatoon, Canada; recently retired as Physician Executive, Provincial Programs for the Saskatchewan Health Authority.
- Clinical Research Division, Fred Hutchinson Cancer Research Center, Seattle, Washington; Division of Pulmonary, Critical Care and Sleep Medicine, University of Washington School of Medicine, Seattle, Washington.
- Chief Technology Officer, RevealDx, Seattle, Washington. Electronic address: email@example.com.
OBJECTIVE: To evaluate whether an imaging classifier for radiology practice can improve lung nodule classification and follow-up.
METHODS: A machine learning classifier was developed and trained using imaging data from the National Lung Screening Trial (NSLT) to produce a malignancy risk score (malignancy Similarity Index [mSI]) for individual lung nodules. In addition to NLST cohorts, external cohorts were developed from a tertiary referral lung cancer screening program data set, and an external nonscreening data set of all nodules detected on CT. Performance of the mSI combined with Lung-RADS was compared with Lung-RADS alone and the Mayo and Brock risk calculators.
RESULTS: We analyzed 963 subjects and 1,331 nodules across these cohorts. The mSi was comparable in accuracy (area under the curve = 0.89) to existing clinical risk models (area under the curve = 0.86-0.88) and independently predictive in the NLST cohort of 704 nodules. When compared with Lung-RADS, the mSi significantly increased sensitivity across all cohorts (25%-117%), with significant increases in specificity in the screening cohorts (17%-33%). When used in conjunction with Lung-RADS, use of mSI would result in earlier diagnoses and reduced follow-up across cohorts, including the potential for early diagnosis in 42% of malignant NLST nodules from prior-year CT scans.
CONCLUSION: A computer-assisted diagnosis software improved risk classification from chest CTs of screening and incidentally detected lung nodules compared with Lung-RADS. mSI added predictive value independent of existing radiological and clinical variables. These results suggest the generalizability and potential clinical impact of a tool that is straightforward to implement in practice.