RESUMO
PURPOSE: To develop a model to estimate lung cancer risk using lung cancer screening CT and clinical data elements (CDEs) without manual reading efforts. MATERIALS AND METHODS: Two screening cohorts were retrospectively studied: the National Lung Screening Trial (NLST; participants enrolled between August 2002 and April 2004) and the Vanderbilt Lung Screening Program (VLSP; participants enrolled between 2015 and 2018). Fivefold cross-validation using the NLST dataset was used for initial development and assessment of the co-learning model using whole CT scans and CDEs. The VLSP dataset was used for external testing of the developed model. Area under the receiver operating characteristic curve (AUC) and area under the precision-recall curve were used to measure the performance of the model. The developed model was compared with published risk-prediction models that used only CDEs or imaging data alone. The Brock model was also included for comparison by imputing missing values for patients without a dominant pulmonary nodule. RESULTS: A total of 23 505 patients from the NLST (mean age, 62 years ± 5 [standard deviation]; 13 838 men, 9667 women) and 147 patients from the VLSP (mean age, 65 years ± 5; 82 men, 65 women) were included. Using cross-validation on the NLST dataset, the AUC of the proposed co-learning model (AUC, 0.88) was higher than the published models predicted with CDEs only (AUC, 0.69; P < .05) and with images only (AUC, 0.86; P < .05). Additionally, using the external VLSP test dataset, the co-learning model had a higher performance than each of the published individual models (AUC, 0.91 [co-learning] vs 0.59 [CDE-only] and 0.88 [image-only]; P < .05 for both comparisons). CONCLUSION: The proposed co-learning predictive model combining chest CT images and CDEs had a higher performance for lung cancer risk prediction than models that contained only CDE or only image data; the proposed model also had a higher performance than the Brock model.Keywords: Computer-aided Diagnosis (CAD), CT, Lung, Thorax Supplemental material is available for this article. © RSNA, 2021.
RESUMO
BACKGROUND: Granulomas caused by infectious lung diseases can present as indeterminate pulmonary nodules (IPN). This study aims to validate an enzyme immunoassay (EIA) for Histoplasma immunoglobulin G (IgG) and immunoglobulin M (IgM) for diagnosing benign IPN in areas with endemic histoplasmosis. METHODS: Prospectively collected serum samples from patients at Vanderbilt University Medical Center (VUMC [n = 204]), University of Pittsburgh Medical Center (n = 71), and University of Cincinnati (n = 51) with IPN measuring 6 to 30 mm were analyzed for Histoplasma IgG and IgM with EIA. Diagnostic test characteristics were compared with results from the VUMC pilot cohort (n = 127). A multivariable logistic regression model was developed to predict granuloma in IPN. RESULTS: Cancer prevalence varied by cohort: VUMC pilot 60%, VUMC validation 65%, University of Pittsburgh Medical Center 35%, and University of Cincinnati 75%. Across all cohorts, 19% of patients had positive IgG titers, 5% had positive IgM, and 3% had positive both IgG and IgM. Of patients with benign disease, 33% were positive for at least one antibody. All patients positive for both IgG and IgM antibodies at acute infection levels had benign disease (n = 13), with a positive predictive value of 100%. The prediction model for granuloma in IPN demonstrated an area under the receiver-operating characteristics curve of 0.84 and Brier score of 0.10. CONCLUSIONS: This study confirmed that Histoplasma EIA testing can be useful for diagnosing benign IPN in areas with endemic histoplasmosis in a population at high risk for lung cancer. Integrating Histoplasma EIA testing into the current diagnostic algorithm where histoplasmosis is endemic could improve management of IPN and potentially decrease unnecessary invasive biopsies.
