No abstract

No abstract

Purpose: The aim of this study was to assess racial/ethnic and socioeconomic disparities in the difference between atherosclerotic vascular disease prevalence measured by a multitask convolutional neural network (CNN) deep learning model using frontal chest radiographs (CXRs) and the prevalence reflected by administrative hierarchical condition category codes in two cohorts of patients with coronavirus disease 2019 (COVID-19). Methods: A CNN model, previously published, was trained to predict atherosclerotic disease from ambulatory frontal CXRs. The model was then validated on two cohorts of patients with COVID-19: 814 ambulatory patients from a suburban location (presenting from March 14, 2020, to October 24, 2020, the internal ambulatory cohort) and 485 hospitalized patients from an inner-city location (hospitalized from March 14, 2020, to August 12, 2020, the external hospitalized cohort). The CNN model predictions were validated against electronic health record administrative codes in both cohorts and assessed using the area under the receiver operating characteristic curve (AUC). The CXRs from the ambulatory cohort were also reviewed by two board-certified radiologists and compared with the CNN-predicted values for the same cohort to produce a receiver operating characteristic curve and the AUC. The atherosclerosis diagnosis discrepancy, D vasc , referring to the difference between the predicted value and presence or absence of the vascular disease HCC categorical code, was calculated. Linear regression was performed to determine the association of D vasc with the covariates of age, sex, race/ethnicity, language preference, and social deprivation index. Logistic regression was used to look for an association between the presence of any hierarchical condition category codes with D vasc and other covariates. Results:The CNN prediction for vascular disease from frontal CXRs in the ambulatory cohort had an AUC of 0.85 (95% confidence interval, 0.82-0.89) and in the hospitalized cohort had an AUC of 0.69 (95% confidence interval, 0.64-0.75) against the electronic health record data. In the ambulatory cohort, the consensus radiologists' reading had an AUC of 0.89 (95% confidence interval, 0.86-0.92) relative to the CNN. Multivariate linear regression of D vasc in the ambulatory cohort demonstrated significant negative associations with non-English-language preference (b ¼ À0.083, P < .05) and Black or Hispanic race/ethnicity (b ¼ À0.048, P < .05) and positive associations with age (b ¼ 0.005, P < .001) and sex (b ¼ 0.044, P < .05). For the hospitalized cohort, age was also significant (b ¼ 0.003, P < .01), as was social deprivation index (b ¼ 0.002, P < .05). The D vasc variable (odds ratio [OR], 0.34), Black or Hispanic race/ethnicity (OR, 1.58), non-English-language preference (OR, 1.74), and site (OR, 0.22) were independent predictors of having one or more hierarchical condition category codes (P < .01 for all) in the combined patient cohort.

We validate a deep learning model predicting comorbidities from frontal chest radiographs (CXRs) in patients with coronavirus disease 2019 (COVID-19) and compare the model’s performance with hierarchical condition category (HCC) and mortality outcomes in COVID-19. The model was trained and tested on 14,121 ambulatory frontal CXRs from 2010 to 2019 at a single institution, modeling select comorbidities using the value-based Medicare Advantage HCC Risk Adjustment Model. Sex, age, HCC codes, and risk adjustment factor (RAF) score were used. The model was validated on frontal CXRs from 413 ambulatory patients with COVID-19 (internal cohort) and on initial frontal CXRs from 487 COVID-19 hospitalized patients (external cohort). The discriminatory ability of the model was assessed using receiver operating characteristic (ROC) curves compared to the HCC data from electronic health records, and predicted age and RAF score were compared using correlation coefficient and absolute mean error. The model predictions were used as covariables in logistic regression models to evaluate the prediction of mortality in the external cohort. Predicted comorbidities from frontal CXRs, including diabetes with chronic complications, obesity, congestive heart failure, arrhythmias, vascular disease, and chronic obstructive pulmonary disease, had a total area under ROC curve (AUC) of 0.85 (95% CI: 0.85–0.86). The ROC AUC of predicted mortality for the model was 0.84 (95% CI,0.79–0.88) for the combined cohorts. This model using only frontal CXRs predicted select comorbidities and RAF score in both internal ambulatory and external hospitalized COVID-19 cohorts and was discriminatory of mortality, supporting its potential use in clinical decision making.

Purpose: Recent trends in US healthcare have seen growing consolidation of healthcare providers, including radiology groups, with fewer and larger radiology groups. We assessed recent trends and characteristics in radiology group network market share (NMS) across the US among Medicare beneficiaries. Methods: Using freely available datasets CareSet DocGraph Hop Teaming, Medicare Physician Compare, and Medicare Physician and Other Supplier Public Use File (PUF), all radiologists were identified and associated to group practices annually between 2014 and 2017. Radiology groups outside the US, not present in all three databases, or with only one radiologist were excluded. The annual frequency of radiological exams performed was determined from the PUF and used to calculate the percentage of magnetic resonance and computed tomography (MR/CT) imaging performed as well as the number of beneficiaries undergoing MR/CT per radiology group. Physician referrers without evaluation and management codes for office visits in the PUF file were excluded from the DocGraph file. Provider connections were geospatially mapped and plotted. The percentage of radiology group NMS was calculated as the number of patients a group received, divided by the total number of potential and actual connections, and multiplied by 100. Univariate analysis of radiology group NMS was performed against a variety of characteristics and compared using Kruskal-Wallis and Dunn tests, as appropriate. Univariate linear regression was used to assess the association between NMS and calendar year, as well as average wait time and calendar year. Multivariate linear regression was used to model the radiology group cumulative normalized percentile NMS, with multiple predictors for the year 2017. Results: Between 2014 and 2017, 1,764 unique radiology groups were identified, representing 17,879 radiologists in 2014, 18,143 radiologists in 2015, 20,915 radiologists in 2016, and 22,187 radiologists in 2017, with an average NMS per group for 2014 of 14.8%, 2015 of 14.5%, 2016 of 13.6%, and 2017 of 13.1%, demonstrating a small but statistically significant negative trend over four years (2014-2017), with a 0.6% decrease per year (P < 0.001). Average day weight across years (2014-2017) demonstrated a slight upward trend, with a 0.3% increase per year. The yearly percentage of MR/CT studies across all groups was 24.6-26.6%, with the most performed studies being chest radiography, mammography, and CT of the head without contrast. Univariate analysis of radiology group NMS was not significantly different between academic and nonacademic groups for all years (P > 0.05) but was significantly different for radiology-only versus multispecialty groups across all years (P < 0.05). Multivariate linear regression on 2017 data demonstrated statistically significant independent negative predictors for NMS including larger group size (50-99, >=100), higher practice MR/CT imaging percentage, and South location, while the increasing log of the number of beneficiaries undergoing MR/CT was a positive predictor, with an adjusted R-squared of 0.56 (all P < 0.01). Conclusions: Among Medicare beneficiaries from 2014 to 2017, radiology group NMS (mean 14%, median 9.0%, IQR 4-19.2%), slightly decreased over time by 0.6% per year, despite occurring during a period of widespread practice consolidation. The negative predictors for NMS at the group level included larger group size, South region, increased average wait time, and higher MR/CT imaging percentage, while the positive predictor was the increased number of beneficiaries undergoing MR/CT. Of these predictors, radiology groups are most likely to increase NMS by decreasing average wait times.