Transfer Learning for Automated COVID-19 B-Line Classification in Lung Ultrasound.

Lung ultrasound (LUS) as a diagnostic tool is gaining support for its role in the diagnosis and management of COVID-19 and a number of other lung pathologies. B-lines are a predominant feature in COVID-19, however LUS requires a skilled clinician to interpret findings. To facilitate the interpretation, our main objective was to develop automated methods to classify B-lines as pathologic vs. normal. We developed transfer learning models based on ResNet networks to classify B-lines as pathologic (at least 3 B-lines per lung field) vs. normal using COVID-19 LUS data. Assessment of B-line severity on a 0-4 multi-class scale was also explored. For binary B-line classification, at the frame-level, all ResNet models pretrained with ImageNet yielded higher performance than the baseline nonpretrained ResNet-18. Pretrained ResNet-18 has the best Equal Error Rate (EER) of 9.1% vs the baseline of 11.9%. At the clip-level, all pretrained network models resulted in better Cohen's kappa agreement (linear-weighted) and clip score accuracy, with the pretrained ResNet-18 having the best Cohen's kappa of 0.815 [95% CI: 0.804-0.826], and ResNet-101 the best clip scoring accuracy of 93.6%. Similar results were shown for multi-class scoring, where pretrained network models outperformed the baseline model. A class activation map is also presented to guide clinicians in interpreting LUS findings. Future work aims to further improve the multi-class assessment for severity of B-lines with a more diverse LUS dataset.

Racial equity in linkage to inpatient opioid use disorder treatment in patients that received emergency care.

OBJECTIVES: Opioid use disorder (OUD) is a national epidemic, and Black and Hispanic patients are less likely to receive treatment when compared to white patients. In this study, race was used as a proxy to assess potential effects of racism on the referral process for OUD treatment. Our primary aim was to examine whether Black or Hispanic patients experienced increased barriers to inpatient OUD detoxification (detox) placement at a community-integrated, substance use disorder support program based in an emergency department (ED). Our secondary aim was to determine if Black and Hispanic patients were more likely to have >3 referrals. METHODS: This retrospective cohort study was conducted at a large urban safety-net hospital and included patients seen in the ED from July 2018 to September 2019 with ICD-10 codes for an opioid-related visit and who sought placement to inpatient detox. A generalized linear mixed model controlling for multiple visits, age, sex, insurance, time, day of week, and time of year was used to assess the association between race/ethnicity and hypothesized barriers to placement. The proportion of patients with >3 visits for referral to inpatient detox was compared between Black and Hispanic patients and white patients using a chi-squared test. RESULTS: We identified 1733 encounters from 782 unique patients seeking connection to inpatient detox for OUD. Of the 1733 encounters, 45% were among Black and Hispanic patients. Hispanic and Black men had significantly lower odds of having a barrier to inpatient OUD detox than white men (OR = 0.734, 95% CI 0.542-0.995). No significant difference was found for Hispanic and Black women (OR = 1.212, 95% CI 0.705-2.082). More Black and Hispanic patients experienced >3 referrals to inpatient detox compared to white patients (19.2% vs 12.9%, p = 0.016). CONCLUSIONS: This study suggests in the context of near-universal health insurance coverage, an ED-based OUD support program staffed by diverse community members can mitigate inequities in access to inpatient detox. However, the increased number of ED visits for OUD detox placement by Black and Hispanic patients suggests racial inequities in OUD treatment exist after linkage to care. Additional research should explore the causes, specifically structural and interpersonal racism, and determine solutions to address racial inequities in detox placement as well as maintenance in treatment programs.

Point-of-care Lung Ultrasound Is More Sensitive than Chest Radiograph for Evaluation of COVID-19.

INTRODUCTION: Current recommendations for diagnostic imaging for moderately to severely ill patients with suspected coronavirus disease 2019 (COVID-19) include chest radiograph (CXR). Our primary objective was to determine whether lung ultrasound (LUS) B-lines, when excluding patients with alternative etiologies for B-lines, are more sensitive for the associated diagnosis of COVID-19 than CXR. METHODS: This was a retrospective cohort study of all patients who presented to a single, academic emergency department in the United States between March 20 and April 6, 2020, and received LUS, CXR, and viral testing for COVID-19 as part of their diagnostic evaluation. The primary objective was to estimate the test characteristics of both LUS B-lines and CXR for the associated diagnosis of COVID-19. Our secondary objective was to evaluate the proportion of patients with COVID-19 that have secondary LUS findings of pleural abnormalities and subpleural consolidations. RESULTS: We identified 43 patients who underwent both LUS and CXR and were tested for COVID-19. Of these, 27/43 (63%) tested positive. LUS was more sensitive (88.9%, 95% confidence interval (CI), 71.1-97.0) for the associated diagnosis of COVID-19 than CXR (51.9%, 95% CI, 34.0-69.3; p = 0.013). LUS and CXR specificity were 56.3% (95% CI, 33.2-76.9) and 75.0% (95% CI, 50.0-90.3), respectively (p = 0.453). Secondary LUS findings of patients with COVID-19 demonstrated 21/27 (77.8%) had pleural abnormalities and 10/27 (37%) had subpleural consolidations. CONCLUSION: Among patients who underwent LUS and CXR, LUS was found to have a higher sensitivity than CXR for the evaluation of COVID-19. This data could have important implications as an aid in the diagnostic evaluation of COVID-19, particularly where viral testing is not available or restricted. If generalizable, future directions would include defining how to incorporate LUS into clinical management and its role in screening lower-risk populations.