Yield of Screening for COVID-19 in Asymptomatic Patients Before Elective or Emergency Surgery Using Chest CT and RT-PCR (SCOUT): Multicenter Study.

OBJECTIVE: To determine the yield of preoperative screening for COVID-19 with chest CT and RT-PCR in patients without COVID-19 symptoms. SUMMARY OF BACKGROUND DATA: Many centers are currently screening surgical patients for COVID-19 using either chest CT, RT-PCR or both, due to the risk for worsened surgical outcomes and nosocomial spread. The optimal design and yield of such a strategy are currently unknown. METHODS: This multicenter study included consecutive adult patients without COVID-19 symptoms who underwent preoperative screening using chest CT and RT-PCR before elective or emergency surgery under general anesthesia. RESULTS: A total of 2093 patients without COVID-19 symptoms were included in 14 participating centers; 1224 were screened by CT and RT-PCR and 869 by chest CT only. The positive yield of screening using a combination of chest CT and RT-PCR was 1.5% [95% confidence interval (CI): 0.8-2.1]. Individual yields were 0.7% (95% CI: 0.2-1.1) for chest CT and 1.1% (95% CI: 0.6-1.7) for RT-PCR; the incremental yield of chest CT was 0.4%. In relation to COVID-19 community prevalence, up to ∼6% positive RT-PCR was found for a daily hospital admission rate >1.5 per 100,000 inhabitants, and around 1.0% for lower prevalence. CONCLUSIONS: One in every 100 patients without COVID-19 symptoms tested positive for SARS-CoV-2 with RT-PCR; this yield increased in conjunction with community prevalence. The added value of chest CT was limited. Preoperative screening allowed us to take adequate precautions for SARS-CoV-2 positive patients in a surgical population, whereas negative patients needed only routine procedures.

Post-Structuring Radiology Reports of Breast Cancer Patients for Clinical Quality Assurance.

Hospitals often set protocols based on well defined standards to maintain the quality of patient reports. To ensure that the clinicians conform to the protocols, quality assurance of these reports is needed. Patient reports are currently written in free-text format, which complicates the task of quality assurance. In this paper, we present a machine learning based natural language processing system for automatic quality assurance of radiology reports on breast cancer. This is achieved in three steps: we i) identify the top-level structure (headings) of the report, ii) classify the report content into the top-level headings, and iii) convert the free-text detailed findings in the report to a semi-structured format (post-structuring). Top level structure and content of report were predicted with an F1 score of 0.97 and 0.94, respectively, using Support Vector Machine (SVM) classifiers. For automatic structuring, our proposed hierarchical Conditional Random Field (CRF) outperformed the baseline CRF with an F1 score of 0.78 versus 0.71. The determined structure of the report is represented in semi-structured XML format of the free-text report, which helps to easily visualize the conformance of the findings to the protocols. This format also allows easy extraction of specific information for other purposes such as search, evaluation, and research.