Trends in oncological imaging during the COVID-19 pandemic through the vaccination era.

BACKGROUND: This study examines the impact that the COVID-19 pandemic has had on computed tomography (CT)-based oncologic imaging utilization. METHODS: We retrospectively analyzed cancer-related CT scans during four time periods: pre-COVID (1/5/20-3/14/20), COVID peak (3/15/20-5/2/20), post-COVID peak (5/3/20-12/19/20), and vaccination period (12/20/20-10/30/21). We analyzed CTs by imaging indication, setting, and hospital type. Using percentage decrease computation and Student's t-test, we calculated the change in mean number of weekly cancer-related CTs for all periods compared to the baseline pre-COVID period. This study was performed at a single academic medical center and three affiliated hospitals. RESULTS: During the COVID peak, mean CTs decreased (-43.0%, p < 0.001), with CTs for (1) cancer screening, (2) initial workup, (3) cancer follow-up, and (4) scheduled surveillance of previously treated cancer dropping by 81.8%, 56.3%, 31.7%, and 45.8%, respectively (p < 0.001). During the post-COVID peak period, cancer screenings and initial workup CTs did not return to prepandemic imaging volumes (-11.4%, p = 0.028; -20.9%, p = 0.024). The ED saw increases in weekly CTs compared to prepandemic levels (+31.9%, p = 0.008), driven by increases in cancer follow-up CTs (+56.3%, p < 0.001). In the vaccination period, cancer screening CTs did not recover to baseline (-13.5%, p = 0.002) and initial cancer workup CTs doubled (+100.0%, p < 0.001). The ED experienced increased cancer-related CTs (+75.9%, p < 0.001), driven by cancer follow-up CTs (+143.2%, p < 0.001) and initial workups (+46.9%, p = 0.007). CONCLUSIONS AND RELEVANCE: The pandemic continues to impact cancer care. We observed significant declines in cancer screening CTs through the end of 2021. Concurrently, we observed a 2× increase in initial cancer workup CTs and a 2.4× increase in cancer follow-up CTs in the ED during the vaccination period, suggesting a boom of new cancers and more cancer examinations associated with emergency level acute care.

Prediction of oxygen requirement in patients with COVID-19 using a pre-trained chest radiograph xAI model: efficient development of auditable risk prediction models via a fine-tuning approach.

Risk prediction requires comprehensive integration of clinical information and concurrent radiological findings. We present an upgraded chest radiograph (CXR) explainable artificial intelligence (xAI) model, which was trained on 241,723 well-annotated CXRs obtained prior to the onset of the COVID-19 pandemic. Mean area under the receiver operating characteristic curve (AUROC) for detection of 20 radiographic features was 0.955 (95% CI 0.938-0.955) on PA view and 0.909 (95% CI 0.890-0.925) on AP view. Coexistent and correlated radiographic findings are displayed in an interpretation table, and calibrated classifier confidence is displayed on an AI scoreboard. Retrieval of similar feature patches and comparable CXRs from a Model-Derived Atlas provides justification for model predictions. To demonstrate the feasibility of a fine-tuning approach for efficient and scalable development of xAI risk prediction models, we applied our CXR xAI model, in combination with clinical information, to predict oxygen requirement in COVID-19 patients. Prediction accuracy for high flow oxygen (HFO) and mechanical ventilation (MV) was 0.953 and 0.934 at 24 h and 0.932 and 0.836 at 72 h from the time of emergency department (ED) admission, respectively. Our CXR xAI model is auditable and captures key pathophysiological manifestations of cardiorespiratory diseases and cardiothoracic comorbidities. This model can be efficiently and broadly applied via a fine-tuning approach to provide fully automated risk and outcome predictions in various clinical scenarios in real-world practice.

Trends in cancer imaging by indication, care setting, and hospital type during the COVID-19 pandemic and recovery at four hospitals in Massachusetts.

BACKGROUND: We aimed to investigate the effects of COVID-19 on computed tomography (CT) imaging of cancer. METHODS: Cancer-related CTs performed at one academic hospital and three affiliated community hospitals in Massachusetts were retrospectively analyzed. Three periods of 2020 were considered as follows: pre-COVID-19 (1/5/20-3/14/20), COVID-19 peak (3/15/20-5/2/20), and post-COVID-19 peak (5/3/20-11/14/20). 15 March 2020 was the day a state of emergency was declared in MA; 3 May 2020 was the day our hospitals resumed to non-urgent imaging. The volumes were assessed by (1) Imaging indication: cancer screening, initial workup, active cancer, and surveillance; (2) Care setting: outpatient and inpatient, ED; (3) Hospital type: quaternary academic center (QAC), university-affiliated community hospital (UACH), and sole community hospitals (SCHs). RESULTS: During the COVID-19 peak, a significant drop in CT volumes was observed (-42.2%, p < 0.0001), with cancer screening, initial workup, active cancer, and cancer surveillance declining by 81.7%, 54.8%, 30.7%, and 44.7%, respectively (p < 0.0001). In the post-COVID-19 peak period, cancer screening and initial workup CTs did not recover (-11.7%, p = 0.037; -20.0%, p = 0.031), especially in the outpatient setting. CT volumes for active cancer recovered, but inconsistently across hospital types: the QAC experienced a 9.4% decline (p = 0.022) and the UACH a 41.5% increase (p < 0.001). Outpatient CTs recovered after the COVID-19 peak, but with a shift in utilization away from the QAC (-8.7%, p = 0.020) toward the UACH (+13.3%, p = 0.013). Inpatient and ED-based oncologic CTs increased post-peak (+20.0%, p = 0.004 and +33.2%, p = 0.009, respectively). CONCLUSIONS: Cancer imaging was severely impacted during the COVID-19 pandemic. CTs for cancer screening and initial workup did not recover to pre-COVID-19 levels well into 2020, a finding that suggests more patients with advanced cancers may present in the future. A redistribution of imaging utilization away from the QAC and outpatient settings, toward the community hospitals and inpatient setting/ED was observed.

Increased per-patient imaging utilization in an emergency department setting during COVID-19.

INTRODUCTION: COVID-19 has resulted in decreases in absolute imaging volumes, however imaging utilization on a per-patient basis has not been reported. Here we compare per-patient imaging utilization, characterized by imaging studies and work relative value units (wRVUs), in an emergency department (ED) during a COVID-19 surge to the same period in 2019. METHODS: This retrospective study included patients presenting to the ED from April 1-May 1, 2020 and 2019. Patients were stratified into three primary subgroups: all patients (n = 9580, n = 5686), patients presenting with respiratory complaints (n = 1373, n = 2193), and patients presenting without respiratory complaints (n = 8207, n = 3493). The primary outcome was imaging studies/patient and wRVU/patient. Secondary analysis was by disposition and COVID status. Comparisons were via the Wilcoxon rank-sum or Chi-squared tests. RESULTS: The total patients, imaging exams, and wRVUs during the 2020 and 2019 periods were 5686 and 9580 (-41%), 6624 and 8765 (-24%), and 4988 and 7818 (-36%), respectively, and the percentage patients receiving any imaging was 67% and 51%, respectively (p < .0001). In 2020 there was a 170% relative increase in patients presenting with respiratory complaints. In 2020, patients without respiratory complaints generated 24% more wRVU/patient (p < .0001) and 33% more studies/patient (p < .0001), highlighted by 38% more CTs/patient. CONCLUSION: We report increased per-patient imaging utilization in an emergency department during COVID-19, particularly in patients without respiratory complaints.

Automated tracking of emergency department abdominal CT findings during the COVID-19 pandemic using natural language processing.

PURPOSE: During the COVID-19 pandemic, emergency department (ED) volumes have fluctuated. We hypothesized that natural language processing (NLP) models could quantify changes in detection of acute abdominal pathology (acute appendicitis (AA), acute diverticulitis (AD), or bowel obstruction (BO)) on CT reports. METHODS: This retrospective study included 22,182 radiology reports from CT abdomen/pelvis studies performed at an urban ED between January 1, 2018 to August 14, 2020. Using a subset of 2448 manually annotated reports, we trained random forest NLP models to classify the presence of AA, AD, and BO in report impressions. Performance was assessed using 5-fold cross validation. The NLP classifiers were then applied to all reports. RESULTS: The NLP classifiers for AA, AD, and BO demonstrated cross-validation classification accuracies between 0.97 and 0.99 and F1-scores between 0.86 and 0.91. When applied to all CT reports, the estimated numbers of AA, AD, and BO cases decreased 43-57% in April 2020 (first regional peak of COVID-19 cases) compared to 2018-2019. However, the number of abdominal pathologies detected rebounded in May-July 2020, with increases above historical averages for AD. The proportions of CT studies with these pathologies did not significantly increase during the pandemic period. CONCLUSION: Dramatic decreases in numbers of acute abdominal pathologies detected by ED CT studies were observed early on during the COVID-19 pandemic, though these numbers rapidly rebounded. The proportions of CT cases with these pathologies did not increase, which suggests patients deferred care during the first pandemic peak. NLP can help automatically track findings in ED radiology reporting.

Susceptibility-weighted imaging reveals cerebral microvascular injury in severe COVID-19.

We evaluated the incidence, distribution, and histopathologic correlates of microvascular brain lesions in patients with severe COVID-19. Sixteen consecutive patients admitted to the intensive care unit with severe COVID-19 undergoing brain MRI for evaluation of coma or neurologic deficits were retrospectively identified. Eleven patients had punctate susceptibility-weighted imaging (SWI) lesions in the subcortical and deep white matter, eight patients had >10 SWI lesions, and four patients had lesions involving the corpus callosum. The distribution of SWI lesions was similar to that seen in patients with hypoxic respiratory failure, sepsis, and disseminated intravascular coagulation. Brain autopsy in one patient revealed that SWI lesions corresponded to widespread microvascular injury, characterized by perivascular and parenchymal petechial hemorrhages and microscopic ischemic lesions. Collectively, these radiologic and histopathologic findings add to growing evidence that patients with severe COVID-19 are at risk for multifocal microvascular hemorrhagic and ischemic lesions in the subcortical and deep white matter.

Multi-Radiologist User Study for Artificial Intelligence-Guided Grading of COVID-19 Lung Disease Severity on Chest Radiographs.

RATIONALE AND OBJECTIVES: Radiographic findings of COVID-19 pneumonia can be used for patient risk stratification; however, radiologist reporting of disease severity is inconsistent on chest radiographs (CXRs). We aimed to see if an artificial intelligence (AI) system could help improve radiologist interrater agreement. MATERIALS AND METHODS: We performed a retrospective multi-radiologist user study to evaluate the impact of an AI system, the PXS score model, on the grading of categorical COVID-19 lung disease severity on 154 chest radiographs into four ordinal grades (normal/minimal, mild, moderate, and severe). Four radiologists (two thoracic and two emergency radiologists) independently interpreted 154 CXRs from 154 unique patients with COVID-19 hospitalized at a large academic center, before and after using the AI system (median washout time interval was 16 days). Three different thoracic radiologists assessed the same 154 CXRs using an updated version of the AI system trained on more imaging data. Radiologist interrater agreement was evaluated using Cohen and Fleiss kappa where appropriate. The lung disease severity categories were associated with clinical outcomes using a previously published outcomes dataset using Fisher's exact test and Chi-square test for trend. RESULTS: Use of the AI system improved radiologist interrater agreement (Fleiss κ = 0.40 to 0.66, before and after use of the system). The Fleiss κ for three radiologists using the updated AI system was 0.74. Severity categories were significantly associated with subsequent intubation or death within 3 days. CONCLUSION: An AI system used at the time of CXR study interpretation can improve the interrater agreement of radiologists.