348. Characteristics and Outcomes in Hospitalized Patients with Covid-19 Complicated by Fungemia: A Single Center Retrospective Study

Abstract Background Covid19 caused by SARS-CoV2 can lead to significant morbidity and mortality. Fungemia is a rare hospital-associated infection and there are limited data regarding its association with Covid19. We reviewed all cases of fungemia in our Covid19 cohort at Stony Brook University Hospital (SBUH). Methods We conducted a retrospective medical record review of patients admitted with Covid19 in a 3-month interval. We reviewed positive blood cultures for fungi and recorded co-morbidities, co-infections, length of stay, treatments, and outcomes (survival vs death). There were 60 positive blood cultures for fungi in 25 unique patients (Table 1); in prior years < 30 per year reported at SBUH. Table 1. Fungal Blood Cultures Collation of each unique identified fungal species from fungal blood cultures in patients hospitalized with Covid-19 Results During a 3 month interval at the local peak of the pandemic 1398 patients hospitalized with Covid19 at SBUH, 25 cases of fungemia were detected; C. albicans (CA) n=8,32%, non C albicans species (nCA) n=16,64%, and C. neoformans n=1,4%, 17/25 (68%) also with bacteremia during same hospitalization. In same 3 months there were 264 cases of bacteremia and Covid19 co-infection. Demographics and medical co-morbidities of fungemic patients are in Table 2. Majority were men (76%). No difference between fungaemic (FC) and total cohort (TC) in median age (62 vs 62), DM p=0.31, HTN p=1.0, COPD p=0.12. Within FC, DM was higher in nCA group (58.8%) vs CA group (37%). Mortality was 40% in FC vs 15% in TC, p< 0.001. Within FC mortality was 56% in nCA and 25% in CA group. C. parapsilosis was the most common nCA species isolated with 43% mortality. FC more likely to require ICU and mechanical ventilation (88% vs 15%, p< 0.0001) and had longer median length of stay 42 days vs 22 days. The median time from admission to fungaemia was 21d, from central line placement 19d, Table 3. Of FC 21 (84%) were treated with steroids/Tocilizumab concurrently. Of note, no mortality was recorded in the 4 patients that did not receive steroids/Tocilizumab. PCT and WBC were significantly higher at time of fungemia as compared to admission, Table 3. Table 2, Patient co-morbidities and hospitalization stay characteristics Co-morbidities and requirement for ICU stay, mechanical ventilation for total cohort Covid-19 and fungemic cohort Table 3, Patient Characteristics and Laboratory Parameters Relevant patient characteristics and laboratory parameters in patients hospitalized with Covid19 and fungemia Conclusion Fungemia in hospitalized patients with COVID-19 is associated with higher mortality. We observed higher fatality in non C. albicans infections. Prolonged use of central line catheters and concurrent treatment with steroids/tociluzimab are likely high-risk factors for development of fungemia. Disclosures All Authors: No reported disclosures

. Clinical features of children with concurrent SARS-CoV-2 and AOM Table 2. Laboratory findings of children with concurrent SARS-CoV-2 and AOM.
Conclusion. SARS-CoV-2 can occur in children with AOM. It is important that providers maintain a high index of suspicion for COVID-19 even in patients with clinical evidence of AOM, particularly to ensure families are appropriately advised on isolation and quarantine requirements. AOM with SARS-CoV-2 does not appear to be more severe than AOM without SARS-CoV-2.
Disclosures  Methods. We conducted a retrospective medical record review of patients admitted with Covid19 in a 3-month interval. We reviewed positive blood cultures for fungi and recorded co-morbidities, co-infections, length of stay, treatments, and outcomes (survival vs death). There were 60 positive blood cultures for fungi in 25 unique patients (Table 1); in prior years < 30 per year reported at SBUH. Results. During a 3 month interval at the local peak of the pandemic 1398 patients hospitalized with Covid19 at SBUH, 25 cases of fungemia were detected; C. albicans (CA) n=8,32%, non C albicans species (nCA) n=16,64%, and C. neoformans n=1,4%, 17/25 (68%) also with bacteremia during same hospitalization. In same 3 months there were 264 cases of bacteremia and Covid19 co-infection. Demographics and medical co-morbidities of fungemic patients are in Table 2. Majority were men (76%). No difference between fungaemic (FC) and total cohort (TC) in median age (62 vs 62), DM p=0.31, HTN p=1.0, COPD p=0.12. Within FC, DM was higher in nCA group (58.8%) vs CA group (37%). Mortality was 40% in FC vs 15% in TC, p< 0.001. Within FC mortality was 56% in nCA and 25% in CA group. C. parapsilosis was the most common nCA species isolated with 43% mortality. FC more likely to require ICU and mechanical ventilation (88% vs 15%, p< 0.0001) and had longer median length of stay 42 days vs 22 days. The median time from admission to fungaemia was 21d, from central line placement 19d, Table 3. Of FC 21 (84%) were treated with steroids/Tocilizumab concurrently. Of note, no mortality was recorded in the 4 patients that did not receive steroids/Tocilizumab.
PCT and WBC were significantly higher at time of fungemia as compared to admission, Table 3. Background. Patients with COVID-19 receive high rates of antibiotic therapy, despite viral origin of infection. Reports of bacterial coinfection range from 3.5 to 8% in the early phase of infection. This study aimed to evaluate the relationship between diagnostic tests and antibiotic utilization in patients admitted with COVID-19 at the University of Maryland Medical Center to better inform future prescribing practices.
Methods. Retrospective cohort study of adult patients with a positive SARS-CoV-2 PCR on admission from March 2020 through June 2020. Associations between diagnostic tests employed and antibiotic initiation and duration were explored using bivariate analysis (SPSS®).

Conclusion.
Despite low coinfection rates, negative diagnostic tests did not result in shorter empiric antibacterial duration. These findings highlight the ongoing need for both diagnostic and antimicrobial stewardship in COVID-19.

Joint Modeling of EHR and CXR Data to Predict COVID-19 Deterioration
Emily Mu 1 ; Sarah Jabbour, PhD Candidate 2 ; Michael Sjoding, Physician 2 ; John Guttag, Professor 3 ; Jenna Wiens, PhD 2 ; Adrian Dalca, PhD 4 ; 1 Massachusetts Institute of Technology, Naperville, IL; 2 University of Michigan, Ann Arbor, Michigan; 3 MIT, Cambridge, Massachusetts; 4 MIT, Harvard MGH, Cambridge, Massachusetts Session: P-14. and Clinical Outcomes Background. Infectious respiratory-track pathogens are a common trigger of healthcare capacity strain, e.g. the COVID19 pandemic. Patient risk stratification models to identify low-risk patients can help improve patient care processes and allocate limited resources. Many existing deterioration indices are based entirely on structured data from the Electronic Health Record (EHR) and ignore important information from other data sources. However, chest radiographs have been demonstrated to be helpful in predicting the progress of respiratory diseases. We developed a joint EHR and chest x-ray (CXR) model method and applied it to identify low-risk COVID19+ patients within the first 48 hours of hospital admission.
Methods. All COVID19+ patients admitted to a large urban hospital between March 2020 and February 2021 were included. We trained an image model using large public chest radiograph datasets and fine-tuned this model to predict acute dyspnea using a cohort from the same hospital. We then combined this image model with two existing EHR deterioration indices to predict the risk of a COVID19+ patient being intubated, receiving a nasal cannula, or being treated with a vasopressor. We evaluated models' ability to identify low-risk patients by using the positive predictive value (PPV).
Results. The image-augmented deterioration index was able to identify 12% of 716 COVID-19+ patients as low risk with 0.95 positive predictive value in the first 48 hours of admission. In contrast, when used individually, the EHR and CXR models each identified roughly 3% of the patients with a PPV of 0.95.
Predicting Low Risk Patients Aggregated predictions for COVID19 positive patients within the first 48 hours of admission, shown with exponential weight moving average and 95% CIs. Each plot shows the number of patients flagged as low-risk by lowest aggregated prediction and the resulting accuracy for that fraction of patients. The bottom plot compares the MCURES fused model to the MCURES model. The top plot compares the EDI fused model to the EDI model.
Conclusion. Our multi-modal models were able to identify far more patients at low-risk of COVID19 deterioration than models trained on either modality alone. This indicates the importance of combining structured data with chest X-rays when creating a deterioration index performance for infectious respiratory-track diseases.
Disclosures. All Authors: No reported disclosures