615. A Year with COVID19 – Experience from the Front Line in a Large Infectious Disease (ID) Clinical Practice

Abstract Background ID Care (IDC) is a large, 43 physician, 74 provider, practice that treats patients in 16 acute care hospitals (ACH) and 120 skilled nursing facilities (SNF) in NJ. March 4, 2021 was the first day a patient with COVID19 seen by IDC. Over the subsequent year IDC evaluated, treated, and tested over 23,000 persons for COVID19. Patients were seen in 2 distinct times - wave 1 (W1) March 5-August 31 and wave 2 (W2) September 1 to March 4. We compare the experience of these 2 waves and report on the year of COVID19 at IDC. Methods The administrative data base for IDC was queried for demographic, visit and testing information. A survey of providers was performed to capture incidence of COVID19 and vaccination rates. Daily census logs were used to create epi curves. Comparisons between waves were performed using student T Test or X2. Results Table 1 provides the comparisons between waves. More patients were seen in W2, however, the number of visits per patient was less, consistent with a shorter length of stay. Fewer patients were seen in SNF in W2 compared to W1. The age and sex distribution between the waves were the same. A total of 8741 molecular tests were performed. Test positivity peaked the week of December 31 at 6.99% and dropped to 0% by May 1 consistent with vaccination and the NJ epidemic curve. During the year of COVID19, 6/74 (8%) clinicians were infected with SARSCoV2. All recovered. Infections in providers were not clearly work-related exposures. 73/74 clinicians were vaccinated. Table 1. Demographics For the Year in COVID19 at ID Care Figure 1. Test Positivity Rate for ID Care Conclusion The year of COVID19 occurred in 2 distinct waves. W1 was short and intense. The age and gender distributions were the same between the waves. Even though wave 2 was numerically greater, the cases in SNF were statistically less than the first wave likely from improved IP practice initiated in W1. The numbers of visits per patient, a surrogate for LOS, was statistically less in W2. The decline in test positivity paralleled deployment of vaccination. Despite an intensity of exposure of 158 patients/provider or 1198 visits/provider to SARSCoV2 infected persons only 8% of the clinician staff were infected. ID clinical practice can use electronic databases to help describe regional outbreaks of transmissible disease giving additional perspective across the care continuum. A more usable standard tool would enhance this capacity. Disclosures Ronald G. Nahass, MD, Abbvie (Grant/Research Support, Speaker's Bureau)Alkermes (Grant/Research Support)Gilead (Grant/Research Support, Speaker's Bureau)Merck (Grant/Research Support, Speaker's Bureau)


Conclusion.
Dalbavancin was associated with clinical cure for diverse infections with low rates of adverse events, readmission and mortality in patients ineligible for traditional OPAT. Although confirmatory data are needed from larger studies, dalbavancin appears to be a versatile therapeutic agent for Gram-positive infections.
Disclosures. All Authors: No reported disclosures

Evaluating the Use of Dalbavancin for Off-Label Indications
Katherine Taylor, PharmD 1 ; John Williamson, PharmD 1 ; Tyler Stone, PharmD 1 ; James Johnson, PharmD 1 ; Zachary Gruss, PharmD 1 ; Vera Luther, MD 2 ; Vera Luther, MD 2 ; Courtney Russ-Friedman, MSN, FNP-BC 1 ; Chris Ohl, MD 2 ; James Beardsley, PharmD 1 ; 1 Wake Forest Baptist Health System, Winston Salem, NC; 2 Wake Forest School of Medicine, Winston Salem, NC Session: P-27. Clinical Practice Issues Background. Dalbavancin (dalba) is a long-acting antibiotic (ABX) approved for skin and soft tissue infections. Post-marketing data suggests dalba is being used for off-label indications that require long term IV ABX; however, data assessing this off-label usage is limited. The purpose of this study was to evaluate the real-world efficacy, safety, and financial impact of off-label dalba use.
Methods. Setting: 4-hospital health system. Design: retrospective, observational study. Adult patients (pts) who received dalba from Jan 2018 to Jan 2021 for an off-label indication were included. Pts who were pregnant or had an infection caused by a pathogen outside dalba's antimicrobial spectrum were excluded. Primary outcome was clinical success at 90 days defined as no need for additional ABX (excluding suppression therapy) or surgical intervention following dalba therapy and no positive cultures post treatment associated with the dalba-targeted infection. Secondary outcomes included safety (nephrotoxicity and hepatotoxicity). A financial analysis was performed by subtracting the cost of dalba from the anticipated cost of pt stay [$427/ day for hospital; $262/day for skilled nursing facility (SNF)] if standard IV therapy was given.
Conclusion. Dalba was associated with a relatively high success rate for the treatment of off-label indications and may have less total costs than traditional IV ABX.

A Year with COVID19 -Experience from the Front Line in a Large Infectious Disease (ID) Clinical Practice
Ronald G. Nahass, MD 1 ; Angelo Giordano, MBA 1 ; Edward J. McManus, MD 2 ; 1 ID Care, Hillsborough, New Jersey; 2 IDCare, Randolph, New Jersey

Session: P-27. Clinical Practice Issues
Background. ID Care (IDC) is a large, 43 physician, 74 provider, practice that treats patients in 16 acute care hospitals (ACH) and 120 skilled nursing facilities (SNF) in NJ. March 4, 2021 was the first day a patient with COVID19 seen by IDC. Over the subsequent year IDC evaluated, treated, and tested over 23,000 persons for COVID19. Patients were seen in 2 distinct times -wave 1 (W1) March 5-August 31 and wave 2 (W2) September 1 to March 4. We compare the experience of these 2 waves and report on the year of COVID19 at IDC.
Methods. The administrative data base for IDC was queried for demographic, visit and testing information. A survey of providers was performed to capture incidence of COVID19 and vaccination rates. Daily census logs were used to create epi curves. Comparisons between waves were performed using student T Test or X 2 .
Results. Table 1 provides the comparisons between waves. More patients were seen in W2, however, the number of visits per patient was less, consistent with a shorter length of stay. Fewer patients were seen in SNF in W2 compared to W1. The age and sex distribution between the waves were the same. A total of 8741 molecular tests were performed. Test positivity peaked the week of December 31 at 6.99% and dropped to 0% by May 1 consistent with vaccination and the NJ epidemic curve. During the year of COVID19, 6/74 (8%) clinicians were infected with SARSCoV2. All recovered. Infections in providers were not clearly work-related exposures. 73/74 clinicians were vaccinated.

. Test Positivity Rate for ID Care
Conclusion. The year of COVID19 occurred in 2 distinct waves. W1 was short and intense. The age and gender distributions were the same between the waves. Even though wave 2 was numerically greater, the cases in SNF were statistically less than the first wave likely from improved IP practice initiated in W1. The numbers of visits per patient, a surrogate for LOS, was statistically less in W2. The decline in test positivity paralleled deployment of vaccination. Despite an intensity of exposure of 158 patients/provider or 1198 visits/provider to SARSCoV2 infected persons only 8% of the clinician staff were infected. ID clinical practice can use electronic databases to help describe regional outbreaks of transmissible disease giving additional perspective across the care continuum. A more usable standard tool would enhance this capacity.

Predicting Misdiagnoses of Infectious Disease in Emergency Department Visits
Alec B. Chapman, MS 1 ; Kelly Peterson, M.S. Computational Linguistics 2 ; Wathsala Widanagamaachchi, PhD 1 ; Makoto M. Jones, MD 3 ; 1 University of Utah, Salt Lake City, Utah; 2 University of Washington, Salt Lake City, Utah; 3 IDEAS Center of Innovation, VA Salt Lake City Health Care System, Salt Lake City, Utah

Session: P-27. Clinical Practice Issues
Background. Diagnostic error leads to delays of care and mistaken therapeutic decisions that can cascade in a downward spiral. Thus, it is important to make accurate diagnostic decisions early on in the clinical care process, such as in the emergency department (ED). Clinical data from the Electronic Health Record (EHR) could identify cases where an initial diagnosis appears unusual in context. This capability could be developed into a quality measure for feedback. To that end, we trained a multiclass machine learning classifier to predict infectious disease diagnoses following an ED visit.
Methods. To train and evaluate our classifier, we sampled ED visits between December 31, 2016, and December 31, 2019, from Veterans Affairs (VA) Corporate Data Warehouse (CDW). Data elements used for prediction included lab orders and results, medication orders, radiology procedures, and vital signs. A multiclass XGBoost classifier was trained to predict one of five infectious disease classes for each ED visit based on the clinical variables extracted from CDW. Our model was trained on an enriched sample of 916,562 ED visits and evaluated on a non-enriched blind testing set of 356,549 visits. We compared our model against an ensemble of univariate Logistic Regression models as a baseline. Our model was trained to predict for an ED visit one of five infectious disease classes or "No Infection". Labels were assigned to each ED visit based on ICD-9/10-CM diagnosis codes used elsewhere and other structured EHR data associated with a patient between 24 hours prior to an ED visit and 48 hours after.
Results. Classifier performance varied across each of the five disease classes ( Table 1). The classifier achieved the highest F1 and AUC for UTI, the lowest F1 for Sepsis, and the lowest AUC for URI. We compared the average precision, recall and F1 scores of the multiclass XGBoost with the ensemble of Logistic Regression models (Table 2). XGBoost achieved higher scores in all three metrics. XGBoost testing set performance in each disease class, visits with no labels, and macro average. The infectious disease classes with the highest score in each metric are shown in bold. Table 2. Baseline comparison Macro average scores for XGBoost and baseline classifiers. Conclusion. We trained a model to predict infectious disease diagnoses in the Emergency Department setting. Future work will further explore this technique and combine our supervised classifier with additional signs of medical error such as increased mortality or anomalous treatment patterns in order to study medical misdiagnosis.
Disclosures. All Authors: No reported disclosures