Search

BackgroundConventional diagnosis of COVID-19 with reverse transcription polymerase chain reaction (RT-PCR) testing (hereafter, PCR) is associated with prolonged time to diagnosis and significant costs to run the test. The SARS-CoV-2 virus might lead to characteristic patterns in the results of widely available, routine blood tests that could be identified with machine learning methodologies. Machine learning modalities integrating findings from these common laboratory test results might accelerate ruling out COVID-19 in emergency department patients. ObjectiveWe sought to develop (ie, train and internally validate with cross-validation techniques) and externally validate a machine learning model to rule out COVID 19 using only routine blood tests among adults in emergency departments. MethodsUsing clinical data from emergency departments (EDs) from 66 US hospitals before the pandemic (before the end of December 2019) or during the pandemic (March-July 2020), we included patients aged ≥20 years in the study time frame. We excluded those with missing laboratory results. Model training used 2183 PCR-confirmed cases from 43 hospitals during the pandemic; negative controls were 10,000 prepandemic patients from the same hospitals. External validation used 23 hospitals with 1020 PCR-confirmed cases and 171,734 prepandemic negative controls. The main outcome was COVID 19 status predicted using same-day routine laboratory results. Model performance was assessed with area under the receiver operating characteristic (AUROC) curve as well as sensitivity, specificity, and negative predictive value (NPV). ResultsOf 192,779 patients included in the training, external validation, and sensitivity data sets (median age decile 50 [IQR 30-60] years, 40.5% male [78,249/192,779]), AUROC for training and external validation was 0.91 (95% CI 0.90-0.92). Using a risk score cutoff of 1.0 (out of 100) in the external validation data set, the model achieved sensitivity of 95.9% and specificity of 41.7%; with a cutoff of 2.0, sensitivity was 92.6% and specificity was 59.9%. At the cutoff of 2.0, the NPVs at a prevalence of 1%, 10%, and 20% were 99.9%, 98.6%, and 97%, respectively. ConclusionsA machine learning model developed with multicenter clinical data integrating commonly collected ED laboratory data demonstrated high rule-out accuracy for COVID-19 status, and might inform selective use of PCR-based testing.

Objective: Computed tomography angiography is limited in the intensive care unit (ICU) due to renal insufficiency, hemodynamic instability, and difficulty transporting unstable patients. A portable ventilation/perfusion (V/Q) scan can be used. However, it is commonly believed that an abnormal chest radiograph can result in a nondiagnostic scan. In this retrospective study, we demonstrate that portable V/Q scans can be helpful in ruling in or out clinically significant pulmonary embolism (PE) despite an abnormal chest x-ray in the ICU. Design: Two physicians conducted chart reviews and original V/Q reports. A staff radiologist, with 40 years of experience, rated chest x-ray abnormalities using predetermined criteria. Setting: The study was conducted in the ICU. Patients: The first 100 consecutive patients with suspected PE who underwent a portable V/Q scan. Interventions: Those with a portable V/Q scan. Results: A normal baseline chest radiograph was found in only 6% of patients. Fifty-three percent had moderate, 24% had severe, and 10% had very-severe radiographic abnormalities. Despite the abnormal xrays, 88% of the V/Q scans were low probability for a PE despite an average abnormal radiograph rating of moderate. A highprobability V/Q for PE was diagnosed in 3% of the population despite chest x-ray ratings of moderate to severe. Six patients had their empiric anticoagulation discontinued after obtaining the results of the V/Q scan, and no anticoagulation was started for PE after a low-probability V/Q scan. Conclusion: Despite the large percentage of moderate-to-severe x-ray abnormalities, PE can still be diagnosed (high-probability scan) in the ICU with a portable V/Q scan. Although low-probability scans do not rule out acute PE, it appeared less likely that any patient with a low-probability V/Q scan had severe hypoxemia or hemodynamic instability due to a significant PE, which was useful to clinicians and allowed them to either stop or not start anticoagulation. [ABSTRACT FROM AUTHOR]

Venous thromboembolic disease is a major problem among critically ill patients, with significant associated morbidity and mortality. Many critically ill patients have contraindications to systemic anticoagulation, and inferior vena cava (IVC) filters are an important alternative in preventing pulmonary emboli (PE) in this population. The Angel Catheter (Mermaid, Stenlose, Denmark) is a novel percutaneous and removable IVC filter attached to the end of a triple lumen central venous catheter which has been demonstrated to reduce PE in surgical and trauma patients. This case series describes 18 critically ill medical patients who had an Angel catheter placed either for diagnosed PE or due to high risk for PE; over half had at least submassive PE at the time of Angel catheter placement. None of the patients had a recurrence of PE during Angel catheter use, 29.4% had clot found in the filter via cavogram upon removal, and only one had a minor complication which had no clinical consequence. In 2 patients, the placement of the Angel Catheter resulted in the prevention of PE during catheter-directed thrombolysis of extensive deep vein thrombosis. This case series demonstrates that in a population of critically ill, elderly, and obese medical patients the bedside placement of the Angel IVC filter is feasible, safe, and may be effective for preventing PE. [ABSTRACT FROM AUTHOR]

Purpose: This study investigated physician compliance with indications for inferior vena cava (IVC) filter placement according to the 2012 American College of Chest Physicians (ACCP) and the 2011 Society of Interventional Radiology (SIR) guidelines., Materials and Methods: A retrospective medical record review of 231 retrievable IVC filters placed between August 15, 2016, and December 28, 2017, at a large urban academic medical center. Guideline compliance to the 2012 ACCP and the 2011 SIR guidelines, and indications for IVC filter placements were assessed through an adjudication protocol. Filter retrieval and complication rates were also examined., Results: Compliance to guidelines was low (60.2% for ACCP; 74.0% for SIR), especially for non-intensive care unit (ICU) patients (ICU 74.6% vs non-ICU 54.8%, p=0.007 for ACCP; ICU 82.5% vs non-ICU 70.8%, p=0.092 for SIR). After adjudication, 8.2% (19/231) of filters were considered non-indicated but reasonable, 17.7% (41/231) non-indicated and unreasonable, and 13.9% (32/231) SIR-indicated but not ACCP-indicated. The most common indication was venous thromboembolism with contraindication to anticoagulation. The most common reasons for non-compliance were distal deep venous thrombosis with contraindication to anticoagulation (19/60, 31.6%) and clot burden (19/60, 31.6%). One-year filter retrieval and 90-day complication rates were 32.0% (74/231) and 6.1% (14/231), respectively., Conclusion: Compliance to established guidelines was low. Reasons for non-compliance included limitations or discrepancies in guidelines, as well as non-evidence-based filter placements., Clinical Impact: Despite increasing utilization of inferior vena cava (IVC) filters, guideline compliance for IVC filter placement among providers is unclear. The results of this study indicate that physician compliance to established guidelines is poor, especially in non-intensive-care-unit patients. Noncompliance stems from non-evidence-based filter placement as well as differences and limitations in guidelines. Avoiding non-indicated IVC filter placement and consolidation of guidelines may significantly improve guideline compliance. The critical insights gained from this study can help promote judicious use of IVC filters and highlight the role of venous thromboembolism experts in navigating complex cases and nuances of guidelines., Competing Interests: Declaration of Conflicting InterestsThe author(s) declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: Dr Tapson has the following disclosures: research grants (Bayer, Janssen/Johnson & Johnson, Genentech), speaker honoraria (Janssen/Johnson & Johnson), stock option (Inari Medical), employment (vice president of medical affairs at Inari Medical). Dr Weinberg has the following disclosures: stock options (Carbon Health, CurieAI), compensated authorship (UpToDate), employment (national director of clinical research and medical director of program development at Carbon Health). Other authors have no conflict of interest to disclose.