ABSTRACT
OBJECTIVE: To rapidly exclude severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection using artificial intelligence applied to the electrocardiogram (ECG). METHODS: A global, volunteer consortium from 4 continents identified patients with ECGs obtained around the time of polymerase chain reaction-confirmed COVID-19 diagnosis and age- and sex-matched controls from the same sites. Clinical characteristics, polymerase chain reaction results, and raw electrocardiographic data were collected. A convolutional neural network was trained using 26,153 ECGs (33.2% COVID positive), validated with 3826 ECGs (33.3% positive), and tested on 7870 ECGs not included in other sets (32.7% positive). Performance under different prevalence values was tested by adding control ECGs from a single high-volume site. RESULTS: The area under the curve for detection of acute COVID-19 infection in the test group was 0.767 (95% CI, 0.756 to 0.778; sensitivity, 98%; specificity, 10%; positive predictive value, 37%; negative predictive value, 91%). To more accurately reflect a real-world population, 50,905 normal controls were added to adjust the COVID prevalence to approximately 5% (2657/58,555), resulting in an area under the curve of 0.780 (95% CI, 0.771 to 0.790) with a specificity of 12.1% and a negative predictive value of 99.2%. CONCLUSION: Infection with SARS-CoV-2 results in electrocardiographic changes that permit the artificial intelligence-enhanced ECG to be used as a rapid screening test with a high negative predictive value (99.2%). This may permit the development of electrocardiography-based tools to rapidly screen individuals for pandemic control.
Subject(s)
Artificial Intelligence , COVID-19/diagnosis , Electrocardiography , Case-Control Studies , Humans , Predictive Value of Tests , Sensitivity and SpecificityABSTRACT
BACKGROUND: Identification of effective treatments in severe cases of COVID-19 requiring mechanical ventilation represents an unmet medical need. Our aim was to determine whether the administration of adipose-tissue derived mesenchymal stromal cells (AT-MSC) is safe and potentially useful in these patients. METHODS: Thirteen COVID-19 adult patients under invasive mechanical ventilation who had received previous antiviral and/or anti-inflammatory treatments (including steroids, lopinavir/ritonavir, hydroxychloroquine and/or tocilizumab, among others) were treated with allogeneic AT-MSC. Ten patients received two doses, with the second dose administered a median of 3 days (interquartile range-IQR- 1 day) after the first one. Two patients received a single dose and another patient received 3 doses. Median number of cells per dose was 0.98 × 106 (IQR 0.50 × 106) AT-MSC/kg of recipient's body weight. Potential adverse effects related to cell infusion and clinical outcome were assessed. Additional parameters analyzed included changes in imaging, analytical and inflammatory parameters. FINDINGS: First dose of AT-MSC was administered at a median of 7 days (IQR 12 days) after mechanical ventilation. No adverse events were related to cell therapy. With a median follow-up of 16 days (IQR 9 days) after the first dose, clinical improvement was observed in nine patients (70%). Seven patients were extubated and discharged from ICU while four patients remained intubated (two with an improvement in their ventilatory and radiological parameters and two in stable condition). Two patients died (one due to massive gastrointestinal bleeding unrelated to MSC therapy). Treatment with AT-MSC was followed by a decrease in inflammatory parameters (reduction in C-reactive protein, IL-6, ferritin, LDH and d-dimer) as well as an increase in lymphocytes, particularly in those patients with clinical improvement. INTERPRETATION: Treatment with intravenous administration of AT-MSC in 13 severe COVID-19 pneumonia under mechanical ventilation in a small case series did not induce significant adverse events and was followed by clinical and biological improvement in most subjects. FUNDING: None.