ABSTRACT
BACKGROUND: The COVID-19 pandemic led authorities to evacuate via various travel modalities critically ill ventilated patients into less crowded units. However, it is not known if interhospital transport impacts COVID-19 patient's mortality in intensive care units (ICUs). A cohort from three French University Hospitals was analysed in ICUs between 15th of March and the 15th of April 2020. Patients admitted to ICU with positive COVID-19 test and mechanically ventilated were recruited. RESULTS: Among the 133 patients included in the study, 95 (71%) were male patients and median age was 63 years old (interquartile range: 54-71). Overall ICU mortality was 11%. Mode of transport included train (48 patients), ambulance (6 patients), and plane plus helicopter (14 patients). During their ICU stay, 7 (10%) transferred patients and 8 (12%) non-transferred patients died (p = 0.71). Median SAPS II score at admission was 33 (interquartile range: 25-46) for the transferred group and 35 (27-42) for non-transferred patients (p = 0.53). SOFA score at admission was 4 (3-6) for the transferred group versus 3 (2-5) for the non-transferred group (p = 0.25). In the transferred group, median PaO2/FiO2 ratio (P/F) value in the 24 h before departure was 197 mmHg (160-250) and remained 166 mmHg (125-222) in the first 24 h post arrival (p = 0.13). During the evacuation 46 (68%) and 21 (31%) of the patients, respectively, benefited from neuromuscular blocking agents and from vasopressors. Transferred and non-transferred patients had similar rate of nosocomial infections, 37/68 (54%) versus 34/65 (52%), respectively (p = 0.80). Median length of mechanical ventilation was significantly increased in the transferred group compared to the non-transferred group, 18 days (11-24) and 14 days (8-20), respectively (p = 0.007). Finally, ICU and hospital length of stay did not differ between groups. CONCLUSIONS: In France, inter-hospital evacuation of COVID-19 ventilated ICU patients did not appear to increase mortality and therefore could be proposed to manage ICU surges in the future.
ABSTRACT
The reverse transcription-polymerase chain reaction (RT-PCR) assay is the accepted standard for coronavirus disease 2019 (COVID-19) diagnosis. As any test, RT-PCR provides false negative results that can be rectified by clinicians by confronting clinical, biological and imaging data. The combination of RT-PCR and chest-CT could improve diagnosis performance, but this would requires considerable resources for its rapid use in all patients with suspected COVID-19. The potential contribution of machine learning in this situation has not been fully evaluated. The objective of this study was to develop and evaluate machine learning models using routine clinical and laboratory data to improve the performance of RT-PCR and chest-CT for COVID-19 diagnosis among post-emergency hospitalized patients. All adults admitted to the ED for suspected COVID-19, and then hospitalized at Rennes academic hospital, France, between March 20, 2020 and May 5, 2020 were included in the study. Three model types were created: logistic regression, random forest, and neural network. Each model was trained to diagnose COVID-19 using different sets of variables. Area under the receiving operator characteristics curve (AUC) was the primary outcome to evaluate model's performances. 536 patients were included in the study: 106 in the COVID group, 430 in the NOT-COVID group. The AUC values of chest-CT and RT-PCR increased from 0.778 to 0.892 and from 0.852 to 0.930, respectively, with the contribution of machine learning. After generalization, machine learning models will allow increasing chest-CT and RT-PCR performances for COVID-19 diagnosis.