Among patients with Coronavirus disease (COVID-19), the ability to identify patients at risk for deterioration during their hospital stay is essential for effective patient allocation and management. To predict patient risk for critical COVID-19 based on status at admission using machine-learning models. Retrospective study based on a database of tertiary medical center with designated departments for patients with COVID-19. Patients with severe COVID-19 at admission, based on low oxygen saturation, low partial arterial oxygen pressure, were excluded. The primary outcome was risk for critical disease, defined as mechanical ventilation, multi-organ failure, admission to the ICU, and/or death. Three different machine-learning models were used to predict patient deterioration and compared to currently suggested predictors and to the APACHEII risk-prediction score. Among 6995 patients evaluated, 162 were hospitalized with non-severe COVID-19, of them, 25 (15.4%) patients deteriorated to critical COVID-19. Machine-learning models outperformed the all other parameters, including the APACHE II score (ROC AUC of 0.92 vs. 0.79, respectively), reaching 88.0% sensitivity, 92.7% specificity and 92.0% accuracy in predicting critical COVID-19. The most contributory variables to the models were APACHE II score, white blood cell count, time from symptoms to admission, oxygen saturation and blood lymphocytes count. Machine-learning models demonstrated high efficacy in predicting critical COVID-19 compared to the most efficacious tools available. Hence, artificial intelligence may be applied for accurate risk prediction of patients with COVID-19, to optimize patients triage and in-hospital allocation, better prioritization of medical resources and improved overall management of the COVID-19 pandemic.

BackgroundProlonged, inappropriate hospital stay after patients’ eligibility for discharge from internal medicine departments is a world-wide health-care systems’ problem. Nevertheless, the extent to which such surplus hospital stays are associated with infectious complications, their time frame of appearance and their long-term implications was not previously addressed.MethodsWe conducted a retrospective cohort analysis of patients experiencing an In-hospital Waiting Period (IHWP) after discharge eligibility in a single, tertiary hospital.ResultsWe screened the records of 245 patients out of which 104 patients fulfilled our inclusion criteria. The mean length of IHWP was 15.7 ± 4.79 day during which 9(8.7 %) patients died. The study primary composite end-point, in-hospital mortality or hospital acquired infection (pneumonia, UTI or sepsis) occurred in 32(31 %) patients. The most hazardous time was during the first 3 IHWP days: 63.7 % of patients experienced a complication and 44 % of the total complications occurred during this period. The occurrence of any complication during IHWP was associated, with statistical significance, with increased risk of mortality during the first year after IHWP initiation (HR = 6.02, p = 0.014).ConclusionProlongation of hospital stay after patients are deemed to be discharged from internal medicine departments is associated with increased morbidity and mortality, mainly during the first surplus days of in-hospital stay. Efforts should be made to shorten such hospital stays as much as possible.

Background: Limited information exists on causes of hospitalization in patients returning from the tropics, and most is focused on febrile diseases. We evaluated all causes of post-travel hospitalization in a tertiary care hospital in Israel.Methods: Demographics, diagnoses, and destinations of patients admitted between January 1999 and December 2003 with a history of recent travel were recorded. Demographics and destination of healthy travelers presenting to our pretravel clinic at the same period were recorded.Results: Of 211 patients admitted, 71% were males, 8% were immigrants/foreign workers, and febrile diseases accounted for 77% of admissions. The most common diagnoses were malaria in 54 (26%), unidentified febrile disease in 34 (16%), and dengue fever in 27 (13%). New World cutaneous leishmaniasis was the most common cause of admission among nonfebrile patients (18 [9%]). Diarrheal diseases accounted for only 11% of admissions. Regarding destination, 101 (48%) patients had been to Asia, 71 (34%) to Africa, and 43 (20%) to the Americas. Of our healthy traveler population, 59% traveled to Asia, 20% to Africa, and 20% to the Americas. Travel to Africa carried the highest risk of being hospitalized (OR 1.85, 95% CI 1.16-2.97; p = .01). Most (59%) patients returning from Africa had malaria. The principal health problem originating in Asia was dengue fever (27%), and from Latin America, cutaneous leishmaniasis (48%). Males comprised 71% of the patients, and 59% of the healthy traveler population (p < .0001). Males were more likely to acquire malaria (OR 2.15, 95% CI 1.13-4.09; p = .02) and leishmaniasis (OR 3.41,; p = .05).Conclusions: Febrile diseases were the most common cause for hospitalization, with malaria, unidentified febrile diseases, and dengue fever being the most common. Diseases were destination related; travel to Africa was associated with a higher rate of hospitalization. Malaria and cutaneous leishmaniasis had a substantially male predominance, probably due to risk-taking behavior.

No abstract