Developing and validating a machine learning prognostic model for alerting to imminent deterioration of hospitalized patients with COVID-19.

Our study was aimed at developing and validating a new approach, embodied in a machine learning-based model, for sequentially monitoring hospitalized COVID-19 patients and directing professional attention to patients whose deterioration is imminent. Model development employed real-world patient data (598 prediction events for 210 patients), internal validation (315 prediction events for 97 patients), and external validation (1373 prediction events for 307 patients). Results show significant divergence in longitudinal values of eight routinely collected blood parameters appearing several days before deterioration. Our model uses these signals to predict the personal likelihood of transition from non-severe to severe status within well-specified short time windows. Internal validation of the model's prediction accuracy showed ROC AUC of 0.8 and 0.79 for prediction scopes of 48 or 96 h, respectively; external validation showed ROC AUC of 0.7 and 0.73 for the same prediction scopes. Results indicate the feasibility of predicting the forthcoming deterioration of non-severe COVID-19 patients by eight routinely collected blood parameters, including neutrophil, lymphocyte, monocyte, and platelets counts, neutrophil-to-lymphocyte ratio, CRP, LDH, and D-dimer. A prospective clinical study and an impact assessment will allow implementation of this model in the clinic to improve care, streamline resources and ease hospital burden by timely focusing the medical attention on potentially deteriorating patients.

Prevalence and clinical implication of thrombocytopenia and heparin-induced thrombocytopenia in patients who are critically ill with COVID-19.

As the COVID-19 pandemic continues to evolve, different clinical manifestations are better understood and studied. These include various haematologic disorders that have been shown to be associated with increased morbidity and mortality. We studied the prevalence of one unusual manifestation, heparin-induced thrombocytopenia (HIT) and its clinical implications in patients who are severely ill with COVID-19 in a single tertiary centre in Israel. The presence of thrombocytopenia, disseminated intravascular coagulation (DIC) and HIT, and their association with clinical course and outcomes were studied. One-hundred and seven patients with COVID-19 were included. Fifty-seven (53.2%) patients developed thrombocytopenia, which was associated with the worst outcomes (ventilation, DIC and increased mortality). Sixteen (28.0%) patients with thrombocytopenia were positive for HIT, all of which were supported by extracorporeal devices. HIT was independently associated with ventilation days, blood product transfusions, longer hospitalisation and mortality.Platelet abnormalities and HIT are common in patients who are critically ill with COVID-19 and are associated with the worst clinical outcomes. The mechanisms underlying HIT in COVID-19 are yet to be studied; HIT may contribute to the dysregulated immunologic response associated with COVID-19 critical illness and may play a significant part in the coagulopathy seen in these patients. As many patients with COVID-19 require aggressive thromboprophylaxis, further understanding of HIT and the implementation of appropriate protocols are important.

Remote Auscultation of Heart and Lungs as an Acceptable Alternative to Legacy Measures in Quarantined COVID-19 Patients-Prospective Evaluation of 250 Examinations.

The COVID-19 pandemic accelerated the assimilation of telemedicine platforms into medical practice. Nevertheless, research-based evidence in this field is still accumulating. This was a prospective, cross-sectional comparative assessment of a remote physical examination device used mainly for heart and lung digital auscultation. We analyzed usage patterns, user (physician) subjective appreciation and compared it to legacy measures. Eighteen physicians (median age 36 years (IQR 32-45): two interns, seven residents and nine senior physicians; eleven internists, five geriatricians and two pediatricians) executed over 250 remote physical examinations. Their median work duration with quarantined patients was 60 days (IQR 45-60). The median number of patients examined by a single physician was 17 (IQR 10-34). Regarding overall estimation, all participants tended to prefer the remote examination in the setting of quarantined patients (median 6, IQR 3.75-8), while no statistically significant difference was demonstrated compared to the indifference value (p = 0.122). Internists preferred tele-medical examination over non-internists, with significant differences between groups regarding heart auscultation, (median 7, (IQR 3-7) vs. median 2, (IQR 1-5, respectively)), p = 0.044. In the setting of quarantined patients, from the physicians' perspective, a digital platform for remote auscultation of heart and lungs was considered as an acceptable alternative to legacy measures.

Clinical Characterization of 162 COVID-19 patients in Israel: Preliminary Report from a Large Tertiary Center.

BACKGROUND: In February 2020, the World Health Organisation designated the name COVID-19 for a clinical condition caused by a virus identified as a cause for a cluster of pneumonia cases in Wuhan, China. The virus subsequently spread worldwide, causing havoc to medical systems and paralyzing global economies. The first COVID-19 patient in Israel was diagnosed on 27 February 2020. OBJECTIVES: To present our findings and experiences as the first and largest center for COVID-19 patients in Israel. METHODS: The current analysis included all COVID-19 patients treated in Sheba Medical Center from February 2020 to April 2020. Clinical, laboratory, and epidemiological data gathered during their hospitalization are presented. RESULTS: Our 162 patient cohort included mostly adult (mean age of 52 ± 20 years) males (65%). Patients classified as severe COVID-19 were significantly older and had higher prevalence of arterial hypertension and diabetes. They also had significantly higher white blood cell counts, absolute neutrophil counts, and lactate dehydrogenase. Low folic acid blood levels were more common amongst severe patients (18.2 vs. 12.9 vs. 9.8, P = 0.014). The rate of immune compromised patients (12%) in our cohort was also higher than in the general population. The rate of deterioration from moderate to severe disease was high: 9% necessitated non-invasive oxygenation and 15% were intubated and mechanically ventilated. The mortality rate was 3.1. CONCLUSIONS: COVID-19 patients present a challenge for healthcare professionals and the whole medical system. We hope our findings will assist other providers and institutions in their care for these patients.