ABSTRACT
BackgroundWith the rapid increase in the number of COVID-19 patients in Japan, the number of patients receiving oxygen at home has also increased rapidly, and some of these patients have died. An efficient approach to identify high-risk patients with slowly progressing and rapidly worsening COVID-19, and to avoid missing the timing of therapeutic intervention will improve patient prognosis and prevent medical complications. MethodsPatients admitted to medical institutions in Japan from November 14, 2020 to April 11, 2021 and registered in the COVID-19 Registry Japan were included. Risk factors for patients with High Flow Nasal Cannula invasive respiratory management or higher were comprehensively explored using machine learning. Age-specific cohorts were created, and severity prediction was performed for the patient surge period and normal times, respectively. ResultsWe were able to obtain a model that was able to predict severe disease with a sensitivity of 57% when the specificity was set at 90% for those aged 40-59 years, and with a specificity of 50% and 43% when the sensitivity was set at 90% for those aged 60-79 years and 80 years and older, respectively. We were able to identify lactate dehydrogenase level (LDH) as an important factor in predicting the severity of illness in all age groups. DiscussionUsing machine learning, we were able to identify risk factors with high accuracy, and predict the severity of the disease. Using machine learning, we were able to identify risk factors with high accuracy, and predict the severity of the disease. We plan to develop a tool that will be useful in determining the indications for hospitalisation for patients undergoing home care and early hospitalisation.
ABSTRACT
ObjectivesAlthough several randomised controlled trials have compared the efficacy of remdesivir with that of placebo, there is limited evidence regarding its effect in the early stage of nonsevere COVID-19 cases. MethodsWe evaluated the efficacy of remdesivir on the early stage of nonsevere COVID-19 using the COVID-19 Registry Japan, a nationwide registry of hospitalised COVID-19 patients in Japan. Two regimens (start remdesivir therapy within 4 days from admission vs. no remdesivir during hospitalisation) among patients without the need for supplementary oxygen therapy were compared by a three-step processing (cloning, censoring, and weighting) method. The primary outcome was supplementary oxygen requirement during hospitalisation. Secondary outcomes were 30-day fatality risk and risk of invasive mechanical ventilation or extracorporeal membrane oxygenation (IMV/ECMO). ResultsThe data of 12,657 cases met our inclusion criteria. The start remdesivir regimen showed a lower risk of supplementary oxygen requirement (hazard ratio: 0.861, p < 0.001). Both 30-day fatality risk and risk of IMV/ECMO introduction were not significantly different between the two regimens (hazard ratios: 1.05 and 0.886, p values: 0.070 and 0.440, respectively). ConclusionsRemdesivir might reduce the risk of oxygen requirement during hospitalisation in the early stage of COVID-19; however, it had no positive effect on the clinical outcome and reduction of IMV/ECMO requirement.
