RESUMO
Severity prediction of COVID-19 remains one of the major clinical challenges for the ongoing pandemic. Here, we have recruited a 144 COVID-19 patient cohort consisting of training, validation, and internal test sets, longitudinally recorded 124 routine clinical and laboratory parameters, and built a machine learning model to predict the disease progression based on measurements from the first 12 days since the disease onset when no patient became severe. A panel of 11 routine clinical factors, including oxygenation index, basophil counts, aspartate aminotransferase, gender, magnesium, gamma glutamyl transpeptidase, platelet counts, activated partial thromboplastin time, oxygen saturation, body temperature and days after symptom onset, constructed a classifier for COVID-19 severity prediction, achieving accuracy of over 94%. Validation of the model in an independent cohort containing 25 patients achieved accuracy of 80%. The overall sensitivity, specificity, PPV and NPV were 0.70, 0.99, 0.93 and 0.93, respectively. Our model captured predictive dynamics of LDH and CK while their levels were in the normal range. This study presents a practical model for timely severity prediction and surveillance for COVID-19, which is freely available at webserver https://guomics.shinyapps.io/covidAI/.
RESUMO
Objective To investigate the various occasions of invasive mechanical ventilation in patients with acute left heart failure. Methods Thirty-two patients with acute severe left heart failure were divided into two groups:17 patients were treated with non-invasive mechanical ventilation (non-invasive mechanical ventilation group) and 15 patients were treated with invasive mechanical ventilation (invasive mechanical ventilation group). The respiratory rate (RR), arterial oxy-gen partial pressure p(O2), heart rate (HR) and mean arterial pressure (MAP) were observed after treatment for 0.5 h,1 h and 3 h in two groups of patients. The in-hospital mortality was compared between two groups. Results Ten patients of non-in-vasive mechanical ventilation group were in remission after 0.5 h, 7 cases without remission switched to endotracheal intuba-tion for invasive mechanical. And 3 of them were in remission in 0.5~1 h, 4 of them dead. Fourteen patients in invasive me-chanical ventilation group were in remission after 0.5 h, one case was in remission after 0.5~1 h and no dead in this group. There were more patients in remission after 0.5 h in invasive mechanical ventilation group than those of non-invasive me-chanical ventilation group (P=0.041). There were no significant differences in the number of patients in clinical remission af-ter 0.5~1 h and mortality between two groups. The values of RR and HR were decreased with the increasing treatment time in two groups. The values of p(O2) and MAP were increased with the increasing treatment time in two groups. There was a sig-nificantly lower RR at 0.5 h and 1 h in invasive mechanical ventilation group than that of non-invasive mechanical ventila-tion group (P ＜ 0.05). The values of p(O2) and MAP were significantly higher at 0.5 h in invasive mechanical ventilation group than those of non-invasive mechanical ventilation group (P＜0.05). The levels of HR at 0.5 h and 3 h were significant-ly lower in invasive mechanical ventilation group than those of non-invasive mechanical ventilation group ( P＜0.05). Con-clusion Invasive mechanical ventilation should be used as soon as possible if non-invasive mechanical ventilation can not alleviate the symptoms in patients more than 0.5 hours.
