Explainable deep learning algorithm for distinguishing incomplete Kawasaki disease by coronary artery lesions on echocardiographic imaging.

BACKGROUND AND OBJECTIVE: Incomplete Kawasaki disease (KD) has often been misdiagnosed due to a lack of the clinical manifestations of classic KD. However, it is associated with a markedly higher prevalence of coronary artery lesions. Identifying coronary artery lesions by echocardiography is important for the timely diagnosis of and favorable outcomes in KD. Moreover, similar to KD, coronavirus disease 2019, currently causing a worldwide pandemic, also manifests with fever; therefore, it is crucial at this moment that KD should be distinguished clearly among the febrile diseases in children. In this study, we aimed to validate a deep learning algorithm for classification of KD and other acute febrile diseases. METHODS: We obtained coronary artery images by echocardiography of children (n = 138 for KD; n = 65 for pneumonia). We trained six deep learning networks (VGG19, Xception, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) using the collected data. RESULTS: SE-ResNext50 showed the best performance in terms of accuracy, specificity, and precision in the classification. SE-ResNext50 offered a precision of 81.12%, a sensitivity of 84.06%, and a specificity of 58.46%. CONCLUSIONS: The results of our study suggested that deep learning algorithms have similar performance to an experienced cardiologist in detecting coronary artery lesions to facilitate the diagnosis of KD.

Clinical and laboratory factors associated with coronavirus disease 2019 (Covid-19): A systematic review and meta-analysis.

SARS Coronavirus-2 is one of the most widespread viruses globally during the 21st century, whose severity and ability to cause severe pneumonia and death vary. We performed a comprehensive systematic review of all studies that met our standardised criteria and then extracted data on the age, symptoms, and different treatments of Covid-19 patients and the prognosis of this disease during follow-up. Cases in this study were divided according to severity and death status and meta-analysed separately using raw mean and single proportion methods. We included 171 complete studies including 62,909 confirmed cases of Covid-19, of which 148 studies were meta-analysed. Symptoms clearly emerged in an escalating manner from mild-moderate symptoms, pneumonia, severe-critical to the group of non-survivors. Hypertension (Pooled proportion (PP): 0.48 [95% Confident interval (CI): 0.35-0.61]), diabetes (PP: 0.23 [95% CI: 0.16-0.33]) and smoking (PP: 0.12 [95% CI: 0.03-0.38]) were highest regarding pre-infection comorbidities in the non-survivor group. While acute respiratory distress syndrome (PP: 0.49 [95% CI: 0.29-0.78]), (PP: 0.63 [95% CI: 0.34-0.97]) remained one of the most common complications in the severe and death group respectively. Bilateral ground-glass opacification (PP: 0.68 [95% CI: 0.59-0.75]) was the most visible radiological image. The mortality rates estimated (PP: 0.11 [95% CI: 0.06-0.19]), (PP: 0.03 [95% CI: 0.01-0.05]), and (PP: 0.01 [95% CI: 0-0.3]) in severe-critical, pneumonia and mild-moderate groups respectively. This study can serve as a high evidence guideline for different clinical presentations of Covid-19, graded from mild to severe, and for special forms like pneumonia and death groups.

Clinical characteristics of COVID-19 in older adults. A retrospective study in long-term nursing homes in Catalonia.

The natural history of COVID-19 and predictors of mortality in older adults need to be investigated to inform clinical operations and healthcare policy planning. A retrospective study took place in 80 long-term nursing homes in Catalonia, Spain collecting data from March 1st to May 31st, 2020. Demographic and clinical data from 2,092 RT-PCR confirmed cases of SARS-CoV-2 infection were registered, including structural characteristics of the facilities. Descriptive statistics to describe the demographic, clinical, and molecular characteristics of our sample were prepared, both overall and by their symptomatology was performed and an analysis of statistically significant bivariate differences and constructions of a logistic regression model were carried out to assess the relationship between variables. The incidence of the infection was 28%. 71% of the residents showed symptoms. Five major symptoms included: fever, dyspnea, dry cough, asthenia and diarrhea. Fever and dyspnea were by far the most frequent (50% and 28%, respectively). The presentation was predominantly acute and symptomatology persisted from days to weeks (mean 9.1 days, SD = 10,9). 16% of residents had confirmed pneumonia and 22% required hospitalization. The accumulated mortality rate was 21.75% (86% concentrated during the first 28 days at onset). A multivariate logistic regression analysis showed a positive predictive value for mortality for some variables such as age, pneumonia, fever, dyspnea, stupor refusal to oral intake and dementia (p<0.01 for all variables). Results suggest that density in the nursing homes did not account for differences in the incidence of the infection within the facilities. This study provides insights into the natural history of the disease in older adults with high dependency living in long-term nursing homes during the first pandemic wave of March-May 2020 in the region of Catalonia, and suggests that some comorbidities and symptoms have a strong predictive value for mortality.

Is carbonic anhydrase inhibition useful as a complementary therapy of Covid-19 infection?

The ongoing Covid-19 is a contagious disease, and it is characterised by different symptoms such as fever, cough, and shortness of breath. Rising concerns about Covid-19 have severely affected the healthcare system in all countries as the Covid-19 outbreak has developed at a rapid rate all around the globe. Intriguing, a clinically used drug, acetazolamide (a specific inhibitor of carbonic anhydrase, CA, EC 4.2.1.1), is used to treat high-altitude pulmonary oedema (HAPE), showing a high degree of clinical similarities with the pulmonary disease caused by Covid-19. In this context, this preliminary study aims to provide insights into some factors affecting the Covid-19 patients, such as hypoxaemia, hypoxia as well as the blood CA activity. We hypothesise that patients with Covid-19 problems could show a dysregulated acid-base status influenced by CA activity. These preliminary results suggest that the use of CA inhibitors as a pharmacological treatment for Covid-19 may be beneficial.

SARS-CoV-2 RNAaemia in children: An Iranian referral hospital-based study.

Although severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) RNA is generally detected in nasopharyngeal swabs, viral RNA can be found in other samples including blood. Recently, associations between SARS-CoV-2 RNAaemia and disease severity and mortality have been reported in adults, while no reports are available in pediatric patients with coronavirus disease 2019 (COVID-19). The aim of this study was to evaluate the mortality, severity, clinical, and laboratory findings of SARS-CoV-2 RNA detection in blood in 96 pediatric patients with confirmed COVID-19. Among all patients, 6 (6%) had SARS-CoV-2 RNAaemia. Out of the six patients with SARS-CoV-2 RNAaemia, four (67%) had a severe form of the disease, and two out of the 6 patients with SARS-CoV-2 RNAaemia passed away (33%). Our results show that the symptoms more commonly found in the cases of COVID-19 in the study (fever, cough, tachypnea, and vomiting), were found at a higher percentage in the patients with SARS-CoV-2 RNAaemia. Creatine phosphokinase and magnesium tests showed significant differences between the positive and negative SARS-CoV-2 RNAaemia groups. Among all laboratory tests, magnesium and creatine phosphokinase could better predict SARS-CoV-2 RNAemia with area under the curve  levels of 0.808 and 0.748, respectively. In conclusion, 67% of individuals with SARS-CoV-2 RNAaemia showed a severe COVID-19 and one-third of the patients with SARS-CoV-2 RNAaemia passed away. Our findings suggest that magnesium and creatine phosphokinase might be considered as markers to estimate the SARS-CoV-2 RNAaemia.

Clinical Features of 69 Cases With Coronavirus Disease 2019 in Wuhan, China.

BACKGROUND: From December 2019 to February 2020, 2019 severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a serious outbreak of coronavirus disease 2019 (COVID-19) in Wuhan, China. Related clinical features are needed. METHODS: We reviewed 69 patients who were hospitalized in Union hospital in Wuhan between 16 January and 29 January 2020. All patients were confirmed to be infected with SARS-CoV-2, and the final date of follow-up was 4 February 2020. RESULTS: The median age of 69 enrolled patients was 42.0 years (interquartile range 35.0-62.0), and 32 patients (46%) were men. The most common symptoms were fever (60 [87%]), cough (38 [55%]), and fatigue (29 [42%]). Most patients received antiviral therapy (66 [98.5%] of 67 patients) and antibiotic therapy (66 [98.5%] of 67 patients). As of 4 February 2020, 18 (26.9%) of 67 patients had been discharged, and 5 patients had died, with a mortality rate of 7.5%. According to the lowest SpO2 during admission, cases were divided into the SpO2 ≥ 90% group (n = 55) and the SpO2 < 90% group (n = 14). All 5 deaths occurred in the SpO2 < 90% group. Compared with SpO2 ≥ 90% group, patients of the SpO2 < 90% group were older and showed more comorbidities and higher plasma levels of interleukin (IL) 6, IL10, lactate dehydrogenase, and C reactive protein. Arbidol treatment showed tendency to improve the discharging rate and decrease the mortality rate. CONCLUSIONS: COVID-19 appears to show frequent fever, dry cough, and increase of inflammatory cytokines, and induced a mortality rate of 7.5%. Older patients or those with underlying comorbidities are at higher risk of death.

Clinical characteristics of 132 healthcare worker cases with COVID-19: A retrospective study from a single center in Wuhan, China.

Many healthcare workers (HCWs) have been confirmed to be infected with SARS-CoV-2 in China. A retrospective, single-center study was conducted. The median age of the 132 HCWs with COVID-19 was 32 years, with 92 (69.7%) being females. There were 47 (35.6%) doctors, 72 (54.6%) nurses, and 13 (9.9%) other HCWs. Ten of the 132 patients (7.6%) had underlying diseases. The most common symptoms of illness onset were fever (70, 53.0%), cough (66, 50.0%), and fatigue (58, 43.9%). All patients were categorized into mild or moderate COVID-19 type on admission to hospital, and five (3.8%) progressed to the severe COVID-19 type. Sixty-six HCWs patients were included in both the early and later discharged group. In the logistic analysis, the later discharged patients had a longer time for illness onset to hospital admission (per 1 day; OR, 1.10; 95% CI, 1.03-1.18; p = .006), a higher proportion of >3 onset symptoms clustering (OR, 3.11; 95% CI, 1.27-7.62; p = .01), and a higher percentage of other HCWs (OR, 6.20; 95% CI, 1.49-25.80; p = .01). HCW patients were young female nurses with fewer comorbidities, and most were mild or moderate COVID-19 type. The later discharged patients exhibited characteristics of longer time for illness onset to hospitalization and clustering of onset symptoms.

Shorter incubation period is associated with severe disease progression in patients with COVID-19.

The diagnosed COVID-19 cases revealed that the incubation periods (IP) varied a lot among patients. However, few studies had emphasized on the different clinical features and prognosis of patients with different IP. A total of 330 patients with laboratory-confirmed COVID-19 were enrolled and classified into immediate onset group(IP<3 days, I group, 57 cases) and late onset group(IP>10 days, L group, 75 cases) based on IP. The difference of clinical characteristics and prognosis of the two groups were compared. There were more patients with fever in I group than in L group(P = 0.003), and counts of all the total lymphocytes, total T lymphocytes, CD4 + and CD8 + T lymphocytes were significantly different between the two groups(all P < 0.01). Besides, patients in L group had more GGOs in CT scan than I group and there were more patients in I group receiving antibiotic treatment than in L group(P < 0.001). For disease aggravation, the median CT scores were comparable between the two groups, but individually, there were more patients with increased CT score during hospitalization in I group than in L group. The aggravation incidence of CT presentation was 21.1% in I group, significantly higher than L group(8.0%, P = 0.042). Multivariable COX models suggested that IP was the only independent factors for CT aggravation. Conclusively, patients with different IP were different in clinical symptoms, laboratory tests, and CT presentations. Shorter IP was associated with the aggravation of lung involvement in CT scan.

Novel Coronavirus Disease 2019 (COVID-19) Pneumonia Progression Course in 17 Discharged Patients: Comparison of Clinical and Thin-Section Computed Tomography Features During Recovery.

BACKGROUND: Our objective was to retrospectively analyze the evolution of clinical features and thin-section computed tomography (CT) imaging of novel coronavirus disease 2019 (COVID-19) pneumonia in 17 discharged patients. METHODS: Serial thin-section CT scans of 17 discharged patients with COVID-19 were obtained during recovery. Longitudinal changes of clinical parameters and a CT pattern were documented in all patients during the 4 weeks after admission. A CT score was used to evaluate the extent of the disease. RESULTS: There were marked improvements of fever, lymphocyte counts, C-reactive proteins, and erythrocyte sedimentation rates within the first 2 weeks after admission. However, the mean CT score rapidly increased from the first to the third week, with a top score of 8.2 obtained in the second week. During the first week, the main CT pattern was ground-glass opacities (GGO; 76.5%). The frequency of GGO (52.9%) decreased in the second week. Consolidation and mixed patterns (47.0%) were noted in the second week. Thereafter, consolidations generally dissipated into GGO, and the frequency of GGO increased in the third week (76.5%) and fourth week (71.4%). Opacities were mainly located in the peripheral (76.5%) and subpleural (47.1%) zones of the lungs; they presented as focal (35.3%) or multifocal (29.4%) in the first week and became more diffuse in the second (47.1%) and third weeks (58.8%), then showed a reduced extent in fourth week (50%). CONCLUSIONS: The progression course of the CT pattern was later than the progression of the clinical parameters within the first 2 weeks after admission; however, there were synchronized improvements in both the clinical and radiologic features in the fourth week.

Absent immune response to SARS-CoV-2 in a 3-month recurrence of coronavirus disease 2019 (COVID-19) case.

BACKGROUND: The viral persistence in patients with Coronavirus Disease 2019 (COVID-19) remains to be investigated. METHODS: We investigated the viral loads, therapies, clinical features, and immune responses in a 70-year patient tested positive for SARS-CoV-2 for 3 months. FINDINGS: The patient exhibited the highest prevalence of abnormal indices of clinical features and immune responses at the first admission, including fever (38.3 â„ƒ), decreased lymphocytes (0.83 × 109/L) and serum potassium (3.1 mmol/L), as well as elevated serum creatinine (115 µmol/L), urea (8.6 mmol/L), and C-reactive protein (80 mg/L). By contrast, at the second and the third admission, these indices were all normal. Through three admissions, IL-2 increased from 0.14 pg/mL, 0.69 pg/mL, to 0.91 pg/mL, while IL-6 decreased from 11.78 pg/mL, 1.52 pg/mL, to 0.69 pg/mL, so did IL-10 from 5.13 pg/mL, 1.85 pg/mL, to 1.75 pg/mL. The steady declining trend was also found in TNF-α (1.49, 1.15, and 0.85 pg/mL) and IFN-γ (0.64, 0.42, and 0.27 pg/mL). The threshold cycle values of RT-PCR were 26.1, 30.5, and 23.5 for ORFlab gene, and 26.2, 30.6, and 22.7 for N gene, showing the patient had higher viral loads at the first and the third admission than during the middle term of the disease. The patient also showed substantially improved acute exudative lesions on the chest CT scanning images. CONCLUSIONS: The patient displayed declining immune responses in spite of the viral shedding for 3 months. We inferred the declining immune responses might result from the segregation of the virus from the immune system.

Pulmonary function in patients surviving to COVID-19 pneumonia.

PURPOSE: The aim of our study was to assess respiratory function at the time of clinical recovery and 6 weeks after discharge in patients surviving to COVID-19 pneumonia. METHODS: Our case series consisted of 13 patients with COVID-19 pneumonia. RESULTS: At the time of clinical recovery, FEV1 (2.07 ± 0.72 L) and FVC (2.25 ± 0.86 L) were lower compared to lower limit of normality (LLN) values (2.56 ± 0.53 L, p = 0.004, and 3.31 ± 0.65 L, p < 0.001, respectively), while FEV1/FVC (0.94 ± 0.07) was higher compared to upper limit of normality (ULN) values (0.89 ± 0.01, p = 0.029). After 6 weeks pulmonary function improved but FVC was still lower than ULN (2.87 ± 0.81, p = 0.014). CONCLUSION: These findings suggest that COVID-19 pneumonia may result in clinically relevant alterations in pulmonary function tests, with a mainly restrictive pattern.

Clinical characteristics of 2019 novel coronavirus pneumonia in Zhejiang province, China.

Since December 2019, an increasing number of cases associated with the 2019 novel coronavirus (2019­nCoV) have emerged in Wuhan, China, which has resulted in a rapid outbreak in China and worldwide. The present study aimed to describe the clinical, laboratory and radiological characteristics of 2019­nCoV pneumonia (NCP) in Zhejiang province, outside of Wuhan. A total of 74 patients with 2019­nCoV were continuously enrolled between January 22 and March 2, 2020 at Zhejiang Hospital. Diagnosis was confirmed at Zhejiang Hospital by reverse transcription­PCR (RT­PCR), which was approved by the Chinese government. Subsequently, the clinical features between positive­ and negative­NCP patients in Zhejiang were compared. Among the 74 hospitalized patients with suspected 2019­NCP, six patients (one male and five female patients) were confirmed to be infected with 2019­nCoV by RT­PCR. The average age of the confirmed patients was 40±13 years. There were three family clusters among the confirmed cases, one patient from each of these families had travel history or contact with patients from Wuhan within 2 weeks. Compared with non­NCP patients, the most common symptoms at onset for patients with NCP were fever (5/6; 83.3%) and cough (5/6; 83.3%), followed by dyspnea/pharyngalgia (2/6; 33.3%), whereas myalgia (1/6; 16.7%) and fatigue (1/6; 16.7%) were less common. All 74 patients with suspected NCP exhibited abnormal computerized tomography (CT) images. In total, 2/6 (33.3%) patients with confirmed NCP presented with bilateral pneumonia, and 21/68 (30.9%) non­NCP patients exhibited bilateral pneumonia, with bilateral distribution of patchy shadows or ground glass opacity. The present study revealed that epidemiological history was critical to the diagnosis of 2019­nCoV in low epidemic regions outside Hubei province. It was also identified that chest CT could not replace nucleic acid testing due to similar radiological manifestations.

Micronutrients as immunomodulatory tools for COVID-19 management.

COVID-19 rapidly turned to a global pandemic posing lethal threats to overwhelming health care capabilities, despite its relatively low mortality rate. The clinical respiratory symptoms include dry cough, fever, anosmia, breathing difficulties, and subsequent respiratory failure. No known cure is available for COVID-19. Apart from the anti-viral strategy, the supports of immune effectors and modulation of immunosuppressive mechanisms is the rationale immunomodulation approach in COVID-19 management. Diet and nutrition are essential for healthy immunity. However, a group of micronutrients plays a dominant role in immunomodulation. The deficiency of most nutrients increases the individual susceptibility to virus infection with a tendency for severe clinical presentation. Despite a shred of evidence, the supplementation of a single nutrient is not promising in the general population. Individuals at high-risk for specific nutrient deficiencies likely benefit from supplementation. The individual dietary and nutritional status assessments are critical for determining the comprehensive actions in COVID-19.

Respiratory viral coinfection in a birth cohort of infants in rural Nepal.

BACKGROUND: Acute respiratory illnesses are a leading cause of global morbidity and mortality in children. Coinfection with multiple respiratory viruses is common. Although the effects of each virus have been studied individually, the impacts of coinfection on disease severity are less understood. METHODS: A secondary analysis was performed of a maternal influenza vaccine trial conducted between 2011 and 2014 in Nepal. Prospective weekly household-based active surveillance of infants was conducted from birth to 180 days of age. Mid-nasal swabs were collected and tested for respiratory syncytial virus (RSV), rhinovirus, influenza, human metapneumovirus (HMPV), coronavirus, parainfluenza (HPIV), and bocavirus by RT-PCR. Coinfection was defined as the presence of two or more respiratory viruses detected as part of the same illness episode. RESULTS: Of 1730 infants with a respiratory illness, 327 (19%) had at least two respiratory viruses detected in their primary illness episode. Of 113 infants with influenza, 23 (20%) had coinfection. Of 214 infants with RSV, 87 (41%) had coinfection. The cohort of infants with coinfection had increased occurrence of fever lasting ≥ 4 days (OR 1.4, 95% CI: 1.1, 2.0), and so did the subset of coinfected infants with influenza (OR 5.8, 95% CI: 1.8, 18.7). Coinfection was not associated with seeking further care (OR 1.1, 95% CI: 0.8, 1.5) or pneumonia (OR 1.2, 95% CI: 0.96, 1.6). CONCLUSION: A high proportion of infants had multiple viruses detected. Coinfection was associated with greater odds of fever lasting for four or more days, but not with increased illness severity by other measures.

Prognostic Factors for Severe Coronavirus Disease 2019 in Daegu, Korea.

BACKGROUND: Since its first detection in December 2019, coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 infection has spread rapidly around the world. Although there have been several studies investigating prognostic factors for severe COVID-19, there have been no such studies in Korea. METHODS: We performed a retrospective observational study of 110 patients with confirmed COVID-19 hospitalized at a tertiary hospital in Daegu, Korea. Demographic, clinical, laboratory, and outcome data were collected and analyzed. Severe disease was defined as a composite outcome of acute respiratory distress syndrome, intensive care unit care, or death. RESULTS: Diabetes mellitus (odds ratio [OR], 19.15; 95% confidence interval [CI], 1.90-193.42; P = 0.012), body temperature ≥ 37.8°C (OR, 10.91; 95% CI, 1.35-88.36; P = 0.025), peripheral oxygen saturation < 92% (OR, 33.31; 95% CI, 2.45-452.22; P = 0.008), and creatine kinase-MB (CK-MB) > 6.3 (OR, 56.84; 95% CI, 2.64-1,223.78, P = 0.010) at admission were associated with higher risk of severe COVID-19. The likelihood of development of severe COVID-19 increased with an increasing number of prognostic factors. CONCLUSION: In conclusion, we found that diabetes mellitus, body temperature ≥ 37.8°C, peripheral oxygen saturation < 92%, and CK-MB > 6.3 are independent predictors of severe disease in hospitalized COVID-19 patients. Appropriate assessment of prognostic factors and close monitoring to provide the necessary interventions at the appropriate time in high-risk patients may reduce the case fatality rate of COVID-19.

Clinical characteristics of COVID-19 in children compared with adults in Shandong Province, China.

AIMS AND BACKGROUND: The COVID-19 outbreak spread in China and is a threat to the world. We reported on the epidemiological, clinical, laboratory, and radiological characteristics of children cases to help health workers better understand and provide timely diagnosis and treatment. METHODS: Retrospectively, two research centers' case series of 67 consecutive hospitalized cases including 53 adult and 14 children cases with COVID-19 between 23 Jan 2020 and 15 Feb 2020 from Jinan and Rizhao were enrolled in this study. Epidemiological, clinical, laboratory, and radiological characteristics of children and adults were analyzed and compared. RESULTS: Most cases in children were mild (21.4%) and conventional cases (78.6%), with mild clinical signs and symptoms, and all cases were of family clusters. Fever (35.7%) and dry cough (21.4%) were described as clinical manifestations in children cases. Dry cough and phlegm were not the most common symptoms in children compared with adults (p = 0.03). In the early stages of the disease, lymphocyte counts did not significantly decline but neutrophils count did in children compared with adults (p = 0.02). There was a lower level of CRP (p = 0.00) in children compared with adults. There were 8 (57.1%) asymptomatic cases and 6 (42.9%) symptomatic cases among the 14 children cases. The age of asymptomatic patients was younger than that of symptomatic patients (p = 0.03). Even among asymptomatic patients, 5 (62.5%) cases had lung injuries including 3 (60%) cases with bilateral involvement, which was not different compared with that of symptomatic cases (p = 0.58, p = 0.74). CONCLUSIONS: The clinical symptoms of children are mild, there is substantial lung injury even among children, but that there is less clinical disease, perhaps because of a less pronounced inflammatory response, and that the occurrence of this pattern appears to inversely correlate with age.

Prediction of fatal adverse prognosis in patients with fever-related diseases based on machine learning: A retrospective study.

BACKGROUND: Fever is the most common chief complaint of emergency patients. Early identification of patients at an increasing risk of death may avert adverse outcomes. The aim of this study was to establish an early prediction model of fatal adverse prognosis of fever patients by extracting key indicators using big data technology. METHODS: A retrospective study of patients' data was conducted using the Emergency Rescue Database of Chinese People's Liberation Army General Hospital. Patients were divided into the fatal adverse prognosis group and the good prognosis group. The commonly used clinical indicators were compared. Recursive feature elimination (RFE) method was used to determine the optimal number of the included variables. In the training model, logistic regression, random forest, adaboost and bagging were selected. We also collected the emergency room data from December 2018 to December 2019 with the same inclusion and exclusion criterion. The performance of the model was evaluated by accuracy, F1-score, precision, sensitivity and the areas under receiver operator characteristic curves (ROC-AUC). RESULTS: The accuracy of logistic regression, decision tree, adaboost and bagging was 0.951, 0.928, 0.924, and 0.924, F1-scores were 0.938, 0.933, 0.930, and 0.930, the precision was 0.943, 0.938, 0.937, and 0.937, ROC-AUC were 0.808, 0.738, 0.736, and 0.885, respectively. ROC-AUC of ten-fold cross-validation in logistic and bagging models were 0.80 and 0.87, respectively. The top six coefficients and odds ratio (OR) values of the variables in the Logistic regression were cardiac troponin T (CTnT) (coefficient=0.346, OR = 1.413), temperature (T) (coefficient=0.235, OR = 1.265), respiratory rate (RR) (coefficient= -0.206,OR = 0.814), serum kalium (K) (coefficient=0.137, OR = 1.146), pulse oxygen saturation (SPO2) (coefficient= -0.101, OR = 0.904), and albumin (ALB) (coefficient= -0.043, OR = 0.958). The weights of the top six variables in the bagging model were: CTnT, RR, lactate dehydrogenase, serum amylase, heartrate, and systolic blood pressure. CONCLUSIONS: The main clinical indicators of concern included CTnT, RR, SPO2, T, ALB and K. The bagging model and logistic regression model had better diagnostic performance comprehesively. Those may be conducive to the early identification of critical patients with fever by physicians.