The Syncretic Effect of Dual-Source Data on Affective Computing in Online Learning Contexts: A Perspective from Convolutional Neural Network with Attention Mechanism

Affective computing (AC) has been regarded as a relevant approach to identifying online learners' mental states and predicting their learning performance. Previous research mainly used one single-source data set, typically learners' facial expression, to compute learners' affection. However, a single facial expression may represent different affections in various head poses. This study proposed a dual-source data approach to solve the problem. Facial expression and head pose are two typical data sources that can be captured from online learning videos. The current study collected a dual-source data set of facial expressions and head poses from an online learning class in a middle school. A deep learning neural network using AlexNet with an attention mechanism was developed to verify the syncretic effect on affective computing of the proposed dual-source fusion strategy. The results show that the dual-source fusion approach significantly outperforms the single-source approach based on the AC recognition accuracy between the two approaches (dual-source approach using Attention-AlexNet model 80.96%;single-source approach, facial expression 76.65% and head pose 64.34%). This study contributes to the theoretical construction of the dual-source data fusion approach, and the empirical validation of the effect of the Attention-AlexNet neural network approach on affective computing in online learning contexts.

Clinical characteristics and outcome of COVID-19 patients with Parkinson's disease: a hospital-based case-control study in Shanghai, China.

Background: Clinical manifestations of Parkinson's disease (PD) after Corona Virus Disease 2019 (COVID-19) infection are poorly investigated. Objective: We aimed to explore the clinical features and outcomes of hospitalized PD patients with COVID-19. Methods: A total of 48 PD patients and 96 age-and sex-matched non-PD patients were included. Demographics, clinical characteristics and outcomes were compared between two groups. Results: PD patients with COVID-19 were elderly (76.69 ± 9.21 years) with advanced stage (H-Y stage 3-5 as 65.3%). They had less clinical symptoms (nasal obstruction, etc.), more proportions of severe/critical COVID-19 clinical classification (22.9 vs. 1.0%, p < 0.001), receiving oxygen (29.2 vs. 11.5%, p = 0.011), antibiotics (39.6 vs. 21.9%, p = 0.031) therapies, as well as longer hospitalization duration (11.39 vs. 8.32, p = 0.001) and higher mortality (8.3% vs. 1.0%, p = 0.001) relative to those without PD. Laboratory results showed that the PD group had higher white blood cell counts (6.29 vs. 5.16*109, p = 0.001), neutrophil-to-lymphocyte ratio (3.14 vs. 2.11, p < 0.001) and C-reactive protein level (12.34 vs. 3.19, p < 0.001). Conclusion: PD patients with COVID-19 have insidious clinical manifestation, elevated proinflammatory markers and are prone to the development of severe/critical condition, contributing to a relatively poor prognosis. Early identification and active treatment of COVID-19 are pivotal to advanced PD patients during the pandemic.

Prevention of nosocomial COVID-19 infections in a designated hospital for children in Guangzhou, China

Background: Guangzhou Women and Children's Medical Center was chosen as the designated facility for screening, diagnosing, and treating children in Guangzhou with SARS-CoV-2 infection after the COVID-19 outbreak in China. From January 23 to March 20, 2020, the center opened new wards for screening and treatment, taking measures to prevent and control nosocomial infections. This article summarizes and evaluates measures for preventing and controlling nosocomial infections to provide reference information during the pandemic. Methods: The COVID-19 nosocomial infection prevention and control strategies were summarized and analyzed, including the formulation of the hospital partition, the improvement of the hospitalization process, environmental cleaning and disinfection, graded protection based on risk assessment, enhanced training on-site quality control inspection, data monitoring and evaluation, among others, and evaluating the effects by comparing before and after the intervention. Results: There were 159 patients admitted to the screening wards, including 98 males and 61 females, with a median age of 34 years (interquartile range (IQR): 15, 60) months. There were no abnormal findings in these patients and their families during follow-up. During the screening ward opening period, hand hygiene compliance was significantly improved. Fifty staff members in close contact with the contaminated area had tested for SARS-CoV-2 nucleic acid by polymerase chain reaction (PCR), which showed zero infections and no nosocomial infections occurred. Conclusions: For SARS-CoV-2 nosocomial infections, taking the "standard prevention & contact isolation & droplet isolation & air isolation" strategies can prevent patients and staff effectively.

Neurological Manifestations of hospitalized patients with mild to moderate infection with SARS-CoV-2 Omicron variant in Shanghai, China.

BACKGROUND: Accumulating studies demonstrated that patients with coronavirus disease 2019(COVID-19) could develop a variety of neurological manifestations and long-term neurological sequelae, which may be different from the strains. At the peak of the Omicron variant outbreak in Shanghai, China, no relevant epidemiological data about neurological manifestations associated with this strain was reported. OBJECTIVE: To investigate neurological manifestations and related clinical features in patients with mild to moderate COVID-19 patients with Omicron variant. METHODS: A self-designed clinical information registration form was used to gather the neurological manifestations of mild to moderate COVID-19 patients admitted to a designated hospital in Shanghai from April 18, 2022 to June 1, 2022. Demographics, clinical presentations, laboratory findings, treatments and clinical outcomes were compared between patients with and without neurological manifestations. RESULTS: One hundred sixty-nine(48.1 %) of 351 patients diagnosed with mild to moderate COVID-19 exhibited neurological manifestations, the most common of which were fatigue/weakness(25.1 %) and myalgia(20.7 %), whereas acute cerebrovascular disease(0.9 %), impaired consciousness(0.6 %) and seizure(0.6 %) were rare. Younger age(p = 0.001), female gender(p = 0.026) and without anticoagulant medication(p = 0.042) were associated with increasing proportions of neurological manifestations as revealed by multivariate logistic regressions. Patients with neurological manifestations had lower creatine kinase and myoglobin levels, as well as higher proportion of patchy shadowing on chest scan. Vaccination status, clinical classification of COVID-19 and clinical outcomes were similar between the two groups. CONCLUSIONS: Nearly half of the involved patients have neurological manifestations which were relatively subjective and closely associated with younger age, female gender and without anticoagulation. Patients with neurologic manifestations may be accompanied by increased lung patchy shadowing.

Psychological and sleep disturbances among first-line, second-line, and at home medical staff during the COVID-19 pandemic in Shanghai, China.

Objectives: Medical workers are prone to psychological and sleep disturbances during the coronavirus disease 2019 (COVID-19) pandemic. Little is known about the varying degrees of influence among vaccinated medical staff working in different positions. The current study is aimed to evaluate and compare depression, anxiety and sleep disturbances among first-line, second-line and at home vaccinated medical staff during the COVID-19 pandemic in Shanghai, China. Methods: A cross-sectional online survey was conducted in May 2022. In addition to demographic data, levels of depression, anxiety, sleep quality, and insomnia were measured using the Patient Health Questionnaire-9 (PHQ-9), Generalized Anxiety Disorder-7 (GAD-7), Pittsburgh Sleep Quality Index (PSQI), and Athens Insomnia Scale (AIS). Results: A total of 236 vaccinated medical workers completed the questionnaires, including 85 first-line medical staff (FMS), 82 second-line medical staff (SMS) and 69 at home medical staff (HMS). The proportions of depressive symptoms, anxiety symptoms, poor sleep quality, and insomnia were 52.1, 44.1, 55.9, and 49.2%, respectively. Compared with HMS, medical staff at work (FMS and SMS) got significantly higher frequency of poor sleep quality (both p < 0.001), insomnia (both p < 0.001), depressive (p < 0.001 and p = 0.003, respectively) and anxiety symptoms (p < 0.001 and p = 0.002, respectively). Compared with SMS, FMS were more likely to have poor sleep quality (p = 0.020). Besides, nurses got significantly higher percentage of poor sleep quality (OR = 1.352, p = 0.016) and insomnia (OR = 1.243, p = 0.041) than doctors. Whereas, the proportion of anxiety symptoms was increased in females than in males (OR = 2.772, p = 0.008). Conclusions: Psychological and sleep disturbances are common among medical staff at work during the COVID-19 pandemic. More psychological intervention should be administrated for FMS, especially for nurses.

Clinical characteristics and short-term recovery of hyposmia in hospitalized non-severe COVID-19 patients with Omicron variant in Shanghai, China.

Background: Olfactory dysfunction is a common neurological symptom of Corona Virus Disease 2019(COVID-19). Little is known about hyposmia after COVID-19 infection with Omicron variant in Chinese population. Objective: To investigate the incidence, clinical characteristics and recovery of hyposmia in hospitalized non-severe COVID-19 patients with Omicron variant in Shanghai, China. Methods: Three hundred and forty-nine Chinese non-severe COVID-19 patients with Omicron variant were consecutively enrolled in a designated hospital to investigate the incidence of hyposmia in hospitalization and the recovery rate 1 month later. The visual assessment scale (VAS) was used to evaluate the severity of hyposmia. We compared the demographic, clinical features and treatment outcomes, as well as laboratory parameters between patients with and without hyposmia. Results: The cross-sectional survey showed that 22 (6.3%) hospitalized patients with non-severe COVID-19 had hyposmia. Patients with hyposmia were younger (61.5 vs. 72.0, p = 0.002), had more related clinical symptoms (sore throat, cough, poor appetite, diarrhea, myalgia and taste impairment, etc.), a higher proportion of moderate clinical type (31.8 vs. 13.5%, p = 0.028) and longer duration of hospitalization (11 vs. 8 days, p = 0.027) than those without hyposmia. Whereas, there were no significant differences regarding gender, comorbidity and nucleic acid conversion time between the two groups. Laboratory subgroup analyses demonstrated that patients with hyposmia had slightly low serum IL-6 and TNF-α levels. However, both of the levels were not associated with hyposmia occurrence in multivariate regression analyses. Further follow-up study disclosed that 16 of 22 (72.7%) hyposmia patients had recovered olfaction 1 month later. Serum IL-6 and TNF-α levels were similar between hyposmia recovered patients and those with persistent hyposmia. Conclusion: Although the incidence of hyposmia after Omicron variant infection is relatively low and the short-term recovery rate is quite high, patients with hyposmia are prone to have a higher proportion of both upper and lower respiratory tract involvements, gastrointestinal and neurological symptoms, contributing to a longer duration of hospitalization.

Designing an optimization model for the vaccine supply chain during the COVID-19 pandemic.

The COVID-19 pandemic has affected people's lives worldwide. Among various strategies being applied to addressing such a global crisis, public vaccination has been arguably the most appropriate approach to control a pandemic. However, vaccine supply chain and management have become a new challenge for governments. In this study, a solution for the vaccine supply chain is presented to address the hurdles in the public vaccination program according to the concerns of the government and the organizations involved. For this purpose, a robust bi-level optimization model is proposed. At the upper level, the risk of mortality due to the untimely supply of the vaccine and the risk of inequality in the distribution of the vaccine is considered. All costs related to the vaccine supply chain are considered at the lower level, including the vaccine supply, allocation of candidate centers for vaccine injection, cost of maintenance and injection, transportation cost, and penalty cost due to the vaccine shortage. In addition, the uncertainty of demand for vaccines is considered with multiple scenarios of different demand levels. Numerical experiments are conducted based on the vaccine supply chain in Kermanshah, Iran, and the results show that the proposed model significantly reduces the risk of mortality and inequality in the distribution of vaccines as well as the total cost, which leads to managerial insights for better coordination of the vaccination network during the COVID-19 pandemic.

Exploratory Research on Satisfaction Degree in Distance Education

In order to solve the education problems caused by teachers and students' unavoidable absence in school during the COVID-19 pandemic, a series of online education activities were carried out by Nanjing University of Posts and Telecommunication in early March. To explore students and teachers' degree of satisfaction with distance education, this paper investigates multiple dimensions such as students' degree of satisfaction with teachers, the regional living standard, educational resources and negative factors that reduce the students' degree of satisfaction, etc. Furthermore, the attitude of teachers toward distance education may be partially reflected by the arrangement of live classes. All of the statistics are analyzed by comparing the distribution of votes. The results show that the degree of satisfaction by students and teachers with distance education is generally high but varies in areas with different living standards. In addition, we find that students are more sensitive to the lack of a learning atmosphere.

Case Report of China/Tianjin's First Novel Coronavirus Variant Omicron.

COVID-19 is a new acute respiratory infectious disease caused by a novel Coronavirus (2019-COV-2) infection. On November 26, 2021, the World Health Organization announced a new 2019-COV-2 variant strain Omicron (B.1.1.529). Omicron's emergence added further uncertainty to the outbreak. Here we report the first case infected with Omicron in China, a 17-year-old female student. In this paper, the clinical symptoms, laboratory and imaging examinations and treatment of the first Omicron-infected patient in China were analyzed. This report might provide a reference for the diagnosis and treatment of patients infected with Omicron strain across the world. The novel Coronavirus antibody tests were performed on the day of admission: IgM level was normal, novel Coronavirus antibody IgG was 132.666s /CO and IgG was 148.47s /CO on the 7th day of admission. IgG showed an increasing trend, which is consistent with the results of multiple novel Coronavirus non-Omicron strain infections.

Mycoplasma pneumoniae and Adenovirus Coinfection Cause Pediatric Severe Community-Acquired Pneumonia.

Consolidation is one complication of pediatric severe community-acquired pneumonia (SCAP) that can respond poorly to conservative medical treatment. We investigated the pathogens that cause pediatric SCAP including cases with persistent consolidation that need bronchoscopy intervention. Alveolar lavage fluid (ALF) samples collected from cases admitted to Children's Hospital of Fudan University with SCAP during January 2019 to March in 2019 were retrospectively tested by the RespiFinder 2SMART multiplex PCR (multi-PCR) assay targeting 22 respiratory pathogens. A total of 90 cases and 91 samples were enrolled; 80.0% (72/90) of the cases had pulmonary consolidation and/or atelectasis. All samples were positive with targeted pathogens tested by multi-PCR, and 92.3% (84/91) of the samples were co-detected with pathogens. Mycoplasma pneumoniae (MP) and adenovirus (ADV) as the two dominant pathogens, with the positive rates of 96.7% (88/91) and 79.1% (72/91), respectively. Most of the samples were positive with MP and ADV simultaneously. As a control, 78.0% (71/91) of the samples were positive by conventional tests (CT), in which MP had the detection rate of 63.9% (55/86) by a traditional real-time PCR assay, while ADV were positive in 13.1% (12/91) of the samples by a direct immunofluorescence assay (DFA). In cases with persistent pulmonary consolidation, the positive rates of pathogens by multi-PCR and CT were 100% (72/72) and 81.9% (59/72), respectively. There were no significant differences of MP or ADV positive rates between cases with and without pulmonary consolidation. MP and ADV most prevalent in pediatric SCAP cases required fiberscope intervention, and presented with coinfections dominantly. IMPORTANCE Pathogens that cause pediatric severe community-acquired pneumonia (SCAP) requiring bronchoscopy intervention are understudied. Through this study, we explore the etiology of SCAP form alveolar lavage fluid (ALF) samples by the RespiFinder 2SMART multi-PCR assay. It is observed that high mixed detection rates of Mycoplasma pneumoniae and adenovirus in ALF samples collected from hospitalized SCAP children experienced bronchoscopy intervention. Eighty percent of the cases had pulmonary consolidation and/or atelectasis. The presence of possible coinfection of these two pathogens might contribute to poor clinical anti-infection response. The results of this study might be helpful for the selection of clinical strategies for the empirical treatment of such pediatric SCAP cases.

Successful combinatorial therapy of sirolimus and neuraminidase inhibitors in a patient with highly pathogenic avian influenza A (H5N6) virus: a case report

Background Highly pathogenic avian influenza A (H5N6) virus poses a continuous threat to human health since 2014. Although neuraminidase inhibitors (NAIs) are prescribed in most patients infected with the H5N6 virus, the fatality remains high, indicating the need for an improved treatment regimen. Sirolimus, an inhibitor of the mammalian target of rapamycin (mTOR), has been reported to reduce viral replication and improve clinical outcomes in severe H1N1 infections when combined with oseltamivir. Here, we report the first case of severe H5N6 pneumonia successfully treated by sirolimus and NAIs. Case Description A 22-year-old man developed high fever and chills on September 24, 2018 (Day-0) and was hospitalized on Day-3. Influenza A (H5N6) was identified on Day-6 from a throat swab specimen. Despite the administration of NAIs and other supportive measures, the patient’s clinical conditions and lung images showed continued deterioration, accompanied by persistently high viral titers. Consequently, sirolimus administration (rapamycin;2 mg per day for 14 days) was started on Day-12. His PaO2/FiO2 values and Sequential Organ Failure Assessment (SOFA) score gradually improved, and imaging outcomes revealed the resolution of bilateral lung infiltrations. The viral titer gradually decreased and turned negative on Day-25. Sirolimus and NAIs were stopped on the same day. The patient was discharged on Day-65. Based on observations from a 2-year follow-up, the patient was found to be in a good condition without complications. Conclusions In conclusion, sirolimus might be a novel and practical therapeutic approach to severe H5N6-associated pneumonia in humans.

The occurrence and risk factors associated with post-traumatic stress disorder among discharged COVID-19 patients in Tianjin, China.

BACKGROUND: Post-traumatic stress disorder (PTSD) is a serious mental health condition that is triggered by a terrifying event. We aimed to investigate the occurrence and risk factors of PTSD among discharged COVID-19 patients. METHODS: This study included 144 discharged COVID-19 patients. PTSD was assessed by using validated cut-offs of the impact of event scale-revised (IES-R, score ≥25). All patients completed a detailed questionnaire survey, and clinical parameters were routinely measured in the hospital. Binary logistic regression models were applied to identify factors associated with PTSD. RESULTS: Of the 144 participants with laboratory-confirmed COVID-19, the occurrence of PTSD was 16.0%. In multivariable analyses, age above 40 years (adjusted OR [95% CI], 5.19 [2.17-12.32]), female sex (adjusted OR [95% CI], 7.82 [3.18-18.21]), current smoker (adjusted OR [95% CI], 6.72 [3.23-15.26]), and ≥3 involved pulmonary lobes (adjusted OR [95% CI], 5.76 [1.19-15.71]) were significantly associated with a higher risk of PTSD. Conversely, history of hypertension and serum hemoglobin levels were significantly associated with a lower risk of PTSD with adjusted ORs (95% CI) of 0.37 (0.12-0.87) and 0.91 (0.82-0.96), respectively. CONCLUSION: Old age, gender (being female), current smoking, bacterial pneumonia, and ≥3 involved pulmonary lobes were associated with an increased occurrence of PTSD among discharged COVID-19 patients.

Relationship between lung injury extent and phenotype manifested in non-contrast CT and cardiac injury during acute stage of COVID-19.

PURPOSE: This study evaluated the diagnostic values of the extent of lung injury manifested in non-contrast enhanced CT (NCCT) images, the inflammatory and immunological biomarkers C-reactive protein (CRP) and lymphocyte for detecting acute cardiac injury (ACI) in patients with COVID-19. The correlations between the NCCT-derived parameters and arterial blood oxygen level were also investigated. METHODS: NCCT lung images and blood tests were obtained in 143 patients with COVID-19 in approximately two weeks after symptom onset, and arterial blood gas measurement was also acquired in 113 (79%) patients. The diagnostic values of normal, moderately and severely abnormal lung parenchyma volume relative to the whole lungs (RVNP, RVMAP, RVSAP, respectively) measured from NCCT images for detecting the heart injury confirmed with high-sensitivity troponin I assay was determined. RESULTS: RVNP, RVMAP and RVSAP exhibited similar accuracy for detecting ACI in COVID-19 patients. RVNP was significantly lower while both RVMAP and RVSAP were significantly higher in the patients with ACI. All of the NCCT-derived parameters exhibited poor linear and non-linear correlations with PaO2 and SaO2. The patients with ACI had a significantly higher CRP level but a lower lymphocyte level compared to the patients without ACI. Combining one of these two biomarkers with any of the three NCCT-derived parameter further improved the accuracy for predicting ACI in patients with COVID-19. CONCLUSION: The NCCT-delineated normal and abnormal lung parenchmyma tissues were statistically significant predictors of ACI in patients with COVID-19, but both exhibited poor correlations with the arterial blood oxygen level. The incremental diagnostic values of lymphocyte and CRP suggested viral infection and inflammation were closely related to the heart injury during the acute stage of COVID-19.

Deep Learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) With CT Images.

A novel coronavirus (COVID-19) recently emerged as an acute respiratory syndrome, and has caused a pneumonia outbreak world-widely. As the COVID-19 continues to spread rapidly across the world, computed tomography (CT) has become essentially important for fast diagnoses. Thus, it is urgent to develop an accurate computer-aided method to assist clinicians to identify COVID-19-infected patients by CT images. Here, we have collected chest CT scans of 88 patients diagnosed with COVID-19 from hospitals of two provinces in China, 100 patients infected with bacteria pneumonia, and 86 healthy persons for comparison and modeling. Based on the data, a deep learning-based CT diagnosis system was developed to identify patients with COVID-19. The experimental results showed that our model could accurately discriminate the COVID-19 patients from the bacteria pneumonia patients with an AUC of 0.95, recall (sensitivity) of 0.96, and precision of 0.79. When integrating three types of CT images, our model achieved a recall of 0.93 with precision of 0.86 for discriminating COVID-19 patients from others. Moreover, our model could extract main lesion features, especially the ground-glass opacity (GGO), which are visually helpful for assisted diagnoses by doctors. An online server is available for online diagnoses with CT images by our server (http://biomed.nscc-gz.cn/model.php). Source codes and datasets are available at our GitHub (https://github.com/SY575/COVID19-CT).

A coarse-refine segmentation network for COVID-19 CT images.

The rapid spread of the novel coronavirus disease 2019 (COVID-19) causes a significant impact on public health. It is critical to diagnose COVID-19 patients so that they can receive reasonable treatments quickly. The doctors can obtain a precise estimate of the infection's progression and decide more effective treatment options by segmenting the CT images of COVID-19 patients. However, it is challenging to segment infected regions in CT slices because the infected regions are multi-scale, and the boundary is not clear due to the low contrast between the infected area and the normal area. In this paper, a coarse-refine segmentation network is proposed to address these challenges. The coarse-refine architecture and hybrid loss is used to guide the model to predict the delicate structures with clear boundaries to address the problem of unclear boundaries. The atrous spatial pyramid pooling module in the network is added to improve the performance in detecting infected regions with different scales. Experimental results show that the model in the segmentation of COVID-19 CT images outperforms other familiar medical segmentation models, enabling the doctor to get a more accurate estimate on the progression of the infection and thus can provide more reasonable treatment options.

Identification and analysis of odor-active compounds from Choerospondias axillaris (Roxb.) Burtt et Hill with different moisture content levels and lacquer treatments.

The problem of indoor odors can greatly affect a room's occupants. To identify odorants and comprehensively evaluate emissions from wooden materials, emissions and odors from Choerospondias axillaris (Roxb.) Burtt et Hill with different moisture content percentages and lacquer treatments were investigated in this study. Thermal desorption-gas chromatography-mass spectroscopy/olfactometry was used to analyze the release characteristics. In total, 11 key odor-active compounds were identified as moisture content gradually decreased, concentrating between 15 and 33 min. Total volatile organic compounds, total very volatile organic compounds, and total odor intensity decreased as moisture content decreased. In addition, 35 odor-active compounds, including aromatics, alkenes, aldehydes, esters, and alcohols, were identified in the odor control list. Polyurethane (PU), ultraviolet (UV), and waterborne coatings had a good inhibitory effect on eight odor characteristics, but some scents arose after lacquer treatment. For equilibrium moisture content, the major characteristics of Choerospondias axillaris were fragrant (9.4) and mint-like (3.0) compared with the fragrant (8.2), fruity (7.8), and pleasant (5.8) characteristics of PU coating; the flowery (5.9), fragrant (5.0), glue-like (4.3), and pineapple-like (4.3) characteristics of UV coating; and the antiseptic solution (3.6), fragrant (2.9), cigarette-like (2.8), and fruity (2.5) characteristics of waterborne coating. Based on multicomponent evaluation, a Choerospondias axillaris board with waterborne coating was suggested for use indoors.

Epidemiology of Viruses Causing Pediatric Community Acquired Pneumonia in Shanghai During 2010-2020: What Happened Before and After the COVID-19 Outbreak?

INTRODUCTION: Since the global outbreak of COVID-19, there has been a significant reduction in pediatric outpatient and emergency visits for infectious diseases. The purpose of this study was to analyze the changes in respiratory viruses in children with community-acquired pneumonia (CAP) in Shanghai in the past 10 years, especially in the first year after COVID-19. METHODS: We conducted a retrospective, observational study; the results for eight common respiratory viruses (respiratory syncytial virus (RSV), influenza virus A and B, parainfluenza virus 1-3 (PIV), adenovirus (ADV) and human metapneumovirus) tested by direct fluorescent antibody assays in hospitalized CAP cases in Children's Hospital of Fudan University during 2010-2020 were analyzed. RESULTS: Of the 5544 hospitalized CAP patients included in this study, 20.2% (1125/5544) were positive for the eight respiratory viruses. The top three pathogens were RSV, PIV3 and ADV, detected from 9.8% (543/5544), 5.3% (294/5544) and 2.0% (111/5544) of the samples, respectively. RSV had the highest positive rates among children < 2 years old. In 2020, the detection rate of all viruses showed a sharp decline from February to August compared with the previous 9 years. When the Shanghai community reopened in August 2020, the detection rate of eight viruses rebounded significantly in September. CONCLUSIONS: These eight respiratory viruses, especially RSV and PIV, were important pathogens of CAP in Shanghai children in the past 10 years. The COVID-19 pandemic had a significant impact on the detection rates for eight respiratory viruses in children with CAP in Shanghai.

Clinical longitudinal evaluation of COVID-19 patients and prediction of organ-specific recovery using artificial intelligence.

Within COVID-19 there is an urgent unmet need to predict at the time of hospital admission which COVID-19 patients will recover from the disease, and how fast they recover to deliver personalized treatments and to properly allocate hospital resources so that healthcare systems do not become overwhelmed. To this end, we have combined clinically salient CT imaging data synergistically with laboratory testing data in an integrative machine learning model to predict organ-specific recovery of patients from COVID-19. We trained and validated our model in 285 patients on each separate major organ system impacted by COVID-19 including the renal, pulmonary, immune, cardiac, and hepatic systems. To greatly enhance the speed and utility of our model, we applied an artificial intelligence method to segment and classify regions on CT imaging, from which interpretable data could be directly fed into the predictive machine learning model for overall recovery. Across all organ systems we achieved validation set area under the receiver operator characteristic curve (AUC) values for organ-specific recovery ranging from 0.80 to 0.89, and significant overall recovery prediction in Kaplan-Meier analyses. This demonstrates that the synergistic use of an artificial intelligence (AI) framework applied to CT lung imaging and a machine learning model that integrates laboratory test data with imaging data can accurately predict the overall recovery of COVID-19 patients from baseline characteristics.

Timing of invasive mechanic ventilation in critically ill patients with coronavirus disease 2019.

BACKGROUND: Invasive mechanical ventilation (IMV) is a lifesaving strategy for critically ill patients with coronavirus disease 2019 (COVID-19). We aim to report the case series of critical patients receiving IMV in Wuhan and to discuss the timing of IMV in these patients. METHODS: Data of 657 patients admitted to emergency intensive care unit of Zhongnan Hospital and isolated isolation wards of Wuhan Union Hospital from January 1 to March 10, 2020, were retrospectively reviewed. All medical records of 40 COVID-19 patients who required IMV were collected at different time points, including baseline (at admission), before receiving IMV, and before death or hospital discharge. RESULTS: Among 40 COVID-19 patients with IMV, 31 died, and 9 survived and was discharged. The median age was 70 years (interquartile range [IQR], 62-76 years), and nonsurvivors were older than survivors. The median period from the noninvasive mechanic ventilation (NIV) or high-flow nasal cannula oxygen therapy (HFNC) to intubation was 7 hours (IQR, 2-42 hours) in IMV survivors and 54 hours (IQR, 28-143 hours) in IMV nonsurvivors. We observed that, when the time interval from NIV/HFNC to intubation was less than 50 hours (about 2 calendar days), together with Acute Physiology and Chronic Health Evaluation II (APACHE II) score of less than 10 or pneumonia severity index (PSI) score of less than 100, mortality can be reduced to 60% or less. Prolonged interval from NIV/HFNC to intubation and high levels of APACHE II and PSI before intubation were associated with higher mortality in critically ill patients. Multiple organ damage was common among these nonsurvivors in the course of treatment. CONCLUSION: Early initial intubation after NIV/HFNC might have a beneficial effect in reducing mortality for critically ill patients meeting IMV indication. Considering APACHE II and PSI scores might help physicians in decision making about timing of intubation for curbing subsequent mortality. LEVEL OF EVIDENCE: Therapeutic, level V.