Search

UNSTRUCTURED The COVID-19 pandemic exposed the dangers of tying healthcare delivery to brick-and-mortar healthcare facilities and has highlighted an ongoing need to create a distributed healthcare delivery ecosystem centered in patients’ homes and the community. Hospital-at-home has been practiced for several decades. However, the wide adoption and implementation of hospital-at-home by patients and service providers remain low. Based on the 5G smart hospital infrastructure, we further explored the smart home ward to extend hospital-based care services to the home setting, which strives to break through the "wall" of trapping centralized hospital-based healthcare services. The home smart ward is a seamless hospital unit managed by health professionals in the hospital. Patients at home receive hospital-level services, including medical monitoring, ward rounds, consultation, and medical care. Smart home ward can be adopted with the two hospital-at-home models: early-supported discharge (ESD) and admission avoidance (AA), offering integrated health monitoring services, medical care, and rehabilitation in the home setting.

With the rapid development of AI techniques, Computer-aided Diagnosis has attracted much attention and has been successfully deployed in many applications of health care and medical diagnosis. For some specific tasks, the learning-based system can compare with or even outperform human experts’ performance. The impressive performance owes to the excellent expressiveness and scalability of the neural networks, although the models’ intuition usually cannot be represented explicitly. Interpretability is, however, very important, even the same as the diagnosis precision, for computer-aided diagnosis. To fill this gap, our approach is intuitive to detect pneumonia interpretably. We first build a large dataset of community-acquired pneumonia consisting of 35389 cases (distinguished from nosocomial pneumonia) based on actual medical records. Second, we train a prediction model with the chest X-ray images in our dataset, capable of precisely detecting pneumonia. Third, we propose an intuitive approach to combine neural networks with an explainable model such as the Bayesian Network. The experiment result shows that our proposal further improves the performance by using multi-source data and provides intuitive explanations for the diagnosis results.

The COVID-19 pandemic has resulted in nosocomial transmission of COVID-19 within hospitals and other healthcare settings such as residential homes and primary care settings. Here, we discuss how a 5G network can be used to reduce such infections.

UNSTRUCTURED The COVID-19 pandemic has accelerated the trend of smart hospital construction that has been cooking for years. However, there is no consistent conceptualization of what a smart hospital truly entails. A few hospitals have truly reached the status of being ‘smart’ so far, primarily failing to bring systems together and consider implications from all perspectives. Hospital Intelligent Twins, a new technology integration was first introduced by Huawei at HUAWEI CONNECT 2020, that powered by IoT, AI and cloud computing, as well as 5G application to create all-scenario intelligence for health care and hospital management.This article presents a smart hospital for all-scenario intelligence by creating the hospital Intelligent Twins.

Background The outbreak of COVID-19 has caused a continuing global pandemic. Hospitals are integral to the control and prevention of COVID-19; however, they are facing numerous challenges during the epidemic. Objective Our study aimed to introduce the practical experience of the design and implementation of a web-based COVID-19 service platform at a tertiary hospital in China as well as the preliminary results of the implementation. Methods The web-based COVID-19 service platform was deployed within the health care system of the Guangdong Second Provincial General Hospital and Internet Hospital; the function of the platform was to provide web-based medical services for both members of the public and lay health care workers. The focal functions of this system included automated COVID-19 screening, related symptom monitoring, web-based consultation, and psychological support; it also served as a COVID-19 knowledge hub. The design and process of each function are introduced. The usage data for the platform service were collected and are represented by three periods: the pre-epidemic period (December 22, 2019, to January 22, 2020, 32 days), the controlled period (January 23 to March 31, 2020, 69 days), and the postepidemic period (April 1 to June 30, 2020, 91 days). Results By the end of June 2020, 96,642 people had used the automated COVID-19 screening and symptom monitoring systems 161,884 and 7,795,194 times, respectively. The number of general web-based consultation services per day increased from 30 visits in the pre-epidemic period to 122 visits during the controlled period, then dropped to 73 visits in the postepidemic period. The psychological counseling program served 636 clients during the epidemic period. For people who used the automated COVID-19 screening service, 160,916 (99.40%) of the total users were classified in the no risk category. 464 (0.29%) of the people were categorized as medium to high risk, and 12 people (0.01%) were recommended for further COVID-19 testing and treatment. Among the 96,642 individuals who used the COVID-19 related symptoms monitoring service, 6696 (6.93%) were symptomatic at some point during the monitoring period. Fever was the most frequently reported symptom, with 2684/6696 symptomatic people (40.1%) having had this symptom. Cough and sore throat were also relatively frequently reported by the 6696 symptomatic users (1657 people, 24.7%, and 1622 people, 24.2%, respectively). Conclusions The web-based COVID-19 service platform implemented at a tertiary hospital in China is exhibited to be a role model for using digital health technologies to respond to the COVID-19 pandemic. The digital solutions of automated COVID-19 screening, daily symptom monitoring, web-based care, and knowledge propagation have plausible acceptability and feasibility for complementing offline hospital services and facilitating disease control and prevention.

BACKGROUND The outbreak of COVID-19 has caused a continuing global pandemic. Hospitals are integral to the control and prevention of COVID-19; however, they are facing numerous challenges during the epidemic. OBJECTIVE Our study aimed to introduce the practical experience of the design and implementation of a web-based COVID-19 service platform at a tertiary hospital in China as well as the preliminary results of the implementation. METHODS The web-based COVID-19 service platform was deployed within the health care system of the Guangdong Second Provincial General Hospital and Internet Hospital; the function of the platform was to provide web-based medical services for both members of the public and lay health care workers. The focal functions of this system included automated COVID-19 screening, related symptom monitoring, web-based consultation, and psychological support; it also served as a COVID-19 knowledge hub. The design and process of each function are introduced. The usage data for the platform service were collected and are represented by three periods: the pre-epidemic period (December 22, 2019, to January 22, 2020, 32 days), the controlled period (January 23 to March 31, 2020, 69 days), and the postepidemic period (April 1 to June 30, 2020, 91 days). RESULTS By the end of June 2020, 96,642 people had used the automated COVID-19 screening and symptom monitoring systems 161,884 and 7,795,194 times, respectively. The number of general web-based consultation services per day increased from 30 visits in the pre-epidemic period to 122 visits during the controlled period, then dropped to 73 visits in the postepidemic period. The psychological counseling program served 636 clients during the epidemic period. For people who used the automated COVID-19 screening service, 160,916 (99.40%) of the total users were classified in the no risk category. 464 (0.29%) of the people were categorized as medium to high risk, and 12 people (0.01%) were recommended for further COVID-19 testing and treatment. Among the 96,642 individuals who used the COVID-19 related symptoms monitoring service, 6696 (6.93%) were symptomatic at some point during the monitoring period. Fever was the most frequently reported symptom, with 2684/6696 symptomatic people (40.1%) having had this symptom. Cough and sore throat were also relatively frequently reported by the 6696 symptomatic users (1657 people, 24.7%, and 1622 people, 24.2%, respectively). CONCLUSIONS The web-based COVID-19 service platform implemented at a tertiary hospital in China is exhibited to be a role model for using digital health technologies to respond to the COVID-19 pandemic. The digital solutions of automated COVID-19 screening, daily symptom monitoring, web-based care, and knowledge propagation have plausible acceptability and feasibility for complementing offline hospital services and facilitating disease control and prevention.

COVID-19 is an emerging disease with transmissibility and severity. So far, there are no effective therapeutic drugs or vaccines for COVID-19. The most serious complication of COVID-19 is a type of pneumonia called 2019 novel coronavirus-infected pneumonia (NCIP) with about 4.3% mortality rate. Comparing to chest Digital Radiography (DR), it is recently reported that chest Computed Tomography (CT) is more useful to serve as the early screening and diagnosis tool for NCIP. In this study, aimed to help physicians make the diagnostic decision, we develop a machine learning (ML) approach for automated diagnosis of NCIP on chest CT. Different from most ML approaches which often require training on thousands or millions of samples, we design a few-shot learning approach, in which we combine few-shot learning with weakly supervised model training, for computerized NCIP diagnosis. A total of 824 patients are retrospectively collected from two Hospitals with IRB approval. We first use 9 patients with clinically confirmed NCIP and 20 patients without known lung diseases for training a location detector which is a multitask deep convolutional neural network (DCNN) designed to output a probability of NCIP and the segmentation of targeted lesion area. An experienced radiologist manually localizes the potential locations of NCIPs on chest CTs of 9 COVID-19 patients and interactively segments the area of the NCIP lesions as the reference standard. Then, the multitask DCNN is furtherly fine-tuned by a weakly supervised learning scheme with 291 case-level labeled samples without lesion labels. A test set of 293 patients is independently collected for evaluation. With our NCIP-Net, the test AUC is 0.91. Our system has potential to serve as the NCIP screening and diagnosis tools for the fight of COVID-19's endemic and pandemic.

UNSTRUCTURED In this viewpoint, we shared the experience of using telemedicine services to bridge the gap of medical services needs when facility-based services were shut down in response to the COIVD-19 epidemic in China. This story in addition to other similar ones is evidence that several lessons can be drawn from the implementation of telemedicine care during this COVID-19 outbreak.

Cardiotocography (CTG) is widely used in fetal monitoring, especially in the diagnosis of fetal acidosis. However, the manual interpretation of CTG analysis may easily lead to a low diagnostic rate, usually caused by various subjective factors. In order to reduce misdiagnosis, we propose an attention-based CNN-BiLSTM hybrid neural network enhanced with features of discrete wavelet transformation (DWT) for fetal acidosis classification. A joint model of convolutional neural network (CNN) and bi-directional long short-term memory (BiLSTM) is established to capture the complex nonlinear spatial and temporal relations of fetal heart rate (FHR) signals. The attention mechanism is then adopted to focus on important input features. And DWT is used to obtain FHR signals transformation coefficient features in order to reduce overfitting. Two features are fused together to classify fetal acidosis. This study uses signals from the public databases of the CTU-UHB for evaluation. A ten different verifications yields average sensitivity (SE), specificity (SP), and quality index (QI) of 75.23%, 70.82% and 72.29%, respectively. Our approach achieves better experimental results than previous works. Moreover, Our hybrid model is an end to end one, with a much simpler DWT feature extraction. With the advent of the big data era, our hybrid model will have great advantages.

ObjectivesHyperuricaemia has been reported to be significantly associated with risk of obesity. However, previous studies on the association between serum uric acid (SUA) and body mass index (BMI) yielded conflicting results. The present study examined the relationship between SUA and obesity among Chinese adults.MethodsData were collected at Guangdong Second Provincial General Hospital in Guangzhou City, China, between January 2010 and December 2018. Participants with ≥2 medical check-up times were included in our analyses. Physical examinations and laboratory measurement variables were obtained from the medical check-up system. The high SUA level group was classified as participants with hyperuricaemia, and obesity was defined as BMI ≥28 kg/m2. Logistic regression model was performed for data at baseline. For all participants, generalised estimation equation (GEE) model was used to assess the association between SUA and obesity, where the data were repeatedly measured over the 9-year study period. Subgroup analyses were performed by gender and age group. We calculated the cut-off values for SUA of obesity using the receiver operating characteristic curves (ROC) technique.ResultsA total of 15 959 participants (10 023 men and 5936 women) were included in this study, with an average age of 37.38 years (SD: 13.27) and average SUA of 367.05 μmol/L (SD: 97.97) at baseline, respectively. Finally, 1078 participants developed obesity over the 9-year period. The prevalence of obesity was approximately 14.2% for high SUA level. In logistic regression analysis at baseline, we observed a positive association between SUA and risk of obesity: OR=1.84 (95% CI: 1.77 to 1.90) for per-SD increase in SUA. Considering repeated measures over 9 year for all participants in the GEE model, the per-SD OR was 1.85 (95% CI: 1.77 to 1.91) for SUA and the increased risk of obesity were greater for men (OR=1.45) and elderly participants (OR=1.01). In subgroup analyses by gender and age, we observed significant associations between SUA and obesity with higher risk in women (OR=2.35) and young participants (OR=1.87) when compared with men (OR=1.70) and elderly participants (OR=1.48). The SUA cut-off points for risk of obesity using ROC curves were approximately consistent with the international standard.ConclusionsOur study observed higher SUA level was associated with increased risk of obesity. More high-quality research is needed to further support these findings.