Background Australia has successfully controlled the COVID-19 pandemic. Similar to other high-income countries, Australia has extensively used telehealth services. Virtual health care, including telemedicine in combination with remote patient monitoring, has been implemented in certain settings as part of new models of care that are aimed at managing patients with COVID-19 outside the hospital setting. Objective This study aimed to describe the implementation of and early experience with virtual health care for community management of patients with COVID-19. Methods This observational cohort study was conducted with patients with COVID-19 who availed of a large Australian metropolitan health service with an established virtual health care program capable of monitoring patients remotely. We included patients with COVID-19 who received the health service, could self-isolate safely, did not require immediate admission to an in-patient setting, had no major active comorbid illness, and could be managed at home or at other suitable sites. Skin temperature, pulse rate, and blood oxygen saturation were remotely monitored. The primary outcome measures were care escalation rates, including emergency department presentation, and hospital admission. Results During March 11-29, 2020, a total of 162 of 173 (93.6%) patients with COVID-19 (median age 38 years, range 11-79 years), who were diagnosed locally, were enrolled in the virtual health care program. For 62 of 162 (38.3%) patients discharged during this period, the median length of stay was 8 (range 1-17) days. The peak of 100 prevalent patients equated to approximately 25 patients per registered nurse per shift. Patients were contacted a median of 16 (range 1-30) times during this period. Video consultations (n=1902, 66.3%) comprised most of the patient contacts, and 132 (81.5%) patients were monitored remotely. Care escalation rates were low, with an ambulance attendance rate of 3% (n=5), emergency department attendance rate of 2.5% (n=4), and hospital admission rate of 1.9% (n=3). No deaths were recorded. Conclusions Community-based virtual health care is safe for managing most patients with COVID-19 and can be rapidly implemented in an urban Australian setting for pandemic management. Health services implementing virtual health care should anticipate challenges associated with rapid technology deployments and provide adequate support to resolve them, including strategies to support the use of health information technologies among consumers.

Background: Deep learning algorithms achieve high classification accuracy in many applications but their integration into clinical processes remains scarce, partly due to their perceived lack of transparency. Attention layers in deep neural networks increase model interpretability by identifying which components of the input are attended to at any point in time. Objective: To evaluate the feasibility of using an attention-based neural network for predicting the risk of readmission within 30 days of discharge from the intensive care unit (ICU) based on longitudinal electronic medical record (EMR) data and to leverage the interpretability of the model to describe patients-at-risk. Methods: A "time-aware attention" model was trained using publicly available EMR data (MIMIC-III) associated with 45,298 ICU stays for 33,150 patients. The analysed EMR data included static (patient demographics) and timestamped variables (diagnoses, procedures, medications, and vital signs). Bayesian inference was used to compute the posterior distribution of network weights. The prediction accuracy of the proposed model was compared with several baseline models, including recursive neural networks and logistic regression, and evaluated based on average precision, AUROC, and F 1 -Score. Odds ratios (ORs) associated with an increased risk of readmission were computed for static variables. Diagnoses, procedures, and medications were ranked according to the associated risk of readmission. The model was also used to generate reports with predicted risk (and associated uncertainty) justified by specific diagnoses, procedures, medications, and vital signs. Results: A Bayesian ensemble of 10 time-aware attention models could be trained to predict the risk of readmission within 30 days of discharge from the ICU and led to the highest predictive accuracy (average precision: 0.282, AUROC: 0.738, F 1 -Score: 0.353). Male gender, number of recent admissions, age, admission location, insurance type, and ethnicity were all associated with risk of readmission. A longer length of stay in the ICU was found to reduce the risk of readmission (OR: 0.909, 95% credible interval: 0.902, 0.916). Groups of patients at risk included those requiring cardiovascular or ventilatory support, those with poor nutritional state, and those for whom standard medical care was not suitable, e.g. due to contraindications to surgery or medications. Conclusions:The presented deep learning model considers the full clinical history of a patient and can be used to gain insight into the patient population at increased risk of readmission. Ultimately, the development of interpretable machine learning techniques such as proposed here is necessary to allow the integration of predictive models in clinical processes.

The high risk of graft loss during adolescence and young adulthood is primarily due to LAR or non-compliance. The elevated risk continues well into the 20s and is independent of paediatric-to-adult transition.