Search

The COVID-19 pandemic has disrupted seeking and delivery of healthcare. Different Australian jurisdictions implemented different COVID-19 restrictions. We used Australian national pharmacy dispensing data to conduct interrupted time series analyses to examine the incidence and prevalence of opioid dispensing in different jurisdictions. Following nationwide COVID-19 restrictions, the incidence dropped by -0.40 (95% confidence interval [CI]: -0.50, -0.31), -0.33 (95% CI: -0.46, -0.21) and -0.21 (95% CI: -0.37, -0.04) per 1000 people per week and the prevalence dropped by -0.85 (95% CI: -1.39, -0.31), -0.54 (95% CI: -1.01, -0.07) and -0.62 (95% CI: -0.99, -0.25) per 1000 people per week in Victoria, New South Wales and other jurisdictions, respectively. Incidence and prevalence increased by 0.29 (95% CI: 0.13, 0.44) and 0.72 (95% CI: 0.11, 1.33) per 1000 people per week, respectively in Victoria post-lockdown; no significant changes were observed in other jurisdictions. No significant changes were observed in the initiation of long-term opioid use in any jurisdictions. More stringent restrictions coincided with more pronounced reductions in overall opioid initiation, but initiation of long-term opioid use did not change.

Avoidable and unplanned readmissions to hospital wards, especially the Intensive Care Unit, have significant implications for the patients’ health and poses additional economic burdens on the health system. If patients who are at risk of readmission are identified early and their risks are mitigated, these complications can be avoided. Machine Learning has been a valuable tool for automatic identification and prediction of various health conditions and situations, including unplanned readmissions. This is made possible through processing large collections of clinical data to build predictive models. However, the clinical data from which these models are built is highly confidential, which has restricted the ability of researchers to provide their data to the wider community, hence limiting reproducibility and comparability between results. The MIMIC databases are large, publicly available clinical datasets, which make reproducibility and comparability feasible. To maximise the benefit the research community derives from this invaluable resource, we developed MiPy, an open source standardised framework for preparing, building, and evaluating machine learning models for predicting both hospital and ICU readmission, on the MIMIC-IV database. The primary aim of this work is to enhance reproducibility and comparability of research in the field.

Live fuel moisture content (LFMC) is an essential variable to model fire danger and behaviour. This paper presents the first application of deep learning to LFMC estimation based on the historical LFMC ground samples of the Globe-LFMC database, as a step towards operational daily LFMC mapping in the Contiguous United States (CONUS). One-year MODerate resolution Imaging Spectroradiometer (MODIS) time series preceding each LFMC sample were extracted as the primary data source for training. The proposed temporal convolutional neural network for LFMC (TempCNN-LFMC) comprises three 1-D convolutional layers that learn the multi-scale temporal dynamics (features) of one-year MODIS time series specific to LFMC estimation. The learned features, together with a few auxiliary variables (e.g., digital elevation model), are then passed to three fully connected layers to extract the non-linear relationships with LFMC. In the primary training and validation scenario, the neural network was trained using samples from 2002 to 2013 and then adopted to estimating the LFMC from 2014 to 2018, achieving an overall root mean square error (RMSE) of 25.57% and a correlation coefficient (R) of 0.74. Good consistency on spatial patterns and temporal trends of accuracy was observed. The trained model achieved a similar RMSE of 25.98%, 25.20% and 25.93% for forest, shrubland, and grassland, respectively, without requiring prior information on the vegetation type.