Medicine (RMH) - Research Publications
Permanent URI for this collection
Search Results
1 - 3 of 3
-
ItemNo Preview AvailableThe Oversight of Clinical Innovation in a Medical Marketplace(Cambridge University Press, 2021-06-24)
-
ItemSex steroids and gender differences in muscle, bone, and fat(Elsevier, 2022)Sex steroids, comprising of the androgens, estrogens, and progestogens, are fundamentally important to the development of muscle, bone, and fat across the life course. Each has roles that differ between these tissues, the male and female sexes, and developmental stage. It is the differential production of sex steroids and expression of their receptors that mediates much of the pubertal development in muscle, bone, and fat, which in turn determines the typical dimorphic sexual phenotypes. It is similar to how this differential production changes over time that is responsible for much of the typical sex-specific changes seen with normal aging. This chapter considers the sex-specific production of sex steroids and their effects upon each muscle, bone, and fat. It additionally covers the developmental changes in sex steroid production, and how this contributes to age-related changes in these three tissues.
-
ItemAutomated Inter-Ictal Epileptiform Discharge Detection from Routine EEG(IOS PRESS, 2021)Epilepsy is the most common neurological disorder. The diagnosis commonly requires manual visual electroencephalogram (EEG) analysis which is time-consuming. Deep learning has shown promising performance in detecting interictal epileptiform discharges (IED) and may improve the quality of epilepsy monitoring. However, most of the datasets in the literature are small (n≤100) and collected from single clinical centre, limiting the generalization across different devices and settings. To better automate IED detection, we cross-evaluated a Resnet architecture on 2 sets of routine EEG recordings from patients with idiopathic generalized epilepsy collected at the Alfred Health Hospital and Royal Melbourne Hospital (RMH). We split these EEG recordings into 2s windows with or without IED and evaluated different model variants in terms of how well they classified these windows. The results from our experiment showed that the architecture generalized well across different datasets with an AUC score of 0.894 (95% CI, 0.881–0.907) when trained on Alfred’s dataset and tested on RMH’s dataset, and 0.857 (95% CI, 0.847–0.867) vice versa. In addition, we compared our best model variant with Persyst and observed that the model was comparable.