Search

Feature engineering remains a major bottleneck when creating predictive systems from electronic medical records. At present, an important missing element is detecting predictive regular clinical motifs from irregular episodic records. We present Deepr (short for Deep record), a new end-to-end deep learning system that learns to extract features from medical records and predicts future risk automatically. Deepr transforms a record into a sequence of discrete elements separated by coded time gaps and hospital transfers. On top of the sequence is a convolutional neural net that detects and combines predictive local clinical motifs to stratify the risk. Deepr permits transparent inspection and visualization of its inner working. We validate Deepr on hospital data to predict unplanned readmission after discharge. Deepr achieves superior accuracy compared to traditional techniques, detects meaningful clinical motifs, and uncovers the underlying structure of the disease and intervention space.

E-mental health is an area within e-health in which the key role of IS/IT has not been well established. Both clinicians and scholars are uncertain as to the role of IS/IT and its potential benefits. This research review is introduced to assist in understanding the enabling role in e-mental health and it focused on one area of mental health, Attention Deficit Hyperactivity Disorder (ADHD) in university students. ADHD is estimated to affect approximately 6% of university students by negatively impacting students' academic performance and social life; hence, fewer of these students complete their degrees as compared to their peers. This review outlines the potentials of using IS/IT in the treatment of ADHD in university students. It also serves to greatly contribute to e-mental health development and thereby to help to uncover further possibilities of IT/IT to support broad areas within mental health disorders and services., Comment: Research-in-progress ISBN# 978-0-646-95337-3 Presented at the Australasian Conference on Information Systems 2015 (arXiv:1605.01032)

Today, cancer is one of the leading causes of death throughout the world. This threatening disease has huge negative impacts, not only on quality of life, but also on the healthcare industry, whose resources are already scarce. Thus, finding new approaches for cancer care has been a central point of interest during the last few decades. One of these approaches is the use of computerised physician order entry (CPOE) systems. This systems have the potential to provide more effective and efficient patient-centric cancer care. This paper serves to examine the business value of an American CPOE in an Australian context. This is achieved by using our specifically designed tool to evaluate the business value of IT in the healthcare, in combination with a resource based view perspective. Our results show that the system has a number of enabling resources to generate business value subject to having other resources., Comment: ISBN# 978-0-646-95337-3 Presented at the Australasian Conference on Information Systems 2015 (arXiv:1605.01032)