The HOTspots digital surveillance platform (HOTspots) is a critical technology of the HOTspots Surveillance and Response Program. It provides timely point-of-care access to pathology and demographic data from previously underserved regions. Co-designed with clinicians, epidemiologists, and health policy makers, the platform provides the evidence-base to empower efficient clinical management of patients with antimicrobial resistant (AMR) infections and supports national disease surveillance efforts in Australia. The pathway from conceptualisation to deployment for the HOTspots digital surveillance platform is described.

The performance of deep learning models in the health domain is desperately limited by the scarcity of labeled data, especially for specific clinical-domain tasks. Conversely, there are vastly available clinical unlabeled data waiting to be exploited to improve deep learning models where their training labeled data are limited. This paper investigates the use of task-specific unlabeled data to boost the performance of classification models for the risk stratification of suspected acute coronary syndrome. By leveraging large numbers of unlabeled clinical notes in task-adaptive language model pretraining, valuable prior task-specific knowledge can be attained. Based on such pretrained models, task-specific fine-tuning with limited labeled data produces better performances. Extensive experiments demonstrate that the pretrained task-specific language models using task-specific unlabeled data can significantly improve the performance of the downstream models for specific classification tasks.

A FHIR based platform for case-based instruction of health professions students has been developed and field tested. The system provides a non-technical case authoring tool; supports individual and team learning using digital virtual patients; and allows integration of SMART Apps into cases via its simulated EMR. Successful trials at the University of Queensland have led to adoption at the University of Melbourne.

The review of pathology test results for missed diagnoses in Emergency Departments is time-consuming, laborious, and can be inaccurate. An automated solution, with text mining and clinical terminology semantic capabilities, was developed to provide clinical decision support. The system focused on the review of microbiology test results that contained information on culture strains and their antibiotic sensitivities, both of which can have a significant impact on ongoing patient safety and clinical care. The system was highly effective at identifying abnormal test results, reducing the number of test results for review by 92%. Furthermore, the system reconciled antibiotic sensitivities with documented antibiotic prescriptions in discharge summaries to identify patient follow-ups with a 91% F-measure - allowing for the accurate prioritization of cases for review. The system dramatically increases accuracy, efficiency, and supports patient safety by ensuring important diagnoses are recognized and correct antibiotics are prescribed.

Queensland Genomics recently undertook a number of Clinical Demonstration Projects (CDPs) to demonstrate the benefits of genomics in clinical practice. Integration of this testing requires the health system to provide the infrastructure for the appropriate ordering of these tests. Ordering of genomics tests will likely require greater exchange of information between the ordering clinician and the lab that is producing a clinical test report. The clinical demonstration projects were used to understand the information flow and the use of genomic, phenotypic and other information through the test ordering, analysis and reporting stages. This information was used to inform a set of requirements for a genomics test ordering and reporting system. A prototype of this system was developed as a SMART on FHIR application. This prototype will inform a future production system with FHIR Resources, software interfaces and interoperability requirements.

Computer-assisted (diagnostic) coding (CAC) aims to improve the operational productivity and accuracy of clinical coders. The level of accuracy, especially for a wide range of complex and less prevalent clinical cases, remains an open research problem. This study investigates this problem on a broad spectrum of diagnostic codes and, in particular, investigates the effectiveness of utilising SNOMED CT for ICD-10 diagnosis coding. Hospital progress notes were used to provide the narrative rich electronic patient records for the investigation. A natural language processing (NLP) approach using mappings between SNOMED CT and ICD-10-AM (Australian Modification) was used to guide the coding. The proposed approach achieved 54.1% sensitivity and 70.2% positive predictive value. Given the complexity of the task, this was encouraging given the simplicity of the approach and what was projected as possible from a manual diagnosis code validation study (76.3% sensitivity). The results show the potential for advanced NLP-based approaches that leverage SNOMED CT to ICD-10 mapping for hospital in-patient coding.

The effectiveness of colonoscopy for diagnosing and preventing colon cancer is largely dependent on the ability of endoscopists to fully inspect the colonic mucosa, which they achieve primarily through skilled manipulation of the colonoscope during withdrawal. Performance assessment during live procedures is problematic. However, a virtual withdrawal simulation can help identify and parameterise actions linked to successful inspection, and offer standardised assessments for trainees.

Optical colonoscopy is performed by insertion of a long flexible endoscope into the colon. Inspecting the whole colonic surface for abnormalities has been a main concern in estimating quality of a colonoscopy procedure. In this paper we aim to estimate areas that have not been inspected thoroughly as a quality metric by generating a visibility map of the colon surface. The colon was modeled as a cylinder. By estimating the camera motion parameters between each consecutive frame, circumferential bands from the cylinder of the colon surface were extracted. Registering these extracted band images from adjacent video frames provide a visibility map, which could reveal uncovered areas by clinicians from colonoscopy videos. The method was validated using a set of realistic videos generated using a colonoscopy simulator for which the ground truth was known, and by analyzing results from processing actual colonoscopy videos by a clinical expert. Our method was able to identify 100% of uncovered areas on simulated data and achieved with sensitivity of 96% and precision of 74% on real videos. The results suggest that visibility map can increase clinicians' awareness of uncovered areas, and would reduce the chance of missed polyps.

Colonoscopy is considered the gold standard for detection and removal of precancerous polyps in the colon. Being a difficult procedure to master, exposure to a large variety of patient and pathology scenarios is crucial for gastroenterologists' training. Currently, most training is done on patients under supervision of experienced gastroenterologists. Being able to undertake a majority of training on simulators would greatly reduce patient risk and discomfort. A next generation colonoscopy simulator is currently under development, which aims to address the shortfalls of existing simulators. The simulator consists of a computer simulation of the colonoscope camera view and a haptic device that allows insertion of an instrumented colonoscope to drive the simulation and provide force feedback to the user. The simulation combines physically accurate models of the colonoscope, colon and surrounding tissues and organs with photorealistic visualization. It also includes the capability to generate randomized case scenarios where complexity of the colon physiology, pathology and environmental factors, such as colon preparation, can be tailored to suit training requirements. The long term goal is to provide a metrics based training and skill evaluation system that is not only useful for trainee instruction but can be leveraged for skills maintenance and eventual certification.

For interactive surgical simulation the physical model of the soft tissue needs to be solved in real-time. This limits the attainable model density to well below the desired mesh density for visual realism. Previous work avoids this problem by using a high-resolution visual mesh mapped onto a low-resolution physical model. We apply the same approach and present an computationally cheap implementation of a known algorithm to avoid texture artefacts caused by the mapping. We also introduce a spline-based algorithm to prevent groups of high-resolution vertices, mapped to the same low-resolution triangle, from exhibiting movements in which the underlying low-resolution structure can be recognised. The resulting mapping algorithm is very efficient, mapping 54,000 vertices in 8.5 ms on the CPU and in 0.88 ms on the GPU. Consequently, the density of the high-resolution visual mesh is limited only by the detail of the CT data from which the mesh was generated.