A5101464148- Pharmaceutical studies and practices
- Pharmacovigilance and Adverse Drug Reactions
- Data Visualization and Analytics
- Pharmaceutical Practices and Patient Outcomes
- Video Analysis and Summarization
- Advanced Text Analysis Techniques
- Software Engineering Research
- Pharmaceutical Economics and Policy
- Topic Modeling
- Academic integrity and plagiarism
- Acute Lymphoblastic Leukemia research
- Artificial Intelligence in Games
- Business Process Modeling and Analysis
- Service-Oriented Architecture and Web Services
- Childhood Cancer Survivors' Quality of Life
- Web Applications and Data Management
The University of Sydney
2019-2024
University of British Columbia
2021
University of Tasmania
2018
Abstract Background Under-reporting of adverse drug reactions (ADRs) by healthcare professionals is prevalent worldwide. Community pharmacists are the most frequently visited professional and well placed to document ADRs as a part their routine practice. Objective To measure community pharmacists’ knowledge perspectives towards ADR reporting practices. Setting in New South Wales, Queensland, Victoria Tasmania, Australia. Method A survey tool consisting 28 items was developed, piloted...
Adverse drug reaction (ADR) underreporting is highly prevalent across the world. This study aimed to identify factors associated with ADR reporting and map these a behavioural change framework help inform future interventions designed improve underreporting.A mixed methods survey was distributed healthcare professionals at tertiary hospital in Sydney, Australia. Quantitative data analysed using logistic regression that predict reporting. Qualitative evaluated content analysis. These were...
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging. In this paper, we present design implementation of a visual analytic framework for assisting researchers such process, by providing them with valuable insights about model's intrinsic properties behaviours. Our offers an intuitive overview that allows user to explore different facets model (e.g., hidden states, attention) through interactive visualization, suite built-in...
Objectives The black triangle scheme was introduced to Australia in January 2018 improve the significant under-reporting of adverse drug events (ADEs). authors investigated impact on quantity and quality ADE reports submitted Therapeutic Goods Administration.Methods An interrupted time series analysis with segmented regression conducted compare pre post intervention for period between 2017 December 2018. measured by ability apply World Health Organization – Uppsala Monitoring Center...
The proliferation of text messaging for mobile health is generating a large amount patient-doctor conversations that can be extremely valuable to care professionals. We present ConVIScope, visual analytic system tightly integrates interactive visualization with natural language processing in analyzing conversations. ConVIScope was developed collaboration healthcare professionals following user-centered iterative design. Case studies six domain experts suggest the potential utility and reveal...
While transformer-based models have achieved state-of-the-art results in a variety of classification and generation tasks, their black-box nature makes them challenging for interpretability. In this work, we present novel visual analytical framework to support the analysis generative networks. contrast previous which has mainly focused on encoder-based models, our is one first dedicated supporting encoder-decoder decoder-only tasks. Hence, offer an intuitive overview that allows user explore...
Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging. In this paper, we present design implementation of a visual analytic framework for assisting researchers such process, by providing them with valuable insights about model's intrinsic properties behaviours. Our offers an intuitive overview that allows user to explore different facets model (e.g., hidden states, attention) through interactive visualization, suite built-in...
The proliferation of text messaging for mobile health is generating a large amount patient-doctor conversations that can be extremely valuable to care professionals. We present ConVIScope, visual analytic system tightly integrates interactive visualization with natural language processing in analyzing conversations. ConVIScope was developed collaboration healthcare professionals following user-centered iterative design. Case studies six domain experts suggest the potential utility and reveal...