Advancing Australian Healthcare

An Australian, clinician-led organisation focused on safe, ethical AI to support disease prevention and detection.

Research

Our Research

Our research explores the safe, effective and evidence-based application of artificial intelligence across healthcare.

Research stream

Correspondences

Correspondences 2025

“A Rising Tide Lifts All Boats”: The Systemic Benefits of Artificial Intelligence on the Practice of Medicine in Regional Hospitals

Late 2025 research in the Australian Journal of Rural Health advanced a “rising tide lifts all boats” argument: if Australia gets implementation right, clinical AI gains in major centres can translate into safer, better-performing regional hospitals too. The practical implication is clear: remote AI adoption is an infrastructure program as much as a model-development program. If we want the “rising tide” effect in remote Australia, prioritise connectivity and interoperability first—then deploy AI that is validated, workflow-aligned, and resilient to outages. More to come in this area...

Australian Journal of Rural Health
Rural & Remote Clinical Practice
Read paper →
Correspondences 2023

ChatGPT-Based Learning: Generative Artificial Intelligence in Medical Education

The traditional "one-size-fits-all" approach to medical education is facing a digital revolution. Case-based and Problem-based learning (CBL/PBL) are vital for developing clinical reasoning, but they are often resource-heavy and static. A recent perspective published in Medical Science Educator explores how ChatGPT and other Large Language Models (LLMs) can act as powerful catalysts for a more personalized, engaging, and efficient medical curriculum. Expert Collaboration: This insightful work was developed in collaboration with the founders of Australian Med AI, demonstrating our ongoing leadership in defining the safe and effective integration of generative AI into medical training and practice. Key Highlights: The Paradigm Shift in Learning The research highlights how LLMs can move beyond simple "chatbots" to become sophisticated educational tools for both teachers and students. Rapid Case Generation: LLMs can assist clinical teachers by generating realistic patient scenarios in seconds. These cases can be finely tuned to include specific clinical findings, genetic data, or laboratory results to align with curriculum goals. The "Virtual Tutor" Model: For students, AI offers a "choose-your-own-adventure" style of learning. Trainees can practice history-taking and diagnostic reasoning in a low-stakes environment, receiving instant feedback on their clinical decisions. Gamification of Learning: By simulating real-time patient interactions, LLMs can turn traditional text-based cases into interactive simulations, significantly increasing student engagement and retention. Constructive Alignment: Educators can use AI to ensure that case content directly supports the broader learning objectives, allowing for a more cohesive and structured educational experience. Why This Matters for the Future of Medicine As medical knowledge expands exponentially, the burden on clinical educators grows. The founders of Australian Med AI argue that by adopting LLMs as collaborative partners, we can alleviate this burden and provide students with 24/7 access to high-quality clinical simulations. This ensures that the next generation of Australian doctors is better prepared for the complexities of modern clinical practice through consistent, high-fidelity training.

Medical Science Educator
Medical Education
Read paper →
Correspondences 2025

When One Size Does Not Fit All: AI in Rural Australian Health

Static case reports are a staple of medical education, but they often lack the engagement of real-world clinical reasoning. At Australian Med AI, we are exploring how generative technology can transform these resources into dynamic tools. Our recent research, published in Heart, Lung and Circulation, evaluates how Large Language Models (LLMs) can bridge this gap. Expert Collaboration: This study was conducted in collaboration with the founders of Australian Med AI, driving forward our mission to integrate safe, accurate, and high-speed AI solutions into the future of medical training. Key Highlights: The LLM Learning Advantage The study assessed the ability of LLMs to convert traditional case-based articles into interactive "screenplays" where learners can ask questions and receive real-time clinical feedback. High Accuracy: The LLM demonstrated a 97.1% adherence rate to provided clinical screenplays, ensuring that the simulated patient interaction remained grounded in factual data. Clinically Appropriate: In instances where the AI generated content outside the original text, 96% of responses were rated as medically appropriate by expert reviewers. Rapid Feedback Loops: Unlike traditional assessments, the system provided near-instant feedback, allowing trainees to practice history-taking and diagnostic reasoning repeatedly without the need for an available human supervisor. Scalable Education: This approach proves that LLMs can effectively function as "virtual tutors," making high-quality case-based learning accessible 24/7. Why This Matters for Medical Training The results highlight that LLMs can provide a safe, interactive "sandbox" for junior doctors and medical students. By automating the delivery of feedback and case interactions, we can reduce the cognitive load on senior clinicians while providing trainees with a sophisticated, personalized learning experience that mimics real-world practice.

The Australian Journal Of Rural Health
Rural & Remote Clinical Practice
Read paper →
Research stream

Literature Reviews

Literature Reviews 2027

Artificial Intelligence for Triage in Primary Care: A Scoping Review of Clinical Applicability

AI triage in primary care is concentrated on clinician-facing diagnostic and referral tasks and is most valuable for augmenting clinician workflows, particularly non-specialists. The evidence base remains immature, constrained by internal validation, unreliable reference standards, sparse equity assessment and absent prospective outcome data. Future work should prioritise prospective, outcome-anchored evaluation, with attention to safety and equity.

International Journal of Medical Informatics
General Practice
Read paper →
Research stream

Primary Data

Research coming soon.
Research stream

Synthetic Data

Research coming soon.
Research programmes

Explore by project

Explore publications grouped by our ongoing research programmes.

Underway

Cardiology Clinical Practice

Investigating the use of Artificial Intelligence to support cardiology clinical practice.

Underway

General Medicine Clinical Practice

Investigation into the role of Artificial Intelligence to support General Medicine Clinical Practice

Active

General Practice

Underway

Medical Education

Underway

Respiratory Clinical Practice

Investigation into the role of Artificial Intelligence to support clinical practice in Respiratory medicine.

Underway

Rural & Remote Clinical Practice

Investigation into the role of Artificial Intelligence in supporting Clinical Medicine in Rural and Remote Australian healthcare locations.