Research & Projects

Research at Nexus is conducted in partnership with the Monash Medical Technology Lab.

Established in 2024, the lab’s mission is to elevate humanity's collective medical wisdom and create a healthier and more equitable world through the development and application of medical AI systems.

Logo of Nexus on the left, two black crossing lines in the middle, and MMTL written in black and blue within brackets on the right.

Medical Benchmarking

James Liu, Ryan Kua, A/Prof. Khoa N. Cao

Few benchmarks are reflective of real-world clinical medicine. This project aims to develop LLM benchmarks which are reflective of how medical doctors operate in the real world. Our first benchmark, the Monash Murtagh Benchmark, examined the performance of LLMs in the diagnosis of over 2,500 case studies based on John Murtagh’s General Practice.

A smiling elderly woman relaxing in a beige armchair, using a tablet with speech bubble icons indicating chatting or messaging, sitting near a window with curtains.

Project Ambi

Bryan Lee, Deepak Rajan, A/Prof. Khoa N. Cao

This project aims to build a full-stack medical AGI agent for deployment in the real-world.

Diagram of an autoencoder neural network with input layer, two hidden layers, an encoded layer, and a decoded output layer. The network encodes input features into a compressed representation and then reconstructs the output.

Medical AI Character

Lucy Liu, Izabella Mancewicz, A/Prof. Khoa N. Cao

Few studies have examined the desirable characteristics of medical LLMs. This project aims to comprehend and assess positive and negative behaviours expected of medical doctors in medical LLMs, commencing with the economic restraint or judiciousness of medical AI (i.e. AI’s ability to choose investigations and treatments wisely).

Illustration of a hand holding a chart showing an upward trend in the Anthropocic Economic Index, with the title 'The Anthropocic Economic Index' on the side.

Economic Index Analysis

Izabella Mancewicz, Dr. Yufei Xu, Dr. Jeffrey Ma, A/Prof. Khoa N. Cao

The extent and nature of LLM use by different medical specialties remain poorly understood. This project aimed to understand how medical doctors across specialties are utilising commercial LLMs through analysis of the Anthropic Economic Index, a dataset which captured millions of conversations in Anthropic’s Claude product. 

A person in business attire interacts with a digital display that reads 'AI Cybersecurity,' surrounded by futuristic holographic graphics and data interfaces.

Medical LLM Cybersecurity

Chun Joo Goh, James Liu, A/Prof. Khoa N. Cao

Cybersecurity considerations for medical LLMs are not well comprehended. This project aims to assess the cybersecurity risks and mitigation strategies before and following LLM deployment to inform information technology systems and hospitals looking to deploy LLMs. 

Close-up of a computer screen displaying a digital dashboard with graphs and data visualizations in yellow and blue colors.

Project Chute

Bryan Lee, Chun Joo Goh, Deepak Rajan, Nethum Devendra, A/Prof. Khoa N. Cao

Significant effort is required for contribution to clinical registries. This project examined, with support from Alfred Health, how to build an AI system which automatically summarises quality management metrics and clinical registry submissions from EMR data.

A man in a blue shirt interacts with a computer screen displaying a search system interface, sitting at a desk with a keyboard, notebooks, and a pen in a well-lit office.

Project Clarity

Bryan Lee, Chun Joo Goh, Deepak Rajan, A/Prof. Khoa N. Cao

Guideline under-utilisation is a widespread problem across hospitals and clinics, due partly to difficulty navigating vast amounts of recommendations and literature. This project is a collaboration with Monash Health to build a retrieval-augmented generation system which provides hospital staff with AI-assisted access to both clinical and non-clinical guidelines.

Screenshot of MurtaghClinEval homepage with title 'The First Clinician-Centric AI Benchmark,' featuring navigation buttons for Leaderboard, Methodology, Results, and Contact Us.