CLOTS – technical solution : 4-model decision support tool for all surgical and interventional procedures

Flagship Program: Intelligent Decision Support to Improve Value and Efficiency

Project Description

Prevention of thromboembolism (TE) – the obstruction of a blood vessel by a blood clot – has been a worldwide priority safety initiative for over a decade.

Post-operative TE remains an important and preventable cause of morbidity and mortality in hospitalised and ambulatory patients, equating to more than 1000 post-operative deaths per year.

Yet systematic real-time approaches to TE prevention – both pre-surgery (prehabilitation) and post-surgery – remain suboptimal.

Despite the availability of safe and efficacious strategies for preventing TE – including guidelines for managing antithrombotics and optimising patients before surgery – patients with identifiable risk factors continue not to receive appropriate or timely interventions.

While the reasons are multi-faceted, current guidelines do not provide easy access to real-time and personalised decision-making and, as a consequence, there is a lack of consistent adoption of recommendations, within and across healthcare settings.

This project has the capacity to transform real world application and embedding of clinical guidance in real-time for point of care decision-making – personalised for the purposes of the patient journey.

It will assess whether simple, accessible, real-time decision-support tools can improve compliance to appropriate evidence-based and patient-centric prehabilitation recommendations, reduce the incidence of adverse outcomes, and provide real-time machine learning for optimal care pathways that are flexible but with sustained implementation.

The tools developed through this project will be scalable to all clinicians across all healthcare institutions, both in Australia and internationally, for all surgical and procedural subspecialties.

The interactive machine learning built into the tools will also provide ongoing professional education and development for all users, creating a sustained culture for quality improvement.

Importantly, the tools will be able to be used remotely, supporting clinicians and care delivery to all patients, regardless of their location in urban, rural or remote areas.

Project Objectives

Develop and validate a 4-Model Decision Support tool that can drive appropriate evidence-based, real time decision-making for surgical and interventional procedures to optimize patient outcomes and prevent avoidable complications. 


Further development and enhancement of CLOTS that provides: 

  1. Contemporaneous de-identified data collection for real world analytics. 
  2. Measurable: user profiles, patient profiles, procedure profiles, applied recommendations, patient outcomes.  
  3. Clinical impact: performance indicators, adverse events, outcome data.  
  4. Research driver: health services and implementation research. 
  5. Expected economic benefit: patient functional optimisation and mitigation of risk for adverse outcomes.  
  6. Machine learning for clinicians in high health priority areas. 
  7. Commercialisation capacity. 
    1. Scalable across ALL surgical procedures. 
    2. Relevant for all healthcare centres – public and private providers.
    3. Relevant for private health funds for peri-operative optimisation. 

Industry Participant

Peter MacCallum Cancer Centre (Peter Mac)
Associate Professor Kate Burbury, Deputy Chief Medical Officer; Professor Penelope Schofield, Head of Behavioural Science

Other Project Participants

Research Participant

Swinburne University of Technology
Prof Nilmini Wickramsinghe, Professor of Digital Health and Deputy Director for Iverson Health Research Innovation Institute; Professor Penelope Schofield, Professor of Health Psychology and Program Lead for Iverson Health Research Innovation Institute; Assoc. Professor Prem Prakash Jayaraman, Head, Digital Innovation Lab

Project Value: