Model-based Virtual Patients for Mechanical Ventilation Treatment

In the rapidly evolving landscape of healthcare, there has been an emerging interest in providing personalised treatment in the intensive care (ICU) setting through the use of engineering model-based/ machine learning approaches. These approaches require vast patient data and an in-depth understanding of patient conditions, allowing clinicians to select the best therapy that matches the patient’s needs. However, substantial barriers exist when investigating their potential in clinical trials in the ICU. These trials require significant clinical resources, and often, the result does not provide the wide information spectrum required to investigate the performance of these approaches. Thus, there is an unmet need for alternate solutions that enable investigation of the feasibility, safety, and performance of new treatment protocols prior to actual testing in the clinical environment.

Comes Virtual patient, a form of digital twin technology. Virtual patient models have been developed to provide an in-silico representation of physical patients in a range of clinical settings, and particularly intensive care. The application of virtual patients in virtual trials ensures in-silico experimental results achieve robust statistical significance and ensures far fewer patients are exposed to trial conditions, which includes the risk of being randomised to an inferior therapy. Supervised by Dr Yeong Shiong Chiew, a member of Medical Engineering and Technology Hub (MET) , a framework for the generation of virtual patients to be used in intensive care hospital mechanical ventilation treatment. The virtual trials in this research show the potential to design, develop, and optimise MV setting selection protocols safely and rapidly through computer simulation.

The framework is divided into 3 sections. (a) virtual patient creation, where retrospective data forms digital twins of actual clinical patients using physiological models. (b) patient-level validation, involving data comparisons between the virtual patients’ predicted responses and actual retrospective patient responses, is thus crucial for validating the model used to form these virtual patients. The final section is (c) virtual-trial simulation, where cohorts of validated virtual patients are used as a platform for rapid prototyping, development, and validation of MV setting selection protocols.

To learn more, please visit: https://lnkd.in/gSf2sEU9

In this research, we seek to recruit potential postgraduate candidates with the following task:

Key Responsibilities:

Develop and refine virtual patient models using retrospective patient data.

Validate physiological models by comparing virtual patient responses to actual clinical data.

Collaborate with a multidisciplinary team of engineers, clinicians, and researchers.

Qualifications:

A Master’s degree in either Biomedical Engineering, Mechanical Engineering, Computer Science, or a related field.

Strong background in physiological modelling, machine learning, and data analysis.

Proficiency in programming languages such as Python or MATLAB

Excellent problem-solving skills and attention to detail.

Strong written and verbal communication skills.

Benefits:

Opportunity to work on cutting-edge research with significant real-world impact.

Access to state-of-the-art facilities and resources.

Collaboration with leading experts in the field.

Competitive stipend and tuition coverage.

Interested candidates should submit the following:

A cover letter detailing your research interests and relevant experience.

A CV highlighting your academic and professional achievements.

Contact information for three academic or professional references.

Join us in revolutionizing ICU treatment through innovative model-based engineering and machine-learning approaches!