Digital Twins of Patients on Non-Invasive Respiratory Support: Mechanistic and Data-Driven Models to Improve Patient Care

Add to your list(s) Download to your calendar using vCal

• Declan Bates (University of Warwick)
• Thursday 07 November 2024, 16:00-17:00
• Lecture Theatre, Department of Pathology, Tennis Court Road.

If you have a question about this talk, please contact Michael Boemo.

Acute respiratory failure is a life-threatening condition that occurs when the respiratory system fails to provide oxygen to, and/or remove carbon dioxide from, the body. Patients with acute respiratory failure consume a disproportionate amount of hospital resources, mortality rates are high, and survivors report low health-related quality of life. Treatment is primarily based on providing external respiratory support, starting with low- or high-flow nasal oxygen therapy, which may be escalated to non-invasive ventilation, and ultimately to endotracheal intubation and invasive mechanical ventilation in the intensive care unit. Each step of this treatment staircase requires clinicians to make critical decisions, in a time-pressured environment, with access to incomplete information about the state of the patient. Complex trade-offs abound. For example, when successful, non-invasive ventilation reduces the length of ICU stay and avoids the risks associated with intubation. However, for the proportion of patients who fail non-invasive ventilation (often around 40%), and subsequently require intubation and mechanical ventilation, risk of mortality is significantly increased. No formal guidelines are currently available to assist clinicians in deciding whether an individual patient should, or should not, be treated with non-invasive ventilation.

Digital Twins are virtual representations of complex systems that mirror the real-world system in real-time, help to analyse its behaviour, and provide predictive insights using advanced simulation and machine learning. Digital Twins of ventilated patients could transform the treatment of acute respiratory failure by facilitating research into more personalised ventilation strategies, and by allowing the development of real-time decision support tools that could assist clinicians in deciding how best to treat patients as their disease state evolves. Digital Twins based on detailed computational models that reflect the underlying disease pathophysiology can provide mechanistic insight into the effects of different ventilation strategies in different patients, facilitating stratification of patients and personalisation of treatments, and opening up the possibility of designing in silico clinical trials of new interventions. This potential is particularly relevant in the context of respiratory support in intensive care medicine, where research into personalised ventilation strategies has made limited progress, and randomised controlled trials are extremely costly and difficult to execute. In parallel with this approach, the development of data-driven Digital Twins using machine learning and other AI methodologies could provide real-time decision support tools to assist clinicians in deciding how best to treat individual patients. Combining the two approaches (mechanistic and data-driven Digital Twins) could bring further benefits and synergies, e.g. providing interpretable and trusted AI, key requirements in the context of safety-critical healthcare technologies.

In this talk I will review recent work in my group on the development of both mechanistic and data-driven digital twins of patients on non-invasive respiratory support, and give some suggestions for potential future work in this area.

This talk is part of the Computational and Systems Biology Seminar Series series.

This talk is included in these lists:

• Lecture Theatre, Department of Pathology, Tennis Court Road

Note that ex-directory lists are not shown.