BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Digital Twins of Patients on Non-Invasive Respiratory Support: Mec
 hanistic and Data-Driven Models to Improve Patient Care - Declan Bates (Un
 iversity of Warwick)
DTSTART:20241107T160000Z
DTEND:20241107T170000Z
UID:TALK222103@talks.cam.ac.uk
CONTACT:Michael Boemo
DESCRIPTION:Acute respiratory failure is a life-threatening condition that
  occurs when the respiratory system fails to provide oxygen to\, and/or re
 move carbon dioxide from\, the body. Patients with acute respiratory failu
 re consume a disproportionate amount of hospital resources\, mortality rat
 es are high\, and survivors report low health-related quality of life. Tre
 atment is primarily based on providing external respiratory support\, star
 ting with low- or high-flow nasal oxygen therapy\, which may be escalated 
 to non-invasive ventilation\, and ultimately to endotracheal intubation an
 d 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 a
 bout the state of the patient. Complex trade-offs abound. For example\, wh
 en successful\, non-invasive ventilation reduces the length of ICU stay an
 d avoids the risks associated with intubation. However\, for the proportio
 n of patients who fail non-invasive ventilation (often around 40%)\, and s
 ubsequently require intubation and mechanical ventilation\, risk of mortal
 ity is significantly increased. No formal guidelines are currently availab
 le to assist clinicians in deciding whether an individual patient should\,
  or should not\, be treated with non-invasive ventilation.\n\nDigital Twin
 s are virtual representations of complex systems that mirror the real-worl
 d system in real-time\, help to analyse its behaviour\, and provide predic
 tive insights using advanced simulation and machine learning. Digital Twin
 s of ventilated patients could transform the treatment of acute respirator
 y failure by facilitating research into more personalised ventilation stra
 tegies\, and by allowing the development of real-time decision support too
 ls 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 me
 chanistic insight into the effects of different ventilation strategies in 
 different patients\, facilitating stratification of patients and personali
 sation of treatments\, and opening up the possibility of designing in sili
 co clinical trials of new interventions. This potential is particularly re
 levant in the context of respiratory support in intensive care medicine\, 
 where research into personalised ventilation strategies has made limited p
 rogress\, and randomised controlled trials are extremely costly and diffic
 ult to execute. In parallel with this approach\, the development of data-d
 riven Digital Twins using machine learning and other AI methodologies coul
 d provide real-time decision support tools to assist clinicians in decidin
 g how best to treat individual patients. Combining the two approaches (mec
 hanistic and data-driven Digital Twins) could bring further benefits and s
 ynergies\, e.g. providing interpretable and trusted AI\, key requirements 
 in the context of safety-critical healthcare technologies.\n\nIn this talk
  I will review recent work in my group on the development of both mechanis
 tic and data-driven digital twins of patients on non-invasive respiratory 
 support\, and give some suggestions for potential future work in this area
 .
LOCATION:Lecture Theatre\, Department of Pathology\, Tennis Court Road
END:VEVENT
END:VCALENDAR