Skip to main content Skip to navigation

Advancing personalised mechanical ventilation through machine learning and advanced control algorithms

Qualification: Doctor of Philosophy in Engineering (PhD)

Start date: 2nd April 2024

Funding for: 3.5 years

Supervisor: Dr Sina Saffaran and Professor Declan Bates

Project Description:

A PhD research opportunity with the ICSM team: Advancing personalised mechanical ventilation through machine learning and advanced control algorithms:

An exciting opportunity exists to join the Interdisciplinary Collaboration in Systems Medicine (ICSM) Research Group as a doctoral candidate. Working with an international team of clinicians and engineers, you will develop and integrate machine learning and advanced control algorithms into the ICSM Cardiopulmonary simulator to facilitate the delivery of truly personalised treatment, which requires rapid and frequent interventions based on changes in the patient’s state that are not achievable within current ICU constraints. The ICSM Cardiopulmonary Simulator is a world-leading simulation platform our group has continuously developed for over 25 years.

Currently, the management of patients on mechanical ventilators is based on protocols derived from large-scale clinical trials, with ventilator settings periodically adjusted by clinicians whose workloads are increasingly unsustainable. A recent study found that important targets for oxygen saturation in ventilated neonates were achieved only 40% of the time. Previous work in the literature has attempted to demonstrate the potential of automated mechanical ventilation systems using proof-of-concept trials in small cohorts of patients of functionally limited systems implementing primitive control algorithms [5,6]. Working with a team of internationally leading intensivists, researchers and engineers from academia and industry, the proposed research will aim to:

1. Develop novel algorithms to continuously assess multiple measures of lung function using data from diverse measurement sources to improve individualised patient modelling and stratification using new patient data across different patient phenotypes.

2. Develop advanced control algorithms to guide continuous, automatic adjustment of multiple ventilator settings by integrating data from different measurement technologies. Implement, test, and validate the potential benefits of advanced automated ventilation for patient care in a high-fidelity computer simulation environment.

3. Detect and react to disease progression in patients suffering from acute lung injury. Investigate the effect of combining different forms of invasive and non-invasive respiratory support, such as non-invasive ventilation (NIV) and airway pressure release ventilation (APRV), in terms of patient oxygenation as well as the mechanical forces produced inside the lung.

This PhD candidate position offers a unique opportunity to make a significant contribution to the field of systems medicine and critical care, working alongside a dedicated team of experts in an innovative and collaborative environment. Join us in pushing the boundaries of personalised healthcare and advancing the future of mechanical ventilation.

Scholarship:

The award will cover the tuition fees at the UK/Home rate £4,712, plus a stipend of £18,622 per annum for 3.5 years of full-time study. Non-UK students can apply but will have to personally fund the difference between the UK (Home) rate and the overseas rate.

Eligibility:

Essential: At least a 2:1 with honours or a Masters Degree at Merit Level in Engineering, Computer Science, Physical Sciences or equivalent.
Desirable: strong interest/background in (a) Computational modelling; (b) Machine Learning for applications in Systems Biology; (c) Computer Programming

How to apply:

Candidates should submit a formal application, details of how to do so can be found here https://warwick.ac.uk/fac/sci/eng/postgraduate/applypgr/ 

Application form 'Course search':

Department: School of Engineering

Academic Year: 2023/24

Type of Course: Postgraduate Research

  • Engineering (MPhil/PhD) (P-H1Q2)

In the application form funding section, enter: Source: ICSM

Informal enquiries are encouraged and should be addressed to Dr Sina Saffaran (sina.saffaran.1@warwick.ac.uk)

References:
1. A. Das, P.P. Menon, J. Hardman and D.G. Bates, “Optimization of Ventilation Settings for Pulmonary Disease States”, IEEE Transactions on Biomedical Engineering, 60(6):1599-607, 2013.
2. M. Chikhani, A. Das, M. Haque, W. Wang, D.G. Bates, and J.G. Hardman, "High PEEP in ARDS: evaluating the trade-off between improved oxygenation and decreased oxygen delivery", British Journal of Anaesthesia, 117 (5): 650–8 (2016) DOI: 10.1093/bja/aew314, 2016.
3. S. Saffaran, A. Das, J.G. Hardman, N. Yehya and D.G. Bates, "High-fidelity Computational Simulation to Refine Strategies for Lung-Protective Ventilation in Paediatric Acute Respiratory Distress Syndrome", Intensive Care Medicine, https://doi.org/10.1007/s00134-019-05559-4, 2019
4. S. Saffaran, A. Das, J.G. Laffey, J.G. Hardman, N. Yehya and D.G. Bates, "Utility of driving pressure and mechanical power to guide protective ventilator settings in two cohorts of adult and pediatric patients with acute respiratory distress syndrome: A computational investigation", Critical Care Medicine, DOI:10.1097/CCM.0000000000004372, 2020.
5. Arnal J-M, Wysocki M, Novotni D, Demory D, Lopez R, Donati S, et al. Safety and efficacy of a fully closed-loop control ventilation (IntelliVent-ASV®) in sedated ICU patients with acute respiratory failure: a prospective randomized crossover study. Intensive Care Med. 2012;38:781–7.
6. Jouvet P, Eddington A, Payen V, Bourdessoule A, Emeriaud G, Lopez Gasco R, et al. A pilot prospective study on closed loop controlled ventilation and oxygenation in ventilated children during the weaning phase. Crit Care. 2012;16:R85.


The University of Warwick provides an inclusive working and learning environment, recognising and respecting every individual’s differences. We welcome applications from individuals who identify with any of the protected characteristics defined by the Equality Act 2010.