Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

LOCATION:

John Radcliffe Hospital, Level 5 and Kadoorie Centre (Level 3), Headley Way, Headington, Oxford, OX3 9DU

Start date

October 2018

Project title                         

A computer-aided decision support system based on patient similarity to improve the management of ward patients deteriorating after surgery

supervisors          

Professor Peter McCullochDr Peter Watkinson and Professor David Clifton

Baptiste Vasey

Master of Medicine (University of Zurich, 2017), Swiss Federal Medical Licensing Examination (2017)


DPhil student

Baptiste is a DPhil candidate with the Nuffield Department of Surgical Sciences, supervised by Professor Peter McCulloch. His research focuses on computer-aided decision support to improve the management of patients presenting with postoperative complications. Although scores and algorithms for the early detection of patients’ deterioration are nowadays commonly used, little is known about the best way to use the enormous amount of data routinely collected in hospitals to better inform physicians’ decision-making when reacting to an alarm trigger.
Baptiste’s project investigates how the linking of new patients to clusters of similar patients in the past (through unsupervised clustering) could provide clinicians with insights on clinical trajectories and appropriate treatment. To this end, he collaborates with the Critical Care Research Group, led by Dr Peter Watkinson, and uses the HAVEN database. The detailed information on inpatients contained in HAVEN makes it unique in the field and a precious source of data to inform better clinical management. Many key components of decision-making depend on the interaction between the human operator and its environment. His research will therefore also include human factor investigations on clinicians’ information needs under the guidance of Dr Lauren Morgan, a human factors specialist.
His interest in artificial intelligence (AI) being used as adjunct, rather than replacement, to human intelligence also led Baptiste to investigate how AI-based algorithms should be evaluated in clinical settings. With an international steering group of experts in machine learning, human factors and guidelines development he is currently leading the development of the DECIDE-AI reporting guidelines. The DECIDE-AI guidelines aim to improve the reporting on early-stage clinical evaluation of decision support systems driven by AI, which can be compared to phase 1/2 trials for drugs development or IDEAL stage IIa/IIb studies for surgical innovation.

Biography

Baptiste obtained a Master of Medicine from the University of Zurich, Switzerland, and passed the Swiss Federal Medical Licensing Examination in September 2017. His Master’s thesis focused on the effects of microgravity on the cytoskeleton of macrophages, under the supervision of Professor Oliver Ullrich and Dr Cora Thiel.

Following graduation, he was awarded one of the four Swiss Mercator Fellowships on International Affairs to investigate the potential of computer-aided decision support to improve access to appropriate healthcare in low-resource settings. As part of this fellowship, he spent three months in Burkina Faso working on IeDA, Western Africa’s largest mHealth project, redesigning the clinical application’s architecture. He subsequently joined the WHO Global Coordination Mechanism on the prevention and control of NCDs at the organisation’s Headquarters in Geneva. He finally collaborated with the MIT Gehrke Lab, under the supervision of Dr Irene Bosch and Dr Anuraj Shankar (Harvard T.H. Chan School of Public Health) investigating new biomarkers for the detection and classification of dengue fever.

Baptiste is a Berrow Foundation Lord Florey scholar at Lincoln College.