The EU-funded WideHealth project aims to conduct research on pervasive eHealth and establish a sustainable network of research and dissemination across Europe.
Title: Predicting deterioration of critically ill patients
Speaker: Venet Osmani (Fondazione Bruno Kessler Research Institute)
When: June 22, 2021; 15h
Where: zoom link shared before the session to those who register
Registration link: https://bit.ly/3vlASGC (free)
Abstract: Intensive care units generate large quantities of data from various patient monitoring and intervention systems. Limited ability of humans to process and act on complex information also extends to intensive care clinicians, at times resulting in information overload, and consequently hindering recognition of early signs of patient deterioration. Machine learning has been touted as a possible approach to address this problem. However, enormous challenges remain despite the significant work carried out in this domain.
In this talk I will provide an overview of the challenges of applying machine learning in medicine in general, and in critical care in particular, especially in comparison to traditional applications such as computer vision. Then, I will present our approach in tackling the challenge of prediction of deterioration of critically ill patients, starting from the definition of the problem, up to the methodology we employed and the results we obtained. Finally, I will also discuss this work in the context of the specific challenges identified in applying machine learning in medicine.
Short bio: Venet Osmani, PhD is a senior researcher at Fondazione Bruno Kessler Research Institute. Previously, he was a lecturer at the department of Psychology and Cognitive Science at University of Trento, Italy and a visiting researcher at Georgia Institute of Technology, USA. His earlier research focused primarily on monitoring and analysing human behaviour. Specifically, using personal and environmental sensing applied to healthcare, including predicting depressive and manic episodes of bipolar patients and detecting occupational stress from smartphone sensors. Currently, the focus of his research is on analysis of clinical data (EHR) using machine learning methods to model disease and patient trajectories both for chronic conditions as well as in critical care. In this work he collaborates with some of the leading healthcare institutions in the US, including Cleveland Clinic, Mayo Clinic, MIT, as well as several leading European research institutions. He is an Expert Evaluator for European Commission (Horizon 2020 Programme), UK Medical Research Council (MRC), Swiss National Science Foundation (SNSF) and several other scientific funding institutions.
Further information can be found in: http://venetosmani.com