CMI seminar (virtual): Machine Intelligence for COVID-19 - Event

Event details

​The Centre for Machine Intelligence (CMI) at the University of Southampton invites you to a seminar on the topic of "Machine Intelligence for COVID-19".  As the fight against the COVID-19 continues, a wide range of research efforts are taking place. We are hosting three talks about the latest academic research on how different aspects of machine intelligence are helping with this endeavour, followed by a live Q/A and panel session with the presenters. The seminar will be conducted virtually on the MS Teams platform, and its open to everyone. (registration required).

Registration link : https://www.eventbrite.co.uk/e/machine-intelligence-for-covid-19-tickets-149191127679

Schedule:

14:00 - 14:05 - Welcome and introduction - Dr. Enrico Gerding (Director of CMI)

14:05 - 14:20 - The sounds of COVID-19: crowdsourcing and analysing respiratory signals for COVID-19 diagnostics -  Prof. Cecilia Mascolo (University of Cambridge) 

Abstract: In this talk I will describe the work we have been doing on crowdsourcing respiratory sounds (coughs, breathing and voice) through a mobile app  (covid-19-sounds.org) and their analysis through audio based machine learning for COVID-19 diagnostics and disease progression. This work is part of a a bigger project which looks at how sounds of the human body (respiratory, cardiovascular, digestive) can be collected through wearables and mobile devices and analysed with the aim of improving automated and efficient medical diagnostics.

Bio: Cecilia Mascolo is the mother of a teenage daughter but also a Full Professor of Mobile Systems in the Department of Computer Science and Technology, University of Cambridge, UK. She is co-director of the Centre for Mobile, Wearable System and Augmented Intelligence and Deputy Head of Department for Research. She is also a Fellow of Jesus College Cambridge and the recipient of an ERC Advanced Research Grant. Prior joining Cambridge in 2008, she was a faculty member in the Department of Computer Science at University College London. She holds a PhD from the University of Bologna. Her research interests are in mobile systems and data for health, human mobility modelling, sensor systems and networking and mobile data analysis. She has published in a number of top tier conferences and journals in the area and her investigator experience spans projects funded by Research Councils and industry. She has received numerous best paper awards and in 2016 was listed in “10 Women in Networking /Communications You Should Know”.  She has served as steering, organizing and programme committee member of mobile, sensor systems, networking, data science conferences and workshops. She has delivered a number of keynote talks at conferences and workshops in the area of mobility, data science, pervasive computing and systems. 

14:20 - 14:35 - Emergency department admissions in COVID-19 and explainable machine learning to understand changes in clinical decision making - Dr. Chris Duckworth (IT Innovation Centre)

Abstract: The COVID-19 pandemic has created rapid and unprecedented changes in how services across the NHS are used. Emergency departments (EDs) have seen a 57% decrease (April 2020) in visits, with indications that patients in need of medical intervention have avoided coming to hospital for reasons unrelated to COVID, as COVID admissions have soared. This changing patient landscape has led to an overhaul in hospital operations and procedure. Decision support systems learn from historical ED operations, to enable early identification of patients who are at high risk of hospital admission, enabling ahead-of-time logistical planning. We test a machine learnt admission model's performance (trained pre COVID), pre COVID, and during the first wave, to understand how decision support systems are impacted by changing patient landscape and operational change. Using explainable machine learning, we understand how different hospital records (used as features) become more (or less) predictive of admission risk. We introduce the idea of using explainable admission models to track and understand changes in clinical decision making over time.

Bio: Chris is a Research Engineer (Healthcare) based in the IT Innovation Centre, as part of the School of Electronics and Computer Science. Since joining the centre in early 2021, his focus has been on the impact of COVID-19 on Emergency Department admissions and developing machine learning models for clinical decision making support. Chris' background in data science comes from a PhD (University of St Andrews) and employment at the Flatiron Institute (Simons Foundation) working in computational Astrophysics.

14:35 - 14:50 - Indirect disease mitigation using targeted interventions - Dr. Edoardo Manino (University of Manchester)

Abstract: The current COVID-19 pandemic is fought on two fronts: reducing the spread of the disease, and educating the population on the importance of vaccines and face masks. Both contribute to curbing the total number of cases, but how do these two factors interact? In this talk I present a mathematical model of coupled disease-awareness systems and propose strategies for optimal control. This is joint work with Dr Markus Brede (University of Southampton).

Bio: Edoardo Manino is a Research Associate in the Computer Science department of the University of Manchester. He is part of the EnnCore project and focuses on automated verification of neural network architectures. His background is in Bayesian machine learning, a topic he recently got awarded a PhD from the University of Southampton. His other research interests range from network science to algorithmic game theory and reinforcement learning.

14:50 - 15:30 - Panel discussion and Q/A - Chair: Dr. Kate Farrahi (University of Southampton)