Healthcare Technologies 2024: Student and Early Career Awards Evening
Hear from some of the winners of the IET Healthcare Technologies Student and Early Career Awards 2024
About
Please note that this is an in person event at IET London: Savoy Place
Join us to hear from the J.A Lodge winner and the Dennis Hill winner in person and the William James winners recorded talk as part of the IET Healthcare Technologies Student and Early Career Awards 2024.
After hearing the winners present their ground-breaking work, we'll be joined by a keynote speaker, Professor Mandic speaking on 'Hearables: Real World Applications of AI for eHealth'.
Award winners:
J.A Lodge Award 2024 (Suitable for *early career engineers)
Dr Harry Davies, Imperial College of Science, Technology and Medicine, A Deep Matched Filter: Harnessing Noisy Ear-ECG
William James Award 2024 (Suitable for students)
Fenglin Liu, University of Oxford, A medical multimodal large language model for future pandemics
Dennis Hill Award 2024 (Suitable for students)
Farheen Muhammed, University of Oxford - Microbubble generation using an acousto-fluidic device
As usual, you'll have the opportunity to ask questions to all presenters.
2
Continuing Professional Development
This event can contribute towards your Continuing Professional Development (CPD) hours as part of the IET's CPD monitoring scheme.
28 Nov 2024
6:00pm - 8:30pm
Organiser
- Healthcare Technologies TN
Speakers
Professor Danilo Mandic
Professor of Machine Intelligence - Department of Electrical and Electronic Engineering - Faculty of Engineering ,Imperial College London
Dr. Mandic received the Ph.D. degree in nonlinear adaptive signal processing in 1999 from Imperial College, London, London, U.K. where he is now a Professor. He specialises in Statistical Learning Theory, Machine Intelligence, and Statistical Signal Processing, and their applications especially in Biomedicine and Finance. He is a pioneer of Hearables (in-ear sensing of neural function and vital signs), an unobtrusive, discreet and long-term wearable solution for long-term physiological monitoring based on miniaturised sensors embedded on an earplug, an area where he holds several patents. He also specialises in Machine Intelligence for Finance, and is a Director of the Financial Signal Processing and Machine Learning Lab a Imperial. He has written over 600 journal and conference articles, and research monographs on Recurrent Neural Networks (with Wiley, 2001), Complex-valued Adaptive Filters and Neural Networks (Wiley 2009), Tensor Networks for Dimensionality Reduction and Large Scale Optimisation (Now Publishers, 2017) and Data Analytics on Graphs (Now Publishers, 2021). Prof Mandic is a Fellow of the IEEE, the 2019 recipient of the Dennis Gabor Award for "Outstanding Achievements in Neural Engineering", given by the International Neural Networks Society (INNS). He is also a 2018 winner of the Best Paper Award in IEEE Signal Processing Magazine, for his article on Tensor Decompositions for Signal Processing Application, and the 2021 winner of the Outstanding Paper Award in the IEEE ICASSP conference. He is also a winner of The Prize in the 2023 IEEE Engineering in Medicine and Biology Prize Paper Awards, and has coauthored 6 more award winning articles. He is a Core Member of the Machine Learning Initiative at Imperial. Danilo is the President of the International Neural Networks Society, and a past Technical Chair of ICASSP 2019, held in Brighton UK. He also received President's Award for Excellence in Research Supevervision at Imperial College in 2014. Danilo is passionate about cross-disciplinary aspects of his work and about bringing research into the curriculum. His current research interests areas are Adaptive Learning Theory, Big Data, Machine Learning on Graphs, Neural Networks, and Complexity Science, and their applications in Biomedicine and Financial Engineering.
Dr Harry Davies
Post Doctoral Researcher - Imperial College London
Harry J. Davies is a Post Doctoral Researcher with Imperial College London, specialising in bio-signal processing and interpretable AI with application to Hearables. During his PhD, he received the Editor’s choice award for his paper “In-Ear SpO2: A Tool for Wearable, Unobtrusive Monitoring of Core Blood Oxygen Saturation”. He was also the first to demonstrate that wearable photoplethysmography (PPG) can be used to screen for chronic obstructive pulmonary disease (COPD), resulting in a patent. Dr Davies has published in numerous journals and conferences at the intersection of biomedical engineering, signal processing, and health technology. In the past year, he has co-delivered two tutorials on interpretable AI for healthcare at international conferences. He was invited to join several of the world’s foremost photoplethysmography researchers to co-author “The 2023 Wearable Photoplethysmography Roadmap” on respiratory monitoring from In-Ear PPG. His recent work on creating a “deep matched-filter” for the processing of Ear-ECG was made a featured article in the July 2024 edition of IEEE Transactions on Biomedical Engineering. Harry has attracted funding from Sony Corporation and Meta and is currently working on cognitive state estimation in virtual reality environments and interpretable foundation models for bio-signal processing
Fenglin Liu
PhD student - University of Oxford
Fenglin Liu is a PhD student at the University of Oxford, supervised by Professor David A. Clifton. His research interests include Clinical AI and Digital Health. He has published papers in premier journals and AI conferences and serves on many review committees for top-tier venues. He was a finalist in the STEM for Britain 2024 scientific poster competition at the UK Houses of Parliament. He was awarded the Best Poster Award at the First Workshop on Multimodal AI, held by The Alan Turing Institute in the UK. He was awarded as the Distinguished Reviewer of top AI conferences CVPR, ACL, and AAAI
Reasons to attend
Award winning presentations
Keynote industry expert
CPD
Networking opportunities
Unique opportunity to learn directly from active and experienced professionals in their respective fields
Comprehensive overview of subjects with latest industry trends, developments, and challenges
Q&A to allow you to explore specific, related issues
Programme
Evening Programme (subject to change):
Arrival 6pm for a 6.30 start with light refreshments
Keynote speaker:
Professor Mandic speaking on 'Hearables: Real World Applications of AI for eHealth'
Award winners:
J.A Lodge Award 2024 (Suitable for *early career engineers): Dr Harry Davies, Imperial College of Science, Technology and Medicine , The Deep-Match Framework: R-Peak Detection in Ear-ECG
The Ear-ECG promises continuous monitoring of the electrical activity of the heart (electrocardiography) by measuring the potential difference across the heart with electrodes embedded within earphones. The increased wearability of the Ear-ECG often comes with a degradation in signal quality. To make full use of the Ear-ECG, even in cases where it is particularly noisy, we created an efficient and interpretable deep-learning based "matched filter" for precise R-peak detection in wearable ECG signals with a poor signal-to-noise ratio. This convolutional neural network is built to behave as a "matched filter", a signal processing concept involving pattern matching, that originated in radar systems 80 years ago. We initialise our matched filter network with the domain knowledge of the ECG signal and demonstrate that it even learns to enhance some aspects of these templates to accurately detect the peaks of the ear-ECG. Our model achieves state-of-the-art results with the benefit of being fully interpretable.
Dennis Hill Award 2024 (Suitable for students): Farheen Muhammed, University of Oxford - Microbubble generation using an acousto-fluidic device
Synopsis will be provided soon.
Due to circumstances outwith our control we will not have a speaker for the William James Award 2024 (Suitable for students).
The winner was Fenglin Liu, University of Oxford, A medical multimodal large language model for future pandemics
Deep neural networks have been integrated into the whole clinical decision procedure which can improve the efficiency of diagnosis and alleviate the heavy workload of physicians. Since most neural networks are supervised, their performance heavily depends on the volume and quality of available labels. However, few such labels exist for rare diseases (e.g., new pandemics). Here we report a medical multimodal large language model (Med-MLLM) for radiograph representation learning, which can learn broad medical knowledge (e.g., image understanding, text semantics, and clinical phenotypes) from unlabelled data. As a result, when encountering a rare disease, our Med-MLLM can be rapidly deployed and easily adapted to them with limited labels. Furthermore, our model supports medical data across visual modality (e.g., chest X-ray and CT) and textual modality (e.g., medical report and free-text clinical note); therefore, it can be used for clinical tasks that involve both visual and textual data. We demonstrate the effectiveness of our Med-MLLM by showing how it would perform using the COVID-19 pandemic "in replay". In the retrospective setting, we test the model on the early COVID-19 datasets; and in the prospective setting, we test the model on the new variant COVID-19-Omicron. The experiments are conducted on 1) three kinds of input data; 2) three kinds of downstream tasks, including disease reporting, diagnosis, and prognosis; 3) five COVID-19 datasets; and 4) three different languages, including English, Chinese, and Spanish. All experiments show that our model can make accurate and robust COVID-19 decision-support with little labelled data.
Networking till 8.30
(Programme can change)