connect with us

We’re thrilled to announce that John Jumper, PhD , will kick-off our 2024/2025 Seminar Series with his talk, "Extending AlphaFold to make predictions across the universe of biomolecular interactions" . John is one of the key pioneers behind the development of Google’s DeepMind AlphaFold - an artificial intelligence model to predict protein structures from their amino acid sequence with high accuracy. This in-person event promises to be an incredible opportunity to hear from one of the foremost innovators in AI and biology. Seminar Series Event: Extending AlphaFold to make predictions across the universe of biomolecular interactions Date and Time: 14:00 – 15.00, Thursday 10 October 2024 Location: The Council Room, 2nd floor, The King’s Building, Strand Campus Registration: Limited to EPSRC DRIVE-Health students in the first instance. Please email drive-health-cdt@kcl.ac.uk to check availability. Abstract: The high accuracy of AlphaFold 2 in predicting protein structures and protein-protein interactions raises the question of how to extend the success of AlphaFold to general biomolecular modeling, including protein-nucleic and protein-small molecule structure predictions as well as the effects of post-translational modification. In this talk, I will discuss our latest work on AlphaFold 3 to develop a single deep learning system that makes accurate predictions across these interaction types, as well as examine some of the remaining challenges in predicting the universe of biologically-relevant protein interactions.

We are thrilled to invite John Vardakis to speak at our EPSRC DRIVE-Health CDT's summer symposium next month. John joins us from Science Card to talk about " Exploring the Frontier: The future of GenAI Investments and Collaborations in Industry and Academia ." John Vardakis, PhD , has a diverse work experience, primarily in the field of scientific research. John is currently serving as the Head of Science Card Investment Group at Science Card, where they are involved in innovative banking. Previously, they worked as a Research Scientist at the University of Glasgow, where they focused on simulation-driven microelectromechanical systems design. John also worked as a Research Scientist at INSERM, investigating tumor mechanics and vascular fractality quantification. At the Center for Computational Imaging & Simulation Technologies in Biomedicine (CISTIB), they conducted research in cardiovascular and cerebrovascular biomechanics. Their work at UCL involved computational modeling of dementia and image-guided neurosurgery for epilepsy. John completed their DPhil in Biomedical Engineering at the University of Oxford, where their research focused on fluid transport in the brain. John also gained experience in the fields of vascular diagnosis and market research at the University of Heidelberg and P2i, respectively. Additionally, they worked as a Mechanical Engineer at Enactus and completed a placement at King's College London's Centre for Robotics Research. John Vardakis, PhD has a strong educational background in engineering and innovation. John obtained their Bachelor of Engineering (BEng) degree in Mechanical Engineering from King's College London in the years 2005 to 2008. John then pursued further education at the University of Oxford, where they completed the Centre for Doctoral Training in Healthcare Innovation from 2009 to 2010. Following this, they earned a Doctor of Philosophy (PhD) degree in Biomedical/Medical Engineering from the University of Oxford from 2010 to 2014. During their time at Oxford, they also pursued a diploma in Strategy & Innovation (Science Innovation Plus programme) from Saïd Business School, University of Oxford, from 2011 to 2012. In addition to their academic degrees, John Vardakis has obtained additional certifications. In December 2010, they received a Mathwork Training Certificate for completing the "Deploying MATLAB Based Applications - .NET Edition" course. John also obtained another Mathwork Training Certificate in December 2010 for completing the "MATLAB Programming Techniques" course. Registration is required, please email drivecdt@kcl.ac.uk for further event details. Our annual Symposium is a one-day face-to-face event for all DRIVE-Health students, academic supervisors, stakeholders and partners. Our aim is to discuss translating scientific and technological innovations in AI and data science, from research to clinical practice and commercial enterprise. The symposium will feature keynote talks, panel discussions, and poster presentations showcasing cutting-edge research and successful case studies. We will also celebrate our coming together with networking drinks at the end of the symposium. The EPSRC DRIVE-Health Centre for Doctoral Training is training the next generation of PhD health data scientists to become the innovation leaders of tomorrow. Our students work within an active NHS environment, and develop new models of data-driven care, whilst leveraging significant recent investment and infrastructure in Health Data Research within the UK. By registering for this event, you give consent to provide your name, e-mail address and registration information with King's College London for the purposes of managing the EPSRC DRIVE-Health CDT's Summer Symposium. Your personal data will be managed by those organisations and by Eventbrite according to their published privacy policies.

We are delighted to share that one of our EPSRC DRIVE-Health CDT students and PhD candidate at the IoPPN, Dina Farran, has been awarded 1st prize presentation at the recent Royal College of Psychiatrists Faculty of Liaison Psychiatry annual conference earlier this month. Dina is working under the supervision of Professor Fiona Gaughran and Professor Mark Ashworth and is about to submit her thesis at the end of this month. In the presentation, Dina summarised her PhD project consisting of a literature review, 2 observational studies, an intervention and 2 qualitative studies. Dina provides further detail below. Background Atrial fibrillation (AF), the most prevalent cardiac arrhythmia, is associated with an increased risk of stroke contributing to heart failure and death. In this project, we aim to improve patient safety by screening for stroke risk among people with AF and co-morbid mental illness. Methods (a) Conducted a systematic review and meta-analysis on prevalence, management, and outcomes of AF in people with Serious Mental Illness (SMI) versus the general population. (b) Evaluated oral anticoagulation (OAC) prescription trends in people with AF and co-morbid SMI in King’s College Hospital. (c) Identified the recorded rates of OAC prescription among people with AF and various mental illnesses and evaluated the association between mental illness severity and OAC prescription in eligible patients in South London and Maudsley (SLaM) NHS Foundation Trust. (d) Implemented an electronic clinical decision support system (eCDSS) consisting of a visual prompt on patient electronic Personal Health Record to screen for AF-related stroke risk in three Mental Health of Older Adults wards at SLaM. (e) Assessed the feasibility and acceptability of the eCDSS by qualitatively investigating clinicians’ perspective of the potential usefulness of the eCDSS (pre-intervention) and their experiences and their views regarding its impact on clinicians and patients (post-intervention). Results (a) People with SMI had low reported rates of AF. AF patients with SMI were less likely to receive OAC than the general population. When receiving warfarin, people with SMI, particularly bipolar disorder, experienced poor anticoagulation control compared to the general population. Meta-analysis showed that SMI was not significantly associated with an increased risk of stroke or major bleeding when adjusting for underlying risk factors. (b) Among AF patients having a high stroke risk, those with co-morbid SMI were less likely than non-SMI patients to be prescribed any OAC, particularly warfarin (but not DOACs). However, there was no evidence of a significant difference between the two groups since 2019. (c) Adjusting for age, sex, stroke and bleeding risk scores, patients with AF and co-morbid SMI were less likely to be prescribed any OAC compared to those with dementia, substance use disorders or common mental disorders. Among AF patients with co-morbid SMI, warfarin was less likely to be prescribed to those having alcohol or substance dependency, serious self-injury, hallucinations or delusions and activities of daily living impairment. (d) Clinicians were asked to confirm the presence of AF, clinically assess stroke and bleeding risks, record risk scores in clinical notes and refer patients at high risk of stroke to OAC clinics. (e) Clinicians reported that the eCDSS saved time, prompted them towards guidelines, boosted their confidence, and identified patients at risk. Perceived barriers to using the tool included low admission rate of AF cases, low or insufficient visibility of the alert/awareness of the tool, and impact of the eCDSS on workload. Conclusions This study presents a unique opportunity to quantify AF patients with mental illness who are at high risk of severe outcomes, using electronic health records. This has the potential to improve health outcomes and therefore patients' quality of life.

We are delighted to announce our first keynote speaker for the EPSRC DRIVE-Health CDT's summer symposium next month. Dr Dina Demner-Fushman joins us from the National Library of Medicine (NLM) to talk about "Getting AI generated results into decision support workflows: research, clinical and policy perspectives." Dina will share insights drawn from her experience utilising a Clinical Decision Support (CDS) tab within the National Institutes of Health's EHR system, and present recent research on the application of LLMs for predicting patient outcomes and generating progress notes. Dina Demner-Fushman, MD, PhD is an Investigator at the National Library of Medicine, NIH, HHS. Dr. Demner-Fushman leads research in the areas of Text and Image Processing for Clinical Decision Support and Education. The outgrowths of these projects are the evidence-based decision support system used at the NIH Clinical Center from 2009 to 2020, an image retrieval engine, Open-i, launched in 2012, and an automatic question answering service CHiQA launched in 2018. Dr. Demner-Fushman earned her doctor of medicine degree from Kazan State Medical Institute in 1980, and clinical research Doctorate (PhD) in Medical Science degree from Moscow Medical and Stomatological Institute in 1989. She earned her MS and PhD in Computer Science from the University of Maryland, College Park in 2003 and 2006, respectively. She earned her BA in Computer Science from Hunter College, CUNY in 2000. She authored more than 300 articles and book chapters in the fields of information retrieval, natural language processing, and biomedical and clinical informatics. Dr. Demner-Fushman is a Fellow of the American College of Medical Informatics (ACMI), an Associate Editor of the Journal of the American Medical Informatics Association, a member of Nature’s Scientific Data Editorial Board, chair of AMIA NLP SIG (2020-2023), and a founding member of the Association for Computational Linguistics (ACL) Special Interest Group on biomedical natural language processing. As the secretary and now chair of this group, she has been an essential organizer of the yearly ACL BioNLP Workshop since 2007. Dr. Demner-Fushman has received sixteen staff recognition and special act NLM awards since 2002. She is a recipient of the 2012, 2022, and 2023 NIH Award of Merit, a 2013 NLM Regents Award for Scholarship or Technical Achievement and a 2014 NIH Office of the Director Honor Award. Registration is required, please email drivecdt@kcl.ac.uk for further event details. Our annual Symposium is a one-day face-to-face event for all DRIVE-Health students, academic supervisors, stakeholders and partners. Our aim is to discuss translating scientific and technological innovations in AI and data science, from research to clinical practice and commercial enterprise. The symposium will feature keynote talks, panel discussions, and poster presentations showcasing cutting-edge research and successful case studies. We will also celebrate our coming together with networking drinks at the end of the symposium. The EPSRC DRIVE-Health Centre for Doctoral Training is training the next generation of PhD health data scientists to become the innovation leaders of tomorrow. Our students work within an active NHS environment, and develop new models of data-driven care, whilst leveraging significant recent investment and infrastructure in Health Data Research within the UK. By registering for this event, you give consent to provide your name, e-mail address and registration information with King's College London for the purposes of managing the EPSRC DRIVE-Health CDT's Summer Symposium. Your personal data will be managed by those organisations and by Eventbrite according to their published privacy policies.

Join our DRIVE-Health community for an exciting in-person event where we dive into the world of Generative AI and how it is shaping the future of healthcare. Our theme this year is ‘From Generative AI to Generating Impact,’ which aims to explore the ways in which developing and deploying AI in the real-world influences healthcare outcomes and advances medical research. From cutting-edge technologies to real-world applications, this symposium will explore the latest trends and innovations in the field. Meet students from across KCL faculties, network with industry partners, exchange ideas, and gain valuable insights to drive results in your own projects. Don't miss out on this opportunity to be part of the conversation! Registrations have now close. To be added to the waiting list, please email drivecdt@kcl.ac.uk Our annual Symposium is a one-day face-to-face event for all DRIVE-Health students, academic supervisors, stakeholders and partners. Our aim is to discuss translating scientific and technological innovations in AI and data science, from research to clinical practice and commercial enterprise. The symposium will feature keynote talks, panel discussions, and poster presentations showcasing cutting-edge research and successful case studies. We will also celebrate our coming together with networking drinks at the end of the symposium. The EPSRC DRIVE-Health Centre for Doctoral Training is training the next generation of PhD health data scientists to become the innovation leaders of tomorrow. Our students work within an active NHS environment, and develop new models of data-driven care, whilst leveraging significant recent investment and infrastructure in Health Data Research within the UK. By registering for this event, you give consent to provide your name, e-mail address and registration information with King's College London for the purposes of managing the EPSRC DRIVE-Health CDT's Summer Symposium. Your personal data will be managed by those organisations and by Eventbrite according to their published privacy policies.

DRIVE-Health has been awarded £7.9 million from The Engineering & Physical Sciences Research Council (EPSRC) for student intake from 2024 onwards. DRIVE-Health is one of 65 CDTs which received funding, totalling more than £1 billion. Using seed funding from King’s Centre for Doctoral Studies awarded in 2020, DRIVE-Health has trained 30 students to date. Building on this, the new award will support five additional cohorts at King’s, totalling at least 85 talented PhD students. The CDT is expecting to welcome its fourth intake of at least 15 students in October 2024. DRIVE-Health is the first health data science training centre in the UK to harness cross-sector collaboration across the NHS, industry, enterprise, policy makers, and academia. Working with diverse partners, DRIVE-Health PhD students develop cutting-edge models which leverage healthcare data to improve patient outcomes, streamline operations, and enhance clinical decision-making processes. EPSRC CDT DRIVE-Health’s vision is informed by three core goals: To provide world-class training in health data science research to the next generation of health data scientists, who will have the multidisciplinary skills needed to enable transformations in public health and breakthrough treatments. To solve the most challenging problems in data-driven health research through a diverse community of the brightest minds in health data science and an open, collaborative culture which fosters exchange and champions innovation. To co-create a translational cross-sector collaboration with the NHS, industry, enterprise, policy makers and academia. Professor Richard Dobson, Co-Director of DRIVE-Health and Professor of Medical Informatics at King’s IoPPN, says "As more data from biological, social, genomic, imaging, smart devices, and electronic health records becomes available, there are significant opportunities to revolutionise the way healthcare is delivered. Through DRIVE-Health, we will train some of the brightest minds in health data science to develop cutting-edge tools which utilise data to improve healthcare systems and patient outcomes." "This is an exciting time for medicine, with new data paradigms creating a novel research and implementation landscape covering the full span from cell to society. Over the next nine years, DRIVE-Health will nurture world-class researchers that will chart that landscape and drive the UK’s health data agenda." Professor Vasa Curcin, Co-Director of DRIVE-Health and Professor of Health Informatics at King’s FoLSM. The DRIVE-Health PhD Programme (2024-2032) focuses on five key scientific research themes: Sustainable health data systems engineering: Investigates methods to develop secure and scalable software systems for healthcare. Theme lead: Dr Zina Ibrahim. Multimodal patient data streams: Integrates diverse patient data types for analysis, including wearables and electronic health records. Theme lead: Dr Jorge Cardoso. Complex simulations and digital twins: Builds simulated environments to train AI models for healthcare applications. Theme lead: Dr Steffen Zschaler. Next-generation clinical user interfaces: Ensures healthcare data science applications are usable in clinical settings. Theme lead: Professor Nick Holliman. Co-designing impactful patient-centric healthcare solutions: Co-producing and co-designing healthcare solutions to maximise impact across all themes. Theme lead: Professor Claire Steves. On top of the £7.9m provided by the EPSRC, DRIVE-Health has received over £5.1m from partners, as well as in-kind contributions worth nearly £4m.

We are delighted to announce that our first Seminar Series of 2024 will be hosted by the esteemed Dr Yves-Alexandre de Mountjoye from Imperial College, London. Companies and governments are increasingly relying on privacy-preserving techniques to collect and process sensitive data. In this talk, Yves-Alexandre will discuss their efforts to red team deployed systems and argue that red teaming is essential to protect privacy in practice. He will describe how traditional de-identification techniques mostly fail in the age of big data and then show how implementation choices and trade-offs have enabled attacks against real-world systems, from query-based systems to differential privacy mechanisms and synthetic data. He plans to conclude by describing recent successes in using AI to automatically discover vulnerabilities.

We were delighted to welcome Professor Paulo Missier who hosted last seminar series of 2023. The past few years have seen the emergence of what the AI community calls “Data-centric AI”, namely the recognition that some of the limiting factors in AI performance are in fact in the data used for training the models, as much as in the expressiveness and complexity of the models themselves. One analogy is that of a powerful engine that will only run as fast as the quality of the fuel allows. A plethora of recent literature has started exploring the connection between data and models in depth, along with startups that offer “data engineering for AI" services. Some concepts are well-known to the data engineering community, including incremental data cleaning, multi-source integration, or data bias control; others are more specific to AI applications, for instance the realisation that some samples in the training space are "easier to learn from” than others. In this “position talk”, Paulo suggested that, from an infrastructure perspective, there is an opportunity to efficiently support patterns of complex pipelines where data and model improvements are entangled in a series of iterations. He focused in particular on end-to-end tracking of data and model versions, as a way to support MLDev and MLOps engineers as they navigate through a complex decision space.

DRIVE-Health's PhD student, Zeljko, launches a podcast where doctors and developers deep dive into the possibilities of AI in healthcare.

We were delighted to welcome Dr Daniel Schofield who hosted our September seminar series. Daniel provided an overview of the team that hosts the internship scheme at NHS England and offered further insights on how the scheme is designed, information on a couple of recent projects plus those available for the coming intake. He presented the different ways of working in the scheme and within the wider organisation.

Interactive workshops with different themes, guest speakers from industry and academia and a final panel discussion with our guest experts.

We are delighted to welcome Professor W.H.Langdon from UCL to host our June seminar series.

We were delighted to have Nick Holliman, from KCL host our May seminar series. Nick demonstrated how their recent research applying information theoretic methods to the challenges of urban data vizualisation addresses key questions for visualization researchers, and argues that successful data visualization increasingly needs rigorous underpinning science.

Dr Peter Waggett from IBM Research UK hosted our April series. Peter is the IBM UK Research Director and Leader of IBM Hursley Emerging Technology Program.

Our wonderful student, Tareen Dawood, presents her work on the idea of uncertainty calibration in #AI for decision-support

We were delighted to welcome Dr Maqbool Hussain, from Derby University, who presented our March Seminar Series.

A London-based startup looking to transform psychosis care through the power of speech has been developing machine learning algorithms that will detect impending psychosis from speech samples collected using just a smartphone. With Psyrin, practitioners along the psychosis care pathway will save time, improve triage accuracy, and increase capacity. Julianna, one of the co-founders of Psyrin has been inspired by the suffering of her loved ones to work on solving mental health problems. By studying psychology, she realized the importance of prevention in mental health care. "In case of severe mental disorders, especially in psychosis, the effect of prevention and early intervention can be really difference-making in the patient's life. However, preventative treatments need tools and technology to upscale and be accessible for as many people as possible." At Psyrin, they want to unlock the potential of objective, scalable, AI-powered analysis of speech to help clinicians screen, triage and monitor and understand patients better, in a more effective way and eventually, use their technology to transform psychosis care pathways from reactive to preventative. Supported by the King's Entrepreneurship Institute .

Foresight has been developed by one of our PhD students, Zeljko Kraljevic, as part of the COGSTACK platform to forecast future medical events and interventions.

We were delighted to welcome Professor Isaac Kohane, from Harvard Medical School, who presented our February Seminar Series.

Eoin Fullam, from the Department of Pscyhological Studies at Birkbeck University hosted our first seminar series of 2023 with discussions around formal bias in AI chatbot therapy. For a list of our previous and upcoming seminars, please see our Seminar Series .

Event comprises of four presentations and a networking moment at the end. (Un)Fairness in medical AI: tackling algorithmic bias in a biased world - Tiarna Lee, Biomedical Engineering and Imaging Sciences. Interpretable data mining techniques for patient phenotyping - Antonio López Martínez-Carrasco, Population health Sciences. The use of retinal imaging methods and AI to sub-type dementia - Zeynep Sahin, Old Age Psychiatry Beating dementia before it arrives – is decentralised artificial intelligence the answer? - Chris Albertyn , Old Age Psychiatry Sponsored by: King's Doctoral Students Association (KDSA) CDT Drive Health CDT Surgical Interventional Engineering EPSRC CDT in Smart Medical Imaging

The HDR UK National Text Analytics Project team recently came together to share the impacts of their work and opportunities for clinical natural language processing (NLP). Rene Ndoyi, one of the attendees, describes his experience of the HDR UK National Text Analytics project symposium. Author: Rene Ndoyi , Intern at Institute of Health Informatics Maximizing text analytics capability for health data research: key learnings from the HDR UK National Text Analytics project symposium On 28 September 2022, the HDR UK National Text Analytics Project team, led by Professor Richard Dobson (UCL Institute of Health Informatics; King’s College London) and Dr Angus Roberts (King’s College London), came together to share the impacts of their work and opportunities for the clinical natural language processing (NLP) community to deliver and use new NLP tools at this HDR UK symposium. This flagship project has delivered a step-change in text analytics capability, enabling a major shift in the UK’s ability to use research-ready, actionable, real-time electronic health records by delivering data-driven systems with potential to transform patient care. Sixty people from across HDR UK and the text analytics community attended the symposium to hear about the wide-reaching impacts of the project, learn about methods, tools and challenges for NLP and text analytics research, and discuss what the community needs to be able to access and use NLP resources for research. One of the attendees, Rene Ndoyi describes his thoughts and learning from the symposium below. My name is Rene Ndoyi, a recent graduate of the HDR UK Black Internship Programme and intern at the UCL Institute of Health Informatics . The internship programme was such a success in my quest to develop a career in health data science. Among the many interesting projects that I was introduced to is the National Text Analytics Resource – led by Professor Richard Dobson (UCL Institute of Health Informatics; King’s College London) and Dr Angus Roberts (King’s College London). This flagship project has delivered a step-change in text analytics capability, enabling a major shift in the UK’s ability to use research-ready, actionable, real-time electronic health records by delivering data-driven systems with potential to transform patient care. The project has built a community and brought together specialised resources that provide researchers with the tools and support to explore unstructured free text clinical data, using natural language processing (NLP) and text analytics. Sixty people from across HDR UK and the text analytics community attended the symposium to hear about the wide-reaching impacts of the project, learn about methods, tools and challenges for NLP and text analytics research. Attendees also discussed what the community needs to be able to access and use NLP resources for research. My internship mentor, Natalie Fitzpatrick, recommended that I attend the symposium as one of the many ways that the project brings together a community but also creates awareness of opportunities for NLP research being carried out across HDR UK. It was very insightful and interesting to learn about the work that has been done and the success the project has earned over the past five years. As an early career researcher who is building my skills in data science, I was keen to learn of the various tools and methods that have been developed to address the challenges of using unstructured free text data. A key piece of work is CogStack , a clinical information retrieval and extraction platform to create richer, more useful clinical information to improve healthcare. The tool enables querying data, without having to code thousands of SQL queries, based on real-time data. Another tool I learnt about was MedCAT , which extracts information from Electronic Health Records and links it to biomedical vocabulary systems like SNOMED-CT and UMLS. Both of these tools are available for the research community to use via the Health Data Research Innovation Gateway , with the code made open source on GitHub . Efforts to develop and apply these kinds of tools are important in tackling challenges around avoiding bias, transferability and model sharing. The team described various ways that they are approaching this – from improving access to unstructured data for research, to developing trusted models of governance and standards. They have developed a template model sharing agreement that is being used across 10 different NHS Trusts to date, so that NLP models can be shared easily. I also learnt that analysis of free text data can be achieved through R programming, a language I am currently learning. The idea of coding reproducible step by step workflows and frameworks is related to my internship learning experiences. Under Dr Johan Thygesen ’s supervision, we are exploring development of reproducible and extensible frameworks, based on a previous study that developed a framework for Covid 19 trajectories among 57 million Adults in England . Speakers also highlighted the importance of data governance and employing user-centred approaches. Natalie Fitzpatrick gave an interesting talk on creating a free text donated databank to develop and train NLP tools. I was fascinated to hear people’s feedback about this databank. Stakeholders, including patients and the public, researchers, clinicians and information governance and ethics experts, shared their thoughts through focus groups. There was a lot of support for the databank, but important issues were highlighted, such as the need to overcome different forms of bias, lack of generalisability, poor quality of data and patients’ ability to access their data to correct errors. From my experiences at the symposium, I have no doubt that these efforts will harness more opportunities for improved patient care. I look forward to future meetings and opportunities to learn more about the National Text Analytics Resource project.

Watch DRIVE-Health PhD student Jaya Chaturvedi talk about the Use of free-text clinical data in healthcare and research as part of the HDR UK Advancing the UK's health data science skills programme here