We are pleased to welcome Dr Antonio de Marvao - Clinical Senior Lecturer at King's College London, and Consultant Cardiologist and Obstetric Physician at GSTT and KCH - who will deliver his talk “Detecting the Rare, Managing the Common: AI-Driven Cardiovascular Care Using EHR Data" as part of our Seminar Series. Abstract: Cardiovascular disease encompasses rare inherited conditions and highly prevalent disorders such as hypertension and cardiometabolic disease. Despite differing epidemiology, both require accurate, dynamic and scalable risk stratification. Electronic health records provide longitudinal, multimodal data at population scale. However, their heterogeneity and fragmentation demand advanced artificial intelligence methods to generate clinically actionable insight. Approximately 70 to 80 percent of NHS data exists in unstructured free text, rendering much of the clinically relevant signal inaccessible to conventional analytics without natural language processing or large language models. To address this challenge, we have been developing an AI-enabled framework for real-world cardiovascular risk prediction using integrated EHR data. The approach brings together structured clinical variables, imaging outputs and free-text documentation within secure hospital environments. Natural language processing and large language models are used to transform narrative records into computable features, while chain-of-thought reasoning architectures extract guideline-defined risk parameters directly from routine documentation. This enables automated calculation of established risk scores and dynamic longitudinal reassessment within an agentic workflow. Local, open-source models are evaluated across parameter scales to ensure an appropriate balance between accuracy, safety and computational efficiency for clinical deployment. In inherited cardiac conditions, this approach enables automated extraction of echocardiographic and clinical features required for sudden cardiac death risk prediction, reducing manual burden and supporting real-time monitoring. The same principles extend to hypertensive disorders of pregnancy, facilitating earlier detection, structured surveillance and stratification of long-term cardiovascular risk. Integration of high-resolution EHR-derived phenotypes with genomic and multi-omics datasets further supports progression from risk prediction to biological insight and therapeutic target discovery. Applied rigorously, AI methodologies operating on routine healthcare data provide a scalable foundation for precision cardiovascular care across the life course. Seminar Series Event : “Detecting the Rare, Managing the Common: AI-Driven Cardiovascular Care Using EHR Data" Date and Time: Tuesday 24 February 2026, 15:30 – 16.30 hrs (GMT) Location: IoPPN Seminar 1 & 2, Denmark Hill Campus Attendance: Mandatory for all DRIVE-Health students; a calendar invitation has already been sent. Registration: Alumni and wider King's College London research community all welcome - please email drive-health-cdt@kcl.ac.uk to let us know if you would like to attend. Biography Antonio de Marvao is a Clinical Senior Lecturer at KCL, and a Consultant Cardiologist and Obstetric Physician at GSTT and KCH, specialising in inherited cardiac conditions, maternal cardiology, and hypertensive disorders of pregnancy. His research sits at the intersection of electronic health records (EHR) derived phenotyping, genomics/multi-omics, and cardiovascular imaging, using machine learning to improve risk prediction modelling and personalise care, across the reproductive continuum - from pregnancy to postpartum - and long-term cardiovascular prevention. He leads work within the NHS England Genomic AI Network, applying natural language processing, large language models and multimodal EHR integration to identify patients with inherited cardiovascular disease, streamline specialist review, and improve access to genetic testing and family screening. In parallel, his group also uses AI and EHR data to better define and detect hypertensive disorders of pregnancy at scale, quantify disparities, and enable earlier, more targeted intervention.