BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Talks.cam//talks.cam.ac.uk// X-WR-CALNAME:Talks.cam BEGIN:VEVENT SUMMARY:Cambridge MedAI Seminar - March 2026 - Anoushka Harit and Dr Hania Paverd DTSTART:20260324T114500Z DTEND:20260324T130000Z UID:TALK245992@talks.cam.ac.uk CONTACT:Hannah Clayton DESCRIPTION:Sign-up on Eventbrite: https://medai-march2026.eventbrite.co.u k\n\nJoin us for the *Cambridge AI in Medicine Seminar Series*\, hosted by the *Cancer Research UK Cambridge Centre* and the *Department of Radiolog y at Addenbrooke’s*. This series brings together leading experts to expl ore cutting-edge AI applications in healthcare – from disease diagnosis to drug discovery. It’s a unique opportunity for researchers\, practitio ners\, and students to stay at the forefront of AI innovations and engage in discussions shaping the future of AI in healthcare.\n\nThis month’s s eminar will be held on *Tuesday 24 March 2026\, 12-1pm at the Jeffrey Chea h Biomedical Centre (Main Lecture Theatre)\, University of Cambridge* and *streamed online via Zoom*. A light lunch from Aromi will be served from 1 1:45. The event will feature the following talks:\n\n*_AI Based Early Dete ction in Hereditary Diffuse Gastric Cancer Patients_ - Anoushka Harit\, Ph D Student\, Cancer Research UK Cambridge Institute\, University of Cambrid ge*\n\nAnoushka Harit is a researcher working at the intersection of artif icial intelligence\, machine learning\, and biomedical imaging. Her work f ocuses on developing computational approaches to improve early detection o f gastrointestinal cancers\, particularly hereditary diffuse gastric cance r (HDGC). She previously completed an MSc in Computer Science at Durham Un iversity\, where her research focused on optimisation strategies for neura l networks. Her broader research interests include machine learning\, grap h-based learning methods\, and explainable AI\, with a focus on applying t hese methods to clinical imaging and healthcare applications.\n\n*Abstract *: Hereditary Diffuse Gastric Cancer (HDGC) is a genetic cancer predisposi tion syndrome most commonly associated with germline mutations in the CDH1 gene and characterised by the development of early signet ring cell carci noma (SRCC). Detecting early SRCC lesions during endoscopic surveillance i s particularly challenging because these lesions often appear as subtle pa le mucosal abnormalities that are difficult to distinguish from normal muc osa. In this work\, we investigate an AI-assisted approach for identifying and characterising pale mucosal regions in endoscopic images using colour \, texture\, and morphological features. Using annotated endoscopic frames \, we developed a computational framework to distinguish SRCC lesions from normal pale mucosa.\n\n*_From radiology reports to early prognostic marke rs: benchmarking LLMs in chronic liver disease_ - Dr Hania Paverd\, PhD St udent\, Early Cancer Institute\, University of Cambridge*\n\nHania is a th ird-year PhD student at the Early Cancer Institute\, working under the sup ervision of Mireia Crispin and Matt Hoare. Her research focuses on applyin g computational techniques to advance the early detection of liver cancer. Hania has a medical background\, having studied medicine at Newnham Colle ge\, and she is a radiology resident at Addenbrooke’s Hospital.\n\n*Abst ract*: Large scale research on real-world clinical data is fundamentally l imited by free-text format of clinical documentation\, with vital prognost ic clues remaining trapped within vast\, unstructured medical narratives. In Hepatocellular carcinoma (HCC)\, this data bottleneck often results in late-stage diagnoses despite regular patient surveillance. To unlock these latent insights and shift toward proactive risk stratification\, we devel oped a scalable\, LLM-driven pipeline capable of transforming free-text cl inical reports into quantitative variables and longitudinal disease timeli nes. By benchmarking open-source large language models\, we found Llama 3. 3 70B outperformed smaller and medically fine-tuned models to achieve ≥9 0% accuracy across 59 of 73 extraction tasks\, allowing us to reliably map disease progression. Deploying this automated framework across more than 22\,000 heterogeneous records from an 835-patient liver transplant cohort\ , we successfully surfaced key HCC risk factors and validated routine clin ical metrics at an unprecedented scale. Ultimately\, this work establishes a new paradigm for research on real-world clinical data\, showcasing that advanced AI can reliably reconstruct clinical histories to power large-sc ale research and hopefully enable earlier\, data-driven interventions.\n\n This is a hybrid event so you can also join via Zoom: https://zoom.us/j/99 050467573?pwd=UE5OdFdTSFdZeUtIcU1DbXpmdlNGZz09\n\nMeeting ID: 990 5046 757 3 and Passcode: 617729\n\nWe look forward to your participation! If you ar e interested in getting involved and presenting your work\, please email I nes Machado at im549@cam.ac.uk\n\nFor more information about this seminar series\, see: https://www.integratedcancermedicine.org/research/cambridge- medai-seminar-series/\n LOCATION:Jeffrey Cheah Biomedical Centre (Main Lecture Theatre)\, Universi ty of Cambridge END:VEVENT END:VCALENDAR