BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Special Joint SAS+MedAI Seminar Series - See info below.
DTSTART:20241112T160000Z
DTEND:20241112T180000Z
UID:TALK224170@talks.cam.ac.uk
CONTACT:Ines Machado
DESCRIPTION:Join us for the *Cambridge AI in Medicine Seminar Series*\, ho
 sted by the Cancer Research UK Cambridge Centre and the Department of Radi
 ology at Addenbrooke's. This series brings together leading experts to exp
 lore cutting-edge AI applications in healthcare—from disease diagnosis t
 o drug discovery. It's a unique opportunity for researchers\, practitioner
 s\, and students to stay at the forefront of AI innovations and engage in 
 discussions shaping the future of AI in healthcare. This month's seminar w
 ill be a joint event with supported by *SAS\, the Maxwell Centre and the O
 ffice for Translational Research. It follows the recent announcement of th
 e “Cambridge and SAS launch partnership in AI and advanced analytics to 
 accelerate innovation in the healthcare sector*.”\n\nThe event will be h
 eld on *12 November 2024\, 4-6pm at the Jeffrey Cheah Biomedical Centre (M
 ain Lecture Theatre)\, University of Cambridge* and *streamed online via Z
 oom*. \n\nThis month will feature the following talks:\n\n*Introduction to
  SAS: Lisa Murch\, Sr Industry Consultant\, Global Health and Life Science
 s Customer Advisory\, SAS*\n\n*AI_PREMie*: Transforming Preeclampsia Care 
 with the Power of SAS Viya: Ms Ana Le Chevillier\, Manager of the AI Healt
 hcare Hub at University College Dublin and Clinical Research Manager for D
 ata and AI for AI_PREMie\n\n*Machine learning for detecting and risk-strat
 ifying clonal haematopoiesis*: Dr William Dunn (CRUK Clinical Research Fel
 low) and Dr Muxin Gu (Research Associate)\, Cambridge Stem Cell Institute\
 , University of Cambridge\n\nThis will be followed by a networking session
  over drinks and snacks\, with a demo on the SAS Viya platform: *Applying 
 Machine Learning and Artificial Intelligence in Real World Data in Persona
 lized Medicine for Non-Small Cell Lung Cancer Patients.*\n\nThis is a *hyb
 rid event* so you can also join via *Zoom*:\nhttps://zoom.us/j/99050467573
 ?pwd=UE5OdFdTSFdZeUtIcU1DbXpmdlNGZz09\nMeeting ID: 990 5046 7573 and Passc
 ode: 617729\n\n\n\n\n*About SAS*:\nSAS delivers the most productive AI and
  analytics platform to transform data into life-changing insights and acce
 lerate breakthroughs in life sciences. SAS aims to:\nAccelerate scientific
  innovation to bring therapies to market faster.\nFacilitate analytics dec
 ision-making and collaboration in a complex ecosystem.\nEvolve with a mode
 rn\, open and flexible platform and industry solutions.\nProvide transpare
 nt and valid insights in a highly regulated environment.\n\n\n*AI_PREMie: 
 Transforming Preeclampsia Care with the Power of SAS Viya - Ms Ana Le Chev
 illier\, Manager of the AI Healthcare Hub at University College Dublin and
  Clinical Research Manager for Data and AI for AI_PREMie*\n\n*Bio:* Ana Le
  Chevillier is Clinical Research Manager for Data and AI for AI_PREMie\, a
  clinical decision support tool for preeclampsia\, and Manager of the AI H
 ealthcare Hub at University College Dublin. Ana leads the development of m
 achine learning models for augmented clinical decision-making using SAS Vi
 ya. Her expertise extends to meticulous data quality and management across
  the entire data lifecycle\, ensuring precision in healthcare analytics. A
 na serves as an Ambassador for Woman in Data Science (WiDS) and was recent
 ly named in the Tech Top 30 under 30 list by the Business Post.\n\n*Abstra
 ct*: Preeclampsia is a dangerous complication that can develop during preg
 nancy and causes the death of 76\,000 mothers and 500\,000 babies annually
 . Preeclampsia is characterised by the development of high blood pressure 
 and protein in the urine. However\, warning signs are difficult to detect\
 , meaning that preeclampsia often goes undetected until complications beco
 me serious. Our team has drawn upon cutting-edge biomedical\, clinical\, a
 nd machine-learning research to develop a clinical decision support tool\,
  AI_PREMie\, that helps to identify individuals with preeclampsia and pred
 ict how they will progress. AI_PREMie has received multiple accolades incl
 uding being rated as excellent in the UNESCO Global Top 100 AI projects ad
 dressing the 17 UN sustainable goals.\n\n\n*Machine learning for detecting
  and risk-stratifying clonal haematopoiesis – Dr William Dunn (CRUK Clin
 ical Research Fellow) and Dr Muxin Gu (Research Associate)\, Cambridge Ste
 m Cell Institute\, University of Cambridge*\n\n*Bio:* Billy is a clinical 
 haematologist studying for a PhD co-supervised by Prof George Vassiliou (c
 linician-scientist) and Dr Irina Mohorianu (Turing Fellow in Machine Learn
 ing). He completed his undergraduate medical training at the University of
  Glasgow\, followed by a Masters in Bioinformatics\, before moving to Camb
 ridge to commence an Academic Clinical Fellowship. His main interests are 
 in applying machine learning and data science approaches to detect and cha
 racterise clonal haematopoiesis.\nMuxin is a computational biologist speci
 alised in genomics. He is currently in Dr George Vassiliou’s group at Ca
 mbridge Stem Cell Institute\, analysing large datasets of genomic data. Mu
 xin’s current research interest is to investigate the stepwise change of
  genomic landscape prior to the onset of cancer and to understand the evol
 utionary trajectory of cancer development.\n\n*Abstract*: Clonal haematopo
 iesis (CH)\, the disproportionate expansion of a haematopoietic stem cell 
 and its progeny\, driven by somatic gene mutations\, is a common age-relat
 ed phenomenon that engenders an increased risk of developing myeloid neopl
 asms. At present\, CH is identified by targeted sequencing of peripheral b
 lood DNA\, which is impractical to apply at population scale. The complete
  blood count (CBC) is an inexpensive\, widely used clinical test. Here\, w
 e explore whether tree-based machine learning approaches applied to CBC da
 ta can identify individuals likely to harbour CH and prioritise them for D
 NA sequencing. We showcase a proof-of-concept that the presence of high-ri
 sk CH can be inferred from CBC perturbations using machine learning classi
 fiers\, and identify challenges in implementing this as a screening test.\
 nUsing whole-exome sequencing data from 454\,340 UK Biobank participants\,
  of whom 1808 developed myeloid caner 0-15 years after recruitment\, we co
 mpared genetic\, haematological and biochemical profiles between the pre-c
 ancer and control groups\, finding that disease-specific changes are detec
 table years before diagnosis. Using these\, we construct MN-predict (https
 ://bioinf.stemcells.cam.ac.uk/shiny/vassiliou/MN_predict/)\, a web applica
 tion that generates time-dependent predictions of myeloid cancer with inpu
 t of basic blood test and genetic data. Our study demonstrates that indivi
 duals that develop myeloid cancer can be identified years in advance and p
 rovides a framework for disease-specific prognostication that will be of s
 ubstantial use to researchers and physicians.\n\n\nWe look forward to your
  participation! If you are interested in getting involved and presenting y
 our work\, please email Ines Machado at im549@cam.ac.uk\n\nFor more inform
 ation about this seminar series\, see: https://www.integratedcancermedicin
 e.org/research/cambridge-medai-seminar-series/
LOCATION:Jeffrey Cheah Biomedical Centre (Main Lecture Theatre)\, Universi
 ty of Cambridge
END:VEVENT
END:VCALENDAR