BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Mining for meaning in electronic health records\; deep semantic no
 rmalisation for precision medicine and discovery. - Paul Schofield
DTSTART:20220223T140000Z
DTEND:20220223T150000Z
UID:TALK163333@talks.cam.ac.uk
CONTACT:Samantha Noel
DESCRIPTION:Electronic health records (EHRs) contain information critical 
 to the realisation of the promise of personalised medicine\, but also data
  essential for the discovery of the molecular basis of disease. Clinical i
 nformation systems and EHRs were not developed for the discovery\, integra
 tion and export of information\, most being based on the concept of paper 
 records going back to the 1990s. Consequently we find in EHRs information 
 contained in administrative\, diagnostic  and procedure codes\, which are 
 highly structured and standardised\, the results of investigative tests\, 
 ranging from blood chemistry to images\, which might be regarded as partia
 lly structured information\, and finally narrative reports of clinical enc
 ounters and discharge letters which are rich sources of information but co
 mpletely unstructured. Reliably extracting and integrating these types of 
 information is a huge challenge\, but the ability to retrieve coded and qu
 antitative data into a common symbolic framework opens up the possibility 
 of connecting these data together with the large amounts of background kno
 wledge now available.\n\nI will discuss three approaches to extracting and
  using EHR information: the first uses the Komenti platform which is desig
 ned to extract information from free text into semantically formalised ont
 ological annotations\, the second is an approach to combine quantitative d
 ata into that same semantic framework. \nThe third\, a new resource\, axio
 matises ICD-10 terms uses the Human phenotype ontology for integration wit
 h existing knowledge and\, for example\, patient classification. The promi
 se of these orthogonal approaches will be discussed.
LOCATION:CMS\, Meeting Room 15
END:VEVENT
END:VCALENDAR