BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260410T163402Z
DESCRIPTION:Click for Latest Location Information: http://dgiq2023east.data
 versity.net/sessionPop.cfm?confid=158&proposalid=14714\nData Governance in 
 Healthcare starts with knowing what data belongs to each patient. But 
 in the United States, where there is no authoritative source of patient ide
 ntity, that knowledge is elusive.  \n\nPrevious methods for ident
 ifying a patient use affinity scoring. If two records have enough comm
 on information, a scoring machine may find that they represent the same pat
 ient. But this approach often undermatches (failing to link records th
 at actually belong to the same patient), overmatches (linking records that 
 actually belong to different patients), or creates non-definitive scores th
 at require a human decision. \n\nNo matching algorithm is perfect.&nbs
 p;But in healthcare, patient identification must be very intolerant of over
 matches, which mix records for two different patients as if they were one p
 atient. \n\nWe present new methods for identifying a patient that leve
 rage demographic information typically available in the healthcare sys
 tem. Examples of those methods include:\n\n
 Splitting the question of identity into two (household v. patient)\n
 Household linkage cascades\n	Contextual uniqueness inference\n
 Recognizing and remedying weak linkages\n	Leveraging continuity of care\n\n
DTSTART:20231206T083000
SUMMARY:Patient Identification: The Core of Data Governance in Health Care
DTEND:20231206T091459
LOCATION: See Description
END:VEVENT
END:VCALENDAR