Leveraging advanced clinical phenotyping to enhance problem lists and support value-based healthcare

Project Summary With newly available electronic health data and a massive increase in processing powerdata driven personalized medicine is just now becoming possibleHoweveradvances to improve health care are inherently limited by data qualityOne of the most used sources of datathe patient problem listis also the greatest source of data inaccuracyAccording to recent studiesthe patient problem list is often less thanaccurate in documenting the most critical conditionsThese errors exacerbate inefficiencies throughout the American health care system from care delivery to quality improvementPrimary care physicians rely on problem lists to develop transitional treatment plans for themillion Americans who change providers every yearErrors related to care transitions harm more thanmillion people each year in the United Statescosting the nation an estimated $billion annuallyPopulation health effortsa cornerstone of value based healthcarerely on problem lists to determine risk levels and deployment of resourcesThese efforts cannot succeed if the source data produce faulty resultsThis application seeks to enable better individual patient careenhanced population health managementand effective downstream analytics by building an automated problem list builderwhich provides an accurate and granular account of the patient s medical conditionsIf the program is successfulone of the greatest technical risks in value based healthcare will be addressedPhase I exceeded success criteria in proving feasibility of core modules in natural language processingNLPand artificial intelligenceBased on Phase I successimplementation pathways are demonstrated through pilots with one of the largest US healthcare systems and one of the largest global biotechnology firmsThe team is comprised of commercial and academic leaders in the field of NLP based products applied to value based healthcare Project Narrative VMT proposes to use advanced semantic technologies and artificial intelligence to enhance the individualized patient problem listwhich frequently hasor lower accuracy for common conditions such as cancersmokingand heart failureThe problem list represents source data in care deliverypopulation healthshared risk contractingand researchThis proposal aims to support more accurate and granular source data to enhance care delivery and value based healthcare