HARVEST, a Holistic Patient Record Summarizer at the Point of Care

In many care settings, clinicians are faced with an overwhelming amount of complex information about their patients, with little time for chart review [1]. Failure to digest patient data may result in errors in diagnosis and delayed care [2,3]. The need for better health information management and visualization tools has long been recognized [4,5], yet current electronic health records (EHRs) do not yet provide the cognitive support necessary for effectively and efficiently reviewing patient data. EHR displays are plagued by low information content, do not honor established interface design principles, and cannot be readily customized without imposing a considerable burden on clinicians and information technology professionals [6,7]. Important research has been undertaken on visualization of patient histories [8–10] and domain-specific summarizers [11], motivating our hypothesis that a holistic patient-record summarizer can impact care in a beneficial fashion. In this abstract, we describe the design, implementation, and deployment of HARVEST, a longitudinal patient record summarization system.