Abstract: Health information technology (HIT) events were listed in the top 10 technology-related hazards since one in six patient safety events (PSE) is related to HIT. Although it becomes a common sense that event reporting is an effective way to accumulate typical cases for learning, the lack of HIT event databases remains a challenge. Aiming to retrieve HIT events from millions of event reports related to medical devices in FDA Manufacturer and User Facility Device Experience (MAUDE) database, we proposed a novel identification strategy composed of a structured data-based filter and an unstructured data-based classifier using both TF-IDF and biterm topic. A dataset with 97% HIT events was retrieved from the raw database of 2015 FDA MAUDE, which contains approximately 0.4~0.9% HIT events. This strategy holds promise of initializing and growing an HIT database to meet the challenges of collecting, analyzing, sharing, and learning from HIT events at an aggregated level.
Learning Objective 1: Learn the strategy of applying TF-IDF and topic modeling techniques on FDA database to extract health IT related events.
Learning Objective 2: Know how the proposed strategy initialized and grew a database for health IT related events.
Learning Objective 3: Understand the significance of a health IT database to patient safety improvement.
Hong Kang (Presenter)
University of Texas at Health Science Center at Houston
Zhiguo Yu, University of Texas at Health Science Center at Houston
Yang Gong, University of Texas at Health Science Center at Houston