Encoding and Processing Patient Allergy Information in EHRs
The research team developed and evaluated a natural language processing allergy module that was used to study different types of allergies in an electronic health record.
The research team developed and evaluated a natural language processing allergy module that was used to study different types of allergies in an electronic health record.
This project created a natural language processing-enabled clinical decision support system to pull patient information and determine recommendations for cervical cancer screening, and demonstrated improvement in overall screening and surveillance rates.
The research team developed and tested algorithms that can predict postoperative adverse outcomes with a high degree of accuracy.
This project will develop and test a personalized motivational text messaging intervention to improve management of diabetes and depression in low-income populations.
This research used natural language processing and machine learning to develop algorithms to recognize diagnostic criteria in free text for autism spectrum disorder, to increase earlier diagnosis and treatment.
This research evaluated the appropriateness, acceptability, feasibility, and effectiveness of the Gabby Health Information Technology System among Black and African American women receiving care at community-based clinical sites.
This research combined the artificial intelligence technology technique Dynamic Logic with natural language processing to create a model to predict risk of death over the next 12 months and found it was better than benchmark statistical and machine learning algorithms.
The 2018-2020 annual Conference on Health IT & Analytics connected a wide range of academic disciplines, Federal agencies, policymakers, funders, practitioners, patient advocates, and industry professionals to develop a health information technology and analytics (HIT+A) research agenda and materials that were widely disseminated to identify trends and knowledge gaps in HIT+A.
Researchers created a drug allergy module that detects inconsistencies in allergy information within the electronic health record and uses a dynamic picklist that puts answers in order of how important they are based on the allergen input.
Working with the American College of Rheumatology, this research created a clinical learning network to increase the use of rheumatoid arthritis patient-reported outcomes (PROs), developed a natural language processing algorithm to abstract PRO measures from the Rheumatology Informatics System for Effectiveness registry, and planned for a toolkit to disseminate best practices in the implementation of PROs.