Natural Language Processing System
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 evaluated a natural language processing allergy module that was used to study different types of allergies in an electronic health record.
This research prospectively evaluated a machine learning algorithm that identifies candidates for neurologic surgery to control epilepsy.
This project developed a natural language processing electronic health record search tool that automatically identifies and ranks relevant clinical information based on a patient’s presenting complaint within the emergency department setting.
This research evaluated the implementation and effectiveness of a clinical decision support tool designed to support the delivery of recommended care to hospitalized patients with heart failure, regardless of the reason for hospitalization.
This project will study the impact of errors in medical documents on quality of care and develop innovative natural language processing methods to automatically detect errors so that physicians can correct the documents before finalizing them in the electronic health record.
This project developed, implemented, and evaluated a voice-generated enhanced electronic note system and found that it did not improve the time to finalize notes or clinician satisfaction.
This project will provide an evidence base to better inform user-centered design and implementation processes to improve health information technology, usability, and safety.
This project explored whether the use of data from pain management practices can be used to develop more robust evidence-based approaches to chronic pain management.
The project team developed automated methods for identifying relevant new information versus redundant information in electronic health record clinical notes.