Using Artificial Intelligence With Natural Language Processing to Combine Electronic Health Record’s Structured and Free Text Data to Identify Nonvalvular Atrial Fibrillation to Decrease Strokes and Death: Evaluation and Case-Control Study

Peter L Elkin   ^{1, 2, 3} , MD ;   Sarah Mullin   ¹ , PHO ;   Jack Mardekian   ⁴ , PhD ;   Christopher Crowner   ¹ , MSc ;   Sylvester Sakilay   ¹ , MSc ;   Shyamashree Sinha   ¹ , MSc, MD ;   Gary Brady   ⁴ , DPH ;   Marcia Wright   ⁴ , PharmD ;   Kimberly Nolen   ⁴ , PharmD ;   JoAnn Trainer   ⁴ , PharmD ;   Ross Koppel   ¹ , PhD ;   Daniel Schlegel   ¹ , PhD ;   Sashank Kaushik   ¹ , MD ;   Jane Zhao   ¹ , MD ;   Buer Song   ¹ , MD, PhD ;   Edwin Anand   ¹ , MD

¹ Department of Biomedical Informatics, University at Buffalo, Buffalo, NY, United States

² Bioinformatics Laboratory, Department of Veterans Affairs, VA Western New York Healthcare System, Buffalo, NY, United States

³ School of Engineering, University of Southern Denmark, Odense, Denmark

⁴ Pfizer, Inc., New York, NY, United States