Mining peripheral arterial disease cases from narrative clinical notes using natural language processing Naveed Afzal, PhD, Sunghwan Sohn, PhD, Sara Abram, MD, Christopher G. Scott, MS, Rajeev Chaudhry, MBBS, MPH, Hongfang Liu, PhD, Iftikhar J. Kullo, MD, Adelaide M. Arruda-Olson, MD, PhD Journal of Vascular Surgery Volume 65, Issue 6, Pages 1753-1761 (June 2017) DOI: 10.1016/j.jvs.2016.11.031 Copyright © 2016 The Authors Terms and Conditions
Fig 1 Dataset description. PAD, Peripheral arterial disease; REP, Rochester Epidemiology Project. Journal of Vascular Surgery 2017 65, 1753-1761DOI: (10.1016/j.jvs.2016.11.031) Copyright © 2016 The Authors Terms and Conditions
Fig 2 Study design. ABI, Ankle-brachial index; EHR, electronic health record; ID, identification; NLP, natural language processing. Journal of Vascular Surgery 2017 65, 1753-1761DOI: (10.1016/j.jvs.2016.11.031) Copyright © 2016 The Authors Terms and Conditions
Fig 3 Peripheral arterial disease (PAD) concept visualization. Journal of Vascular Surgery 2017 65, 1753-1761DOI: (10.1016/j.jvs.2016.11.031) Copyright © 2016 The Authors Terms and Conditions
Fig 4 Accuracy of natural language processing (NLP) algorithm compared with billing code algorithms (simple model and full model) for ascertainment of peripheral arterial disease (PAD) status. Journal of Vascular Surgery 2017 65, 1753-1761DOI: (10.1016/j.jvs.2016.11.031) Copyright © 2016 The Authors Terms and Conditions