Peter Pruitt1,2, Andrew Naidech3,4, Jonathan Van Ornam5,6,7, Pierre Borczuk6,7, William Thompson8. 1. Department of Emergency Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL, USA. peter.pruitt@northwestern.edu. 2. Center for Healthcare Studies, Northwestern University Feinberg School of Medicine, 633 N St. Clair Street, Chicago, IL, 60622, USA. peter.pruitt@northwestern.edu. 3. Center for Healthcare Studies, Northwestern University Feinberg School of Medicine, 633 N St. Clair Street, Chicago, IL, 60622, USA. 4. Department of Neurology, Northwestern University Feinberg School of Medicine, Chicago, IL, USA. 5. Harvard Affiliated Emergency Medicine Residency, Boston, MA, USA. 6. Department of Emergency Medicine, Massachusetts General Hospital, 55 Fruit Street, Boston, MA, 02114, USA. 7. Department of Emergency Medicine, Harvard Medical School, Boston, MA, USA. 8. Center for Health Information Partnerships, Northwestern University Feinberg School of Medicine, 625 N Michigan Ave., Chicago, IL, 60611, USA.
Abstract
PURPOSE: Subdural hematoma (SDH) is the most common form of traumatic intracranial hemorrhage, and radiographic characteristics of SDH are predictive of complications and patient outcomes. We created a natural language processing (NLP) algorithm to extract structured data from cranial computed tomography (CT) scan reports for patients with SDH. METHODS: CT scan reports from patients with SDH were collected from a single center. All reports were based on cranial CT scan interpretations by board-certified attending radiologists. Reports were then coded by a pair of physicians for four variables: number of SDH, size of midline shift, thickness of largest SDH, and side of largest SDH. Inter-rater reliability was assessed. The annotated reports were divided into training (80%) and test (20%) datasets. Relevant information was extracted from text using a pattern-matching approach, due to the lack of a mention-level gold-standard corpus. Then, the NLP pipeline components were integrated using the Apache Unstructured Information Management Architecture. Output performance was measured as algorithm accuracy compared to the data coded by the two ED physicians. RESULTS: A total of 643 scans were extracted. The NLP algorithm accuracy was high: 0.84 for side of largest SDH, 0.88 for thickness of largest SDH, and 0.92 for size of midline shift. CONCLUSION: A NLP algorithm can structure key data from non-contrast head CT reports with high accuracy. The NLP is a potential tool to detect important radiographic findings from electronic health records, and, potentially, add decision support capabilities.
PURPOSE: Subdural hematoma (SDH) is the most common form of traumatic intracranial hemorrhage, and radiographic characteristics of SDH are predictive of complications and patient outcomes. We created a natural language processing (NLP) algorithm to extract structured data from cranial computed tomography (CT) scan reports for patients with SDH. METHODS: CT scan reports from patients with SDH were collected from a single center. All reports were based on cranial CT scan interpretations by board-certified attending radiologists. Reports were then coded by a pair of physicians for four variables: number of SDH, size of midline shift, thickness of largest SDH, and side of largest SDH. Inter-rater reliability was assessed. The annotated reports were divided into training (80%) and test (20%) datasets. Relevant information was extracted from text using a pattern-matching approach, due to the lack of a mention-level gold-standard corpus. Then, the NLP pipeline components were integrated using the Apache Unstructured Information Management Architecture. Output performance was measured as algorithm accuracy compared to the data coded by the two ED physicians. RESULTS: A total of 643 scans were extracted. The NLP algorithm accuracy was high: 0.84 for side of largest SDH, 0.88 for thickness of largest SDH, and 0.92 for size of midline shift. CONCLUSION: A NLP algorithm can structure key data from non-contrast head CT reports with high accuracy. The NLP is a potential tool to detect important radiographic findings from electronic health records, and, potentially, add decision support capabilities.
Authors: Guergana K Savova; James J Masanz; Philip V Ogren; Jiaping Zheng; Sunghwan Sohn; Karin C Kipper-Schuler; Christopher G Chute Journal: J Am Med Inform Assoc Date: 2010 Sep-Oct Impact factor: 4.497
Authors: Andrew J Gawron; William K Thompson; Rajesh N Keswani; Luke V Rasmussen; Abel N Kho Journal: Am J Gastroenterol Date: 2014-06-17 Impact factor: 10.864
Authors: Kabir Yadav; Efsun Sarioglu; Hyeong Ah Choi; Walter B Cartwright; Pamela S Hinds; James M Chamberlain Journal: Acad Emerg Med Date: 2016-01-14 Impact factor: 3.451
Authors: Viren D Patel; Roxanna M Garcia; Dionne E Swor; Eric M Liotta; Matthew B Maas; Andrew Naidech Journal: J Stroke Cerebrovasc Dis Date: 2020-05-15 Impact factor: 2.136
Authors: Sujay Kulshrestha; Dmitriy Dligach; Cara Joyce; Marshall S Baker; Richard Gonzalez; Ann P O'Rourke; Joshua M Glazer; Anne Stey; Jacqueline M Kruser; Matthew M Churpek; Majid Afshar Journal: Injury Date: 2020-10-25 Impact factor: 2.586
Authors: Arlene Casey; Emma Davidson; Michael Poon; Hang Dong; Daniel Duma; Andreas Grivas; Claire Grover; Víctor Suárez-Paniagua; Richard Tobin; William Whiteley; Honghan Wu; Beatrice Alex Journal: BMC Med Inform Decis Mak Date: 2021-06-03 Impact factor: 2.796