Margaret Mahan1, Daniel Rafter1, Hannah Casey1, Marta Engelking1, Tessneem Abdallah1, Charles Truwit2, Mark Oswood3,4, Uzma Samadani1,5. 1. Department of Biomedical Informatics and Computational Biology, University of Minnesota, Minneapolis, Minnesota, United States of America. 2. Diagnostic Imaging, Philips Global, Maple Grove, Minnesota, United States of America. 3. Department of Radiology, Hennepin Healthcare, Minneapolis, Minnesota, United States of America. 4. Department of Radiology, University of Minnesota, Minneapolis, Minnesota, United States of America. 5. Department of Neurosurgery, Minneapolis VA Medical Center, Minneapolis, Minnesota, United States of America.
Abstract
BACKGROUND: The manual extraction of valuable data from electronic medical records is cumbersome, error-prone, and inconsistent. By automating extraction in conjunction with standardized terminology, the quality and consistency of data utilized for research and clinical purposes would be substantially improved. Here, we set out to develop and validate a framework to extract pertinent clinical conditions for traumatic brain injury (TBI) from computed tomography (CT) reports. METHODS: We developed tbiExtractor, which extends pyConTextNLP, a regular expression algorithm using negation detection and contextual features, to create a framework for extracting TBI common data elements from radiology reports. The algorithm inputs radiology reports and outputs a structured summary containing 27 clinical findings with their respective annotations. Development and validation of the algorithm was completed using two physician annotators as the gold standard. RESULTS: tbiExtractor displayed high sensitivity (0.92-0.94) and specificity (0.99) when compared to the gold standard. The algorithm also demonstrated a high equivalence (94.6%) with the annotators. A majority of clinical findings (85%) had minimal errors (F1 Score ≥ 0.80). When compared to annotators, tbiExtractor extracted information in significantly less time (0.3 sec vs 1.7 min per report). CONCLUSION: tbiExtractor is a validated algorithm for extraction of TBI common data elements from radiology reports. This automation reduces the time spent to extract structured data and improves the consistency of data extracted. Lastly, tbiExtractor can be used to stratify subjects into groups based on visible damage by partitioning the annotations of the pertinent clinical conditions on a radiology report.
BACKGROUND: The manual extraction of valuable data from electronic medical records is cumbersome, error-prone, and inconsistent. By automating extraction in conjunction with standardized terminology, the quality and consistency of data utilized for research and clinical purposes would be substantially improved. Here, we set out to develop and validate a framework to extract pertinent clinical conditions for traumatic brain injury (TBI) from computed tomography (CT) reports. METHODS: We developed tbiExtractor, which extends pyConTextNLP, a regular expression algorithm using negation detection and contextual features, to create a framework for extracting TBI common data elements from radiology reports. The algorithm inputs radiology reports and outputs a structured summary containing 27 clinical findings with their respective annotations. Development and validation of the algorithm was completed using two physician annotators as the gold standard. RESULTS:tbiExtractor displayed high sensitivity (0.92-0.94) and specificity (0.99) when compared to the gold standard. The algorithm also demonstrated a high equivalence (94.6%) with the annotators. A majority of clinical findings (85%) had minimal errors (F1 Score ≥ 0.80). When compared to annotators, tbiExtractor extracted information in significantly less time (0.3 sec vs 1.7 min per report). CONCLUSION:tbiExtractor is a validated algorithm for extraction of TBI common data elements from radiology reports. This automation reduces the time spent to extract structured data and improves the consistency of data extracted. Lastly, tbiExtractor can be used to stratify subjects into groups based on visible damage by partitioning the annotations of the pertinent clinical conditions on a radiology report.
Authors: L F Marshall; S B Marshall; M R Klauber; M Van Berkum Clark; H Eisenberg; J A Jane; T G Luerssen; A Marmarou; M A Foulkes Journal: J Neurotrauma Date: 1992-03 Impact factor: 5.269
Authors: E Mark Haacke; Ann Christine Duhaime; Alisa D Gean; Gerard Riedy; Max Wintermark; Pratik Mukherjee; David L Brody; Thomas DeGraba; Timothy D Duncan; Elie Elovic; Robin Hurley; Lawrence Latour; James G Smirniotopoulos; Douglas H Smith Journal: J Magn Reson Imaging Date: 2010-09 Impact factor: 4.813
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