Tags

Type your tag names separated by a space and hit enter

tbiExtractor: A framework for extracting traumatic brain injury common data elements from radiology reports.
PLoS One. 2020; 15(7):e0214775.Plos

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.

Authors+Show Affiliations

Department of Biomedical Informatics and Computational Biology, University of Minnesota, Minneapolis, Minnesota, United States of America.Department of Biomedical Informatics and Computational Biology, University of Minnesota, Minneapolis, Minnesota, United States of America.Department of Biomedical Informatics and Computational Biology, University of Minnesota, Minneapolis, Minnesota, United States of America.Department of Biomedical Informatics and Computational Biology, University of Minnesota, Minneapolis, Minnesota, United States of America.Department of Biomedical Informatics and Computational Biology, University of Minnesota, Minneapolis, Minnesota, United States of America.Diagnostic Imaging, Philips Global, Maple Grove, Minnesota, United States of America.Department of Radiology, Hennepin Healthcare, Minneapolis, Minnesota, United States of America. Department of Radiology, University of Minnesota, Minneapolis, Minnesota, United States of America.Department of Biomedical Informatics and Computational Biology, University of Minnesota, Minneapolis, Minnesota, United States of America. Department of Neurosurgery, Minneapolis VA Medical Center, Minneapolis, Minnesota, United States of America.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

32609723

Citation

Mahan, Margaret, et al. "TbiExtractor: a Framework for Extracting Traumatic Brain Injury Common Data Elements From Radiology Reports." PloS One, vol. 15, no. 7, 2020, pp. e0214775.
Mahan M, Rafter D, Casey H, et al. TbiExtractor: A framework for extracting traumatic brain injury common data elements from radiology reports. PLoS ONE. 2020;15(7):e0214775.
Mahan, M., Rafter, D., Casey, H., Engelking, M., Abdallah, T., Truwit, C., Oswood, M., & Samadani, U. (2020). TbiExtractor: A framework for extracting traumatic brain injury common data elements from radiology reports. PloS One, 15(7), e0214775. https://doi.org/10.1371/journal.pone.0214775
Mahan M, et al. TbiExtractor: a Framework for Extracting Traumatic Brain Injury Common Data Elements From Radiology Reports. PLoS ONE. 2020;15(7):e0214775. PubMed PMID: 32609723.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - tbiExtractor: A framework for extracting traumatic brain injury common data elements from radiology reports. AU - Mahan,Margaret, AU - Rafter,Daniel, AU - Casey,Hannah, AU - Engelking,Marta, AU - Abdallah,Tessneem, AU - Truwit,Charles, AU - Oswood,Mark, AU - Samadani,Uzma, Y1 - 2020/07/01/ PY - 2019/03/15/received PY - 2020/05/18/accepted PY - 2020/7/2/entrez PY - 2020/7/2/pubmed PY - 2020/7/2/medline SP - e0214775 EP - e0214775 JF - PloS one JO - PLoS ONE VL - 15 IS - 7 N2 - 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. SN - 1932-6203 UR - https://www.unboundmedicine.com/medline/citation/32609723/tbiExtractor:_A_framework_for_extracting_traumatic_brain_injury_common_data_elements_from_radiology_reports L2 - https://dx.plos.org/10.1371/journal.pone.0214775 DB - PRIME DP - Unbound Medicine ER -
Try the Free App:
Prime PubMed app for iOS iPhone iPad
Prime PubMed app for Android
Prime PubMed is provided
free to individuals by:
Unbound Medicine.