Advertisement

A natural language processing algorithm to extract characteristics of subdural hematoma from head CT reports

  • Peter PruittEmail author
  • Andrew Naidech
  • Jonathan Van Ornam
  • Pierre Borczuk
  • William Thompson
Original Article
  • 33 Downloads

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.

Keywords

Subdural hematoma Natural language processing Cranial CT reports Intracranial hemorrhage 

Notes

Funding sources

Dr. Pruitt was supported by a National Research Service Award postdoctoral fellow supported by the Agency for Healthcare Research and Quality (AHRQ) T-32 HS 000078 (PI: Jane L. Holl, MD, MPH). AHRQ was not involved in the design or execution of this research. Dr. Pruitt is now supported by a career development award from the Society for Academic Emergency Medicine Foundation.

Author contributions

PP, AN, and WKT conceived of the study and designed the analysis. PB, JO, and PP participated in the abstraction and coding of data. WKT programmed the algorithm. PP performed the data analysis. PP drafted the manuscript and all authors contributed substantially to its revision. PP takes responsibility for the paper as a whole.

Compliance with ethical standards

Conflicts of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Marin JR, Weaver MD, Yealy DM, Mannix RC (2014) Trends in visits for traumatic brain injury to emergency departments in the United States. JAMA 311:1917–1919.  https://doi.org/10.1001/jama.2014.3979 CrossRefGoogle Scholar
  2. 2.
    Pruitt P, Van OJ, Borczuk P (2017) A decision instrument to identify isolated traumatic subdural hematomas at low risk of neurologic deterioration, surgical intervention, or radiographic worsening. Acad Emerg Med 24:1377–1386.  https://doi.org/10.1111/acem.13306 CrossRefGoogle Scholar
  3. 3.
    Pons E, Braun LMM, Hunink MGM, Kors JA (2016) Natural language processing in radiology: a systematic review. Radiology 279:329–343.  https://doi.org/10.1148/radiol.16142770 CrossRefGoogle Scholar
  4. 4.
    Jain NL, Friedman C (1997) Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports. Proc AMIA Annu Fall Symp: 829–833Google Scholar
  5. 5.
    Kreimeyer K, Foster M, Pandey A, Arya N, Halford G, Jones SF, Forshee R, Walderhaug M, Botsis T (2017) Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review. J Biomed Inform 73:14–29.  https://doi.org/10.1016/j.jbi.2017.07.012 CrossRefGoogle Scholar
  6. 6.
    Cai T, Giannopoulos AA, Yu S, Kelil T, Ripley B, Kumamaru KK, Rybicki FJ, Mitsouras D (2016) Natural language processing technologies in radiology research and clinical applications. RadioGraphics 36:176–191.  https://doi.org/10.1148/rg.2016150080 CrossRefGoogle Scholar
  7. 7.
    Gawron AJ, Thompson WK, Keswani RN, Rasmussen LV, Kho AN (2014) Anatomic and advanced adenoma detection rates as quality metrics determined via natural language processing. Am J Gastroenterol 109:1844–1849.  https://doi.org/10.1038/ajg.2014.147 CrossRefGoogle Scholar
  8. 8.
    Kuo T-T, Rao P, Maehara C, et al (2016) Ensembles of NLP tools for data element extraction from clinical notes. AMIA. Annu Symp proceedings AMIA Symp 2016:1880–1889Google Scholar
  9. 9.
    Orlando A, Levy AS, Rubin BA, Tanner A, Carrick MM, Lieser M, Hamilton D, Mains CW, Bar-Or D (2018) Isolated subdural hematomas in mild traumatic brain injury. Part 2: a preliminary clinical decision support tool for neurosurgical intervention. J Neurosurg:1–8.  https://doi.org/10.3171/2018.1.JNS171906
  10. 10.
    Yadav K, Sarioglu E, Choi HA et al (2016) Automated outcome classification of computed tomography imaging reports for pediatric traumatic brain injury. Acad Emerg Med 23:171–178.  https://doi.org/10.1111/acem.12859 CrossRefGoogle Scholar
  11. 11.
    Esuli A, Marcheggiani D, Sebastiani F (2013) An enhanced CRFs-based system for information extraction from radiology reports. J Biomed Inform 46:425–435.  https://doi.org/10.1016/j.jbi.2013.01.006 CrossRefGoogle Scholar
  12. 12.
    Demner-Fushman D, Chapman WW, McDonald CJ (2009) What can natural language processing do for clinical decision support? J Biomed Inform 42:760–772.  https://doi.org/10.1016/j.jbi.2009.08.007 CrossRefGoogle Scholar
  13. 13.
    Lakhani P, Sundaram B (2017) Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284:574–582.  https://doi.org/10.1148/radiol.2017162326 CrossRefGoogle Scholar
  14. 14.
    Savova GK, Masanz JJ, Ogren PV, Zheng J, Sohn S, Kipper-Schuler KC, Chute CG (2010) Mayo clinical text analysis and knowledge extraction system (cTAKES): architecture, component evaluation and applications. J Am Med Inform Assoc 17:507–513.  https://doi.org/10.1136/jamia.2009.001560 CrossRefGoogle Scholar

Copyright information

© American Society of Emergency Radiology 2019

Authors and Affiliations

  1. 1.Department of Emergency MedicineNorthwestern University Feinberg School of MedicineChicagoUSA
  2. 2.Center for Healthcare StudiesNorthwestern University Feinberg School of MedicineChicagoUSA
  3. 3.Department of NeurologyNorthwestern University Feinberg School of MedicineChicagoUSA
  4. 4.Harvard Affiliated Emergency Medicine ResidencyBostonUSA
  5. 5.Department of Emergency MedicineMassachusetts General HospitalBostonUSA
  6. 6.Department of Emergency MedicineHarvard Medical SchoolBostonUSA
  7. 7.Center for Health Information PartnershipsNorthwestern University Feinberg School of MedicineChicagoUSA

Personalised recommendations