IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0158762.html
   My bibliography  Save this article

Predictors of Outcome in Traumatic Brain Injury: New Insight Using Receiver Operating Curve Indices and Bayesian Network Analysis

Author

Listed:
  • Zsolt Zador
  • Matthew Sperrin
  • Andrew T King

Abstract

Background: Traumatic brain injury remains a global health problem. Understanding the relative importance of outcome predictors helps optimize our treatment strategies by informing assessment protocols, clinical decisions and trial designs. In this study we establish importance ranking for outcome predictors based on receiver operating indices to identify key predictors of outcome and create simple predictive models. We then explore the associations between key outcome predictors using Bayesian networks to gain further insight into predictor importance. Methods: We analyzed the corticosteroid randomization after significant head injury (CRASH) trial database of 10008 patients and included patients for whom demographics, injury characteristics, computer tomography (CT) findings and Glasgow Outcome Scale (GCS) were recorded (total of 13 predictors, which would be available to clinicians within a few hours following the injury in 6945 patients). Predictions of clinical outcome (death or severe disability at 6 months) were performed using logistic regression models with 5-fold cross validation. Predictive performance was measured using standardized partial area (pAUC) under the receiver operating curve (ROC) and we used Delong test for comparisons. Variable importance ranking was based on pAUC targeted at specificity (pAUCSP) and sensitivity (pAUCSE) intervals of 90–100%. Probabilistic associations were depicted using Bayesian networks. Results: Complete AUC analysis showed very good predictive power (AUC = 0.8237, 95% CI: 0.8138–0.8336) for the complete model. Specificity focused importance ranking highlighted age, pupillary, motor responses, obliteration of basal cisterns/3rd ventricle and midline shift. Interestingly when targeting model sensitivity, the highest-ranking variables were age, severe extracranial injury, verbal response, hematoma on CT and motor response. Simplified models, which included only these key predictors, had similar performance (pAUCSP = 0.6523, 95% CI: 0.6402–0.6641 and pAUCSE = 0.6332, 95% CI: 0.62–0.6477) compared to the complete models (pAUCSP = 0.6664, 95% CI: 0.6543–0.679, pAUCSE = 0.6436, 95% CI: 0.6289–0.6585, de Long p value 0.1165 and 0.3448 respectively). Bayesian networks showed the predictors that did not feature in the simplified models were associated with those that did. Conclusion: We demonstrate that importance based variable selection allows simplified predictive models to be created while maintaining prediction accuracy. Variable selection targeting specificity confirmed key components of clinical assessment in TBI whereas sensitivity based ranking suggested extracranial injury as one of the important predictors. These results help refine our approach to head injury assessment, decision-making and outcome prediction targeted at model sensitivity and specificity. Bayesian networks proved to be a comprehensive tool for depicting probabilistic associations for key predictors giving insight into why the simplified model has maintained accuracy.

Suggested Citation

  • Zsolt Zador & Matthew Sperrin & Andrew T King, 2016. "Predictors of Outcome in Traumatic Brain Injury: New Insight Using Receiver Operating Curve Indices and Bayesian Network Analysis," PLOS ONE, Public Library of Science, vol. 11(7), pages 1-18, July.
  • Handle: RePEc:plo:pone00:0158762
    DOI: 10.1371/journal.pone.0158762
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0158762
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0158762&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0158762?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Chiu, W.-T. & Kuo, C.-Y. & Hung, C.-C. & Chen, M., 2000. "The effect of the Taiwan motorcycle helmet use law on head injuries," American Journal of Public Health, American Public Health Association, vol. 90(5), pages 793-796.
    2. M Berkan Sesen & Ann E Nicholson & Rene Banares-Alcantara & Timor Kadir & Michael Brady, 2013. "Bayesian Networks for Clinical Decision Support in Lung Cancer Care," PLOS ONE, Public Library of Science, vol. 8(12), pages 1-1, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. David Bishai & Asma Quresh & Prashant James & Abdul Ghaffar, 2006. "National road casualties and economic development," Health Economics, John Wiley & Sons, Ltd., vol. 15(1), pages 65-81, January.
    2. Holman Ospina-Mateus & Leonardo Augusto Quintana Jiménez & Francisco J. Lopez-Valdes & Katherinne Salas-Navarro, 2019. "Bibliometric analysis in motorcycle accident research: a global overview," Scientometrics, Springer;Akadémiai Kiadó, vol. 121(2), pages 793-815, November.
    3. Annemieke Witteveen & Gabriela F. Nane & Ingrid M.H. Vliegen & Sabine Siesling & Maarten J. IJzerman, 2018. "Comparison of Logistic Regression and Bayesian Networks for Risk Prediction of Breast Cancer Recurrence," Medical Decision Making, , vol. 38(7), pages 822-833, October.
    4. Heng-Yu Lin & Jian-Sing Li & Chih-Wei Pai & Wu-Chien Chien & Wen-Cheng Huang & Chin-Wang Hsu & Chia-Chieh Wu & Shih-Hsiang Yu & Wen-Ta Chiu & Carlos Lam, 2022. "Environmental Factors Associated with Severe Motorcycle Crash Injury in University Neighborhoods: A Multicenter Study in Taiwan," IJERPH, MDPI, vol. 19(16), pages 1-16, August.
    5. Carlos Lam & Chih-Wei Pai & Chia-Chang Chuang & Yu-Chun Yen & Chia-Chieh Wu & Shih-Hsiang Yu & Kuo-Sheng Hung & Wen-Ta Chiu, 2019. "Rider factors associated with severe injury after a light motorcycle crash: A multicentre study in an emerging economy setting," PLOS ONE, Public Library of Science, vol. 14(6), pages 1-17, June.
    6. Jacob R Lepard & Riccardo Spagiari & Jacquelyn Corley & Ernest J Barthélemy & Eliana Kim & Rolvix Patterson & Sara Venturini & Megan E H Still & Yu Tung Lo & Gail Rosseau & Rania A Mekary & Kee B Park, 2021. "Differences in outcomes of mandatory motorcycle helmet legislation by country income level: A systematic review and meta-analysis," PLOS Medicine, Public Library of Science, vol. 18(9), pages 1-18, September.
    7. John Christopher Walsh & Karl Stefan Meneghella, 2018. "An Examination of Strategies to Mitigate the Number of Motorcycle Rider Fatalities in Thailand," Acta Universitatis Danubius. OEconomica, Danubius University of Galati, issue 14(4), pages 72-87, AUGUST.
    8. Yen-Hsiu Liu & Bayu Satria Wiratama & Chung-Jen Chao & Ming-Heng Wang & Rui-Sheng Chen & Wafaa Saleh & Chih-Wei Pai, 2023. "Unhelmeted Riding, Drunk Riding, and Unlicensed Riding among Motorcyclists: A Population Study in Taiwan during 2011–2016," IJERPH, MDPI, vol. 20(2), pages 1-15, January.
    9. Ting-Min Hsieh & Tsung-Cheng Tsai & Yueh-Wei Liu & Ching-Hua Hsieh, 2016. "How Does the Severity of Injury Vary between Motorcycle and Automobile Accident Victims Who Sustain High-Grade Blunt Hepatic and/or Splenic Injuries? Results of a Retrospective Analysis," IJERPH, MDPI, vol. 13(7), pages 1-9, July.
    10. Catarina Moreira & Emmanuel Haven & Sandro Sozzo & Andreas Wichert, 2018. "Process mining with real world financial loan applications: Improving inference on incomplete event logs," PLOS ONE, Public Library of Science, vol. 13(12), pages 1-31, December.
    11. Mroczek Teresa & Skica Tomasz & Rodzinka Jacek, 2019. "Optimal Size of the General Government Sector from the Point of View of its Impact on the EU Economies," South East European Journal of Economics and Business, Sciendo, vol. 14(2), pages 95-105, December.
    12. Lisa Stolzenberg & Stewart J. D’Alessio, 2003. "“Born To Be Wildâ€," Evaluation Review, , vol. 27(2), pages 131-150, April.
    13. Mroczek Teresa & Skica Tomasz & Rodzinka Jacek, 2018. "Application of Probabilistic Inference in Defining Impact of the General Government Sector’s Size on the Economy and Determining the Size of the Sector by the Economy in the EU," Financial Internet Quarterly (formerly e-Finanse), Sciendo, vol. 14(1), pages 1-11, March.
    14. I-Lin Hsu & Chung-Yi Li & Da-Chen Chu & Li-Chien Chien, 2018. "An Epidemiological Analysis of Head Injuries in Taiwan," IJERPH, MDPI, vol. 15(11), pages 1-12, November.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0158762. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.