IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0213836.html
   My bibliography  Save this article

Dynamic multi-outcome prediction after injury: Applying adaptive machine learning for precision medicine in trauma

Author

Listed:
  • S Ariane Christie
  • Amanda S Conroy
  • Rachael A Callcut
  • Alan E Hubbard
  • Mitchell J Cohen

Abstract

Objective: Machine learning techniques have demonstrated superior discrimination compared to conventional statistical approaches in predicting trauma death. The objective of this study is to evaluate whether machine learning algorithms can be used to assess risk and dynamically identify patient-specific modifiable factors critical to patient trajectory for multiple key outcomes after severe injury. Methods: SuperLearner, an ensemble machine-learning algorithm, was applied to prospective observational cohort data from 1494 critically-injured patients. Over 1000 agnostic predictors were used to generate prediction models from multiple candidate learners for outcomes of interest at serial time points post-injury. Model accuracy was estimated using cross-validation and area under the curve was compared to select among predictors. Clinical variables responsible for driving outcomes were estimated at each time point. Results: SuperLearner fits demonstrated excellent cross-validated prediction of death (overall AUC 0.94–0.97), multi-organ failure (overall AUC 0.84–0.90), and transfusion (overall AUC 0.87–0.9) across multiple post-injury time points, and good prediction of Acute Respiratory Distress Syndrome (overall AUC 0.84–0.89) and venous thromboembolism (overall AUC 0.73–0.83). Outcomes with inferior data quality included coagulopathic trajectory (AUC 0.48–0.88). Key clinical predictors evolved over the post-injury timecourse and included both anticipated and unexpected variables. Non-random missingness of data was identified as a predictor of multiple outcomes over time. Conclusions: Machine learning algorithms can be used to generate dynamic prediction after injury while avoiding the risk of over- and under-fitting inherent in ad hoc statistical approaches. SuperLearner prediction after injury demonstrates promise as an adaptable means of helping clinicians integrate voluminous, evolving data on severely-injured patients into real-time, dynamic decision-making support.

Suggested Citation

  • S Ariane Christie & Amanda S Conroy & Rachael A Callcut & Alan E Hubbard & Mitchell J Cohen, 2019. "Dynamic multi-outcome prediction after injury: Applying adaptive machine learning for precision medicine in trauma," PLOS ONE, Public Library of Science, vol. 14(4), pages 1-13, April.
    • Handle: RePEc:plo:pone00:0213836
    DOI: 10.1371/journal.pone.0213836
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0213836
    Download Restriction: no
    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0213836&type=printable
    Download Restriction: no
    File URL: https://libkey.io/10.1371/journal.pone.0213836?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. Friedman, Jerome H. & Hastie, Trevor & Tibshirani, Rob, 2010. "Regularization Paths for Generalized Linear Models via Coordinate Descent," Journal of Statistical Software, Foundation for Open Access Statistics, vol. 33(i01).
    2. van der Laan Mark J. & Rubin Daniel, 2006. "Targeted Maximum Likelihood Learning," The International Journal of Biostatistics, De Gruyter, vol. 2(1), pages 1-40, December.
    3. Iván Díaz & Alan Hubbard & Anna Decker & Mitchell Cohen, 2015. "Variable Importance and Prediction Methods for Longitudinal Problems with Missing Variables," PLOS ONE, Public Library of Science, vol. 10(3), pages 1-17, March.
    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. Susan Athey & Guido W. Imbens & Stefan Wager, 2018. "Approximate residual balancing: debiased inference of average treatment effects in high dimensions," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 80(4), pages 597-623, September.
    2. Iván Díaz & Nima S. Hejazi, 2020. "Causal mediation analysis for stochastic interventions," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 82(3), pages 661-683, July.
    3. Guanbo Wang & Mireille E. Schnitzer & Dick Menzies & Piret Viiklepp & Timothy H. Holtz & Andrea Benedetti, 2020. "Estimating treatment importance in multidrug‐resistant tuberculosis using Targeted Learning: An observational individual patient data network meta‐analysis," Biometrics, The International Biometric Society, vol. 76(3), pages 1007-1016, September.
    4. Victor Chernozhukov & Whitney K. Newey & Rahul Singh, 2022. "Automatic Debiased Machine Learning of Causal and Structural Effects," Econometrica, Econometric Society, vol. 90(3), pages 967-1027, May.
    5. Lundberg, Ian & Brand, Jennie E. & Jeon, Nanum, 2022. "Researcher reasoning meets computational capacity: Machine learning for social science," SocArXiv s5zc8, Center for Open Science.
    6. Anders Munch & Marie Skov Breum & Torben Martinussen & Thomas A. Gerds, 2023. "Targeted estimation of state occupation probabilities for the non‐Markov illness‐death model," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 50(3), pages 1532-1551, September.
    7. Tutz, Gerhard & Pößnecker, Wolfgang & Uhlmann, Lorenz, 2015. "Variable selection in general multinomial logit models," Computational Statistics & Data Analysis, Elsevier, vol. 82(C), pages 207-222.
    8. Viet Hoang Dinh & Didier Nibbering & Benjamin Wong, 2023. "Random Subspace Local Projections," CAMA Working Papers 2023-34, Centre for Applied Macroeconomic Analysis, Crawford School of Public Policy, The Australian National University.
    9. Ernesto Carrella & Richard M. Bailey & Jens Koed Madsen, 2018. "Indirect inference through prediction," Papers 1807.01579, arXiv.org.
    10. Rui Wang & Naihua Xiu & Kim-Chuan Toh, 2021. "Subspace quadratic regularization method for group sparse multinomial logistic regression," Computational Optimization and Applications, Springer, vol. 79(3), pages 531-559, July.
    11. Mkhadri, Abdallah & Ouhourane, Mohamed, 2013. "An extended variable inclusion and shrinkage algorithm for correlated variables," Computational Statistics & Data Analysis, Elsevier, vol. 57(1), pages 631-644.
    12. Masakazu Higuchi & Mitsuteru Nakamura & Shuji Shinohara & Yasuhiro Omiya & Takeshi Takano & Daisuke Mizuguchi & Noriaki Sonota & Hiroyuki Toda & Taku Saito & Mirai So & Eiji Takayama & Hiroo Terashi &, 2022. "Detection of Major Depressive Disorder Based on a Combination of Voice Features: An Exploratory Approach," IJERPH, MDPI, vol. 19(18), pages 1-13, September.
    13. Vincent, Martin & Hansen, Niels Richard, 2014. "Sparse group lasso and high dimensional multinomial classification," Computational Statistics & Data Analysis, Elsevier, vol. 71(C), pages 771-786.
    14. Chen, Le-Yu & Lee, Sokbae, 2018. "Best subset binary prediction," Journal of Econometrics, Elsevier, vol. 206(1), pages 39-56.
    15. Perrot-Dockès Marie & Lévy-Leduc Céline & Chiquet Julien & Sansonnet Laure & Brégère Margaux & Étienne Marie-Pierre & Robin Stéphane & Genta-Jouve Grégory, 2018. "A variable selection approach in the multivariate linear model: an application to LC-MS metabolomics data," Statistical Applications in Genetics and Molecular Biology, De Gruyter, vol. 17(5), pages 1-14, October.
    16. Fan, Jianqing & Jiang, Bai & Sun, Qiang, 2022. "Bayesian factor-adjusted sparse regression," Journal of Econometrics, Elsevier, vol. 230(1), pages 3-19.
    17. Chuliá, Helena & Garrón, Ignacio & Uribe, Jorge M., 2024. "Daily growth at risk: Financial or real drivers? The answer is not always the same," International Journal of Forecasting, Elsevier, vol. 40(2), pages 762-776.
    18. Jun Li & Serguei Netessine & Sergei Koulayev, 2018. "Price to Compete … with Many: How to Identify Price Competition in High-Dimensional Space," Management Science, INFORMS, vol. 64(9), pages 4118-4136, September.
    19. Sung Jae Jun & Sokbae Lee, 2024. "Causal Inference Under Outcome-Based Sampling with Monotonicity Assumptions," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 42(3), pages 998-1009, July.
    20. Rina Friedberg & Julie Tibshirani & Susan Athey & Stefan Wager, 2018. "Local Linear Forests," Papers 1807.11408, arXiv.org, revised Sep 2020.

    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:pone00:0213836. 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.