×

Prediction of neurological deterioration of patients with mild traumatic brain injury using machine learning. (English) Zbl 1445.62265

Nguyen, Hien (ed.), Statistics and data science. Proceedings of the research school on statistics and data science, RSSDS 2019, Melbourne, Australia, July 24–26, 2019. Singapore: Springer. Commun. Comput. Inf. Sci. 1150, 198-210 (2019).
Summary: Possible Neurological Deterioration (ND) of patients with Traumatic Brain Injury (TBI) is difficult to identify especially the mild and moderate injuries. When ND happens, death or lifelong disability is prevalent. Early prediction of possible ND would allow medical and healthcare institutions to provide the needed medical treatment. This paper presents the results that show Machine Learning (ML) can be used to create predicative models with high prediction rates even with a small set of patient records (219 patient records with 54 variables). From the patient records, 20 randomized data sets with preconditions on the testing and training data were created and fed to selected Artificial Neural Network (ANN) and Classification Algorithms. Preconditions on testing and training data can affect the prediction models created by the different algorithms. The best prediction models created by the ANN algorithms (multilayer perceptron (MLP), recurrent neural network (RNN), and long short-term memory (LSTM)) and two classification algorithms (linear regression and logistic regression algorithms) are considered acceptable and could be applied as medical decision support to identify patients that may potentially have ND. Early prediction of a possible ND of a patient can now be easily carried out as soon as his or her records and medical test results are ready and match the 54 variables needed for prediction.
For the entire collection see [Zbl 1433.68029].

MSC:

62P10 Applications of statistics to biology and medical sciences; meta analysis
62M20 Inference from stochastic processes and prediction
68T05 Learning and adaptive systems in artificial intelligence

Software:

Scikit
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Ji, S.Y., Smith, R., Huynh, T., Najarian, K.: A comparative analysis of multi-level computer-assisted decision making systems for traumatic injuries. BMC Med. Inform. Decis. Mak. 9, 2 (2009) · doi:10.1186/1472-6947-9-2
[2] Lawrence, T.P., Pretorius, P.M., Ezra, M., Cadoux-Hudson, T., Voets, N.L.: Early detection of cerebral microbleeds following traumatic brain injury using MRI in the hyper-acute phase. Neurosci. Lett. 655, 143-150 (2017). https://doi.org/10.1016/j.neulet.2017.06.046 · doi:10.1016/j.neulet.2017.06.046
[3] Burke, J.F., Stulc, J.L., Skolarus, L.E., Sears, E.D., Zahuranec, D.B., Morgenstern, L.B.: Traumatic brain injury may be an independent risk factor for stroke. Neurology 81(1), 33-39 (2013). https://doi.org/10.1212/WNL.0b013e318297eecf · doi:10.1212/WNL.0b013e318297eecf
[4] Hirtz, D., Thurman, D.J., Gwinn-Hardy, K., Mohamed, M., Chadhuri, A.R., Zalutsky, R.: How common are the “common” neurologic disorders? Neurology 68, 326-337 (2007) · doi:10.1212/01.wnl.0000252807.38124.a3
[5] Vos, P.E., et al.: Mild traumatic brain injury. Eur. J. Neurol. 19, 191-198 (2012) · doi:10.1111/j.1468-1331.2011.03581.x
[6] Pang, B.C.: Hybrid outcome prediction model for severe traumatic brain injury. J. Neurotrauma 24, 136-146 (2017) · doi:10.1089/neu.2006.0113
[7] Alanazi, H.O., Abdullah, A.H., Qureshi, K.N.: A critical review for developing accurate and dynamic predictive models using machine learning methods in medicine and health care. J. Med. Syst. 41, 69 (2017). https://doi.org/10.1007/s10916-017-0715-6 · doi:10.1007/s10916-017-0715-6
[8] Celtikci, E.: A systematic review on machine learning in neurosurgery: the future of decision-making in patient care. Turk. Neurosurg. 28, 167-173 (2018)
[9] Murray, G.D., et al.: Multivariable prognostic analysis in traumatic brain injury: results from the IMPACT study. J. Neurotrauma 24, 329-337 (2007) · doi:10.1089/neu.2006.0035
[10] MRC CRASH Trial Collaborators, Perel P., Arango, M., et al.: Predicting outcome after traumatic brain injury: practical prognostic models based on large cohort of international patients. BMJ 336, 425-429 (2008)
[11] Hsu, M.H., Li, Y.C., Chiu, W.T., Yen, J.C.: Outcome prediction after moderate and severe head injury using an artificial neural network. Stud. Health Technol. Inf. 116, 241-245 (2005)
[12] Eftekhar, B., Mohammad, K., Ardebili, H.E., Ghodsi, M., Ketabchi, E.: Comparison of artificial neural network and logistic regression models for prediction of mortality in head trauma based on initial clinical data. BMC Med. Inf. Decis. Making 5, 3 (2005) · doi:10.1186/1472-6947-5-3
[13] Zador, Z., Sperrin, M., King, A.T.: Predictors of outcome of traumatic brain injury: new insight using receiver operating curve indices and Bayesian network analysis. PLoS ONE 11, e0158762 (2016) · doi:10.1371/journal.pone.0158762
[14] Donald, R., Howells, T., Piper, I., et al.: Forewarning of hypotensive events using a Bayesian artificial neural network in neurocritical care. J. Clin. Monit. Comput. (2018). https://doi.org/10.1007/s10877-018-0139-y · doi:10.1007/s10877-018-0139-y
[15] Keras, C.F.: (2015). https://keras.io
[16] Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825-2830 (2011) · Zbl 1280.68189
[17] Ribeiro, M.T., Singh, S., Guestrin, C.: “Why Should I Trust You?” Explaining the Predictions of Any Classifier (2016). CoRR. http://arxiv.org/abs/1602.04938
[18] Steyerberg, E.W., et al.: Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology 21, 128-138 (2010) · doi:10.1097/EDE.0b013e3181c30fb2
[19] Kim, S.C., et al.: Preventable deaths in patients with traumatic brain injury. Clin. Exp. Emerg. Med. 2(1), 51-58 (2015) · doi:10.15441/ceem.14.023
[20] Ovesen, C. · doi:10.1136/bmjopen-2015-008563
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.