Background Traumatic brain injury (TBI), which occurs commonly worldwide, is among the more costly of health and socioeconomic problems. Accurate prediction of favorable outcomes in severe TBI patients could assist with optimizing treatment procedures, predicting clinical outcomes, and result in substantial economic savings. Methods: In this study, we examined the capability of a machine learning-based model in predicting “favorable” or “unfavorable” outcomes after 6 months in severe TBI patients using only parameters measured on admission. Three models were developed using logistic regression, random forest, and support vector machines trained on parameters recorded from 2,381 severe TBI patients admitted to the neuro-intensive care unit of Rajaee (Emtiaz) Hospital (Shiraz, Iran) between 2015 and 2017. Model performance was evaluated using three indices: sensitivity, specificity, and accuracy. A ten-fold cross-validation method was used to estimate these indices. Results: Overall, the developed models showed excellent performance with the area under the curve around 0.81, sensitivity and specificity of around 0.78. The top-three factors important in predicting 6-month post-trauma survival status in TBI patients are “Glasgow coma scale motor response,” “pupillary reactivity,” and “age.” Conclusions: Machine learning techniques might be used to predict the 6-month outcome in TBI patients using only the parameters measured on admission when the machine learning is trained using a large data set.
Citations
Citations to this article as recorded by
Enhancing hospital course and outcome prediction in patients with traumatic brain injury: A machine learning study Guangming Zhu, Burak B Ozkara, Hui Chen, Bo Zhou, Bin Jiang, Victoria Y Ding, Max Wintermark The Neuroradiology Journal.2024; 37(1): 74. CrossRef
Machine Learning in Neuroimaging of Traumatic Brain Injury: Current Landscape, Research Gaps, and Future Directions Kevin Pierre, Jordan Turetsky, Abheek Raviprasad, Seyedeh Mehrsa Sadat Razavi, Michael Mathelier, Anjali Patel, Brandon Lucke-Wold Trauma Care.2024; 4(1): 31. CrossRef
Science fiction or clinical reality: a review of the applications of artificial intelligence along the continuum of trauma care Olivia F. Hunter, Frances Perry, Mina Salehi, Hubert Bandurski, Alan Hubbard, Chad G. Ball, S. Morad Hameed World Journal of Emergency Surgery.2023;[Epub] CrossRef
Gastrointestinal failure, big data and intensive care Pierre Singer, Eyal Robinson, Orit Raphaeli Current Opinion in Clinical Nutrition & Metabolic Care.2023; 26(5): 476. CrossRef
Prediction performance of the machine learning model in predicting mortality risk in patients with traumatic brain injuries: a systematic review and meta-analysis Jue Wang, Ming Jing Yin, Han Chun Wen BMC Medical Informatics and Decision Making.2023;[Epub] CrossRef
Predicting return to work after traumatic brain injury using machine learning and administrative data Helena Van Deynse, Wilfried Cools, Viktor-Jan De Deken, Bart Depreitere, Ives Hubloue, Eva Kimpe, Maarten Moens, Karen Pien, Ellen Tisseghem, Griet Van Belleghem, Koen Putman International Journal of Medical Informatics.2023; 178: 105201. CrossRef
Fluid-Based Protein Biomarkers in Traumatic Brain Injury: The View from the Bedside Denes V. Agoston, Adel Helmy International Journal of Molecular Sciences.2023; 24(22): 16267. CrossRef
Predicting Outcome in Patients with Brain Injury: Differences between Machine Learning versus Conventional Statistics Antonio Cerasa, Gennaro Tartarisco, Roberta Bruschetta, Irene Ciancarelli, Giovanni Morone, Rocco Salvatore Calabrò, Giovanni Pioggia, Paolo Tonin, Marco Iosa Biomedicines.2022; 10(9): 2267. CrossRef