Predicting Surgical Complications in Adult Patients Undergoing Anterior Cervical Discectomy and Fusion Using Machine Learning

Objective Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

[1]  Zhen Hu,et al.  Automated Detection of Postoperative Surgical Site Infections Using Supervised Methods with Electronic Health Record Data , 2017, MedInfo.

[2]  Jun S. Kim,et al.  Comparing National Inpatient Sample and National Surgical Quality Improvement Program: An Independent Risk Factor Analysis for Risk Stratification in Anterior Cervical Discectomy and Fusion , 2017, Spine.

[3]  Hongfang Liu,et al.  Detection of clinically important colorectal surgical site infection using Bayesian network. , 2017, The Journal of surgical research.

[4]  Mario Michael Krell,et al.  Classifier transfer with data selection strategies for online support vector machine classification with class imbalance , 2017, Journal of neural engineering.

[5]  Zhong Liu,et al.  A Novel Ensemble Method for Imbalanced Data Learning: Bagging of Extrapolation-SMOTE SVM , 2017, Comput. Intell. Neurosci..

[6]  M. McGirt,et al.  Anterior cervical discectomy and fusion in the outpatient ambulatory surgery setting compared with the inpatient hospital setting: analysis of 1000 consecutive cases. , 2016, Journal of neurosurgery. Spine.

[7]  Timothy Y. Wang,et al.  Risk Assessment and Characterization of 30-Day Perioperative Myocardial Infarction Following Spine Surgery: A Retrospective Analysis of 1346 Consecutive Adult Patients , 2016, Spine.

[8]  I. Rubinfeld,et al.  Quantifying surgical complexity with machine learning: looking beyond patient factors to improve surgical models. , 2014, Surgery.

[9]  Samuel K. Cho,et al.  National Trends in Outpatient Surgical Treatment of Degenerative Cervical Spine Disease , 2014, Global spine journal.

[10]  I. Kohane,et al.  Finding the missing link for big biomedical data. , 2014, JAMA.

[11]  C. Ko,et al.  Development and evaluation of the universal ACS NSQIP surgical risk calculator: a decision aid and informed consent tool for patients and surgeons. , 2013, Journal of the American College of Surgeons.

[12]  L. Specht,et al.  Diabetes mellitus, hemoglobin A1C, and the incidence of total joint arthroplasty infection. , 2012, The Journal of arthroplasty.

[13]  Licia K. Gaber-Baylis,et al.  National Trends in Anterior Cervical Fusion Procedures , 2010, Spine.

[14]  Wayne Cheng,et al.  Diabetes Associated with Increased Surgical Site Infections in Spinal Arthrodesis , 2009, Clinical orthopaedics and related research.

[15]  Haibo He,et al.  ADASYN: Adaptive synthetic sampling approach for imbalanced learning , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[16]  Joseph A. Cruz,et al.  Applications of Machine Learning in Cancer Prediction and Prognosis , 2006, Cancer informatics.

[17]  W. Yue,et al.  Long-Term Results After Anterior Cervical Discectomy and Fusion With Allograft and Plating: A 5- to 11-Year Radiologic and Clinical Follow-up Study , 2005, Spine.

[18]  A. Møller,et al.  Effect of smoking on early complications after elective orthopaedic surgery. , 2003, The Journal of bone and joint surgery. British volume.

[19]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[20]  Krzysztof J. Cios,et al.  Uniqueness of medical data mining , 2002, Artif. Intell. Medicine.

[21]  T. Albert,et al.  Health outcome assessment before and after anterior cervical discectomy and fusion for radiculopathy: a prospective analysis. , 2000, Spine.

[22]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[23]  J.J. Hopfield,et al.  Artificial neural networks , 1988, IEEE Circuits and Devices Magazine.

[24]  M. Dew,et al.  A Prospective Analysis , 2015 .

[25]  Tung-Kuan Liu,et al.  Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm , 2006, IEEE Trans. Neural Networks.