TY - JOUR
T1 - Using machine learning and big data for the prediction of venous thromboembolic events after spine surgery
T2 - A single-center retrospective analysis of multiple models on a cohort of 6869 patients
AU - Hopkins, Benjamin S.
AU - Cloney, Michael B.
AU - Dhillon, Ekamjeet S.
AU - Texakalidis, Pavlos
AU - Dallas, Jonathan
AU - Nguyen, Vincent N.
AU - Ordon, Matthew
AU - El Tecle, Najib
AU - Chen, Thomas C.
AU - Hsieh, Patrick C.
AU - Liu, John C.
AU - Koski, Tyler R.
AU - Dahdaleh, Nader S.
N1 - Publisher Copyright:
© 2023 Wolters Kluwer Medknow Publications. All rights reserved.
PY - 2023/7
Y1 - 2023/7
N2 - Objective: Venous thromboembolic event (VTE) after spine surgery is a rare but potentially devastating complication. With the advent of machine learning, an opportunity exists for more accurate prediction of such events to aid in prevention and treatment. Methods: Seven models were screened using 108 database variables and 62 preoperative variables. These models included deep neural network (DNN), DNN with synthetic minority oversampling technique (SMOTE), logistic regression, ridge regression, lasso regression, simple linear regression, and gradient boosting classifier. Relevant metrics were compared between each model. The top four models were selected based on area under the receiver operator curve; these models included DNN with SMOTE, linear regression, lasso regression, and ridge regression. Separate random sampling of each model was performed 1000 additional independent times using a randomly generated training/testing distribution. Variable weights and magnitudes were analyzed after sampling. Results: Using all patient-related variables, DNN using SMOTE was the top-performing model in predicting postoperative VTE after spinal surgery (area under the curve [AUC] =0.904), followed by lasso regression (AUC = 0.894), ridge regression (AUC = 0.873), and linear regression (AUC = 0.864). When analyzing a subset of only preoperative variables, the top-performing models were lasso regression (AUC = 0.865) and DNN with SMOTE (AUC = 0.864), both of which outperform any currently published models. Main model contributions relied heavily on variables associated with history of thromboembolic events, length of surgical/anesthetic time, and use of postoperative chemoprophylaxis. Conclusions: The current study provides promise toward machine learning methods geared toward predicting postoperative complications after spine surgery. Further study is needed in order to best quantify and model real-world risk for such events.
AB - Objective: Venous thromboembolic event (VTE) after spine surgery is a rare but potentially devastating complication. With the advent of machine learning, an opportunity exists for more accurate prediction of such events to aid in prevention and treatment. Methods: Seven models were screened using 108 database variables and 62 preoperative variables. These models included deep neural network (DNN), DNN with synthetic minority oversampling technique (SMOTE), logistic regression, ridge regression, lasso regression, simple linear regression, and gradient boosting classifier. Relevant metrics were compared between each model. The top four models were selected based on area under the receiver operator curve; these models included DNN with SMOTE, linear regression, lasso regression, and ridge regression. Separate random sampling of each model was performed 1000 additional independent times using a randomly generated training/testing distribution. Variable weights and magnitudes were analyzed after sampling. Results: Using all patient-related variables, DNN using SMOTE was the top-performing model in predicting postoperative VTE after spinal surgery (area under the curve [AUC] =0.904), followed by lasso regression (AUC = 0.894), ridge regression (AUC = 0.873), and linear regression (AUC = 0.864). When analyzing a subset of only preoperative variables, the top-performing models were lasso regression (AUC = 0.865) and DNN with SMOTE (AUC = 0.864), both of which outperform any currently published models. Main model contributions relied heavily on variables associated with history of thromboembolic events, length of surgical/anesthetic time, and use of postoperative chemoprophylaxis. Conclusions: The current study provides promise toward machine learning methods geared toward predicting postoperative complications after spine surgery. Further study is needed in order to best quantify and model real-world risk for such events.
KW - Big data
KW - machine learning
KW - venous thromboembolic events
KW - venous thromboembolism
UR - http://www.scopus.com/inward/record.url?scp=85176427007&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85176427007&partnerID=8YFLogxK
U2 - 10.4103/jcvjs.jcvjs_69_23
DO - 10.4103/jcvjs.jcvjs_69_23
M3 - Article
C2 - 37860027
AN - SCOPUS:85176427007
SN - 0974-8237
VL - 14
SP - 221
EP - 229
JO - Journal of Craniovertebral Junction and Spine
JF - Journal of Craniovertebral Junction and Spine
IS - 3
ER -