+ Site Statistics
+ Search Articles
+ PDF Full Text Service
How our service works
Request PDF Full Text
+ Follow Us
Follow on Facebook
Follow on Twitter
Follow on LinkedIn
+ Subscribe to Site Feeds
Most Shared
PDF Full Text
+ Translate
+ Recently Requested

Predicting Surgical Complications in Patients Undergoing Elective Adult Spinal Deformity Procedures Using Machine Learning



Predicting Surgical Complications in Patients Undergoing Elective Adult Spinal Deformity Procedures Using Machine Learning



Spine Deformity 6(6): 762-770



Cross-sectional database study. To train and validate machine learning models to identify risk factors for complications following surgery for adult spinal deformity (ASD). Machine learning models such as logistic regression (LR) and artificial neural networks (ANNs) are valuable tools for analyzing and interpreting large and complex data sets. ANNs have yet to be used for risk factor analysis in orthopedic surgery. The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried for patients who underwent surgery for ASD. This query returned 4,073 patients, which data were used to train and evaluate our models. The predictive variables used included sex, age, ethnicity, diabetes, smoking, steroid use, coagulopathy, functional status, American Society of Anesthesiologists (ASA) class >3, body mass index (BMI), pulmonary comorbidities, and cardiac comorbidities. The models were used to predict cardiac complications, wound complications, venous thromboembolism (VTE), and mortality. Using ASA class as a benchmark for prediction, area under receiver operating characteristic curves (AUC) was used to determine the accuracy of our machine learning models. The mean age of patients was 59.5 years. Forty-one percent of patients were male whereas 59.0% of patients were female. ANN and LR outperformed ASA scoring in predicting every complication (p<.05). The ANN outperformed LR in predicting cardiac complication, wound complication, and mortality (p<.05). Machine learning algorithms outperform ASA scoring for predicting individual risk prognosis. These algorithms also outperform LR in predicting individual risk for all complications except VTE. With the growing size of medical data, the training of machine learning on these large data sets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios. Level III.

Please choose payment method:






(PDF emailed within 0-6 h: $19.90)

Accession: 065884867

Download citation: RISBibTeXText

PMID: 30348356

DOI: 10.1016/j.jspd.2018.03.003


Related references

Predicting Surgical Complications in Adult Patients Undergoing Anterior Cervical Discectomy and Fusion Using Machine Learning. Neurospine 15(4): 329-337, 2018

Increased 30-Day Complication Rates Associated with Laminectomy in 874 Adult Patients with Spinal Deformity Undergoing Elective Spinal Fusion: A Single Institutional Study. World Neurosurgery 102: 370-375, 2017

Predicting critical care unit-level complications after long-segment fusion procedures for adult spinal deformity. Journal of Spine Surgery 4(1): 55-61, 2018

The prevalence of undiagnosed pre-surgical cognitive impairment and its post-surgical clinical impact in elderly patients undergoing surgery for adult spinal deformity. Journal of Spine Surgery 3(3): 358-363, 2017

165 What Is the Effect of Open vs Percutaneous Screws on Complications Among Patients Undergoing Lateral Interbody Fusion for Adult Spinal Deformity?. Neurosurgery 63 Suppl 1(): 166-166, 2016

Adult spinal deformity surgical decision-making score : Part 1: development and validation of a scoring system to guide the selection of treatment modalities for patients below 40 years with adult spinal deformity. European Spine Journal 28(7): 1652-1660, 2019

What is the Effect of Open versus Percutaneous Screws on Complications among Patients Undergoing Lateral Interbody Fusion for Adult Spinal Deformity?. Spine Journal 16(10): S262-S263, 2016

Postoperative complications in adult spinal deformity patients with a mental illness undergoing reconstructive thoracic or thoracolumbar spine surgery. Spine Journal 19(4): 662-669, 2019

Psychosocial Factors and Surgical Outcomes in Adult Spinal Deformity: Do Dementia Patients Have More Complications?. Spine 43(15): 1038-1043, 2018

Comparison of Complications and Clinical and Radiographic Outcomes Between Nonobese and Obese Patients with Adult Spinal Deformity Undergoing Minimally Invasive Surgery. World Neurosurgery 87: 55-60, 2016

Comparison of I-gel with proseal LMA in adult patients undergoing elective surgical procedures under general anesthesia without paralysis: A prospective randomized study. Journal of Anaesthesiology Clinical Pharmacology 30(2): 183-187, 2014

Predicting discharge placement after elective surgery for lumbar spinal stenosis using machine learning methods. European Spine Journal 28(6): 1433-1440, 2019

Incidence, Impact, and Risk Factors for 30-Day Wound Complications Following Elective Adult Spinal Deformity Surgery. Global Spine Journal 7(5): 417-424, 2017

Diabetes Mellitus as a Risk Factor for Acute Postoperative Complications Following Elective Adult Spinal Deformity Surgery. Global Spine Journal 8(6): 615-621, 2018

Instrumentation-related complications of multilevel fusions for adult spinal deformity patients over age 65: surgical considerations and treatment options in patients with poor bone quality. Spine 31(19 Suppl): S144, 2006