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

Abstract

Study Design

Cross-sectional database study.

Objective

To train and validate machine learning models to identify risk factors for complications following surgery for adult spinal deformity (ASD).

Summary of Background Data

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.

Methods

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.

Results

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).

Conclusions

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 of Evidence

Level III.

Introduction

The advent of digital technology, machine learning and deep learning in particular, is increasingly making it possible to utilize big data to more precisely risk stratify and prognosticate how an individual patient will behave given a disease or intervention. Machine learning has already been used in other realms such as retail and search engines. However, healthcare has lagged in the uptake of newer techniques to leverage the rich information contained in electronic health records (EHRs).

The practice of evidence-based medicine has sustained the progress seen in modern care and diagnosis. Traditional statistical approaches have gleaned much about what is known regarding risk factors used for prognostication. Machine learning (ML) combines these fundamental statistical insights with modern high-performance computing to learn patterns that can be used for recognition and prediction. Importantly, machine learning often identifies patterns that are not readily apparent to human intuition, thus identifying otherwise unknown connections [1]. Multivariate logistic regression and artificial neural networks are the two most commonly used machine learning models employed in medicine [2]. Artificial neural networks were first developed to model the neural architecture of the brain. Harnessing the structure of biology, artificial neural networks (ANNs) are particularly well suited for modeling complex, nonlinear data when little is known regarding the underlying distribution of the data or colinearity among the variables [3]. Importantly, ANNs can perform these functions without prior assumptions, leading to a highly adaptable system less susceptible to anchoring biases [3]. However, similar to any machine learning algorithm, neural networks are susceptible to intrinsic limitations and biases of the underlying data set. Additionally, limitations of model design such as neural network architecture, feature selection, and optimization functions can lead to model biases and overfitting that decrease generalizability and prognostication value of neural networks on external data [4]. Advancements in neural network science and proper implementation with recognition of these limitations are important for future integration of machine learning in surgical practice, and the utility of machine learning in adult deformity surgery has not yet been explored.

Adult spinal deformity (ASD) is a spinal disorder defined as a complex spectrum of spinal diseases that present in adulthood including adult scoliosis (progression of childhood scoliosis), degenerative scoliosis, sagittal and coronal imbalance, and iatrogenic deformity (with or without spinal stenosis) [5]. Adult degenerative scoliosis is the most common cause of ASD and is commonly seen in elderly adults, particularly those older than 60 years, as degeneration of intervertebral discs and facet joints exacerbate scoliotic curvature [6]. With the aging baby boomer generation and overall population structure of the United States, it is not surprising that the demand and prevalence for ASD surgery continues to increase [7]. In the burgeoning era of rising healthcare costs and greater scrutiny over surgical outcomes, there has been increasing emphasis on understanding the risk factors and possible predictors to optimize perioperative planning and management. Data-driven clinical decision support tools have the potential to lead to cost savings by leveraging the information contained in large medical databases. Uptake of machine learning approaches in the realm of spinal surgery have lagged. However, the patient population and associated increased rate of postoperative complications renders ASD a prime target for quality improvement through the utilization of machine learning.

ML algorithms have the capability of “learning” using newly generated information to improve their predictive capability. Briefly explained, these algorithms work by utilizing a subset of the overall study data (70% in this case) to “train” and create an accurate predictive model. This established model is then validated using the remainder of the data to determine the accuracy of the post-training model. This study seeks to develop and validate ML algorithms to precisely predict complications following ASD using a national database, in order to compare ML algorithms with logistic regression (LR) or American Society of Anesthesiologists (ASA) classification.