Predicting nonroutine discharge after elective spine surgery: external validation of machine learning algorithms

The Evolution of Risk Assessment in Spine Surgery: A Narrative Review

BACKGROUND

Risk assessment is critically important in elective and high-risk interventions, particularly spine surgery. This narrative review describes the evolution of risk assessment from the earliest instruments focused on general surgical risk stratification, to more accurate and spine-specific risk calculators that quantified risk, to the current era of big data.

METHODS

The PubMed and SCOPUS databases were queried on October 11, 2023 using search terms to identify risk assessment tools (RATs) in spine surgery. A total of 108 manuscripts were included after screening with full-text review using the following inclusion criteria: 1) study population of adult spine surgical patients, 2) studies describing validation and subsequent performance of preoperative RATs, and 3) studies published in English.

RESULTS

Early RATs provided stratified patients into broad categories and allowed for improved communication between physicians. Subsequent risk calculators attempted to quantify risk by estimating general outcomes such as mortality, but then evolved to estimate spine-specific surgical complications. The integration of novel concepts such as invasiveness, frailty, genetic biomarkers, and sarcopenia led to the development of more sophisticated predictive models that estimate the risk of spine-specific complications and long-term outcomes.

CONCLUSIONS

RATs have undergone a transformative shift from generalized risk stratification to quantitative predictive models. The next generation of tools will likely involve integration of radiographic and genetic biomarkers, machine learning, and artificial intelligence to improve the accuracy of these models and better inform patients, surgeons, and payers.

Postoperative Discharge to Acute Rehabilitation or Skilled Nursing Facility Compared With Home Does Not Reduce Hospital Readmissions, Return to Surgery, or Improve Outcomes Following Adult Spine Deformity Surgery

STUDY DESIGN

Retrospective review of a prospective multicenter adult spinal deformity (ASD) study.

OBJECTIVE

The aim of this study was to evaluate 30-day readmissions, 90-day return to surgery, postoperative complications, and patient-reported outcomes (PROs) for matched ASD patients receiving nonhome discharge (NON), including acute rehabilitation (REHAB), and skilled nursing facility (SNF), or home (HOME) discharge following ASD surgery.

SUMMARY OF BACKGROUND DATA

Postoperative disposition following ASD surgery frequently involves nonhome discharge. Little data exists for longer term outcomes for ASD patients receiving nonhome discharge versus patients discharged to home.

MATERIALS AND METHODS

Surgically treated ASD patients prospectively enrolled into a multicenter study were assessed for NON or HOME disposition following hospital discharge. NON was further divided into REHAB or SNF. Propensity score matching was used to match for patient age, frailty, spine deformity, levels fused, and osteotomies performed at surgery. Thirty-day hospital readmissions, 90-day return to surgery, postoperative complications, and 1-year and minimum 2-year postoperative PROs were evaluated.

RESULTS

A total of 241 of 374 patients were eligible for the study. NON patients were identified and matched to HOME patients. Following matching, 158 patients remained for evaluation; NON and HOME had similar preoperative age, frailty, spine deformity magnitude, surgery performed, and duration of hospital stay ( P >0.05). Thirty-day readmissions, 90-day return to surgery, and postoperative complications were similar for NON versus HOME and similar for REHAB (N=64) versus SNF (N=42) versus HOME ( P >0.05). At 1-year and minimum 2-year follow-up, HOME demonstrated similar to better PRO scores including Oswestry Disability Index, Short-Form 36v2 questionnaire Mental Component Score and Physical Component Score, and Scoliosis Research Society scores versus NON, REHAB, and SNF ( P <0.05).

CONCLUSIONS

Acute needs must be considered following ASD surgery, however, matched analysis comparing 30-day hospital readmissions, 90-day return to surgery, postoperative complications, and PROs demonstrated minimal benefit for NON, REHAB, or SNF versus HOME at 1- and 2-year follow-up, questioning the risk and cost/benefits of routine use of nonhome discharge.

LEVEL OF EVIDENCE

Level III-prognostic.

Development of a Machine Learning Algorithm to Correlate Lumbar Disc Height on X-rays with Disc Bulging or Herniation

Lumbar disc bulging or herniation (LDBH) is one of the major causes of spinal stenosis and related nerve compression, and its severity is the major determinant for spine surgery. MRI of the spine is the most important diagnostic tool for evaluating the need for surgical intervention in patients with LDBH. However, MRI utilization is limited by its low accessibility. Spinal X-rays can rapidly provide information on the bony structure of the patient. Our study aimed to identify the factors associated with LDBH, including disc height, and establish a clinical diagnostic tool to support its diagnosis based on lumbar X-ray findings. In this study, a total of 458 patients were used for analysis and 13 clinical and imaging variables were collected. Five machine-learning (ML) methods, including LASSO regression, MARS, decision tree, random forest, and extreme gradient boosting, were applied and integrated to identify important variables for predicting LDBH from lumbar spine X-rays. The results showed L4-5 posterior disc height, age, and L1-2 anterior disc height to be the top predictors, and a decision tree algorithm was constructed to support clinical decision-making. Our study highlights the potential of ML-based decision tools for surgeons and emphasizes the importance of L1-2 disc height in relation to LDBH. Future research will expand on these findings to develop a more comprehensive decision-supporting model.

Machine Learning in Spine Surgery: A Narrative Review

Artificial intelligence and machine learning (ML) can offer revolutionary advances in their application to the field of spine surgery. Within the past 5 years, novel applications of ML have assisted in surgical decision-making, intraoperative imaging and navigation, and optimization of clinical outcomes. ML has the capacity to address many different clinical needs and improve diagnostic and surgical techniques. This review will discuss current applications of ML in the context of spine surgery by breaking down its implementation preoperatively, intraoperatively, and postoperatively. Ethical considerations to ML and challenges in ML implementation must be addressed to maximally benefit patients, spine surgeons, and the healthcare system. Areas for future research in augmented reality and mixed reality, along with limitations in generalizability and bias, will also be highlighted.

Limitations in Evaluating Machine Learning Models for Imbalanced Binary Outcome Classification in Spine Surgery: A Systematic Review

Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models' effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and evaluate current research-based ML and DL models applied for spine surgery, specifically those predicting binary outcomes with a focus on their evaluation metrics. Overall, 60 papers were included, and the findings were reported according to the PRISMA guidelines. A total of 13 papers focused on lengths of stay (LOS), 12 on readmissions, 12 on non-home discharge, 6 on mortality, and 5 on reoperations. The target outcomes exhibited data imbalances ranging from 0.44% to 42.4%. A total of 59 papers reported the model's area under the receiver operating characteristic (AUROC), 28 mentioned accuracies, 33 provided sensitivity, 29 discussed specificity, 28 addressed positive predictive value (PPV), 24 included the negative predictive value (NPV), 25 indicated the Brier score with 10 providing a null model Brier, and 8 detailed the F1 score. Additionally, data visualization varied among the included papers. This review discusses the use of appropriate evaluation schemes in ML and identifies several common errors and potential bias sources in the literature. Embracing these recommendations as the field advances may facilitate the integration of reliable and effective ML models in clinical settings.

Machine Learning Applications in Spine Surgery

This literature review sought to identify and evaluate the current applications of artificial intelligence (AI)/machine learning (ML) in spine surgery that can effectively guide clinical decision-making and surgical planning. By using specific keywords to maximize search sensitivity, a thorough literature research was conducted in several online databases: Scopus, PubMed, and Google Scholar, and the findings were filtered according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 46 studies met the requirements and were included in this review. According to this study, AI/ML models were sufficiently accurate with a mean overall value of 74.9%, and performed best at preoperative patient selection, cost prediction, and length of stay. Performance was also good at predicting functional outcomes and postoperative mortality. Regression analysis was the most frequently utilized application whereas deep learning/artificial neural networks had the highest sensitivity score (81.5%). Despite the relatively brief history of engagement with AI/ML, as evidenced by the fact that 77.5% of studies were published after 2018, the outcomes have been promising. In light of the Big Data era, the increasing prevalence of National Registries, and the wide-ranging applications of AI, such as exemplified by ChatGPT (OpenAI, San Francisco, California), it is highly likely that the field of spine surgery will gradually adopt and integrate AI/ML into its clinical practices. Consequently, it is of great significance for spine surgeons to acquaint themselves with the fundamental principles of AI/ML, as these technologies hold the potential for substantial improvements in overall patient care.

Hospital Frailty Risk Score and Healthcare Resource Utilization After Surgery for Primary Spinal Intradural/Cord Tumors

OBJECTIVE

The Hospital Frailty Risk Score (HFRS) is a metric that measures frailty among patients in large national datasets using ICD-10 codes. While other metrics have been utilized to demonstrate the association between frailty and poor outcomes in spine oncology, none have examined the HFRS. The aim of this study was to investigate the impact of frailty using the HFRS on complications, length of stay, cost of admission, and discharge disposition in patients undergoing surgery for primary tumors of the spinal cord and meninges.

METHODS

A retrospective cohort study was performed using the Nationwide Inpatient Sample database from 2016 to 2018. Adult patients undergoing surgery for primary tumors of the spinal cord and meninges were identified using ICD-10-CM codes. Patients were categorized into 2 cohorts based on HFRS score: Non-Frail (HFRS<5) and Frail (HFRS≥5). Patient characteristics, treatment, perioperative complications, LOS, discharge disposition, and cost of admission were assessed.

RESULTS

Of the 5955 patients identified, 1260 (21.2%) were Frail. On average, the Frail cohort was nearly 8 years older (P < .001) and experienced more postoperative complications (P = .001). The Frail cohort experienced longer LOS (P < .001), a higher rate of non-routine discharge (P = .001), and a greater mean cost of admission (P < .001). Frailty was found to be an independent predictor of extended LOS (P < .001) and non-routine discharge (P < .001).

CONCLUSION

Our study is the first to use the HFRS to assess the impact of frailty on patients with primary spinal tumors. We found that frailty was associated with prolonged LOS, non-routine discharge, and increased hospital costs.

Artificial Intelligence in Neurosurgery: A State-of-the-Art Review from Past to Future

In recent years, there has been a significant surge in discussions surrounding artificial intelligence (AI), along with a corresponding increase in its practical applications in various facets of everyday life, including the medical industry. Notably, even in the highly specialized realm of neurosurgery, AI has been utilized for differential diagnosis, pre-operative evaluation, and improving surgical precision. Many of these applications have begun to mitigate risks of intraoperative and postoperative complications and post-operative care. This article aims to present an overview of the principal published papers on the significant themes of tumor, spine, epilepsy, and vascular issues, wherein AI has been applied to assess its potential applications within neurosurgery. The method involved identifying high-cited seminal papers using PubMed and Google Scholar, conducting a comprehensive review of various study types, and summarizing machine learning applications to enhance understanding among clinicians for future utilization. Recent studies demonstrate that machine learning (ML) holds significant potential in neuro-oncological care, spine surgery, epilepsy management, and other neurosurgical applications. ML techniques have proven effective in tumor identification, surgical outcomes prediction, seizure outcome prediction, aneurysm prediction, and more, highlighting its broad impact and potential in improving patient management and outcomes in neurosurgery. This review will encompass the current state of research, as well as predictions for the future of AI within neurosurgery.

Association of frailty with healthcare resource utilization after open thoracic/thoracolumbar posterior spinal fusion for adult spinal deformity

PURPOSE

The Hospital Frailty Risk Score (HFRS) is a frailty-identifying metric developed using ICD-10-CM codes. While other studies have examined frailty in adult spinal deformity (ASD), the HFRS has not been assessed in this population. The aim of this study was to utilize the HFRS to investigate the impact of frailty on outcomes in ASD patients undergoing posterior spinal fusion (PSF).

METHODS

A retrospective study was performed using the 2016-2019 National Inpatient Sample database. Adults with ASD undergoing elective PSF were identified using ICD-10-CM codes. Patients were categorized into HFRS-based frailty cohorts: Low (HFRS < 5) and Intermediate-High (HFRS ≥ 5). Patient demographics, comorbidities, intraoperative variables, and outcomes were assessed. Multivariate regression analyses were used to determine whether HFRS independently predicted extended length of stay (LOS), non-routine discharge, and increased cost.

RESULTS

Of the 7500 patients identified, 4000 (53.3%) were in the Low HFRS cohort and 3500 (46.7%) were in the Intermediate-High HFRS cohort. On average, age increased progressively with increasing HFRS scores (p < 0.001). The frail cohort experienced more postoperative adverse events (p < 0.001), greater LOS (p < 0.001), accrued greater admission costs (p < 0.001), and had a higher rate of non-routine discharge (p < 0.001). On multivariate analysis, Intermediate-High HFRS was independently associated with extended LOS (OR: 2.58, p < 0.001) and non-routine discharge (OR: 1.63, p < 0.001), though not increased admission cost (OR: 1.01, p = 0.929).

CONCLUSION

Our study identified HFRS to be significantly associated with prolonged hospitalizations and non-routine discharge. Other factors that were found to be associated with increased healthcare resource utilization include age, Hispanic race, West hospital region, large hospital size, and increasing number of AEs.

Implementing a discharge process for patients undergoing elective surgery: Rapid review

BACKGROUND

Hospital discharge is a 'vulnerable stage' in care. A delayed, inappropriate or poorly planned discharge increases hazards and costs, inhibiting recovery, and often leading to unplanned readmission. New discharge processes could boost practice, reduce the length of stay, and, consequently, reduce costs and improve patients' quality of life.

AIM

To identify technology based interventions that have been implemented to facilitate a safe and timely discharge procedure after elective surgery, and to describe implementation barriers and facilitators and patient satisfaction.

METHOD

This rapid review followed a restricted systematic review framework, searching Medline, EMBASE, CINAHL, PsychINFO, and ClinicalTrials.gov. for relevant studies published from 2015 to 2021 in English.

RESULTS

Eleven studies were included. Most interventions were machine-learning-based, and only one study reported patient involvement. Effective leadership, team work and communication were stated as implementation facilitators. The main barriers to implementation were: lack of support from leaders, poor clinical documentation, resistance to change, and financial and logistical concerns. None of the studies evaluated patient satisfaction.

CONCLUSIONS

Findings highlight factors that support the implementation of technology based interventions aimed at a safe and timely discharge process following elective surgery. Nurses play an important role in the provision of information, and in the development and implementation of discharge processes.

Development and internal validation of predictive models to assess risk of post-acute care facility discharge in adults undergoing multi-level instrumented fusions for lumbar degenerative pathology and spinal deformity

PURPOSE

To develop a model for factors predictive of Post-Acute Care Facility (PACF) discharge in adult patients undergoing elective multi-level (≥ 3 segments) lumbar/thoracolumbar spinal instrumented fusions.

METHODS

The State Inpatient Databases acquired from the Healthcare Cost and Utilization Project from 2005 to 2013 were queried for adult patients who underwent elective multi-level thoracolumbar fusions for spinal deformity. Outcome variables were classified as discharge to home or PACF. Predictive variables included demographic, pre-operative, and operative factors. Univariate and multivariate logistic regression analyses informed development of a logistic regression-based predictive model using seven selected variables. Performance metrics included area under the curve (AUC), sensitivity, and specificity.

RESULTS

Included for analysis were 8866 patients. The logistic model including significant variables from multivariate analysis yielded an AUC of 0.75. Stepwise logistic regression was used to simplify the model and assess number of variables needed to reach peak AUC, which included seven selected predictors (insurance, interspaces fused, gender, age, surgical region, CCI, and revision surgery) and had an AUC of 0.74. Model cut-off for predictive PACF discharge was 0.41, yielding a sensitivity of 75% and specificity of 59%.

CONCLUSIONS

The seven variables associated significantly with PACF discharge (age > 60, female gender, non-private insurance, primary operations, instrumented fusion involving 8+ interspaces, thoracolumbar region, and higher CCI scores) may aid in identification of adults at risk for discharge to a PACF following elective multi-level lumbar/thoracolumbar spinal fusions for spinal deformity. This may in turn inform discharge planning and expectation management.

Comparison of Deep Learning and Classical Machine Learning Algorithms to Predict Postoperative Outcomes for Anterior Cervical Discectomy and Fusion Procedures With State-of-the-art Performance

STUDY DESIGN

Retrospective cohort.

OBJECTIVE

Due to anterior cervical discectomy and fusion (ACDF) popularity, it is important to predict postoperative complications, unfavorable 90-day readmissions, and two-year reoperations to improve surgical decision-making, prognostication, and planning.

SUMMARY OF BACKGROUND DATA

Machine learning has been applied to predict postoperative complications for ACDF; however, studies were limited by sample size and model type. These studies achieved ≤0.70 area under the curve (AUC). Further approaches, not limited to ACDF, focused on specific complication types and resulted in AUC between 0.70 and 0.76.

MATERIALS AND METHODS

The IBM MarketScan Commercial Claims and Encounters Database and Medicare Supplement were queried from 2007 to 2016 to identify adult patients who underwent an ACDF procedure (N=176,816). Traditional machine learning algorithms, logistic regression, and support vector machines, were compared with deep neural networks to predict: 90-day postoperative complications, 90-day readmission, and two-year reoperation. We further generated random deep learning model architectures and trained them on the 90-day complication task to approximate an upper bound. Last, using deep learning, we investigated the importance of each input variable for the prediction of 90-day postoperative complications in ACDF.

RESULTS

For the prediction of 90-day complication, 90-day readmission, and two-year reoperation, the deep neural network-based models achieved AUC of 0.832, 0.713, and 0.671. Logistic regression achieved AUCs of 0.820, 0.712, and 0.671. Support vector machine approaches were significantly lower. The upper bound of deep learning performance was approximated as 0.832. Myelopathy, age, human immunodeficiency virus, previous myocardial infarctions, obesity, and documentary weakness were found to be the strongest variable to predict 90-day postoperative complications.

CONCLUSIONS

The deep neural network may be used to predict complications for clinical applications after multicenter validation. The results suggest limited added knowledge exists in interactions between the input variables used for this task. Future work should identify novel variables to increase predictive power.

External Validation of a Machine Learning Algorithm for Predicting Clinically Meaningful Functional Improvement After Arthroscopic Hip Preservation Surgery

BACKGROUND

Individualized risk prediction has become possible with machine learning (ML), which may have important implications in enhancing clinical decision making. We previously developed an ML algorithm to predict propensity for clinically meaningful outcome improvement after hip arthroscopy for femoroacetabular impingement syndrome. External validity of prognostic models is critical to determine generalizability, although it is rarely performed.

PURPOSE

To assess the external validity of an ML algorithm for predicting clinically meaningful improvement after hip arthroscopy.

STUDY DESIGN

Cohort study; Level of evidence, 3.

METHODS

An independent hip preservation registry at a tertiary academic medical center was queried for consecutive patients/athletes who underwent hip arthroscopy for femoroacetabular impingement syndrome between 2015 and 2017. By assuming a minimal clinically important difference (MCID) outcome/event proportion of 75% based on the original study, a minimum sample of 132 patients was required. In total, 154 patients were included. Age, body mass index, alpha angle on anteroposterior pelvic radiographs, Tönnis grade and angle, and preoperative Hip Outcome Score-Sports Subscale were used as model inputs to predict the MCID for the Hip Outcome Score-Sports Subscale 2 years postoperatively. Performance was assessed using identical metrics to the internal validation study and included discrimination, calibration, Brier score, and decision curve analysis.

RESULTS

The concordance statistic in the validation cohort was 0.80 (95% CI, 0.71 to 0.87), suggesting good to excellent discrimination. The calibration slope was 1.16 (95% CI, 0.74 to 1.61) and the calibration intercept 0.13 (95% CI, -0.26 to 0.53). The Brier score was 0.15 (95% CI, 0.12 to 0.18). The null model Brier score was 0.20. Decision curve analysis revealed favorable net treatment benefit for patients with use of the algorithm as compared with interventional changes made for all and no patients.

CONCLUSION

The performance of this algorithm in an independent patient population in the northeast region of the United States demonstrated superior discrimination and comparable calibration to that of the derivation cohort. The external validation of this algorithm suggests that it is a reliable method to predict propensity for clinically meaningful improvement after hip arthroscopy and is an essential step forward toward introducing initial use in clinical practice. Potential uses include integration into electronic medical records for automated prediction, enhanced shared decision making, and more informed allocation of resources to optimize patient outcomes.

Octogenarians Are Independently Associated With Extended LOS and Non-Routine Discharge After Elective ACDF for CSM

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

The aim of this study was to determine the impact age has on LOS and discharge disposition following elective ACDF for cervical spondylotic myelopathy (CSM).

METHODS

A retrospective cohort study was performed using the National Inpatient Sample (NIS) database from 2016 and 2017. All adult patients >50 years old undergoing ACDF for CSM were identified using the ICD-10-CM diagnosis and procedural coding system. Patients were then stratified by age: 50 to 64 years-old, 65 to 79 years-old, and greater than or equal to 80 years-old. Weighted patient demographics, comorbidities, perioperative complications, LOS, discharge disposition, and total cost of admission were assessed.

RESULTS

A total of 14 865 patients were identified. Compared to the 50-64 and 65-79 year-old cohorts, the 80+ years cohort had a significantly higher rate of postoperative complication (50-64 yo:10.2% vs. 65-79 yo:12.6% vs. 80+ yo:18.9%, P = 0.048). The 80+ years cohort experienced significantly longer hospital stays (50-64 yo: 2.0 ± 2.4 days vs. 65-79 yo: 2.2 ± 2.8 days vs. 80+ yo: 2.3 ± 2.1 days, P = 0.028), higher proportion of patients with extended LOS (50-64 yo:18.3% vs. 65-79 yo:21.9% vs. 80+ yo:28.4%, P = 0.009), and increased rates of non-routine discharges (50-64 yo:15.1% vs. 65-79 yo:23.0% vs. 80+ yo:35.8%, P < 0.001). On multivariate analysis, age 80+ years was found to be a significant independent predictor of extended LOS [OR:1.97, 95% CI:(1.10,3.55), P = 0.023] and non-routine discharge [OR:2.46, 95% CI:(1.44,4.21), P = 0.001].

CONCLUSIONS

Our study demonstrates that octogenarian age status is a significant independent risk factor for extended LOS and non-routine discharge after elective ACDF for CSM.

Artificial Learning and Machine Learning Applications in Spine Surgery: A Systematic Review

OBJECTIVES

This current systematic review sought to identify and evaluate all current research-based spine surgery applications of AI/ML in optimizing preoperative patient selection, as well as predicting and managing postoperative outcomes and complications.

METHODS

A comprehensive search of publications was conducted through the EMBASE, Medline, and PubMed databases using relevant keywords to maximize the sensitivity of the search. No limits were placed on level of evidence or timing of the study. Findings were reported according to the PRISMA guidelines.

RESULTS

After application of inclusion and exclusion criteria, 41 studies were included in this review. Bayesian networks had the highest average AUC (.80), and neural networks had the best accuracy (83.0%), sensitivity (81.5%), and specificity (71.8%). Preoperative planning/cost prediction models (.89,82.2%) and discharge/length of stay models (.80,78.0%) each reported significantly higher average AUC and accuracy compared to readmissions/reoperation prediction models (.67,70.2%) (P < .001, P = .005, respectively). Model performance also significantly varied across postoperative management applications for average AUC and accuracy values (P < .001, P < .027, respectively).

CONCLUSIONS

Generally, authors of the reviewed studies concluded that AI/ML offers a potentially beneficial tool for providers to optimize patient care and improve cost-efficiency. More specifically, AI/ML models performed best, on average, when optimizing preoperative patient selection and planning and predicting costs, hospital discharge, and length of stay. However, models were not as accurate in predicting postoperative complications, adverse events, and readmissions and reoperations. An understanding of AI/ML-based applications is becoming increasingly important, particularly in spine surgery, as the volume of reported literature, technology accessibility, and clinical applications continue to rapidly expand.

Hospital Frailty Risk Score and healthcare resource utilization after surgery for metastatic spinal column tumors

OBJECTIVE

The Hospital Frailty Risk Score (HFRS) was developed utilizing ICD-10 diagnostic codes to identify frailty and predict adverse outcomes in large national databases. While other studies have examined frailty in spine oncology, the HFRS has not been assessed in this patient population. The aim of this study was to examine the association of HFRS-defined frailty with complication rates, length of stay (LOS), total cost of hospital admission, and discharge disposition in patients undergoing spine surgery for metastatic spinal column tumors.

METHODS

A retrospective cohort study was performed using the years 2016 to 2019 of the National Inpatient Sample (NIS) database. All adult patients (≥ 18 years old) undergoing surgical intervention for metastatic spinal column tumors were identified using the ICD-10-CM diagnostic codes and Procedural Coding System. Patients were categorized into the following three cohorts based on their HFRS: low frailty (HFRS < 5), intermediate frailty (HFRS 5-15), and high frailty (HFRS > 15). Patient demographics, comorbidities, treatment modality, perioperative complications, LOS, discharge disposition, and total cost of hospital admission were assessed. A multivariate logistic regression analysis was used to identify independent predictors of prolonged LOS, nonroutine discharge, and increased cost.

RESULTS

Of the 11,480 patients identified, 7085 (61.7%) were found to have low frailty, 4160 (36.2%) had intermediate frailty, and 235 (2.0%) had high frailty according to HFRS criteria. On average, age increased along with progressively worsening frailty scores (p ≤ 0.001). The proportion of patients in each cohort who experienced ≥ 1 postoperative complication significantly increased along with increasing frailty (low frailty: 29.2%; intermediate frailty: 53.8%; high frailty: 76.6%; p < 0.001). In addition, the mean LOS (low frailty: 7.9 ± 5.0 days; intermediate frailty: 14.4 ± 13.4 days; high frailty: 24.1 ± 18.6 days; p < 0.001), rate of nonroutine discharge (low frailty: 40.4%; intermediate frailty: 60.6%; high frailty: 70.2%; p < 0.001), and mean total cost of hospital admission (low frailty: $48,603 ± $29,979; intermediate frailty: $65,271 ± $43,110; high frailty: $96,116 ± $60,815; p < 0.001) each increased along with progressing frailty. On multivariate regression analysis, intermediate and high frailty were each found to be significant predictors of both prolonged LOS (intermediate: OR 3.75 [95% CI 2.96-4.75], p < 0.001; high: OR 7.33 [95% CI 3.47-15.51]; p < 0.001) and nonroutine discharge (intermediate: OR 2.05 [95% CI 1.68-2.51], p < 0.001; high: OR 5.06 [95% CI 1.93-13.30], p = 0.001).

CONCLUSIONS

This study is the first to use the HFRS to assess the impact of frailty on perioperative outcomes in patients with metastatic bony spinal tumors. Among patients with metastatic bony spinal tumors, frailty assessed using the HFRS was associated with longer hospitalizations, more nonroutine discharges, and higher total hospital costs.

Assessment of Frailty Indices and Charlson Comorbidity Index for Predicting Adverse Outcomes in Patients Undergoing Surgery for Spine Metastases: A National Database Analysis

OBJECTIVE

The aim of this study was to assess the predictive ability of Metastatic Spinal Tumor Frailty Index (MSTFI) and the Modified 5-Item Frailty Index (mFI-5) on adverse outcomes, compared with the known Charlson Comorbidity Index (CCI).

METHODS

A retrospective cohort study was performed using National Surgical Quality Improvement Program database from 2011 to 2019. All adult patients undergoing various procedures for extradural spinal metastases were identified. Patients were stratified into frail and nonfrail cohorts based on CCI, mFI-5, and MSTFI scores. A multivariate logistic regression analysis was used to identify independent predictors of prolonged length of stay, nonroutine discharge, adverse events, and unplanned readmission.

RESULTS

Of the 1613 patients included in this study, 21.4% had a CCI >0, 56.6% had an mFI-5 >0, and 76.7% of patients had an MSTFI >0. On multivariate analysis, all 3 indices were found to be predictive of nonroutine discharge (CCI: adjusted odds ratio [aOR], 1.41 vs. mFI-5: aOR, 1.37 vs. MSTFI: aOR, 1.5) and adverse events (CCI: aOR, 1.53 vs. mFI-5: aOR, 1.23 vs. MSTFI: aOR, 1.43). High CCI (adjusted relative risk, 1.67) and MSTFI (adjusted relative risk, 1.14), but not mFI-5, were also associated with a prolonged length of stay, whereas MSTFI was found to be the only significant predictor of unplanned readmission (aOR, 1.22).

CONCLUSIONS

Our study suggests that MSTFI frailty index may be more sensitive than both CCI and mFI-5 in identifying adverse outcomes after spine surgery for metastases.

Artificial Intelligence-Driven Prediction Modeling and Decision Making in Spine Surgery Using Hybrid Machine Learning Models

Healthcare systems worldwide generate vast amounts of data from many different sources. Although of high complexity for a human being, it is essential to determine the patterns and minor variations in the genomic, radiological, laboratory, or clinical data that reliably differentiate phenotypes or allow high predictive accuracy in health-related tasks. Convolutional neural networks (CNN) are increasingly applied to image data for various tasks. Its use for non-imaging data becomes feasible through different modern machine learning techniques, converting non-imaging data into images before inputting them into the CNN model. Considering also that healthcare providers do not solely use one data modality for their decisions, this approach opens the door for multi-input/mixed data models which use a combination of patient information, such as genomic, radiological, and clinical data, to train a hybrid deep learning model. Thus, this reflects the main characteristic of artificial intelligence: simulating natural human behavior. The present review focuses on key advances in machine and deep learning, allowing for multi-perspective pattern recognition across the entire information set of patients in spine surgery. This is the first review of artificial intelligence focusing on hybrid models for deep learning applications in spine surgery, to the best of our knowledge. This is especially interesting as future tools are unlikely to use solely one data modality. The techniques discussed could become important in establishing a new approach to decision-making in spine surgery based on three fundamental pillars: (1) patient-specific, (2) artificial intelligence-driven, (3) integrating multimodal data. The findings reveal promising research that already took place to develop multi-input mixed-data hybrid decision-supporting models. Their implementation in spine surgery may hence be only a matter of time.

AI MSK clinical applications: spine imaging

Recent investigations have focused on the clinical application of artificial intelligence (AI) for tasks specifically addressing the musculoskeletal imaging routine. Several AI applications have been dedicated to optimizing the radiology value chain in spine imaging, independent from modality or specific application. This review aims to summarize the status quo and future perspective regarding utilization of AI for spine imaging. First, the basics of AI concepts are clarified. Second, the different tasks and use cases for AI applications in spine imaging are discussed and illustrated by examples. Finally, the authors of this review present their personal perception of AI in daily imaging and discuss future chances and challenges that come along with AI-based solutions.

External validation of a predictive model of adverse events following spine surgery

BACKGROUND CONTEXT

We lack models that reliably predict 30-day postoperative adverse events (AEs) following spine surgery.

PURPOSE

We externally validated a previously developed predictive model for common 30-day adverse events (AEs) after spine surgery.

STUDY DESIGN/SETTING

This prospective cohort study utilizes inpatient and outpatient data from a tertiary academic medical center.

PATIENT SAMPLE

We assessed a prospective cohort of all 276 adult patients undergoing spine surgery in the Department of Neurosurgery at a tertiary academic institution between April 1, 2018 and October 31, 2018. No exclusion criteria were applied.

OUTCOME MEASURES

Incidence of observed AEs was compared with predicted incidence of AEs. Fifteen assessed AEs included: pulmonary complications, congestive heart failure, neurological complications, pneumonia, cardiac dysrhythmia, renal failure, myocardial infarction, wound infection, pulmonary embolus, deep venous thrombosis, wound hematoma, other wound complication, urinary tract infection, delirium, and other infection.

METHODS

Our group previously developed the Risk Assessment Tool for Adverse Events after Spine Surgery (RAT-Spine), a predictive model of AEs within 30 days following spine surgery using a cohort of approximately one million patients from combined Medicare and MarketScan databases. We applied RAT-Spine to the single academic institution prospective cohort by entering each patient's preoperative medical and demographic characteristics and surgical type. The model generated a patient-specific overall risk score ranging from 0 to 1 representing the probability of occurrence of any AE. The predicted risks are presented as absolute percent risk and divided into low (<17%), medium (17%-28%), and high (>28%).

RESULTS

Among the 276 patients followed prospectively, 76 experienced at least one 30-day postoperative AE. Slightly more than half of the cohort were women (53.3%). The median age was slightly lower in the non-AE cohort (63 vs. 66.5 years old). Patients with Medicaid comprised 2.5% of the non-AE cohort and 6.6% of the AE cohort. Spinal fusion was performed in 59.1% of cases, which was comparable across cohorts. There was good agreement between the predicted AE and observed AE rates, Area Under the Curve (AUC) 0.64 (95% CI 0.56-0.710). The incidence of observed AEs in the prospective cohort was 17.8% among the low-risk group, 23.0% in the medium-risk group, and 38.4% in the high risk group (p =.003).

CONCLUSIONS

We externally validated a model for postoperative AEs following spine surgery (RAT-Spine). The results are presented as low-, moderate-, and high-risk designations.

Diagnosis of Suspected Scaphoid Fractures

»

Suspected scaphoid fractures are a diagnostic and therapeutic challenge despite the advances in knowledge regarding these injuries and imaging techniques. The risks and restrictions of routine immobilization as well as the restriction of activities in a young and active population must be weighed against the risks of nonunion that are associated with a missed fracture.

»

The prevalence of true fractures among suspected fractures is low. This greatly reduces the statistical probability that a positive diagnostic test will correspond with a true fracture, reducing the positive predictive value of an investigation.

»

There is no consensus reference standard for a true fracture; therefore, alternative statistical methods for calculating sensitivity, specificity, and positive and negative predictive values are required.

»

Clinical prediction rules that incorporate a set of demographic and clinical factors may allow stratification of secondary imaging, which, in turn, could increase the pretest probability of a scaphoid fracture and improve the diagnostic performance of the sophisticated radiographic investigations that are available.

»

Machine-learning-derived probability calculators may augment risk stratification and can improve through retraining, although these theoretical benefits need further prospective evaluation.

»

Convolutional neural networks (CNNs) are a form of artificial intelligence that have demonstrated great promise in the recognition of scaphoid fractures on radiographs. However, in the more challenging diagnostic scenario of a suspected or so-called "clinical" scaphoid fracture, CNNs have not yet proven superior to a diagnosis that has been made by an experienced surgeon.

Utility of machine learning algorithms in degenerative cervical and lumbar spine disease: a systematic review

Machine learning is a rapidly evolving field that offers physicians an innovative and comprehensive mechanism to examine various aspects of patient data. Cervical and lumbar degenerative spine disorders are commonly age-related disease processes that can utilize machine learning to improve patient outcomes with careful patient selection and intervention. The aim of this study is to examine the current applications of machine learning in cervical and lumbar degenerative spine disease. A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A search of PubMed, Embase, Medline, and Cochrane was conducted through May 31st, 2020, using the following terms: "artificial intelligence" OR "machine learning" AND "neurosurgery" AND "spine." Studies were included if original research on machine learning was utilized in patient care for degenerative spine disease, including radiographic machine learning applications. Studies focusing on robotic applications in neurosurgery, navigation, or stereotactic radiosurgery were excluded. The literature search identified 296 papers, with 35 articles meeting inclusion criteria. There were nine studies involving cervical degenerative spine disease and 26 studies on lumbar degenerative spine disease. The majority of studies for both cervical and lumbar spines utilized machine learning for the prediction of postoperative outcomes, with 5 (55.6%) and 15 (61.5%) studies, respectively. Machine learning applications focusing on degenerative lumbar spine greatly outnumber the current volume of cervical spine studies. The current research in lumbar spine also demonstrates more advanced clinical applications of radiographic, diagnostic, and predictive machine learning models.

Artificial Intelligence and Robotics in Spine Surgery

STUDY DESIGN

Narrative review.

OBJECTIVES

Artificial intelligence (AI) and machine learning (ML) have emerged as disruptive technologies with the potential to drastically affect clinical decision making in spine surgery. AI can enhance the delivery of spine care in several arenas: (1) preoperative patient workup, patient selection, and outcome prediction; (2) quality and reproducibility of spine research; (3) perioperative surgical assistance and data tracking optimization; and (4) intraoperative surgical performance. The purpose of this narrative review is to concisely assemble, analyze, and discuss current trends and applications of AI and ML in conventional and robotic-assisted spine surgery.

METHODS

We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2019 examining AI, ML, and robotics in spine surgery. Key findings were then compiled and summarized in this review.

RESULTS

The majority of the published AI literature in spine surgery has focused on predictive analytics and supervised image recognition for radiographic diagnosis. Several investigators have studied the use of AI/ML in the perioperative setting in small patient cohorts; pivotal trials are still pending.

CONCLUSIONS

Artificial intelligence has tremendous potential in revolutionizing comprehensive spine care. Evidence-based, predictive analytics can help surgeons improve preoperative patient selection, surgical indications, and individualized postoperative care. Robotic-assisted surgery, while still in early stages of development, has the potential to reduce surgeon fatigue and improve technical precision.

Race Is an Independent Predictor for Nonroutine Discharges After Spine Surgery for Spinal Intradural/Cord Tumors

OBJECTIVE

The aim of this study was to determine if race was an independent predictor of extended length of stay (LOS), nonroutine discharge, and increased health care costs after surgery for spinal intradural/cord tumors.

METHODS

A retrospective cohort study was performed using the National Inpatient Sample database from 2016 to 2017. All adult (>18 years old) inpatients who underwent surgical intervention for a benign or malignant spinal intradural/cord tumor were identified using International Classification of Diseases, Tenth Revision, Clinical Modification diagnosis and procedural coding systems. Patients were then categorized based on race: White, African American (AA), Hispanic, and other. Postoperative complications, LOS, discharge disposition, and total cost of hospitalization were assessed. A backward stepwise multivariable logistic regression analysis was used to identify independent predictors of extended LOS and nonroutine discharge disposition.

RESULTS

Of 3595 patients identified, there were 2620 (72.9%) whites (W), 310 (8.6%) AAs/blacks, 275 (7.6%) Hispanic (H), and 390 (10.8%) other (O). Postoperative complication rates were similar among the cohorts (P = 0.887). AAs had longer mean (W, 5.4 ± 4.2 days vs. AA, 8.9 ± 9.5 days vs. H, 5.9 ± 3.9 days vs. O, 6.1 ± 3.9 days; P = 0.014) length of hospitalizations than the other cohorts. The overall incidence of nonroutine discharge was 55% (n = 1979), with AA race having the highest rate of nonroutine discharges (W, 53.8% vs. AA, 74.2% vs. H, 45.5% vs. O, 43.6%; P = 0.016). On multivariate regression analysis, AA race was the only significant racial independent predictor of nonroutine discharge disposition (odds ratio, 3.32; confidence interval, 1.67-6.60; P < 0.001), but not extended LOS (P = 0.209).

CONCLUSIONS

Our study indicates that AA race is an independent predictor of nonroutine discharge disposition in patients undergoing surgical intervention for a spinal intradural/cord tumor.

Web-Based Calculator Predicts Surgical-Site Infection After Thoracolumbar Spine Surgery

BACKGROUND

Surgical-site infection (SSI) after spine surgery leads to increased length of stay, reoperation, and worse patient quality of life. We sought to develop a web-based calculator that computes an individual's risk of a wound infection following thoracolumbar spine surgery.

METHODS

We performed a retrospective review of consecutive patients undergoing elective degenerative thoracolumbar spine surgery at a tertiary-care institution between January 2016 and December 2018. Patients who developed SSI requiring reoperation were identified. Regression analysis was performed and model performance was assessed using receiver operating curve analysis to derive an area under the curve. Bootstrapping was performed to check for overfitting, and a Hosmer-Lemeshow test was employed to evaluate goodness-of-fit and model calibration.

RESULTS

In total, 1259 patients were identified; 73% were index operations. The overall infection rate was 2.7%, and significant predictors of SSI included female sex (odds ratio [OR] 3.0), greater body mass index (OR 1.1), active smoking (OR 2.8), worse American Society of Anesthesiologists physical status (OR 2.1), and greater surgical invasiveness (OR 1.1). The prediction model had an optimism-corrected area under the curve of 0.81. A web-based calculator was created: https://jhuspine2.shinyapps.io/Wound_Infection_Calculator/.

CONCLUSIONS

In this pilot study, we developed a model and simple web-based calculator to predict a patient's individualized risk of SSI after thoracolumbar spine surgery. This tool has a predictive accuracy of 83%. Through further multi-institutional validation studies, this tool has the potential to alert both patients and providers of an individual's SSI risk to improve informed consent, mitigate risk factors, and ultimately drive down rates of SSIs.

Cost and Health Care Resource Utilization Differences After Spine Surgery for Bony Spine versus Primary Intradural Spine Tumors

OBJECTIVE

The aim of this study was to compare complication rates, length of stay (LOS), and hospital costs after spine surgery for bony spine tumors and intradural spinal neoplasms.

METHODS

A retrospective cohort study was performed using the National Inpatient Sample database from 2016 to 2017. All adult inpatients who underwent surgical intervention for a primary intradural spinal tumor or primary/metastatic bony spine tumor were identified using International Classification of Diseases, Tenth Revision, Clinical Modification diagnosis/procedural coding systems. Patient demographics, comorbidities, intraoperative variables, complications, LOS, discharge disposition, and total cost of hospitalization were assessed. Backward stepwise multivariable logistic regression analyses were used to identify independent predictors of perioperative complication, extended LOS (≥75th percentile), and increased cost (≥75th percentile).

RESULTS

A total of 9855 adult patients were included in the study; 3850 (39.1%) were identified as having a primary intradural spinal tumor and 6005 (60.9%) had a primary or metastatic bony spine tumor. Those treated for bony tumors had more comorbidities (≥3, 67.8% vs. 29.2%) and more commonly experienced ≥1 complications (29.9% vs. 7.9%). Multivariate analyses also showed those in the bony spine cohort had a higher odds of experiencing ≥1 complications (odds ratio [OR], 4.26; 95% confidence interval [CI], 3.04-5.97; P < 0.001), extended LOS (OR, 2.44; 95% CI, 1.75-3.38; P < 0.001), and increased cost (OR, 5.32; 95% CI, 3.67-7.71; P < 0.001).

CONCLUSIONS

Relative to patients being treated for primary intradural tumors, those undergoing spine surgery for bony spine tumors experience significantly higher risk for perioperative complications, extended LOS, and increased cost of hospital admission. Further identification of patient and treatment characteristics that may optimize management of spine oncology may reduce adverse outcomes, improve patient care, and reduce health care resources.

Prediction Models in Degenerative Spine Surgery: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVES

To review the existing literature of prediction models in degenerative spinal surgery.

METHODS

Review of PubMed/Medline and Embase databases was conducted to identify articles between January 1, 2000 and March 1, 2020 that reported prediction model performance for outcomes following elective degenerative spine surgery.

RESULTS

Thirty-one articles were included. Twenty studies were of thoracolumbar, 5 were of cervical, and 6 included all spine patients. Five studies were externally validated. Prediction models were developed using machine learning (42%) and logistic regression (42%) as well as other techniques. Web-based calculators were included in 45% of published articles. Various outcomes were investigated, including complications, infection, length of stay, discharge disposition, reoperation, readmission, disability score, back pain, leg pain, return to work, and opioid dependence.

CONCLUSIONS

Significant heterogeneity exists in methods used to develop prediction models of postoperative outcomes after degenerative spine surgery. Most internally validate their scores, but a few have been externally validated. Areas under the curve for most models range from 0.6 to 0.9. Techniques for development are becoming increasingly sophisticated with different machine learning tools. With further external validation, these models can be deployed online for patient, physician, and administrative use, and have the potential to optimize outcomes and maximize value in spine surgery.

A Machine Learning Algorithm to Identify Patients with Tibial Shaft Fractures at Risk for Infection After Operative Treatment

BACKGROUND

Risk stratification of individual patients who are prone to infection would allow surgeons to monitor high-risk patients more closely and intervene early when needed. This could reduce infection-related consequences such as increased health-care costs. The purpose of this study was to develop a machine learning (ML)-derived risk-stratification tool using the SPRINT (Study to Prospectively Evaluate Reamed Intramedullary Nails in Patients with Tibial Fractures) and FLOW (Fluid Lavage of Open Wounds) trial databases to estimate the probability of infection in patients with operatively treated tibial shaft fractures (TSFs).

METHODS

Patients with unilateral TSFs from the SPRINT and FLOW trials were randomly split into derivation (80%) and validation (20%) cohorts. Random forest algorithms were used to select features that are relevant to predicting infection. These features were included for algorithm training. Five ML algorithms were trained in recognizing patterns associated with infection. The performance of each ML algorithm was evaluated and compared based on (1) the area under the ROC (receiver operating characteristic) curve (AUC), (2) the calibration slope and the intercept, and (3) the Brier score.

RESULTS

There were 1,822 patients included in this study: 170 patients (9%) developed an infection that required treatment, 62 patients (3%) received nonoperative treatment with oral or intravenous antibiotics, and 108 patients (6%) underwent subsequent surgery in addition to antibiotic therapy. Random forest algorithms identified 7 variables that were relevant for predicting infection: (1) Gustilo-Anderson or Tscherne classification, (2) bone loss, (3) mechanism of injury, (4) multitrauma, (5) AO/OTA fracture classification, (6) age, and (7) fracture location. Training of the penalized logistic regression algorithm resulted in the best-performing prediction model, with AUC, calibration slope, calibration intercept, and Brier scores of 0.75, 0.94, 0.00, and 0.076, respectively, in the derivation cohort and 0.81, 1.07, 0.09, and 0.079, respectively, in the validation cohort.

CONCLUSIONS

We developed an ML prediction model that can estimate the probability of infection for individual patients with TSFs based on patient and fracture characteristics that are readily available at hospital admission.

LEVEL OF EVIDENCE

Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Utility of prediction model score: a proposed tool to standardize the performance and generalizability of clinical predictive models based on systematic review

OBJECTIVE

The objective of this study was to evaluate the characteristics and performance of current prediction models in the fields of spine metastasis and degenerative spine disease to create a scoring system that allows direct comparison of the prediction models.

METHODS

A systematic search of PubMed and Embase was performed to identify relevant studies that included either the proposal of a prediction model or an external validation of a previously proposed prediction model with 1-year outcomes. Characteristics of the original study and discriminative performance of external validations were then assigned points based on thresholds from the overall cohort.

RESULTS

Nine prediction models were included in the spine metastasis category, while 6 prediction models were included in the degenerative spine category. After assigning the proposed utility of prediction model score to the spine metastasis prediction models, only 1 reached the grade of excellent, while 2 were graded as good, 3 as fair, and 3 as poor. Of the 6 included degenerative spine models, 1 reached the excellent grade, while 3 studies were graded as good, 1 as fair, and 1 as poor.

CONCLUSIONS

As interest in utilizing predictive analytics in spine surgery increases, there is a concomitant increase in the number of published prediction models that differ in methodology and performance. Prior to applying these models to patient care, these models must be evaluated. To begin addressing this issue, the authors proposed a grading system that compares these models based on various metrics related to their original design as well as internal and external validation. Ultimately, this may hopefully aid clinicians in determining the relative validity and usability of a given model.

Artificial intelligence in orthopaedics: false hope or not? A narrative review along the line of Gartner's hype cycle

Artificial Intelligence (AI) in general, and Machine Learning (ML)-based applications in particular, have the potential to change the scope of healthcare, including orthopaedic surgery.

The greatest benefit of ML is in its ability to learn from real-world clinical use and experience, and thereby its capability to improve its own performance.

Many successful applications are known in orthopaedics, but have yet to be adopted and evaluated for accuracy and efficacy in patients’ care and doctors’ workflows.

The recent hype around AI triggered hope for development of better risk stratification tools to personalize orthopaedics in all subsequent steps of care, from diagnosis to treatment.

Computer vision applications for fracture recognition show promising results to support decision-making, overcome bias, process high-volume workloads without fatigue, and hold the promise of even outperforming doctors in certain tasks.

In the near future, AI-derived applications are very likely to assist orthopaedic surgeons rather than replace us. ‘If the computer takes over the simple stuff, doctors will have more time again to practice the art of medicine’.⁷⁶

Cite this article: EFORT Open Rev 2020;5:593-603. DOI: 10.1302/2058-5241.5.190092

The Role of Machine Learning in Spine Surgery: The Future Is Now

The recent influx of machine learning centered investigations in the spine surgery literature has led to increased enthusiasm as to the prospect of using artificial intelligence to create clinical decision support tools, optimize postoperative outcomes, and improve technologies used in the operating room. However, the methodology underlying machine learning in spine research is often overlooked as the subject matter is quite novel and may be foreign to practicing spine surgeons. Improper application of machine learning is a significant bioethics challenge, given the potential consequences of over- or underestimating the results of such studies for clinical decision-making processes. Proper peer review of these publications requires a baseline familiarity of the language associated with machine learning, and how it differs from classical statistical analyses. This narrative review first introduces the overall field of machine learning and its role in artificial intelligence, and defines basic terminology. In addition, common modalities for applying machine learning, including classification and regression decision trees, support vector machines, and artificial neural networks are examined in the context of examples gathered from the spine literature. Lastly, the ethical challenges associated with adapting machine learning for research related to patient care, as well as future perspectives on the potential use of machine learning in spine surgery, are discussed specifically.

A Review on the Use of Artificial Intelligence in Spinal Diseases

Artificial neural networks (ANNs) have been used in a wide variety of real-world applications and it emerges as a promising field across various branches of medicine. This review aims to identify the role of ANNs in spinal diseases. Literature were searched from electronic databases of Scopus and Medline from 1993 to 2020 with English publications reported on the application of ANNs in spinal diseases. The search strategy was set as the combinations of the following keywords: “artificial neural networks,” “spine,” “back pain,” “prognosis,” “grading,” “classification,” “prediction,” “segmentation,” “biomechanics,” “deep learning,” and “imaging.” The main findings of the included studies were summarized, with an emphasis on the recent advances in spinal diseases and its application in the diagnostic and prognostic procedures. According to the search strategy, a set of 3,653 articles were retrieved from Medline and Scopus databases. After careful evaluation of the abstracts, the full texts of 89 eligible papers were further examined, of which 79 articles satisfied the inclusion criteria of this review. Our review indicates several applications of ANNs in the management of spinal diseases including (1) diagnosis and assessment of spinal disease progression in the patients with low back pain, perioperative complications, and readmission rate following spine surgery; (2) enhancement of the clinically relevant information extracted from radiographic images to predict Pfirrmann grades, Modic changes, and spinal stenosis grades on magnetic resonance images automatically; (3) prediction of outcomes in lumbar spinal stenosis, lumbar disc herniation and patient-reported outcomes in lumbar fusion surgery, and preoperative planning and intraoperative assistance; and (4) its application in the biomechanical assessment of spinal diseases. The evidence suggests that ANNs can be successfully used for optimizing the diagnosis, prognosis and outcome prediction in spinal diseases. Therefore, incorporation of ANNs into spine clinical practice may improve clinical decision making.

The Impact of Artificial Intelligence on Quality and Safety

As exponential expansion of computing capacity converges with unsustainable health care spending, a hopeful opportunity has emerged: the use of artificial intelligence to enhance health care quality and safety. These computer-based algorithms can perform the intricate and extremely complex mathematical operations of classification or regression on immense amounts of data to detect intricate and potentially previously unknown patterns in that data, with the end result of creating predictive models that can be utilized in clinical practice. Such models are designed to distinguish relevant from irrelevant data regarding a particular patient; choose appropriate perioperative care, intervention or surgery; predict cost of care and reimbursement; and predict future outcomes on a variety of anchored measures. If and when one is brought to fruition, an artificial intelligence platform could serve as the first legitimate clinical decision-making tool in spine care, delivering on the value equation while serving as a source for improving physician performance and promoting appropriate, efficient care in this era of financial uncertainty in health care.

Applications of Machine Learning Using Electronic Medical Records in Spine Surgery

Developments in machine learning in recent years have precipitated a surge in research on the applications of artificial intelligence within medicine. Machine learning algorithms are beginning to impact medicine broadly, and the field of spine surgery is no exception. Electronic medical records are a key source of medical data that can be leveraged for the creation of clinically valuable machine learning algorithms. This review examines the current state of machine learning using electronic medical records as it applies to spine surgery. Studies across the electronic medical record data domains of imaging, text, and structured data are reviewed. Discussed applications include clinical prognostication, preoperative planning, diagnostics, and dynamic clinical assistance, among others. The limitations and future challenges for machine learning research using electronic medical records are also discussed.