Development of predictive models for all individual questions of SRS-22R after adult spinal deformity surgery: a step toward individualized medicine

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.

Artificial Intelligence in Spine Surgery

The amount and quality of data being used in our everyday lives continue to advance in an unprecedented pace. This digital revolution has permeated healthcare, specifically spine surgery, allowing for very advanced and complex computational analytics, such as artificial intelligence (AI) and machine learning (ML). The integration of these methods into clinical practice has just begun, and the following review article will describe AI/ML, demonstrate how it has been applied in adult spinal deformity surgery, and show its potential to improve patient care touching on future directions.

Emerging Technologies within Spine Surgery

New innovations within spine surgery continue to propel the field forward. These technologies improve surgeons' understanding of their patients and allow them to optimize treatment planning both in the operating room and clinic. Additionally, changes in the implants and surgeon practice habits continue to evolve secondary to emerging biomaterials and device design. With ongoing advancements, patients can expect enhanced preoperative decision-making, improved patient outcomes, and better intraoperative execution. Additionally, these changes may decrease many of the most common complications following spine surgery in order to reduce morbidity, mortality, and the need for reoperation. This article reviews some of these technological advancements and how they are projected to impact the field. As the field continues to advance, it is vital that practitioners remain knowledgeable of these changes in order to provide the most effective treatment possible.

Revision surgery following long lumbopelvic constructs for adult spinal deformity: prospective experience from two dedicated databases

PURPOSE

Pan Lumbar Arthodesis (PLA) are often required for Adult Spinal Deformity (ASD) correction, reducing significantly the compensatory capacity in case of postoperative sagittal malalignment. Few papers have investigated outcomes and complications in this vulnerable subset of patients. The objective of this study was to assess revision surgery rate for PLA in ASD, its risk factors and impact on clinical outcomes.

METHODS

Retrospective multicenter review of prospective ASD data from 7 hospitals covering Europe and Asia. ASD patients included in two prospective databases having a posterior instrumentation spanning the whole lumbar region with more than 2-years of follow-up were reviewed. Demographic, surgical, radiographic parameters and Health-Related Quality of Life (HRQoL) scores were analyzed. Univariate and multivariate regression models analyzed risk factors for revision surgery as well as surgical outcomes. Patients with Early versus Late and PJK versus Non-PJK mechanical complications were also compared.

RESULTS

Out of 1359 ASD patients included in the database 589 (43%) had a PLA and 357 reached 2-years mark. They were analyzed and compared to non-PLA patients. Average age was 67 and 82% were females. 100 Patients (28.1%) needed 114 revision surgeries (75.4% for mechanical failures). Revised patients were more likely to have a nerve system disorder, higher BMI and worst immediate postoperative alignment (as measured by GAP Parameters). These risk factors were also associated with earlier mechanical complications and PJK. Deformity and HRQoL parameters were comparable at baseline. Non-revised patients had significantly better clinical outcomes at 2-years (SRS 22 scores, ODI, Back pain). Multivariate analysis could identify nerve system disorder (OR 4.8; CI 1.8-12.6; p = 0.001), postoperative sagittal alignment (GAP Score) and high BMI (OR 1.07; CI 1.01-1.13; p = 0.004) as independent risk factors for revisions.

CONCLUSIONS

Revision surgery due to mechanical failures is relatively common after PLA leading to worse clinical outcomes. Prevention strategies should focus on individualized restoration of sagittal alignment and better weight control to decrease stress on these rigid constructs in non-compliant spines. Nerve system disorders independently increase revision risk in PLA.

LEVEL OF EVIDENCE II

Prognosis.

Artificial intelligence and treatment algorithms in spine surgery

Artificial intelligence (AI) is a set of theories and techniques in which machines are used to simulate human intelligence with complex computer programs. The various machine learning (ML) methods are a subtype of AI. They originate from computer science and use algorithms established from analyzing a database to accomplish certain tasks. Among these methods are decision trees or random forests, support vector machines along with artificial neural networks. Convolutive neural networks were inspired from the visual cortex; they process combinations of information used in image or voice recognition. Deep learning (DL) groups together a set of ML methods and is useful for modeling complex relationships with a high degree of abstraction by using multiple layers of artificial neurons. ML techniques have a growing role in spine surgery. The main applications are the segmentation of intraoperative images for surgical navigation or robotics used for pedicle screw placement, the interpretation of images of intervertebral discs or full spine radiographs, which can be automated using ML algorithms. ML techniques can also be used as aids for surgical decision-making in complex fields, such as preoperative evaluation of adult spinal deformity. ML algorithms "learn" from large clinical databases. They make it possible to establish the intraoperative risk level and make a prognosis on how the postoperative functional scores will change over time as a function of the patient profile. These applications open a new path relative to standard statistical analyses. They make it possible to explore more complex relationships with multiple indirect interactions. In the future, AI algorithms could have a greater role in clinical research, evaluating clinical and surgical practices, and conducting health economics analyses.

Inventory of Patient-Reported Outcome Measures Used in the Non-Operative Care of Scoliosis: A Scoping Review

It is unclear which patient-reported outcome measures (PROMs) can assess non-operative care for scoliosis. Most existing tools aim to assess the effects of surgery. This scoping review aimed to inventory the PROMs used to assess non-operative scoliosis treatment by population and languages. We searched Medline (OVID) as per COSMIN guidelines. Studies were included if patients were diagnosed with idiopathic scoliosis or adult degenerative scoliosis and used PROMs. Studies without quantitative data or reporting on fewer than 10 participants were excluded. Nine reviewers extracted the PROMs used, the population(s), language(s), and study setting(s). We screened 3724 titles and abstracts. Of these, the full texts of 900 articles were assessed. Data were extracted from 488 studies, in which 145 PROMs were identified across 22 languages and 5 populations (Adolescent Idiopathic Scoliosis, Adult Degenerative Scoliosis, Adult Idiopathic Scoliosis, Adult Spine Deformity, and an Unclear category). Overall, the most used PROMs were the Oswestry Disability Index (ODI, 37.3%), Scoliosis Research Society-22 (SRS-22, 34.8%), and the Short Form-36 (SF-36, 20.1%), but the frequency varied by population. It is now necessary to determine the PROMs that demonstrate the best measurement properties in the non-operative treatment of scoliosis to include in a core set of outcomes.

Validation of Adult Spinal Deformity Surgical Outcome Prediction Tools in Adult Symptomatic Lumbar Scoliosis

STUDY DESIGN

A post hoc analysis.

OBJECTIVE

Advances in machine learning (ML) have led to tools offering individualized outcome predictions for adult spinal deformity (ASD). Our objective is to examine the properties of these ASD models in a cohort of adult symptomatic lumbar scoliosis (ASLS) patients.

SUMMARY OF BACKGROUND DATA

ML algorithms produce patient-specific probabilities of outcomes, including major complication (MC), reoperation (RO), and readmission (RA) in ASD. External validation of these models is needed.

METHODS

Thirty-nine predictive factors (12 demographic, 9 radiographic, 4 health-related quality of life, 14 surgical) were retrieved and entered into web-based prediction models for MC, unplanned RO, and hospital RA. Calculated probabilities were compared with actual event rates. Discrimination and calibration were analyzed using receiver operative characteristic area under the curve (where 0.5=chance, 1=perfect) and calibration curves (Brier scores, where 0.25=chance, 0=perfect). Ninety-five percent confidence intervals are reported.

RESULTS

A total of 169 of 187 (90%) surgical patients completed 2-year follow up. The observed rate of MCs was 41.4% with model predictions ranging from 13% to 68% (mean: 38.7%). RO was 20.7% with model predictions ranging from 9% to 54% (mean: 30.1%). Hospital RA was 17.2% with model predictions ranging from 13% to 50% (mean: 28.5%). Model classification for all three outcome measures was better than chance for all [area under the curve=MC 0.6 (0.5-0.7), RA 0.6 (0.5-0.7), RO 0.6 (0.5-0.7)]. Calibration was better than chance for all, though best for RA and RO (Brier Score=MC 0.22, RA 0.16, RO 0.17).

CONCLUSIONS

ASD prediction models for MC, RA, and RO performed better than chance in a cohort of adult lumbar scoliosis patients, though the homogeneity of ASLS affected calibration and accuracy. Optimization of models require samples with the breadth of outcomes (0%-100%), supporting the need for continued data collection as personalized prediction models may improve decision-making for the patient and surgeon alike.

Failure in Adult Spinal Deformity Surgery: A Comprehensive Review of Current Rates, Mechanisms, and Prevention Strategies

STUDY DESIGN

Literature review.

OBJECTIVE

The aim of this review is to summarize recent literature on adult spinal deformity (ASD) treatment failure as well as prevention strategies for these failure modes.

SUMMARY OF BACKGROUND DATA

There is substantial evidence that ASD surgery can provide significant clinical benefits to patients. The volume of ASD surgery is increasing, and significantly more complex procedures are being performed, especially in the aging population with multiple comorbidities. Although there is potential for significant improvements in pain and disability with ASD surgery, these procedures continue to be associated with major complications and even outright failure.

METHODS

A systematic search of the PubMed database was performed for articles relevant to failure after ASD surgery. Institutional review board approval was not needed.

RESULTS

Failure and the potential need for revision surgery generally fall into 1 of 4 well-defined phenotypes: clinical failure, radiographic failure, the need for reoperation, and lack of cost-effectiveness. Revision surgery rates remain relatively high, challenging the overall cost-effectiveness of these procedures.

CONCLUSION

By consolidating the key evidence regarding failure, further research and innovation may be stimulated with the goal of significantly improving the safety and cost-effectiveness of ASD surgery.

Individual differences in postoperative recovery trajectories for adult symptomatic lumbar scoliosis

OBJECTIVE

The Adult Symptomatic Lumbar Scoliosis-1 (ASLS-1) trial demonstrated the benefit of adult symptomatic lumbar scoliosis (ASLS) surgery. However, the extent to which individuals differ in their postoperative recovery trajectories is unknown. This study's objective was to evaluate variability in and factors moderating recovery trajectories after ASLS surgery.

METHODS

The authors used longitudinal, multilevel models to analyze postoperative recovery trajectories following ASLS surgery. Study outcomes included the Oswestry Disability Index (ODI) score and Scoliosis Research Society-22 (SRS-22) subscore, which were measured every 3 months until 2 years postoperatively. The authors evaluated the influence of preoperative disability level, along with other potential trajectory moderators, including radiographic, comorbidity, pain/function, demographic, and surgical factors. The impact of different parameters was measured using the R2, which represented the amount of variability in ODI/SRS-22 explained by each model. The R2 ranged from 0 (no variability explained) to 1 (100% of variability explained).

RESULTS

Among 178 patients, there was substantial variability in recovery trajectories. Applying the average trajectory to each patient explained only 15% of the variability in ODI and 21% of the variability in SRS-22 subscore. Differences in preoperative disability (ODI/SRS-22) had the strongest influence on recovery trajectories, with patients having moderate disability experiencing the greatest and most rapid improvement after surgery. Reflecting this impact, accounting for the preoperative ODI/SRS-22 level explained an additional 56%-57% of variability in recovery trajectory, while differences in the rate of postoperative change explained another 7%-9%. Among the effect moderators tested, pain/function variables-such as visual analog scale back pain score-had the biggest impact, explaining 21%-25% of variability in trajectories. Radiographic parameters were the least influential, explaining only 3%-6% more variance than models with time alone. The authors identified several significant trajectory moderators in the final model, such as significant adverse events and the number of levels fused.

CONCLUSIONS

ASLS patients have highly variable postoperative recovery trajectories, although most reach steady state at 12 months. Preoperative disability was the most important influence, although other factors, such as number of levels fused, also impacted recovery.

Combined anterior-posterior versus all-posterior approaches for adult spinal deformity correction: a matched control study

PURPOSE

Anterior approaches are gaining popularity for adult spinal deformity (ASD) surgeries especially with the introduction of hyperlordotic cages and improvement in MIS techniques. Combined Approaches provide powerful segmental sagittal correction potential and increase the surface area available for fusion in ASD surgery, both of which would improve overall. This is the first study directly comparing surgical outcomes between combined anterior-posterior approaches and all-posterior approach in a matched ASD population.

METHODS

This is a retrospective matched control cohort analysis with substitution using a multicenter prospectively collected ASD data of patients with > 2 year FU. Matching criteria include: age, American Society of Anesthesiologists Score, Lumbar Cobb angle, sagittal deformity (Global tilt) and ODI.

RESULTS

In total, 1024 ASD patients were available for analysis. 29 Combined Approaches patients met inclusion criteria, and only 22 could be matched (1:2 ratio). Preoperative non-matched demographical, clinical, surgical and radiological parameters were comparable between both groups. Combined approaches had longer surgeries (548 mns vs 283) with more blood loss (2850 ml vs 1471) and needed longer ICU stays (74 h vs 27). Despite added morbidity, they had comparable complication rates but with significantly less readmissions (9.1% vs 38.1%) and reoperations (18.2% vs 43.2%) at 2 years. Combined Approaches achieved more individualised and harmonious deformity correction initially. At the 2 years control, Combined Approaches patients reported better outcomes as measured by COMI and SRS scores. This trend was maintained at 3 years.

CONCLUSION

Despite an increased initial surgical invasiveness, combined approaches seem to achieve more harmonious correction with superior sagittal deformity control; they need fewer revisions and have improved long-term functional outcomes when compared to all-posterior approaches for ASD deformity correction.

Surgeons' risk perception in ASD surgery: The value of objective risk assessment on decision making and patient counselling

BACKGROUND

Surgeons often rely on their intuition, experience and published data for surgical decision making and informed consent. Literature provides average values that do not allow for individualized assessments. Accurate validated machine learning (ML) risk calculators for adult spinal deformity (ASD) patients, based on 10 year multicentric prospective data, are currently available. The objective of this study is to assess surgeon ASD risk perception and compare it to validated risk calculator estimates.

METHODS

Nine ASD complete (demographics, HRQL, radiology, surgical plan) preoperative cases were distributed online to 100 surgeons from 22 countries. Surgeons were asked to determine the risk of major complications and reoperations at 72 h, 90 d and 2 years postop, using a 0-100% risk scale. The same preoperative parameters circulated to surgeons were used to obtain ML risk calculator estimates. Concordance between surgeons' responses was analyzed using intraclass correlation coefficients (ICC) (poor < 0.5/excellent > 0.85). Distance between surgeons' and risk calculator predictions was assessed using the mean index of agreement (MIA) (poor < 0.5/excellent > 0.85).

RESULTS

Thirty-nine surgeons (74.4% with > 10 years' experience), from 12 countries answered the survey. Surgeons' risk perception concordance was very low and heterogeneous. ICC ranged from 0.104 (reintervention risk at 72 h) to 0.316 (reintervention risk at 2 years). Distance between calculator and surgeon prediction was very large. MIA ranged from 0.122 to 0.416. Surgeons tended to overestimate the risk of major complications and reintervention in the first 72 h and underestimated the same risks at 2 years postop.

CONCLUSIONS

This study shows that expert surgeon ASD risk perception is heterogeneous and highly discordant. Available validated ML ASD risk calculators can enable surgeons to provide more accurate and objective prognosis to adjust patient expectations, in real time, at the point of care.

Adult Spinal Deformity Surgery and Frailty: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVES

Adult spinal deformity (ASD) can be a debilitating condition with a profound impact on patients' health-related quality of life (HRQoL). Many reports have suggested that the frailty status of a patient can have a significant impact on the outcome of the surgery. The present review aims to identify all pre-operative patient-specific frailty markers that are associated with postoperative outcomes following corrective surgery for ASD of the lumbar and thoracic spine.

METHODS

A systematic review of the literature was performed to identify findings regarding pre-operative markers of frailty and their association with postoperative outcomes in patients undergoing ASD surgery of the lumbar and thoracic spine. The search was performed in the following databases: PubMed, Embase, Cochrane and CINAHL.

RESULTS

An association between poorer performance on frailty scales and worse postoperative outcomes. Comorbidity indices were even more frequently employed with similar patterns of association between increased comorbidity burden and postoperative outcomes. Regarding the assessment of HRQoL, worse pre-operative ODI, SF-36, SRS-22 and NRS were shown to be predictors of post-operative complications, while ODI, SF-36 and SRS-22 were found to improve post-operatively.

CONCLUSIONS

The findings of this review highlight the true breadth of the concept of "frailty" in ASD surgical correction. These parameters, which include frailty scales and various comorbidity and HRQoL indices, highlight the importance of identifying these factors preoperatively to ensure appropriate patient selection while helping to limit poor postoperative outcomes.

Adult Spinal Deformity Surgery Is Associated with Increased Productivity and Decreased Absenteeism From Work and School

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

We hypothesized that adult spinal deformity (ASD) surgery would be associated with improved work- and school-related productivity, as well as decreased rates of absenteeism.

SUMMARY OF BACKGROUND DATA

ASD patients experience markedly decreased health-related quality of life along many dimensions.

METHODS

Only patients eligible for 2-year follow-up were included, and those with a history of previous spinal fusion were excluded. The primary outcome measures in this study were Scoliosis Research Society-22r score (SRS-22r) questions 9 and 17. A repeated measures mixed linear regression was used to analyze responses over time among patients managed operatively (OP) versus nonoperatively (NON-OP).

RESULTS

In total, 1188 patients were analyzed. 66.6% were managed operatively. At baseline, the mean percentage of activity at work/school was 56.4% (standard deviation [SD] 35.4%), and the mean days off from work/school over the past 90 days was 1.6 (SD 1.8). Patients undergoing ASD surgery exhibited an 18.1% absolute increase in work/school productivity at 2-year follow-up versus baseline (P < 0.0001), while no significant change was observed for the nonoperative cohort (P > 0.5). Similarly, the OP cohort experienced 1.1 fewer absent days over the past 90 days at 2 years versus baseline (P < 0.0001), while the NON-OP cohort showed no such difference (P > 0.3). These differences were largely preserved after stratifying by baseline employment status, age group, sagittal vertical axis (SVA), pelvic incidence minus lumbar lordosis (PI-LL), and deformity curve type.

CONCLUSION

ASD patients managed operatively exhibited an average increase in work/school productivity of 18.1% and decreased absenteeism of 1.1 per 90 days at 2-year follow-up, while patients managed nonoperatively did not exhibit change from baseline. Given the age distribution of patients in this study, these findings should be interpreted as pertaining primarily to obligations at work or within the home. Further study of the direct and indirect economic benefits of ASD surgery to patients is warranted.Level of Evidence: 3.

Quality metrics in adult spinal deformity surgery over the last decade: a combined analysis of the largest prospective multicenter data sets

OBJECTIVE

The reported rate of complications and cost of adult spinal deformity (ASD) surgery, associated with an exponential increase in the number of surgeries, cause alarm among healthcare payers and providers worldwide. The authors conjointly analyzed the largest prospective available ASD data sets to define trends in quality-of-care indicators (complications, reinterventions, and health-related quality of life [HRQOL] outcomes) since 2010.

METHODS

This is an observational prospective longitudinal cohort study. Patients underwent surgery between January 2010 and December 2016, with > 2 years of follow-up data. Demographic, surgical, radiological, and HRQOL (i.e., Oswestry Disability Index, SF-36, Scoliosis Research Society-22r) data obtained preoperatively and at 3, 6, 12, and 24 months after surgery were evaluated. Trends and changes in indicators were analyzed using local regression (i.e., locally estimated scatterplot smoothing [LOESS]) and adjusted odds ratio (OR).

RESULTS

Of the 2286 patients included in the 2 registries, 1520 underwent surgery between 2010 and 2016. A total of 1151 (75.7%) patients who were treated surgically at 23 centers in 5 countries met inclusion criteria. Patient recruitment increased progressively (2010-2011 vs 2015-2016: OR 1.64, p < 0.01), whereas baseline clinical characteristics (age, American Society of Anesthesiologists class, HRQOL scores, sagittal deformity) did not change. Since 2010 there has been a sustained reduction in major and minor postoperative complications observed at 90 days (major: OR 0.59; minor: OR 0.65; p < 0.01); at 1 year (major: OR 0.52; minor: 0.75; p < 0.01); and at 2 years of follow-up (major: OR 0.4; minor: 0.80; p < 0.01) as well as in the 2-year reintervention rate (OR 0.41, p < 0.01). Simultaneously, there has been a slight improvement in the correction of sagittal deformity (i.e., pelvic incidence-lumbar lordosis mismatch: OR 1.11, p = 0.19) and a greater gain in quality of life (i.e., Oswestry Disability Index 26% vs 40%, p = 0.02; Scoliosis Research Society-22r, self-image domain OR 1.16, p = 0.13), and these are associated with a progressive reduction of surgical aggressiveness (number of fused segments: OR 0.81, p < 0.01; percent pelvic fixation: OR 0.66, p < 0.01; percent 3-column osteotomies: OR 0.63, p < 0.01).

CONCLUSIONS

The best available data show a robust global improvement in quality metrics in ASD surgery over the last decade. Surgical complications and reoperations have been reduced by half, while improvement in disability increased and correction rates were maintained, in patients with similar baseline characteristics.

The Influence of Baseline Clinical Status and Surgical Strategy on Early Good to Excellent Result in Spinal Lumbar Arthrodesis: A Machine Learning Approach

The study aims to create a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome using a machine learning (ML) approach. A single spine surgery center retrospective review of prospectively collected data from January 2016 to December 2020 from the institutional registry (SpineREG) was performed. The inclusion criteria were age ≥ 18 years, both sexes, lumbar arthrodesis procedure, a complete follow up assessment (Oswestry Disability Index-ODI, SF-36 and COMI back) and the capability to read and understand the Italian language. A delta of improvement of the ODI higher than 12.7/100 was considered a "good early outcome". A combined target model of ODI (Δ ≥ 12.7/100), SF-36 PCS (Δ ≥ 6/100) and COMI back (Δ ≥ 2.2/10) was considered an "excellent early outcome". The performance of the ML models was evaluated in terms of sensitivity, i.e., True Positive Rate (TPR), specificity, i.e., True Negative Rate (TNR), accuracy and area under the receiver operating characteristic curve (AUC ROC). A total of 1243 patients were included in this study. The model for predicting ODI at 6 months' follow up showed a good balance between sensitivity (74.3%) and specificity (79.4%), while providing a good accuracy (75.8%) with ROC AUC = 0.842. The combined target model showed a sensitivity of 74.2% and specificity of 71.8%, with an accuracy of 72.8%, and an ROC AUC = 0.808. The results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

Artificial Intelligence in Adult Spinal Deformity

Artificial Intelligence is gaining traction in medicine for its ease of use and advancements in technology. This study evaluates the current literature on the use of artificial intelligence in adult spinal deformity.

Artificial intelligence for adult spinal deformity: current state and future directions

As we experience a technological revolution unlike any other time in history, spinal surgery as a discipline is poised to undergo a dramatic transformation. As enormous amounts of data become digitized and more readily available, medical professionals approach a critical juncture with respect to how advanced computational techniques may be incorporated into clinical practices. Within neurosurgery, spinal disorders in particular, represent a complex and heterogeneous disease entity that can vary dramatically in its clinical presentation and how it may impact patients' lives. The spectrum of pathologies is extremely diverse, including many different etiologies such as trauma, oncology, spinal deformity, infection, inflammatory conditions, and degenerative disease among others. The decision to perform spine surgery, especially complex spine surgery, involves several nuances due to the interplay of biomechanical forces, bony composition, neurologic deficits, and the patient's desired goals. Adult spinal deformity as an example is one of the most complex, given its involvement of not only the spine, but rather the entirety of the skeleton in order to appreciate radiographic completeness. With the vast array of variables contributing to spinal disorders, treatment algorithms can vary significantly, and it is very difficult for surgeons to predict how patients will respond to surgery. As such, it will become imperative for spine surgeons to utilize the burgeoning availability of advanced computational tools to process unprecedented amounts of data and provide novel insights into spinal disease. These tools range from predictive models built using machine learning algorithms, to deep learning methods for imaging analysis, to natural language processing that can mine text from electronic medical records or transcribed patient visits - all to better treat the intricacies of spinal disorders. The adoption of such techniques will empower patients and propel spine surgeons into the era of personalized medicine, by allowing clinical plans to be tailored to address individual patients' needs. This paper, which exists in the context of a larger body of literatutre, provides a comprehensive review of the current state and future of artificial intelligence and machine learning with a particular emphasis on Adult spinal deformity surgery.

SMART on FHIR in spine: integrating clinical prediction models into electronic health records for precision medicine at the point of care

Recent applications of artificial intelligence have shown great promise for improving the quality and efficiency of clinical care. Numerous clinical decision support tools exist in today's electronic health records (EHRs) such as medication dosing support, order facilitators (eg, procedure specific order sets), and point of care alerts. However, less has been done to integrate artificial intelligence (AI)-enabled risk predictors into EHRs despite wide availability of validated risk prediction tools. An interoperability standard known as SMART on FHIR (substitutable medical applications and reusable technologies on fast health interoperability resources) offers a promising path forward, enabling digital innovations to be seamlessly integrated with the EHR with regard to the user interface and patient data. For the next step in progress towards the goal of learning healthcare and informatics-enabled spine surgery, we propose the application of SMART on FHIR to integrate existing and new risk predictions tools in spine surgery through an EHR add-on-application.

Does state malpractice environment affect outcomes following spinal fusions? A robust statistical and machine learning analysis of 549,775 discharges following spinal fusion surgery in the United States

OBJECTIVE

Spine surgery is especially susceptible to malpractice claims. Critics of the US medical liability system argue that it drives up costs, whereas proponents argue it deters negligence. Here, the authors study the relationship between malpractice claim density and outcomes.

METHODS

The following methods were used: 1) the National Practitioner Data Bank was used to determine the number of malpractice claims per 100 physicians, by state, between 2005 and 2010; 2) the Nationwide Inpatient Sample was queried for spinal fusion patients; and 3) the Area Resource File was queried to determine the density of physicians, by state. States were categorized into 4 quartiles regarding the frequency of malpractice claims per 100 physicians. To evaluate the association between malpractice claims and death, discharge disposition, length of stay (LOS), and total costs, an inverse-probability-weighted regression-adjustment estimator was used. The authors controlled for patient and hospital characteristics. Covariates were used to train machine learning models to predict death, discharge disposition not to home, LOS, and total costs.

RESULTS

Overall, 549,775 discharges following spinal fusions were identified, with 495,640 yielding state-level information about medical malpractice claim frequency per 100 physicians. Of these, 124,425 (25.1%), 132,613 (26.8%), 130,929 (26.4%), and 107,673 (21.7%) were from the lowest, second-lowest, second-highest, and highest quartile states, respectively, for malpractice claims per 100 physicians. Compared to the states with the fewest claims (lowest quartile), surgeries in states with the most claims (highest quartile) showed a statistically significantly higher odds of a nonhome discharge (OR 1.169, 95% CI 1.139-1.200), longer LOS (mean difference 0.304, 95% CI 0.256-0.352), and higher total charges (mean difference [log scale] 0.288, 95% CI 0.281-0.295) with no significant associations for mortality. For the machine learning models-which included medical malpractice claim density as a covariate-the areas under the curve for death and discharge disposition were 0.94 and 0.87, and the R2 values for LOS and total charge were 0.55 and 0.60, respectively.

CONCLUSIONS

Spinal fusion procedures from states with a higher frequency of malpractice claims were associated with an increased odds of nonhome discharge, longer LOS, and higher total charges. This suggests that medicolegal climate may potentially alter practice patterns for a given spine surgeon and may have important implications for medical liability reform. Machine learning models that included medical malpractice claim density as a feature were satisfactory in prediction and may be helpful for patients, surgeons, hospitals, and payers.

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.

Association of Spinal Alignment Correction With Patient-Reported Outcomes in Adult Cervical Deformity: Review of the Literature

Objective

Adult cervical deformity (ACD) is a debilitating spinal condition that causes significant pain, neurologic dysfunction, and functional impairment. Surgery is often performed to correct cervical alignment, but the optimal amount of correction required to improve patient-reported outcomes (PROs) are not yet well-defined.

Methods

A review of the literature was performed and Fisher's z-transformation (Zr) was used to pool the correlation coefficients between alignment parameters and PROs. The strength of correlation was defined according to the following: poor (0 < r ≤ 0.3), fair (0.3 < r ≤ 0.5), moderate (0.5 < r ≤ 0.8), and strong (0.8 < r ≤ 1).

Results

Increased C2-C7 SVA was fairly associated with increased Neck Disability Index (NDI) (pooled Zr = 0.31; 95% CI, -0.03, 0.58). Changes in TS-CL poorly correlated with NDI (pooled Zr = -0.04; 95% CI, -0.23-0.30). Increased C7-S1 was poorly associated with worse EQ-5D (pooled Zr = -0.22; 95% CI, -0.36, -0.06). Correction of horizontal gaze (CBVA) did not correlate with legacy metrics. mJOA correlated with C2-slope, C7-S1, and C2-S1.

Conclusion

Spinal alignment parameters variably correlated with improved HRQoL and myelopathy after corrective surgery for ACD. Further studies evaluating legacy PROs, PROMIS, and ACD specific instruments are needed for further validation.

Narrative Review of Predictive Analytics of Patient-Reported Outcomes in Adult Spinal Deformity Surgery

STUDY DESIGN

Narrative review.

OBJECTIVE

Decision making in surgery for adult spinal deformity (ASD) is complex due to the multifactorial etiology, numerous surgical options, and influence of multiple medical and psychosocial factors on patient outcomes. Predictive analytics provide computational tools to analyze large data sets and generate hypotheses regarding new data. In this review, we examine the use of predictive analytics to predict patient-reported outcomes (PROs) in ASD surgery.

METHODS

A search of PubMed, Web of Science, and Embase databases was performed to identify all potentially relevant studies up to February 1, 2020. Studies were included based on the use of predictive analytics to predict PROs in ASD.

RESULTS

Of 57 studies identified and reviewed, 7 studies were included. Multiple algorithms including supervised and unsupervised methods were used. Significant heterogeneity was observed with choice of PROs modeled including ODI, SRS22, and SF36, assessment of model accuracy, and with the model accuracy and area under the receiver operating curve values (ranging from 30% to 86% and 0.57 to 0.96, respectively). Models were built with data sets of patients ranging from 89 to 570 patients with a range of 22 to 267 variables.

CONCLUSIONS

Predictive analytics makes accurate predictions regarding PROs regarding pain, disability, and work and social function; PROs regarding satisfaction, self-image, and psychologic aspects of ASD were predicted with the lowest accuracy. Our review demonstrates a relative paucity of studies on ASD with limited databases. Future studies should include larger and more diverse databases and provide external validation of preexisting models.

State-of-the-art: outcome assessment in adult spinal deformity

Adult spinal deformity (ASD) is a diagnosis that encompasses heterogeneous disorders with an increasing prevalence. This increasing prevalence may be due to greater patient longevity or greater awareness of available treatments. Outcome assessment in ASD has evolved over the last 3 decades from physician-based assessments to a patient-centered perception of improvement. Outcome assessment that is reliable, accurate and responsive to change is especially important in ASD, as surgical treatment is known to carry a high cost and complication rate Glassman (Spine Deform 3:199-203, 2015); Glassman (Spine (Phila Pa 1976) 32: 2764-2770, 2007); Smith (J Neurosurg Spine 25:1-14, 2016). In an era of value-based care, diagnosis associated with such heterogeneity and high cost must provide sound evidence to support the cost versus outcome ratio. Numerous general health and disease specific patient-reported outcome measures (PROMs) have been utilized in ASD. We discuss these instruments in detail in the following state-of-the-art review.

A narrative review of machine learning as promising revolution in clinical practice of scoliosis

Machine learning (ML), as an advanced domain of artificial intelligence (AI), is progressively changing our view of the world. By implementing its algorithms, our ability to detect previously undiscoverable patterns in data has the potential to revolutionize predictive analytics. Scoliosis, as a relatively specialized branch in the spine field, mainly covers the pediatric, adult and the elderly populations, and its diagnosis and treatment remain difficult. With recent efforts and interdisciplinary cooperation, ML has been widely applied to investigate issues related to scoliosis, and surprisingly augment a surgeon's ability in clinical practice related to scoliosis. Meanwhile, ML models penetrate in every stage of the clinical practice procedure of scoliosis. In this review, we first present a brief description of the application of ML in the clinical practice procedures regarding scoliosis, including screening, diagnosis and classification, surgical decision making, intraoperative manipulation, complication prediction, prognosis prediction and rehabilitation. Meanwhile, the ML models and specific applications adopted are presented. Additionally, current limitations and future directions are briefly discussed regarding its use in the field of scoliosis. We believe that the implementation of ML is a promising revolution to assist surgeons in all aspects of clinical practice related to scoliosis in the near future.

State-of-the-art reviews predictive modeling in adult spinal deformity: applications of advanced analytics

Adult spinal deformity (ASD) is a complex and heterogeneous disease that can severely impact patients' lives. While it is clear that surgical correction can achieve significant improvement of spinopelvic parameters and quality of life measures in adults with spinal deformity, there remains a high risk of complication associated with surgical approaches to adult deformity. Over the past decade, utilization of surgical correction for ASD has increased dramatically as deformity correction techniques have become more refined and widely adopted. Along with this increase in surgical utilization, there has been a massive undertaking by spine surgeons to develop more robust models to predict postoperative outcomes in an effort to mitigate the relatively high complication rates. A large part of this revolution within spine surgery has been the gradual adoption of predictive analytics harnessing artificial intelligence through the use of machine learning algorithms. The development of predictive models to accurately prognosticate patient outcomes following ASD surgery represents a dramatic improvement over prior statistical models which are better suited for finding associations between variables than for their predictive utility. Machine learning models, which offer the ability to make more accurate and reproducible predictions, provide surgeons with a wide array of practical applications from augmenting clinical decision making to more wide-spread public health implications. The inclusion of these advanced computational techniques in spine practices will be paramount for improving the care of patients, by empowering both patients and surgeons to more specifically tailor clinical decisions to address individual health profiles and needs.

Clinical Performance and Concurrent Validity of the Adult Spinal Deformity Surgical Decision-making Score

STUDY DESIGN

Multicenter, retrospective study.

OBJECTIVE

The aim of this study was to examine the performance and concurrent validity of the adult spinal deformity surgical decision-making (ASD-SDM) score compared to decision-making factors in the ASD population.

SUMMARY OF BACKGROUND DATA

The ASD-SDM score, which has been recently proposed, is a scoring system to guide the selection of treatment modality for the ASD population. To secure the justification for its clinical use, it is necessary to verify its clinical performance and concurrent validity.

METHODS

A multicenter prospective ASD database was retrospectively reviewed. The data were analyzed separately in younger (≤40 years) and older (≥41 years) age groups. The discriminating capacity of the ASD-SDM score in cases who selected surgical and nonsurgical management was compared using area under the receiver operator characteristic curves (AUROC). Concurrent validity was examined using Spearman correlation coefficients, comparing factors that are reported to be associated with the decision-making process for ASD, including baseline symptomatology, health-related quality of life measures, and the severity of radiographic spinal deformity.

RESULTS

There were 338 patients (mean age: 26.6 years; 80.8% female; 129 surgical and 209 nonsurgical) in the younger age group and 750 patients (mean age: 63.5 years; 84.3% female; 410 surgical and 340 nonsurgical) in the older age group. In both younger and older patients, the ASD-SDM score showed a significantly higher performance for discriminating the surgical and nonsurgical cases (AUROC: 0.767, standard error [SE]: 0.026, P < 0.001, 95% confidence interval [CI]: 0.712-0.813; AUROC: 0.781, SE: 0.017, P < 0.001, 95% CI: 0.747-0.812, respectively) compared to the decision-making factors analyzed. In addition, the ASD-SDM showed significant correlations with multiple decision-making factors.

CONCLUSION

The ASD-SDM score alone can effectively grade the indication for surgical management whilst considering multiple decision-making factors.

LEVEL OF EVIDENCE

3.

Artificial Intelligence for Adult Spinal Deformity

Adult spinal deformity (ASD) is a complex disease that significantly affects the lives of many patients. Surgical correction has proven to be effective in achieving improvement of spinopelvic parameters as well as improving quality of life (QoL) for these patients. However, given the relatively high complication risk associated with ASD correction, it is of paramount importance to develop robust prognostic tools for predicting risk profile and outcomes. Historically, statistical models such as linear and logistic regression models were used to identify preoperative factors associated with postoperative outcomes. While these tools were useful for looking at simple associations, they represent generalizations across large populations, with little applicability to individual patients. More recently, predictive analytics utilizing artificial intelligence (AI) through machine learning for comprehensive processing of large amounts of data have become available for surgeons to implement. The use of these computational techniques has given surgeons the ability to leverage far more accurate and individualized predictive tools to better inform individual patients regarding predicted outcomes after ASD correction surgery. Applications range from predicting QoL measures to predicting the risk of major complications, hospital readmission, and reoperation rates. In addition, AI has been used to create a novel classification system for ASD patients, which will help surgeons identify distinct patient subpopulations with unique risk-benefit profiles. Overall, these tools will help surgeons tailor their clinical practice to address patients’ individual needs and create an opportunity for personalized medicine within spine surgery.