Predicting complication risk in spine surgery: a prospective analysis of a novel risk assessment tool

Prediction Tools in Spine Surgery: A Narrative Review

There have been increasing reports on prediction models in spine surgery. Interest in prognostic tools or risk calculators can facilitate shared decision-making about treatment between patients and clinicians. In recent years, there has been a steady increase in the number of models developed using varying methods. External validation is an essential component of prediction model testing to ensure the appropriate use of these models in populations outside of the developing center. This narrative review aimed to provide an overview of the literature describing the development and validation of prediction models in the field of spine surgery.

Chondrosarcoma of the Mobile Spine in the Elderly: A National Cancer Database Study

BACKGROUND

The current research on geriatric patients with spinal chondrosarcoma is limited. This study aimed to investigate the demographics, patterns of care, and survival of geriatric patients with chondrosarcoma of the mobile spine.

METHODS

The National Cancer Database was queried from 2008 to 2018 for geriatric patients (60-89 years) with chondrosarcoma of the mobile spine. The primary outcome of this study was overall survival. The secondary outcome was treatment utilization patterns. Survival analyses were conducted using log-rank tests and Cox proportional hazards regressions. Logistic regression models were utilized to assess correlations between baseline variables and treatment utilization.

RESULTS

The database retrieved 122 patients. While 43.7% of the patients presented with tumors exceeding 5 cm in size, the incidence of regional lymph node involvement or distant metastases was relatively low, affecting only 5% of the patients. Furthermore, 22.3% of the patients had tumors graded as 3-4. The 5-year overall survival rate was 52.9% (95% confidence interval: 42-66.6). The mortality risk was significantly associated with age, tumor grade and stage, and treatment plan. Most patients (79.5%) underwent surgery, while 35.9% and 4.2% were treated with radiotherapy and chemotherapy, respectively. Age, race, comorbidities, geographical region, tumor stage, and healthcare facility type significantly correlated with treatment utilization.

CONCLUSIONS

Surgical resection significantly lowered the mortality risk in geriatric patients with spinal chondrosarcomas. Demographic and geographical factors significantly dictated treatment plans. Further studies are required to assess the role of radiotherapy and chemotherapy in treating these patients in the modern era.

Machine-learning-based models for the optimization of post-cervical spinal laminoplasty outpatient follow-up schedules

BACKGROUND

Patients undergo regular clinical follow-up after laminoplasty for cervical myelopathy. However, those whose symptoms significantly improve and remain stable do not need to conform to a regular follow-up schedule. Based on the 1-year postoperative outcomes, we aimed to use a machine-learning (ML) algorithm to predict 2-year postoperative outcomes.

METHODS

We enrolled 80 patients who underwent cervical laminoplasty for cervical myelopathy. The patients' Japanese Orthopedic Association (JOA) scores (range: 0-17) were analyzed at the 1-, 3-, 6-, and 12-month postoperative timepoints to evaluate their ability to predict the 2-year postoperative outcomes. The patient acceptable symptom state (PASS) was defined as a JOA score ≥ 14.25 at 24 months postoperatively and, based on clinical outcomes recorded up to the 1-year postoperative timepoint, eight ML algorithms were developed to predict PASS status at the 24-month postoperative timepoint. The performance of each of these algorithms was evaluated, and its generalizability was assessed using a prospective internal test set.

RESULTS

The long short-term memory (LSTM)-based algorithm demonstrated the best performance (area under the receiver operating characteristic curve, 0.90 ± 0.13).

CONCLUSIONS

The LSTM-based algorithm accurately predicted which group was likely to achieve PASS at the 24-month postoperative timepoint. Although this study included a small number of patients with limited available clinical data, the concept of using past outcomes to predict further outcomes presented herein may provide insights for optimizing clinical schedules and efficient medical resource utilization.

TRIAL REGISTRATION

This study was registered as a clinical trial (Clinical Trial No. NCT02487901), and the study protocol was approved by the Seoul National University Hospital Institutional Review Board (IRB No. 1505-037-670).

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.

Pushing the Limits of Minimally Invasive Spine Surgery-From Preoperative to Intraoperative to Postoperative Management

The introduction of minimally invasive surgery ushered in a new era of spine surgery by minimizing the undue iatrogenic injury, recovery time, and blood loss, among other complications, of traditional open procedures. Over time, technological advancements have further refined the care of the operative minimally invasive spine patient. Moreover, pre-, and postoperative care have also undergone significant change by way of artificial intelligence risk stratification, advanced imaging for surgical planning and patient selection, postoperative recovery pathways, and digital health solutions. Despite these advancements, challenges persist necessitating ongoing research and collaboration to further optimize patient care in minimally invasive spine surgery.

Development of a Prediction Model for Significant Adverse Outcome After Spine Surgery

STUDY DESIGN

Retrospective cohort study.

OBJECTIVES

Development, validation, and decision curve analysis of a novel tool (NZSpine) for modelling risk of complications within 30 days of spine surgery.

METHODS

Data was gathered retrospectively from medical records of patients who underwent spine surgery at a single tertiary centre between January 2019 and December 2020 (n = 488). Postoperative adverse events were classified objectively using the Comprehensive Complication Index (CCI). The model was derived using backward stepwise logistic regression. Validation was undertaken using bootstrap resampling. Discrimination was determined by calculating the area under the receiver operating characteristic (AUC). Calibration was assessed graphically. Clinical utility of the model was assessed using decision curve analysis (DCA). Performance measures were compared to an existing tool, SpineSage.

RESULTS

Overall complication rate was 34%. Modelling showed higher age, surgical invasiveness and preoperative anemia were most strongly predictive of any complication (OR = 1.03, 1.09, 2.1 respectively, P < .001), whereas the occurrence of a major complication (CCI >26) was most strongly associated with the presence of respiratory disease (OR = 2.82, P < .001). At validation, the model showed good discrimination with an AUC of .73 (.71 - .75) and excellent calibration. SpineSage had an AUC of .71, while DCA showed the novel model had greater expected benefit at all risk thresholds.

CONCLUSION

NZSpine is a novel risk assessment tool for patients undergoing acute and elective spine surgery and may help inform clinicians and patients of their perioperative risk.

A meta-analysis of the American college of surgeons risk calculator's predictive accuracy among different surgical sub-specialties

Background

The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) provides risk estimates of postoperative complications. While several studies have examined the accuracy of the ACS-Surgical Risk Calculator (SRC) within a single specialty, the respective conclusions are limited by sample size. We sought to conduct a meta-analysis to determine the accuracy of the ACS-SRC among various surgical specialties.

Study design

Clinical studies that utilized the ACS-SRC, predicted complication rates compared to actual rates, and analyzed at least one metric reported by ACS-SRC met the inclusion criteria. Data for each specialty were pooled using the DerSimonian and Laird random-effect models and analyzed with the binary random-effect model to produce risk difference (RD) and 95 % confidence intervals (CIs) using Open Meta[Analyst].

Results

The initial search yielded 281 studies and, after applying inclusion and exclusion criteria, a total of 53 studies remained with a total sample of 30,134 patients spanning 10 surgical specialties. When considering any complication and death, the ACS-SRC significantly underpredicted complications for: Orthopaedic Surgery (RD -0.067, p = 0.008), Spine (RD -0.027, p < 0.001), Urology (RD -0.03, p < 0.001), Surgical Oncology (RD -0.045, p < 0.001), and Gynecology (RD -0.098, p = 0.01).

Conclusion

The ACS-SRC proved useful in General, Acute Care, Colorectal, Otolaryngology, and Cardiothoracic Surgery, but significantly underpredicted complication rates in Spine, Orthopaedics, Urology, Surgical Oncology, and Gynecology. These data indicate the ACS-SRC is a reliable predictor in some specialties, but its use should be cautioned in the remaining specialties evaluated here.

Utility of preoperative comorbidity burden on PROMIS outcomes after lumbar decompression: Cohort matched analysis

The influence of Charlson Comorbidity Index (CCI) burden on Patient-Reported Outcomes Measurement Information System (PROMIS) outcomes following lumbar decompression (LD) is limited. The objective of this study is to evaluate CCI burden impact on PROMIS outcomes. Retrospective review of elective LD excluding revision or surgeries for infectious, malignant, or traumatic reasons. Demographics and PROMIS scores collected preoperatively and postoperatively up to 2 years included: PROMIS-Physical Function (PF)/Sleep Disturbance (SD)/Pain Interference (PI)/Anxiety (A), VR-12 Physical/Mental Health Composite scores (VR-12 PCS/MCS)/Oswestry Disability Index (ODI). Patients were divided into two groups based on their preoperative CCI score <3 (mild) or ≥4 (moderate to severe). Descriptive statistical analysis and MCID achievement rate calculations were conducted. A total of 182 patients were included: 93 CCI < 3 and 88 CCI ≥ 4. No significant differences were reported across preoperative PROMIS/legacy PROMs or final follow-up (p > 0.05, all). At 6-weeks, VR-12 PCS and ΔPROM scores indicated improved physician function in the CCI < 3 group (p = 0.020 and p = 0.040, respectively). Significant PROMIS-A ΔPROM score at final post-op was noted for CCI < 3 group (p = 0.026). MCID achievement demonstrated no significant differences for PROMIS outcomes and legacy PROMs. Results demonstrated that PROMIS outcomes were not impacted by a greater baseline comorbidity burden. At 6-weeks, the physical function scores were improved for the lower CCI group, and at final reported less anxiety. Our data suggests that comorbidity burden has a limited effect on PROMIS and legacy outcomes in patients undergoing LD.

Perioperative Management for Complex Spine Fusion Surgery

Complex spine surgeries performed worldwide continue to increase in number, as do the age and comorbidity of patients undergoing these operations. Perioperative care protocols related to blood management, postoperative pain control, and intraoperative measures to mitigate morbidity may improve clinical workflows and patient outcomes.

Impact of Patient-Reported Allergies on Post-operative Complications and Healthcare Utilization Following Carpal Tunnel Release

INTRODUCTION

Open carpal tunnel release (O-CTR) is associated with high patient satisfaction and low complication rates. Risk factors for complications are well-established. Recent studies have found that patient-reported allergies (PRAs) and psychiatric comorbidities may be associated with increased complication rates. The impact of these factors after elective hand surgery has not been evaluated. This study sought to identify whether PRAs and psychiatric comorbidities are associated with complications after O-CTR and to evaluate their association with prolonged follow-up and the need for post-operative occupational therapy (OT).

METHODS

Patient demographics, PRAs, Patient Health Questionnaire-2 score, Charlson Comorbidity Index, Carpal Tunnel Symptoms-6 score, postoperative complications, OT utilization, and time to final follow-up were recorded for patients who underwent elective O-CTR between 2014 and 2022. Multivariable binomial logistic regression analysis was used to determine pre-operative variables associated with increased risk for complication.

RESULTS

About 250 patients met the inclusion criteria. Fifty-one (20.4%) patients developed minor complications, including scar tenderness (N=34, 13.6%), superficial wound dehiscence (N=9, 3.6%), and superficial infection (N=8, 3.2%). There were no major complications. Independent risk factors for complications included PRAs (OR 1.80, p<0.01) and PHQ-2 score (OR 1.39, p=0.04). Five or more PRAs and PHQ-2 score ≥3 are significant independent risk factors for increased post-operative complications. Increased PRAs and PHQ-2 scores were associated with longer follow-up (p=0.01 and p<0.01, respectively) but not increased OT utilization.

CONCLUSION

An increased number of PRAs and higher PHQ-2 scores are significant, independent risk factors for minor complications following O-CTR. Risk adjustment and peri-operative counseling should incorporate and account for these variables.

Prophylactic Muscle Flaps Decrease Wound Complication Rates in Patients with Oncologic Spine Disease

BACKGROUND

Patients with oncologic spine disease face a high systemic illness burden and often require surgical intervention to alleviate pain and maintain spine stability. Wound healing complications are the most common reason for reoperation in this population and are known to impact quality of life and initiation of adjuvant therapy. Prophylactic muscle flap (MF) closure is known to reduce wound healing complications in high-risk patients; however, the efficacy in oncologic spine patients is not well established.

METHODS

A collaboration at our institution presented an opportunity to study the outcomes of prophylactic MF closure. The authors performed a retrospective cohort study of patients who underwent MF closure versus a cohort who underwent non-MF closure in the preceding time. Demographic and baseline health data were collected, as were postoperative wound complication data.

RESULTS

A total of 166 patients were enrolled, including 83 patients in the MF cohort and 83 control patients. Patients in the MF group were more likely to smoke ( P = 0.005) and had a higher incidence of prior spine irradiation ( P = 0.002). Postoperatively, five patients (6%) in the MF group developed wound complications, compared with 14 patients (17%) in the control group ( P = 0.028). The most common overall complication was wound dehiscence requiring conservative therapy, which occurred in six control patients (7%) and one MF patient (1%) ( P = 0.053).

CONCLUSIONS

Prophylactic MF closure during oncologic spine surgery significantly reduces the wound complication rate. Future studies should examine the precise patient population that stands to benefit most from this intervention.

CLINICAL QUESTION/LEVEL OF EVIDENCE

Therapeutic, III.

Augmented and virtual reality in spine surgery

Augmented Reality (AR) and Virtual Reality (VR) have developed unprecedentedly in recent years, providing interesting opportunities for medical applications. Their integration into clinical assessment, surgical workflow, and training has shown tremendous potential to improve daily life activity in spine surgery. The paper explores the utilization of VR and AR in spine surgery, with their applications, benefits, challenges, and forthcoming prospects.

Association of telomere length with risk of complications in adult spinal deformity surgery: a pilot study of 43 patients

OBJECTIVE

Risk stratification is a critical element of surgical planning. Early tools were fairly crude, while newer instruments incorporate disease-specific elements and markers of frailty. It is unknown if discrepancies between chronological and cellular age can guide surgical planning or treatment. Telomeres are DNA-protein complexes that serve an important role in protecting genomic DNA. Their shortening is a consequence of aging and environmental exposures, with well-established associations with diseases of aging and mortality. There are compelling data to suggest that telomere length can provide insight toward overall health. The authors sought to determine potential associations between telomere length and postoperative complications.

METHODS

Adults undergoing elective surgery for spinal deformity were prospectively enrolled. Telomere length was measured from preoperative whole blood using quantitative polymerase chain reaction and expressed as the ratio of telomere (T) to single-copy gene (S) abundance (T/S ratio), with higher T/S ratios indicating longer telomere length. Demographic and patient data included age, BMI, and results for the following rating scales: the Adult Spinal Deformity Frailty Index (ASD-FI), Oswestry Disability Index (ODI), Scoliosis Research Society-22r (SRS-22r), American Society of Anesthesiology (ASA) classification, and Charlson Comorbidity Index (CCI). Operative and postoperative complication data (medical or surgical within 90 days) were also collected.

RESULTS

Forty-three patients were enrolled, including 31 women (53%), with a mean age of 66 years and a mean BMI of 28.5. The mean number of levels fused was 11, with 21 (48.8%) combined anterior-posterior approaches. Twenty-two patients (51.2%) had a medical or surgical complication. Patients with a postoperative complication had a significantly lower T/S ratio (0.712 vs 0.813, p = 0.008), indicating shorter telomere length, despite a mild difference in age compared with patients without a postoperative complication (68 vs 63 years, p = 0.069). Patients with complications also had higher CCI scores than patients without complications (2.3 vs 3.8, p = 0.004). There were no significant differences in sex, BMI, ASD-FI score, ASA class, preoperative ODI and SRS-22r scores, number of levels fused, or use of three-column osteotomies. In a multivariate model including age, frailty, ASA class, use of an anterior-posterior approach, CCI score, and telomere length, the authors found that short telomere length was significantly associated with postoperative complications. Patients whose telomere length fell in the shortest quartile had the highest risk (OR 18.184, p = 0.030).

CONCLUSIONS

Short telomere length was associated with an increased risk of postoperative complications despite only a mild difference in chronological age. Increasing comorbidity scores also trended toward significance. Larger prospective studies are needed; however, these data provide a compelling impetus to investigate the role of biological aging as a component of surgical risk stratification.

Increased risks of vertebral fracture and reoperation in primary spinal fusion patients who test positive for osteoporosis by Biomechanical Computed Tomography analysis

BACKGROUND CONTEXT

While osteoporosis is a risk factor for adverse outcomes in spinal fusion patients, diagnosing osteoporosis reliably in this population has been challenging due to degenerative changes and spinal deformities. Addressing that challenge, biomechanical computed tomography analysis (BCT) is a CT-based diagnostic test for osteoporosis that measures both bone mineral density and bone strength (using finite element analysis) at the spine; CT scans taken for spinal evaluation or previous care can be repurposed for the analysis.

PURPOSE

Assess the effectiveness of BCT for preoperatively identifying spinal fusion patients with osteoporosis who are at high risk of reoperation or vertebral fracture.

STUDY DESIGN

Observational cohort study in a multi-center integrated managed care system using existing data from patient medical records and imaging archives.

PATIENT SAMPLE

We studied a randomly sampled subset of all adult patients who had any type of primary thoracic (T4 or below) or lumbar fusion between 2005 and 2018. For inclusion, patients with accessible study data needed a preop CT scan without intravenous contrast that contained images (before any instrumentation) of the upper instrumented vertebral level.

OUTCOME MEASURES

Reoperation for any reason (primary outcome) or a newly documented vertebral fracture (secondary outcome) occurring up to 5 years after the primary surgery.

METHODS

All study data were extracted using available coded information and CT scans from the medical records. BCT was performed at a centralized lab blinded to the clinical outcomes; patients could test positive for osteoporosis based on either low values of bone strength (vertebral strength ≤ 4,500 N women or 6,500 N men) and/or bone mineral density (vertebral trabecular bone mineral density ≤ 80 mg/cm³ both sexes). Cox proportional hazard ratios were adjusted by age, presence of obesity, and whether the fusion was long (four or more levels fused) or short (3 or fewer levels fused); Kaplan-Meier survival was compared by the log rank test. This project was funded by NIH (R44AR064613) and all physician co-authors and author 1 received salary support from their respective departments. Author 6 is employed by, and author 1 has equity in and consults for, the company that provides the BCT test; the other authors declare no conflicts of interest.

RESULTS

For the 469 patients analyzed (298 women, 171 men), median follow-up time was 44.4 months, 11.1% had a reoperation (median time 14.5 months), and 7.7% had a vertebral fracture (median time 2.0 months). Overall, 25.8% of patients tested positive for osteoporosis and no patients under age 50 tested positive. Compared to patients without osteoporosis, those testing positive were at almost five-fold higher risk for vertebral fracture (adjusted hazard ratio 4.7, 95% confidence interval = 2.2-9.7; p<.0001 Kaplan-Meier survival). Of those positive-testing patients, those who tested positive concurrently for low values of both bone strength and bone mineral density (12.6% of patients overall) were at almost four-fold higher risk for reoperation (3.7, 1.9-7.2; Kaplan-Meier survival p<.0001); the remaining positive-testing patients (those who tested positive for low values of either bone strength or bone mineral density but not both) were not at significantly higher risk for reoperation (1.6, 0.7-3.7) but were for vertebral fracture (4.3, 1.9-10.2). For both clinical outcomes, risk remained high for patients who underwent short or long fusion.

CONCLUSION

In a real-world clinical setting, BCT was effective in identifying primary spinal fusion patients aged 50 or older with osteoporosis who were at elevated risks of reoperation and vertebral fracture.

Risk Factors for Postoperative Complications After Surgical Treatment of Type B and C Injuries of the Thoracolumbar Spine

BACKGROUND

Unstable thoracolumbar spinal injuries benefit from surgical fixation. However, perioperative complications significantly affect outcomes in surgicallytreated spine patients. We evaluated associations between risk factors and postoperative complications in patients surgically treated for thoracolumbar spine fractures.

METHODS

We conducted a retrospective multicenter study collating data from 21 spine centers across 9 countries on the treatment of AOSpine types B and C injuries of the thoracolumbar spine treated via a posterior approach. Comparative analysis was performed between patients with postoperative complications and those without. Univariate and multivariable analyses were performed.

RESULTS

Among 535 patients, at least 1 complication occurred in 43%. The most common surgical complication was surgical-site infection (6.9%), while the most common medical complication was urinary tract infection (13.8%). Among 136 patients with American Spinal Injury Association (ASIA) Impairment Scalelevel A disability, 77.9% experienced at least 1 complication. The rate of complications also rose sharply among patients waiting >3 days for surgery (P<0.001), peaking at 68.4% among patients waiting ≥30 days. On multivariable analysis, significant predictors of complications were surgery at a governmental hospital (odds ratio = 3.38, 95% confidence interval = 1.73-6.60), having ≥1 comorbid illness (2.44, 1.61-3.70), surgery delayed due to health instability (2.56, 1.50-4.37), and ASIA Impairment Scalelevel A (3.36, 1.78-6.35), while absence of impairment (0.39, 0.22-0.71), ASIAlevel E (0.39, 0.22-0.67) and, unexpectedly, delay caused by operating room unavailability (0.60, 0.36-0.99) were protective.

CONCLUSIONS

Types B and C thoracolumbar spine injuries are associated with a high risk of postoperative complications, especially common at governmental hospitals, and among patients with comorbidity, health instability, longer delays to surgery, and worse preoperative neurologic status.

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.

Predictive Models for Length of Stay and Discharge Disposition in Elective Spine Surgery: Development, Validation, and Comparison to the ACS NSQIP Risk Calculator

STUDY DESIGN

A retrospective study at a single academic institution.

OBJECTIVE

The purpose of this study is to utilize machine learning to predict hospital length of stay (LOS) and discharge disposition following adult elective spine surgery, and to compare performance metrics of machine learning models to the American College of Surgeon's National Surgical Quality Improvement Program's (ACS NSQIP) prediction calculator.

SUMMARY OF BACKGROUND DATA

A total of 3678 adult patients undergoing elective spine surgery between 2014 and 2019, acquired from the electronic health record.

METHODS

Patients were divided into three stratified cohorts: cervical degenerative, lumbar degenerative, and adult spinal deformity groups. Predictive variables included demographics, body mass index, surgical region, surgical invasiveness, surgical approach, and comorbidities. Regression, classification trees, and least absolute shrinkage and selection operator (LASSO) were used to build predictive models. Validation of the models was conducted on 16% of patients (N=587), using area under the receiver operator curve (AUROC), sensitivity, specificity, and correlation. Patient data were manually entered into the ACS NSQIP online risk calculator to compare performance. Outcome variables were discharge disposition (home vs. rehabilitation) and LOS (days).

RESULTS

Of 3678 patients analyzed, 51.4% were male (n=1890) and 48.6% were female (n=1788). The average LOS was 3.66 days. In all, 78% were discharged home and 22% discharged to rehabilitation. Compared with NSQIP (Pearson R2 =0.16), the predictions of poisson regression ( R2 =0.29) and LASSO ( R2 =0.29) models were significantly more correlated with observed LOS ( P =0.025 and 0.004, respectively). Of the models generated to predict discharge location, logistic regression yielded an AUROC of 0.79, which was statistically equivalent to the AUROC of 0.75 for NSQIP ( P =0.135).

CONCLUSION

The predictive models developed in this study can enable accurate preoperative estimation of LOS and risk of rehabilitation discharge for adult patients undergoing elective spine surgery. The demonstrated models exhibited better performance than NSQIP for prediction of LOS and equivalent performance to NSQIP for prediction of discharge location.

Predicting complications of spine surgery: external validation of three models

BACKGROUND CONTEXT

Numerous prediction tools are available for estimating postoperative risk following spine surgery. External validation and comparison of these tools is critical prior to clinical use. No model for adverse events after spine surgery has undergone decision curve analysis.

PURPOSE

External validation, comparison, and decision curve analysis of 3 previously described models [SpineSage, Risk Assessment Tool (RAT), National Surgical Quality Improvement Program Risk Calculator (NSQIP)] for predicting 30-day postoperative complications after spine surgery STUDY DESIGN: Retrospective cohort study.

PATIENT SAMPLE

Three hundred fifteen patients who underwent spine surgery at a tertiary academic surgical center in New Zealand between January 2019 and April 2020.

OUTCOME MEASURES

As defined by each risk prediction tool and objectively using the Comprehensive Complication Index.

METHODS

We retrospectively reviewed risk of postoperative complication was calculated for each patient according to the 3 models. Overall model fit, calibration, discrimination, and decision curve analysis for each model were assessed in line with the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines.

RESULTS

100 (35%) patients experienced complications. SpineSage and RAT were well calibrated, NSQIP systematically underestimated risk. Area under the curve was greatest for SpineSage (0.75) compared with the NSQIP (0.72) and the RAT (0.69). Decision curve analysis showed SpineSage resulted in greatest net benefit across all risk thresholds.

CONCLUSIONS

Of the models studied, SpineSage most accurately predicted risk and can be expected to perform better than a strategy of treating all patients if patient or surgeon deem complication risk >10% significant. NSQIP may not be suitable for the clinical use in our local population.

Accuracy of Risk Estimation for Surgeons Versus Risk Calculators in Emergency General Surgery

INTRODUCTION

Surgical risk calculators have expanded in both number and sophistication of their predictive approach. These calculators are gaining popularity as validated tools to help surgeons estimate mortality and complications following emergency general surgery (EGS). However, the accuracy of risk estimates generated by these calculators compared to risk estimation by practicing surgeons has not been explored.

METHODS

Acute care surgeons at a quaternary care center prospectively estimated 30-d mortality and complications for adult EGS patients (2019-2021). Surgeon predictions were compared to Predictive OpTimal Trees in Emergency Surgery Risk (POTTER) and NSQIP estimates. Observed-to-expected (O:E) ratios of median aggregate estimates were calculated. C-statistics for surgeon and calculator estimations were utilized to quantify predictive accuracy.

RESULTS

Among 150 patients (median 61 y, 45% male), 30-d mortality was 15% (n = 23). Observed rates of prolonged mechanical ventilation and acute renal failures were 30% and 10%, respectively. Overall, surgeon predictions were similar to risk calculator estimates for mortality (c-statistics 0.843 [surgeon] versus 0.848 [POTTER] and 0.815 [NSQIP]) and need for prolonged ventilation (c-statistics 0.801 versus 0.722 and 0.689, respectively). Surgeons tended to overestimate complication risks. Surgeon experience was not significantly associated with mortality prediction in an adjusted model.

CONCLUSIONS

Acute care surgeons at a quaternary care center predicted postoperative mortality and complications with similar discrimination when compared to surgical risk calculators. Surgeon expertise should be utilized in conjunction with risk calculators when counseling EGS patients regarding anticipated postoperative outcomes. Surgeons should be cognizant of patterns in overestimation or underestimation of complications.

A scoping review of complication prediction models in spinal surgery: An analysis of model development, validation and impact

Background

Predictive analytics are being used increasingly in the field of spinal surgery with the development of models to predict post-surgical complications. Predictive models should be valid, generalizable, and clinically useful. The purpose of this review was to identify existing post-surgical complication prediction models for spinal surgery and to determine if these models are being adequately investigated with internal/external validation, model updating and model impact studies.

Methods

This was a scoping review of studies pertaining to models for the prediction of post-surgical complication after spinal surgery published over 10 years (2010-2020). Qualitative data was extracted from the studies to include study classification, adherence to Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) guidelines and risk of bias (ROB) assessment using the Prediction model study Risk Of Bias Assessment Tool (PROBAST). Model evaluation was determined using area under the curve (AUC) when available. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) statement was used as a basis for the search methodology in four different databases.

Results

Thirty studies were included in the scoping review and 80% (24/30) included model development with or without internal validation. Twenty percent (6/30) were exclusively external validation studies and only one study included an impact analysis in addition to model development and internal validation. Two studies referenced the TRIPOD guidelines and there was a high ROB in 100% of the studies using the PROBAST tool.

Conclusions

The majority of post-surgical complication prediction models in spinal surgery have not undergone standardized model development and internal validation or adequate external validation and impact evaluation. As such there is uncertainty as to their validity, generalizability, and clinical utility. Future efforts should be made to use existing tools to ensure standardization in development and rigorous evaluation of prediction models in spinal surgery.

Indirect Lumbar Decompression Combined With or Without Additional Direct Posterior Decompression: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVE

Indirect decompression via lateral lumbar interbody fusion (LLIF) can ameliorate central and foraminal lumbar stenosis. In severe central stenosis, additional posterior direct decompression is utilized. The aim of this review is to synthesize existing literature on these 2 techniques and identify significant differences in outcomes between isolated indirect decompression via LLIF and combined indirect decompression supplemented with direct posterior decompression.

METHODS

A database search algorithm was utilized to query MEDLINE, COCHRANE, and EMBASE to identify literature reporting adult decompression study groups that involved an oblique or lateral fusion approach through September 2020. Improvement in outcomes measures and complication rates were pooled and tested for significance.

RESULTS

A total of 110 publications were assessed with 15 studies meeting inclusion criteria, including 557 patients and 1008 levels. Mean age was 63.1 years with BMI of 27.5 kg/m². For the combined indirect and direct decompression cohort, lumbar lordosis (LL) increased 133.9%, from 22.8^o to 48.7^o, while the indirect decompression cohort LL increased 8.9%, from 41.9^o to 45.5^o. Difference in LL improvement between cohorts was insignificant (P > .05). Oswestry Disability Index (ODI) decreased from 36.5 to 19.4 in the combined indirect and direct decompression cohort, and from 44.4 to 23.1 in the indirect decompression cohort. ODI reduction was insignificant (P = .053).

CONCLUSIONS

Prior studies of both indirect decompression as well as combined indirect and direct decompression of lumbar spine stenosis are limited by small samples, heterogeneous populations, and lack of direct comparisons. Both procedures result in improved function and pain postoperatively with direct decompression restoring more lordosis in patients with worse preoperative alignment.

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.

Increased risk of postoperative wound complications among obesity classes II & III after ALIF in 10-year ACS-NSQIP analysis of 10,934 cases

BACKGROUND CONTEXT

Anterior lumbar interbody fusion (ALIF) procedures for lumbar spine disease have been increasing amid a growing obese patient population with limited studies available focusing exclusively on risk-factors for post-operative ALIF complications.

PURPOSE

The objective of this study was to compare 30-day post-operative complications among different obesity World Health Organization classes according to body mass index (BMI) in comparison to non-obese patients who underwent an ALIF procedure.

STUDY DESIGN/SETTING

Retrospective cohort study of the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) from 2009 to 2019.

PATIENT SAMPLE

A total of 10,934 patients undergoing an ALIF.

OUTCOME MEASURES

Primary outcome measures include 30 day cardiac, pulmonary, urinary, infectious, and wound complications. Secondary outcomes included rates of blood transfusion, reintubation, deep vein thrombosis, pulmonary embolism, 30-day return to the operating room (OR), and 30 day mortality.

METHODS

Patients were identified by use of the current procedural terminology codes 22558 and 22585 from 2009 to 2019. Patients were divided into the following groups: non-obese (BMI 18.5-29.9 kg/m²), Obese I (BMI 30-34.9 kg/m²), Obese II (BMI 35-39.9 kg/m²), and Obese III (BMI ≥40 kg/m²). Age, gender, race, American Society of Anesthesiologists status, smoking status, hypertension requiring medication, steroid used, chronic obstructive pulmonary disease, history of a bleeding disorder, and diabetes was identified as risk factors after a univariate analysis conducted for demographic variables and pre-operative comorbidities. A multivariate logistic regression analysis was then performed to adjust for these preoperative risk factors and compare obesity classes I-III to non-obese patients.

RESULTS

Obesity classes II and III had a significant odds ratio (OR) for superficial infection (OR:2.7, 95%CI(1.7-4.5); OR:2.8, 95%CI(1.5-5.2) respectively), organ space infection (OR:3.8, 95%CI(1.6-7.4); OR:3.2, 95%CI(1.1-9.9) respectively), wound disruption (OR:2.8, 95%CI(1.1-7.4); OR:4.6, 95%CI(1.6-13.6) respectively), and total wound complication (OR:2.6, 95%CI(1.8-3.9); OR:3.4, 95%CI(2.2-5.4) respectively) following a multivariate logistic regression analysis.

CONCLUSIONS

Risk for post-operative wound complications following an ALIF were found to be significantly higher for obesity classes II-III in comparison to non-obese patients. These findings can further support the use of additional wound care in the perioperative setting for certain levels of obesity.

Association of Mortality and Charlson Comorbidity Index in Surgical Spinal Trauma Patients at a Level I Academic Center

OBJECTIVES

The Charlson Comorbidity Index score (CCI) records the presence of comorbidities with various weights for a total score to estimate mortality within 1 year of hospital admission. Our study sought to assess the association of CCI with mortality rates of patients undergoing surgical intervention.

STUDY DESIGN

Retrospective study.

METHODS

Retrospective study of patients with surgical spinal trauma at a large academic level I trauma tertiary center from 2015 to 2018. Information collected included age, sex, American Society of Anesthesiologists physical status, body mass index, Charlson comorbidities, injury severity score, the presence of spinal cord injury, and mortality. Mortality was measured at 30 days, 90 days, and 1 year. Descriptive and bivariate analyses were completed. The results were significant at P < 0.05.

RESULTS

The highest proportion of 1-year mortality was in the patients with cervical (11.3%) and thoracolumbar injuries (7.4%) (P = 0.002). Patients with low CCI had low 1-year mortality (1.7%). Patients with high CCI had high 1-year mortality (13.8%) (P < 0.001). A significant association existed between CCI and mortality at 30 days, 90 days, and 1 year (P < 0.001). Mortality was higher in patients with spinal cord injury (14/108; 13%) than in those without (11/232; 5%) (P = 0.021). No association existed between ISS and mortality (P = 0.26).

DISCUSSION

The CCI was associated with a higher proportion of deaths at 30 days, 90 days, and 1 year. This association may help predict this unfortunate complication and guide the surgical team in formulating treatment plans and counseling patients and families regarding mortality associated with these injuries and the risks of surgical intervention.

Epidemiological Relevance of Elevated Preoperative Patient Health Questionnaire-9 Scores on Clinical Improvement Following Lumbar Decompression

BACKGROUND

Limited research exists regarding the influence of preoperative depression on postoperative mental health, physical function, and pain in lumbar decompression (LD) patients. This study aims to evaluate the association of depressive symptoms as measured by the Patient Health Questionnaire-9 (PHQ-9) with other mental health and physical function clinical outcomes among patients undergoing LD.

METHODS

A prospectively maintained surgical registry was reviewed for primary LD from March 2016 to May 2019. Patients were stratified into 3 preoperative PHQ-9 score subgroups. Higher PHQ-9 scores indicated greater depressive symptoms. We assessed demographic and perioperative characteristics among subgroups with appropriate statistical testing. We also evaluated outcome instruments and postoperative improvement for the following outcomes: PHQ-9, Short Form 12 (SF-12), Veterans RAND 12-Item (VR-12), Patient-Reported Outcomes Measurement Information System Physical Function (PROMIS-PF), visual analog scale (VAS) leg, and VAS back.

RESULTS

The 351-subject cohort was 70.4% men with an average age of 47 years; 186 subjects had minimal preoperative depressive symptoms (PHQ-9 <5), 94 had moderate (5≤ PHQ-9 ≤10), and 71 had severe (PHQ-9 >10). Subgroups with more severe symptoms of depression had worse mental health outcome scores (PHQ-9, 12-Mental Health Composite Score [12-MCS], and VR-12-MCS) and a positive linear association with greater pre- to postoperative mental health improvements at all timepoints. Subgroups with more severe symptoms of depression had worse PROMIS-PF scores at all timepoints, though VAS pain scores had no depression symptom association by 1 year.

CONCLUSION

Patients with more severe preoperative depressive symptoms, as evaluated by PHQ-9, have a greater improvement in PHQ-9, SF-12, and VR-12 scores, but more severe PHQ-9 scores are associated with worse overall physical function scores. This study demonstrates the relevance of preoperative depressive symptoms and their necessity in future risk factor models.

CLINICAL RELEVANCE

Severity of preoperative PHQ-9 acts as a significant risk factor to postoperative pain and mental and physical health improvement.

Muscle Flap Closures in Spine Surgery: Predictors of Usage Patterns and Factors Associated With Postoperative Complications From the NSQIP Database

STUDY DESIGN

Retrospective cohort study using the National Surgical Quality Improvement Program.

OBJECTIVE

The objective of this study was to identify preoperative factors that impact the decision to perform prophylactic muscle flap closure and assess risk factors for wound healing complications in patients undergoing spinal procedures with and without muscle flap closure.

SUMMARY OF BACKGROUND DATA

Prior studies suggest that muscle flap closure following complex spine surgery results in a lower risk of wound healing complications. However, these studies have been limited to single institutions and/or surgeons.

METHODS

The National Surgical Quality Improvement Program database was queried for all patients undergoing spine surgery between 2005 and 2017 with and without concomitant muscle flaps. Preoperative and perioperative variables were extracted. Univariate and multivariate analyses were performed to assess risk factors influencing surgical site infection (SSI) and wound disruption, as well as to delineate which preoperative factors increased the likelihood of patients receiving flap closures a priori.

RESULTS

Concomitant muscle flaps were performed on 758 patients; 301,670 patients did not receive a flap. Overall 29 (3.83%) patients in the flap group experienced SSI compared to 5154 (1.71%) in the nonflap group (P<0.0001). Preoperative steroid use [odds ratio (OR) 0.5; P<0.0001], wound infection (OR 0.24; P<0.0001), elevated white blood cell count (OR 1.034; P<0.0001), low hematocrit (OR 0.94; P<0.0001), preoperative transfusion (OR 0.22; P=0.0068) were significantly associated with utilization of muscle flaps. Perioperative factors including a contaminated wound (OR 4.72; P<0.0001), the American Society of Anesthesiologists classification of severe disease (OR 1.92; P=0.024), and longer operative time (OR 1.001; P=0.0024) were significantly associated with postoperative wound disruption. In addition, after propensity score matching for these factors that increase risk of wound complications, there was no difference in the rates of SSI between the flap and nonflap group.

CONCLUSION

Our results suggest that patients with a higher burden of illness preoperatively are more likely to receive prophylactic paraspinal flaps which can reduce the rates of wound-related complications.

Deployment of Clinical Prediction Models: A Practical Guide to Nomograms and Online Calculators

The use of predictive models within neurosurgery is increasing and many models described in published journal articles are made available to readers in formats such as nomograms and online calculators. The present chapter details a step-by-step methodology with accompanying R code that may be used to implement models both in the form of traditional nomograms and as open-access, online calculators through RStudio's Shinyapps. The chapter assumes a basic understanding of predictive modeling in R and utilizes open-access files created by the Machine Intelligence in Clinical Neuroscience (MICN) Lab (Department of Neurosurgery and the Clinical Neuroscience Center of the University Hospital Zurich). When implemented correctly, tools such as nomograms and predictive calculators have the potential to improve user understanding of the underlying statistical models, facilitate broader adoption, and to streamline the eventual use of such models in clinical settings.

Chondrosarcoma of the spine: a narrative review

Chondrosarcoma is an uncommon primary bone tumor with an estimated incidence of 0.5 per 100,000 patient-years. Primary chondrosarcoma of the mobile spine and sacrum cumulatively account for less than 20% of all cases, most .commonly causing patients to present with focal pain with or without radiculopathy, or myelopathy secondary to neural element compression. Because of the rarity, patients benefit from multidisciplinary care at academic tertiary-care centers. Current standard-of-care consists of en bloc surgical resection with negative margins; for high grade lesions adjuvant focused radiation with ≥60 gray equivalents is taking an increased role in improving local control. Prognosis is dictated by lesion grade at the time of resection. Several groups have put forth survival calculators and epidemiological evidence suggests prognosis is quite good for lesions receiving R0 resection. Future efforts will be focused on identifying potential chemotherapeutic adjuvants and refining radiation treatments as a means of improving local control.

Predictors of long-term clinical outcomes in adult patients after lumbar total disc replacement: development and validation of a prediction model

OBJECTIVE

Long-term outcomes of single-level lumbar arthroplasty are understood to be very good, with the most recent Investigational Device Exemption (IDE) trial showing a < 5% reoperation rate at the close of the 7-year study. This post hoc analysis was conducted to determine whether specific patients from the activL IDE data set had better outcomes than the mean good outcome of the IDE trial, as well as to identify contributing factors that could be optimized in real-world use.

METHODS

Univariable and multivariable logistic regression models were developed using the randomized patient set (n = 283) from the activL trial and used to identify predictive factors and to derive risk equations. The models were internally validated using the randomized patient set and externally validated using the nonrandomized patient set (n = 52) from the activL trial. Predictive power was assessed using area under the receiver operating characteristic curve analysis.

RESULTS

Two factors were significantly associated with achievement of better than the mean outcomes at 7 years. Randomization to receive the activL device was positively associated with better than the mean visual analog scale (VAS)-back pain and Oswestry Disability Index (ODI) scores, whereas preoperative narcotics use was negatively associated with better than the mean ODI score. Preoperative narcotics use was also negatively associated with return to unrestricted full-time work. Other preoperative factors associated with positive outcomes included unrestricted full-time work, working manual labor after index back injury, and decreasing disc height. Older age, greater VAS-leg pain score, greater ODI score, female sex, and working manual labor before back injury were identified as preoperative factors associated with negative outcomes. Preoperative BMI, VAS-back pain score, back pain duration ≥ 1 year, SF-36 physical component summary score, and recreational activity had no effect on outcomes.

CONCLUSIONS

Lumbar total disc replacement for symptomatic single-level lumbar degenerative disc disease is a well-established option for improving long-term patient outcomes. Discontinuing narcotics use may further improve patient outcomes, as this analysis identified associations between no preoperative narcotics use and better ODI score relative to the mean score of the activL trial at 7 years and increased likelihood of return to work within 7 years. Other preoperative factors that may further improve outcomes included unrestricted full-time work, working manual labor despite back injury, sedentary work status before back injury, and randomization to receive the activL device. Tailoring patient care before total disc replacement may further improve patient outcomes.

Comparison of Cost and Perioperative Outcome Profiles for Primary and Revision Posterior Cervical Fusion Procedures

STUDY DESIGN

Retrospective analysis.

OBJECTIVE

To compare perioperative outcomes and hospitalization costs between patients undergoing primary or revision posterior cervical discectomy and fusion (PCDF).

SUMMARY OF BACKGROUND DATA

While prior studies found differences in outcomes between primary and revision anterior cervical discectomy and fusion (ACDF), risk, and outcome profiles for posterior cervical revision procedures have not yet been elucidated.

METHODS

Institutional records were queried for cases involving isolated PCDF procedures to evaluate preoperative characteristics and outcomes for patients undergoing primary versus revision PCDF between 2008 and 2016. The primary outcome was perioperative complications, while perioperative and resource utilization measures such as hospitalization length, required stay in the intensive care unit (ICU), direct hospitalization costs, and 30-day emergency department (ED) admissions were explored as secondary outcomes.

RESULTS

One thousand one hundred twenty four patients underwent PCDF, with 218 (19.4%) undergoing a revision procedure. Patients undergoing revision procedures were younger (53.0 vs. 60.5 yrs), but had higher Elixhauser scores compared with the non-revision cohort. Revision cases tended to involve fewer spinal segments (3.6 vs. 4.1 segments) and shorter surgical durations (179.3 vs. 206.3 min), without significant differences in estimated blood loss. There were no significant differences in the overall complication rates (P = 0.20), however, the primary cohort had greater rates of required ICU stays (P = 0.0005) and non-home discharges (P = 0.0003). The revision cohort did experience significantly increased odds of 30-day ED admission (P = 0.04) and had higher direct hospitalization (P = 0.03) and surgical (P < 0.0001) costs.

CONCLUSION

Complication rates, including incidental durotomy, were similar between primary and revision PCDF cohorts. Although prior surgery status did not predict complication risk, comorbidity burden did. Nevertheless, patients undergoing revision procedures had decreased risk of required ICU stay but greater risk of 30-day ED admission and higher direct hospitalization and surgical costs.Level of Evidence: 3.

Utilizing the Most Accurate Preoperative Risk Calculator

The most commonly used preoperative assessment tools include the American College of Surgeons National Surgical Quality Improvement Program and the Revised Cardiac Risk Index. These tools seek to predict the risk of an individual experiencing postoperative complications, including but not limited to mortality, myocardial infarction, pneumonia, stroke, venous thromboembolism, and pneumonia. Many published studies have sought to objectively quantify the utility of the preoperative risk calculations by retrospectively compiling data for patients who underwent the same or comparable surgeries to compare actual complications to predicted complications. Therefore, we searched these studies to review the literature to draw more general conclusions and recommend which risk calculator is best for different types of surgeries.

Administrative Data Are Unreliable for Ranking Hospital Performance Based on Serious Complications After Spine Fusion

STUDY DESIGN

Retrospective analysis of administrative billing data.

OBJECTIVE

To evaluate the extent to which a metric of serious complications determined from administrative data can reliably profile hospital performance in spine fusion surgery.

SUMMARY OF BACKGROUND DATA

While payers are increasingly focused on implementing pay-for-performance measures, quality metrics must reliably reflect true differences in performance among the hospitals profiled.

METHODS

We used State Inpatient Databases from nine states to characterize serious complications after elective cervical and thoracolumbar fusion. Hierarchical logistic regression was used to risk-adjust differences in case mix, along with variability from low case volumes. The reliability of this risk-stratified complication rate (RSCR) was assessed as the variation between hospitals that was not due to chance alone, calculated separately by fusion type and year. Finally, we estimated the proportion of hospitals that had sufficient case volumes to obtain reliable (>0.7) complication estimates.

RESULTS

From 2010 to 2017 we identified 154,078 cervical and 213,133 thoracolumbar fusion surgeries. 4.2% of cervical fusion patients had a serious complication, and the median RSCR increased from 4.2% in 2010 to 5.5% in 2017. The reliability of the RSCR for cervical fusion was poor and varied substantially by year (range 0.04-0.28). Overall, 7.7% of thoracolumbar fusion patients experienced a serious complication, and the RSCR varied from 6.8% to 8.0% during the study period. Although still modest, the RSCR reliability was higher for thoracolumbar fusion (range 0.16-0.43). Depending on the study year, 0% to 4.5% of hospitals had sufficient cervical fusion case volume to report reliable (>0.7) estimates, whereas 15% to 36% of hospitals reached this threshold for thoracolumbar fusion.

CONCLUSION

A metric of serious complications was unreliable for benchmarking cervical fusion outcomes and only modestly reliable for thoracolumbar fusion. When assessed using administrative datasets, these measures appear inappropriate for high-stakes applications, such as public reporting or pay-for-performance.Level of Evidence: 3.

The Influence of Comorbidity on Postoperative Outcomes Following Lumbar Decompression

STUDY DESIGN

Retrospective.

OBJECTIVE

Evaluate the association between comorbidity burden and reaching minimum clinically important difference (MCID) following lumbar decompression (LD).

SUMMARY OF BACKGROUND DATA

There is limited research on the influence of preoperative comorbidity burden on patient-reported outcome improvement following LD.

METHODS

A prospectively maintained surgical registry was retrospectively reviewed for eligible spine surgeries between 2015 and 2019. Inclusion criteria were primary, single, or multilevel LD. Patients were excluded for missing preoperative patient-reported outcome surveys. Stratification was based on Charlson Comorbidity Index (CCI) score: 0 points (no comorbidities), 1-2 points (low CCI), ≥3 points (high CCI). Demographics and perioperative characteristics were evaluated for differences. Linear regression assessed postoperative improvement for visual analogue scale (VAS) back, VAS leg, Oswestry disability index (ODI), Short Form-12 Physical Composite Score (SF-12 PCS), and Patient-Reported Outcomes Measurement Information System physical function (PROMIS-PF) scores through 1 year. Achievement rate of MCID was compared between groups and evaluated for significant predictors.

RESULTS

Three hundred fourteen patients were included (123 no comorbidities, 100 low CCI, 91 high CCI). Higher CCI patients were older, more likely to smoke, and have comorbid diseases (all P<0.001). Perioperative differences included increased operative time, levels decompressed, length of stay, and discharge day in the CCI≥3 group. No differences in the rate of achieving MCID for VAS back, VAS leg, and ODI. CCI≥3 subgroup had a lower rate of reaching MCID at 6 months for SF-12 PCS, at 6 weeks for PROMIS-PF, and the overall rate for both SF-12 PCS and PROMIS-PF (all P<0.05). Multilevel procedures was a predictor for MCID achievement for ODI.

CONCLUSIONS

Patients with increased comorbidities undergoing LD had an equivalent MCID achievement rate for pain and disability metrics through 1 year. High CCI patients did, however, have a lower rate of achieving MCID for their physical function surveys which suggests that comorbidity burden influences improvement in physical function following LD.

Prediction of Major Complications and Readmission After Lumbar Spinal Fusion: A Machine Learning-Driven Approach

BACKGROUND

Given the significant cost and morbidity of patients undergoing lumbar fusion, accurate preoperative risk-stratification would be of great utility. We aim to develop a machine learning model for prediction of major complications and readmission after lumbar fusion. We also aim to identify the factors most important to performance of each tested model.

METHODS

We identified 38,788 adult patients who underwent lumbar fusion at any California hospital between 2015 and 2017. The primary outcome was major perioperative complication or readmission within 30 days. We build logistic regression and advanced machine learning models: XGBoost, AdaBoost, Gradient Boosting, and Random Forest. Discrimination and calibration were assessed using area under the receiver operating characteristic curve and Brier score, respectively.

RESULTS

There were 4470 major complications (11.5%). The XGBoost algorithm demonstrates the highest discrimination of the machine learning models, outperforming regression. The variables most important to XGBoost performance include angina pectoris, metastatic cancer, teaching hospital status, history of concussion, comorbidity burden, and workers' compensation insurance. Teaching hospital status and concussion history were not found to be important for regression.

CONCLUSIONS

We report a machine learning algorithm for prediction of major complications and readmission after lumbar fusion that outperforms logistic regression. Notably, the predictors most important for XGBoost differed from those for regression. The superior performance of XGBoost may be due to the ability of advanced machine learning methods to capture relationships between variables that regression is unable to detect. This tool may identify and address potentially modifiable risk factors, helping risk-stratify patients and decrease complication rates.

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.

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.

Complications After Adult Spinal Deformity Surgeries: All Are Not Created Equal

BACKGROUND

Data on timing of complications are important for accurate quality assessments. We sought to better define pre- and postdischarge complications occurring within 90 days of adult spinal deformity (ASD) surgery and quantify the effect of multiple complications on recovery.

METHODS

We performed a review of 1040 patients who underwent ASD surgery (age: 46 ± 23; body mass index: 25 ± 7, American Society of Anesthesiologists [ASA] score: 2.5 ± 0.6, levels: 10 ± 4, revision: 9%, 3-column osteotomy: 13%). We assessed pre- and postdischarge complications and risk factors for isolated versus multiple complications, as well as the impact of multiple complications.

RESULTS

The 90-day complication rate was 17.7%. 85 patients (8.2%) developed a predischarge complication, most commonly ileus (12%), and pulmonary embolism (PE; 7.1%). The most common causes of predischarge unplanned reoperation were neurologic injury (12.9%) and surgical site drainage (8.2%). Predictors of a predischarge complication included smoking (odds ratio [OR]: 2.2, P = .02), higher ASA (OR: 1.8, P = .008), hypertension (HTN; OR: 2.0, P = .004), and iliac fixation (OR: 4.3, P < .001). Ninety-nine patients (9.5%) developed a postdischarge complication, most commonly infection (34%), instrumentation failure (13.4%), and proximal junctional failure (10.4%). Predictors of postdischarge complications included chronic obstructive pulmonary disease (OR: 3.6, P < .0001), congestive heart failure (OR: 4.4, P = .016), HTN (OR: 2.3, P < .0001), and multiple rod construct (OR: 1.8, P = .02). Patients who developed multiple complications (9.3%) had a longer length of stay, and increased risk for readmission and unplanned reoperation.

CONCLUSIONS

Knowledge regarding timing of postoperative complications in relation to discharge may better inform quality improvement measures. PE and implant-related complications play a prominent role in perioperative complications and need for readmission, with several modifiable risk factors identified.

LEVEL OF EVIDENCE

Level 3.

CLINICAL RELEVANCE

Advances in surgical techniques and instrumentation have improved postoperative radiographic and clinical outcomes after ASD surgery. The rate of complications after complex ASD surgery remains high, both at early postoperative and long term follow-up. This study reviews complications within 90 days of surgery, with an assessment of patient and surgical risk factors. We found that modifiable risk factors for early complications after ASD surgery include COPD, and current smoking. The data presented in this study also provide surgeons with knowledge of the most common complications encountered after ASD surgery, to aid in preoperative patient discussion.

Complication Events After Spinal Surgery Performed by American Board of Orthopaedic Surgery (ABOS) Part II Candidates (2008-2017)

STUDY DESIGN

Retrospective cohort study.

OBJECTIVE

To evaluate complications following spine surgery using American Board of Orthopaedic Surgeons (ABOS) Part II examination data from 2008 to 2017.

SUMMARY OF BACKGROUND DATA

Recent research has demonstrated the importance of surgical experience and clinical volume in minimizing complications after spine surgery. This may be challenging for orthopedic spine surgeons who are just starting their practice.

METHODS

We performed a retrospective review of surgical cases submitted to the ABOS by candidates taking the Part II Spine examination between 2008 and 2017. Complications, including peri-operative mortality as reported by candidates to the ABOS, were tracked over time. Complications were classified as surgical or medical using a predefined algorithm. Multivariable Poisson regression analyses adjusting for confounders were used to assess rates of complications and mortality over time. All analyses controlled for biologic sex, age, surgical diagnosis, and surgical location.

RESULTS

A total of 37,539 spine surgical patients were analyzed, with an average of 3754 cases performed each year. Following adjusted Poisson analysis, we determined that cases in 2017 had an increased likelihood of complications when compared to those treated in 2008 (IRR 1.20; 95% CI 1.09, 1.32). Similar findings were encountered for surgical complications (IRR 1.20; 95% CI 1.07, 1.34). In contrast, spine surgical cases reported to the ABOS in 2017 had a 55% lower likelihood of mortality when compared to procedures performed in 2008 (IRR 0.45; 95% CI 0.24, 0.84; P = 0.01).

CONCLUSIONS

Our analysis of ABOS Part II candidates demonstrates that reported complication rates may be increasing while mortality is decreasing. The etiologies behind these findings are likely multifactorial. Encouragingly, we believe that observed reductions in mortality suggest overall improvements in patient safety following spine surgery. At a minimum, our data provide benchmarks through which spine surgeons, hospitals, and residency or fellowship programs can evaluate performance.Level of Evidence: 4.

Compilation and Analysis of Web-Based Orthopedic Personalized Predictive Tools: A Scoping Review

Web-based personalized predictive tools in orthopedic surgery are becoming more widely available. Despite rising numbers of these tools, many orthopedic surgeons may not know what tools are available, how these tools were developed, and how they can be utilized. The aim of this scoping review is to compile and synthesize the profile of existing web-based orthopedic tools. We conducted two separate PubMed searches-one a broad search and the second a more targeted one involving high impact journals-with the aim of comprehensively identifying all existing tools. These articles were then screened for functional tool URLs, methods regarding the tool's creation, and general inputs and outputs required for the tool to function. We identified 57 articles, which yielded 31 unique web-based tools. These tools involved various orthopedic conditions (e.g., fractures, osteoarthritis, musculoskeletal neoplasias); interventions (e.g., fracture fixation, total joint arthroplasty); outcomes (e.g., mortality, clinical outcomes). This scoping review highlights the availability and utility of a vast array of web-based personalized predictive tools for orthopedic surgeons. Increased awareness and access to these tools may allow for better decision support, surgical planning, post-operative expectation management, and improved shared decision-making.

Systematic review and evaluation of predictive modeling algorithms in spinal surgeries

In order to better educate patients, predictive models have been implemented to stratify surgical risk, thereby instituting greater uniformity across surgical practices and prioritizing the safety and outcomes of patients. The purpose of this study is to conduct a systematic review summarizing the major predictive models used to evaluate patients as candidates for spinal surgery. A search was conducted for articles related to predictive modeling in spinal surgeries using PubMed, MEDLINE, and Scopus databases. Papers with area under the receiver operating curve (AUROC) scores reported were included in the analysis. Models not relevant to spinal procedures were excluded. Comparison between models was only attainable for those that reported AUROCs for individual procedures. Based on a combination of AUROC scores and demonstrated applicability to spinal procedures, the models by Scheer et al. (0.89), Ratliff et al. (0.70), the Seattle Spine Score (0.712), Risk Assessment Tool (0.67-0.7), and the Spine Sage calculator (0.81-0.85) were determined to be ideal for predictive modeling in spinal surgeries and were subsequently broken down into their individual inputs and outputs to determine what elements a theoretical model should assimilate. Alongside the model by Scheer et al., the Spine Sage calculator, Seattle Spine Score, Risk Assessment Tool, and a model by Ratliff et al. showed the most promise for patients undergoing spinal procedures. Using the first model as a springboard, new spinal predictive models can be optimized through use of larger prospective databases, with longer follow-up times, and greater inclusion of reliable high impact variables.

Adverse Events and Bundled Costs after Cranial Neurosurgical Procedures: Validation of the LACE Index Across 40,431 Admissions and Development of the LACE-Cranial Index

OBJECTIVE

Anticipating postdischarge complications after neurosurgery remains difficult. The LACE index, based on 4 hospitalization descriptors, stratifies patients by risk of 30-day postdischarge adverse events but has not been validated in a procedure-specific manner in neurosurgery. Our study sought to explore the usefulness of the LACE index in a population undergoing cranial neurosurgery and to develop an enhanced model, LACE-Cranial.

METHODS

The OptumClinformatics Database was used to identify cranial neurosurgery admissions (2004-2017). Procedures were grouped as trauma/hematoma/intracranial pressure, open vascular, functional/pain, skull base, tumor, or endovascular. Adverse events were defined as postdischarge death/readmission. LACE-Cranial was developed using a logistic regression framework incorporating an expanded feature set in addition to the original LACE components.

RESULTS

A total of 40,431 admissions were included. Predictions of 30-day readmissions was best for skull base (area under the curve [AUC], 0.636) and tumor (AUC, 0.63) admissions but was generally poor. Predictive ability of 30-day mortality was best for functional/pain admissions (AUC, 0.957) and poorest for trauma/hematoma/intracranial pressure admissions (AUC, 0.613). Across procedure types except for functional/pain, a high-risk LACE score was associated with higher postdischarge bundled payment costs. Incorporating features identified to contribute independent predictive value, the LACE-Cranial model achieved procedure-specific 30-day mortality AUCs ranging from 0.904 to 0.98. Prediction of 30-day and 90-day readmissions was also improved, with tumor and skull base cases achieving 90-day readmission AUCs of 0.718 and 0.717, respectively.

CONCLUSIONS

Although the unmodified LACE index shows inconsistent classification performance, the enhanced LACE-Cranial model offers excellent prediction of short-term postdischarge mortality across procedure groups and significantly improved anticipation of short-term postdischarge readmissions.

Consent for spine surgery: an observational study

BACKGROUND

The tension between the ideal of informed consent and the reality of the process is under-investigated in spine surgery. Guidelines around consent imply a logical, plain-speaking process with a clear endpoint, agreement and signature yet surgeons' surveys and patient interviews suggest that surgeons' explanation is anecdotally variable and patient understanding remains poor. To obtain a more authentic reflection of practice, spine surgeons obtaining 'informed consent' for non-instrumented spine surgery were studied via video recording and risk/benefit discussions were analysed.

METHODS

A prospective observational study was conducted at a single neurosurgical institution. Twelve video recordings involving six surgeons obtaining an informed consent for non-instrumented spine surgery were transcribed verbatim and blindly analysed using descriptive quantification and linguistic ethnography.

RESULTS

Ten (83%) consultations discussed surgical benefit but less than half (41%) quantified the likelihood of benefit from surgery. The most discussed risks were nerve damage or paralysis (92%), bleeding (92%), infection (92%), cerebrospinal fluid leak (83%) and bowel and bladder dysfunction (75%). Surgeons commonly used a quantitative statement of risk (58%) but only half of the risks were explained in words patients were likely to understand.

CONCLUSIONS

This study highlights inconsistencies in the way spine surgeons explain risks and obtain informed consent for 'simple' spine procedures in a real-world setting. There are wide disparities in the provision of informed consent, which may be encountered in other surgical fields. Direct observation and qualitative analysis can provide insights into the limitations of current informed consent practice and help guide future practice.

Can the Charlson Comorbidity Index be used to predict the ASA grade in patients undergoing spine surgery?

BACKGROUND

The American Society of Anaesthesiologists' Physical Status Score (ASA) is a key variable in predictor models of surgical outcome and "appropriate use criteria". However, at the time when such tools are being used in decision-making, the ASA rating is typically unknown. We evaluated whether the ASA class could be predicted statistically from Charlson Comorbidy Index (CCI) scores and simple demographic variables.

METHODS

Using established algorithms, the CCI was calculated from the ICD-10 comorbidity codes of 11'523 spine surgery patients (62.3 ± 14.6y) who also had anaesthetist-assigned ASA scores. These were randomly split into training (N = 8078) and test (N = 3445) samples. A logistic regression model was built based on the training sample and used to predict ASA scores for the test sample and for temporal (N = 341) and external validation (N = 171) samples.

RESULTS

In a simple model with just CCI predicting ASA, receiver operating characteristics (ROC) analysis revealed a cut-off of CCI ≥ 1 discriminated best between being ASA ≥ 3 versus < 3 (area under the curve (AUC), 0.70 ± 0.01, 95%CI,0.82-0.84). Multiple logistic regression analyses including age, sex, smoking, and BMI in addition to CCI gave better predictions of ASA (Nagelkerke's pseudo-R² for predicting ASA class 1 to 4, 46.6%; for predicting ASA ≥ 3 vs.  < 3, 37.5%). AUCs for discriminating ASA ≥ 3 versus < 3 from multiple logistic regression were 0.83 ± 0.01 (95%CI, 0.82-0.84) for the training sample and 0.82 ± 0.01 (95%CI, 0.81-0.84), 0.85 ± 0.02 (95%CI, 0.80-0.89), and 0.77 ± 0.04 (95%CI,0.69-0.84) for the test, temporal and external validation samples, respectively. Calibration was adequate in all validation samples.

CONCLUSIONS

It was possible to predict ASA from CCI. In a simple model, CCI ≥ 1 best distinguished between ASA ≥ 3 and < 3. For a more precise prediction, regression algorithms were created based on CCI and simple demographic variables obtainable from patient interview. The availability of such algorithms may widen the utility of decision aids that rely on the ASA, where the latter is not readily available.

The F2RaD Score: A Novel Prediction Score and Calculator Tool to Identify Patients at Risk of Postoperative C5 Palsy

BACKGROUND

Postoperative C5 palsy is a debilitating complication following posterior cervical decompression.

OBJECTIVE

To create a simple clinical risk score predicting the occurrence of C5 palsy

METHODS

We retrospectively reviewed all patients who underwent posterior cervical decompressions between 2007 and 2017. Data was randomly split into training and validation datasets. Multivariable analysis was performed to construct the model from the training dataset. A scoring system was developed based on the model coefficients and a web-based calculator was deployed.

RESULTS

The cohort consisted of 415 patients, of which 65 (16%) developed C5 palsy. The optimal model consisted of: mean C4/5 foraminal diameter (odds ratio [OR] = 9.1 for lowest quartile compared to highest quartile), preoperative C5 radiculopathy (OR = 3.5), and dexterity loss (OR = 2.9). The receiver operating characteristic yielded an area under the curve of 0.757 and 0.706 in the training and validation datasets, respectively. Every characteristic was worth 1 point except the lowest quartile of mean C4/5 foraminal diameter, which was worth 2 points, and the factors were summarized by the acronym F2RaD. The median predicted probability of C5 palsy increased from 2% in patients with a score of 0 to 70% in patients with a score of 4. The calculator can be accessed on https://jhuspine2.shinyapps.io/FRADscore/.

CONCLUSION

This study yielded a simplified scoring system and clinical calculator that predicts the occurrence of C5 palsy. Individualized risk prediction for patients may facilitate better understanding of the risks and benefits for an operation, and better prepare them for this possible adverse outcome. Furthermore, modifying the surgical plan in high-risk patients may possibly improve outcomes.

Data for registry and quality review can be retrospectively collected using natural language processing from unstructured charts of arthroplasty patients

Aims

Natural Language Processing (NLP) offers an automated method to extract data from unstructured free text fields for arthroplasty registry participation. Our objective was to investigate how accurately NLP can be used to extract structured clinical data from unstructured clinical notes when compared with manual data extraction.

Methods

A group of 1,000 randomly selected clinical and hospital notes from eight different surgeons were collected for patients undergoing primary arthroplasty between 2012 and 2018. In all, 19 preoperative, 17 operative, and two postoperative variables of interest were manually extracted from these notes. A NLP algorithm was created to automatically extract these variables from a training sample of these notes, and the algorithm was tested on a random test sample of notes. Performance of the NLP algorithm was measured in Statistical Analysis System (SAS) by calculating the accuracy of the variables collected, the ability of the algorithm to collect the correct information when it was indeed in the note (sensitivity), and the ability of the algorithm to not collect a certain data element when it was not in the note (specificity).

Results

The NLP algorithm performed well at extracting variables from unstructured data in our random test dataset (accuracy = 96.3%, sensitivity = 95.2%, and specificity = 97.4%). It performed better at extracting data that were in a structured, templated format such as range of movement (ROM) (accuracy = 98%) and implant brand (accuracy = 98%) than data that were entered with variation depending on the author of the note such as the presence of deep-vein thrombosis (DVT) (accuracy = 90%).

Conclusion

The NLP algorithm used in this study was able to identify a subset of variables from randomly selected unstructured notes in arthroplasty with an accuracy above 90%. For some variables, such as objective exam data, the accuracy was very high. Our findings suggest that automated algorithms using NLP can help orthopaedic practices retrospectively collect information for registries and quality improvement (QI) efforts. Cite this article: Bone Joint J 2020;102-B(7 Supple B):99–104.

Analysis and Review of Automated Risk Calculators Used to Predict Postoperative Complications After Orthopedic Surgery

PURPOSE OF REVIEW

To discuss the automated risk calculators that have been developed and evaluated in orthopedic surgery.

RECENT FINDINGS

Identifying predictors of adverse outcomes following orthopedic surgery is vital in the decision-making process for surgeons and patients. Recently, automated risk calculators have been developed to quantify patient-specific preoperative risk associated with certain orthopedic procedures. Automated risk calculators may provide the orthopedic surgeon with a valuable tool for clinical decision-making, informed consent, and the shared decision-making process with the patient. Understanding how an automated risk calculator was developed is arguably as important as the performance of the calculator. Additionally, conveying and interpreting the results of these risk calculators with the patient and its influence on surgical decision-making are paramount. The most abundant research on automated risk calculators has been conducted in the spine, total hip and knee arthroplasty, and trauma literature. Currently, many risk calculators show promise, but much research is still needed to improve them. We recommend they be used only as adjuncts to clinical decision-making. Understanding how a calculator was developed, and accurate communication of results to the patient, is paramount.

Predicting Patient-Centered Outcomes from Spine Surgery Using Risk Assessment Tools: a Systematic Review

PURPOSE OF REVIEW

The purpose of this systematic review is to evaluate the current literature in patients undergoing spine surgery in the cervical, thoracic, and lumbar spine to determine the available risk assessment tools to predict the patient-centered outcomes of pain, disability, physical function, quality of life, psychological disposition, and return to work after surgery.

RECENT FINDINGS

Risk assessment tools can assist surgeons and other healthcare providers in identifying the benefit-risk ratio of surgical candidates. These tools gather demographic, medical history, and other pertinent patient-reported measures to calculate a probability utilizing regression or machine learning statistical foundations. Currently, much is still unknown about the use of these tools to predict quality of life, disability, and other factors following spine surgery. A systematic review was conducted using PRISMA guidelines that identified risk assessment tools that utilized patient-reported outcome measures as part of the calculation. From 8128 identified studies, 13 articles met inclusion criteria and were accepted into this review. The range of c-index values reported in the studies was between 0.63 and 0.84, indicating fair to excellent model performance. Post-surgical patient-reported outcomes were identified in the following categories (n = total number of predictive models): return to work (n = 3), pain (n = 9), physical functioning and disability (n = 5), quality of life (QOL) (n = 6), and psychosocial disposition (n = 2). Our review has synthesized the available evidence on risk assessment tools for predicting patient-centered outcomes in patients undergoing spine surgery and described their findings and clinical utility.