Reliable Prediction of Discharge Disposition Following Cervical Spine Surgery With Ensemble Machine Learning and Validation on a National Cohort.

STUDY DESIGN: A retrospective cohort study. OBJECTIVE: The purpose of this study is to develop a machine learning algorithm to predict nonhome discharge after cervical spine surgery that is validated and usable on a national scale to ensure generalizability and elucidate candidate drivers for prediction. SUMMARY OF BACKGROUND DATA: Excessive length of hospital stay can be attributed to delays in postoperative referrals to intermediate care rehabilitation centers or skilled nursing facilities. Accurate preoperative prediction of patients who may require access to these resources can facilitate a more efficient referral and discharge process, thereby reducing hospital and patient costs in addition to minimizing the risk of hospital-acquired complications. METHODS: Electronic medical records were retrospectively reviewed from a single-center data warehouse (SCDW) to identify patients undergoing cervical spine surgeries between 2008 and 2019 for machine learning algorithm development and internal validation. The National Inpatient Sample (NIS) database was queried to identify cervical spine fusion surgeries between 2009 and 2017 for external validation of algorithm performance. Gradient-boosted trees were constructed to predict nonhome discharge across patient cohorts. The area under the receiver operating characteristic curve (AUROC) was used to measure model performance. SHAP values were used to identify nonlinear risk factors for nonhome discharge and to interpret algorithm predictions. RESULTS: A total of 3523 cases of cervical spine fusion surgeries were included from the SCDW data set, and 311,582 cases were isolated from NIS. The model demonstrated robust prediction of nonhome discharge across all cohorts, achieving an area under the receiver operating characteristic curve of 0.87 (SD=0.01) on both the SCDW and nationwide NIS test sets. Anterior approach only, age, elective admission status, Medicare insurance status, and total Elixhauser Comorbidity Index score were the most important predictors of discharge destination. CONCLUSIONS: Machine learning algorithms reliably predict nonhome discharge across single-center and national cohorts and identify preoperative features of importance following cervical spine fusion surgery.

Robust prediction of nonhome discharge following elective anterior cervical discectomy and fusion using explainable machine learning.

PURPOSE: Predict nonhome discharge (NHD) following elective anterior cervical discectomy and fusion (ACDF) using an explainable machine learning model. METHODS: 2227 patients undergoing elective ACDF from 2008 to 2019 were identified from a single institutional database. A machine learning model was trained on preoperative variables, including demographics, comorbidity indices, and levels fused. The validation technique was repeated stratified K-Fold cross validation with the area under the receiver operating curve (AUROC) statistic as the performance metric. Shapley Additive Explanation (SHAP) values were calculated to provide further explainability regarding the model's decision making. RESULTS: The preoperative model performed with an AUROC of 0.83 ± 0.05. SHAP scores revealed the most pertinent risk factors to be age, medicare insurance, and American Society of Anesthesiology (ASA) score. Interaction analysis demonstrated that female patients over 65 with greater fusion levels were more likely to undergo NHD. Likewise, ASA demonstrated positive interaction effects with female sex, levels fused and BMI. CONCLUSION: We validated an explainable machine learning model for the prediction of NHD using common preoperative variables. Adding transparency is a key step towards clinical application because it demonstrates that our model's "thinking" aligns with clinical reasoning. Interactive analysis demonstrated that those of age over 65, female sex, higher ASA score, and greater fusion levels were more predisposed to NHD. Age and ASA score were similar in their predictive ability. Machine learning may be used to predict NHD, and can assist surgeons with patient counseling or early discharge planning.

The Impact of Obstructive Sleep Apnea on Clinical, Perioperative, and Cost Outcomes in Patients Who Underwent Posterior Cervical Decompression and Fusion: A Single-Center Retrospective Analysis From 2008 to 2016.

BACKGROUND: Obstructive sleep apnea (OSA) is a pervasive problem that can result in diminished neurocognitive performance, increased risk of all-cause mortality, and significant cardiovascular disease. While previous studies have examined risk factors that influence outcomes following cervical fusion procedures, to our knowledge, no study has examined the cost or outcome profiles for posterior cervical decompression and fusion (PCDF) procedures in patients with OSA. METHODS: All cases at a single institution between 2008 and 2016 involving a PCDF were included. The primary outcome was prolonged extubation, defined as an extubation that took place outside of the operating room. Secondary outcomes included admission to the intensive care unit (ICU), complications, extended hospitalization, nonhome discharge, readmission within 30 and 90 days, emergency room visit within 30 and 90 days, and higher total costs. RESULTS: We reviewed 1191 PCDF cases, of which 93 patients (7.81%) had a history of OSA. At the univariate level, patients with OSA had higher rates of ICU admissions (33.3% vs 16.8%, P < 0.0001), total complications (29.0% vs 19.0%, P = 0.0202), and respiratory complications (12.9% vs 6.6%, P = 0.0217). Multivariate regression analyses revealed no difference in the odds of a prolonged extubation (P = 0.4773) and showed that history of OSA was not predictive of higher costs. However, a significant difference was observed in the odds of having an ICU admission (P = 0.0046). CONCLUSION: While patients with sleep apnea may be more likely to be admitted to the ICU postoperatively, OSA status a lone is not a risk factor for poor primary and secondary clinical outcomes following posterior cervical fusion procedures. CLINICAL RELEVANCE: Various deformities of the cervical spine can exert extraluminal forces that partially collapse or obstruct the airway, thereby predisposing patients to OSA; however, no study has examined the cost or outcome profiles for PCDF procedures in patients with OSA. Therefore, this investigation highlights the ways in which OSA influences the risks, outcomes, and costs following PCDF using medical data from an institutional registry.

Robust Prediction of Non-home Discharge After Thoracolumbar Spine Surgery With Ensemble Machine Learning and Validation on a Nationwide Cohort.

BACKGROUND: Delays in postoperative referrals to rehabilitation or skilled nursing facilities contribute toward extended hospital stays. Facilitating more efficient referrals through accurate preoperative prediction algorithms has the potential to reduce unnecessary economic burden and minimize risk of hospital-acquired complications. We develop a robust machine learning algorithm to predict non-home discharge after thoracolumbar spine surgery that generalizes to unseen populations and identifies markers for prediction. METHODS: Retrospective electronic health records were obtained from our single-center data warehouse (SCDW) to identify patients undergoing thoracolumbar spine surgeries between 2008 and 2019 for algorithm development and internal validation. The National Inpatient Sample (NIS) database was queried to identify thoracolumbar surgeries between 2009 and 2017 for out-of-sample validation. Ensemble decision trees were constructed for prediction and area under the receiver operating characteristic curve (AUROC) was used to assess performance. Shapley additive explanations values were derived to identify drivers of non-home discharge for interpretation of algorithm predictions. RESULTS: A total of 5224 cases of thoracolumbar spine surgeries were isolated from the SCDW and 492,312 cases were identified from NIS. The model achieved an AUROC of 0.81 (standard deviation [SD] = 0.01) on the SCDW test set and 0.77 (SD = 0.01) on the nationwide NIS data set, thereby demonstrating robust prediction of non-home discharge across all diverse patient cohorts. Age, total Elixhauser comorbidities, Medicare insurance, weighted Elixhauser score, and female sex were among the most important predictors of non-home discharge. CONCLUSIONS: Machine learning algorithms reliably predict non-home discharge after thoracolumbar spine surgery across single-center and national cohorts and identify preoperative features of importance that elucidate algorithm decision-making.

Neurosurgical Performance in the First 2 Years of Merit-Based Incentive Payment System: A Descriptive Analysis and Predictors of Receiving Bonus Payments.

BACKGROUND: The merit-based incentive payment system (MIPS) program was implemented to tie Medicare reimbursements to value-based care measures. Neurosurgical performance in MIPS has not yet been described. OBJECTIVE: To characterize neurosurgical performance in the first 2 years of MIPS. METHODS: Publicly available data regarding MIPS performance for neurosurgeons in 2017 and 2018 were queried. Descriptive statistics about physician characteristics, MIPS performance, and ensuing payment adjustments were performed, and predictors of bonus payments were identified. RESULTS: There were 2811 physicians included in 2017 and 3147 in 2018. Median total MIPS scores (99.1 vs 90.4, P < .001) and quality scores (97.9 vs 88.5, P < .001) were higher in 2018 than in 2017. More neurosurgeons (2758, 87.6%) received bonus payments in 2018 than in 2017 (2013, 71.6%). Of the 2232 neurosurgeons with scores in both years, 1347 (60.4%) improved their score. Reporting through an alternative payment model (odds ratio [OR]: 32.3, 95% CI: 16.0-65.4; P < .001) and any practice size larger than 10 (ORs ranging from 2.37 to 10.2, all P < .001) were associated with receiving bonus payments. Increasing years in practice (OR: 0.99; 95% CI: 0.982-0.998, P = .011) and having 25% to 49% (OR: 0.72; 95% CI: 0.53-0.97; P = .029) or ≥50% (OR: 0.48; 95% CI: 0.28-0.82; P = .007) of a physician's patients eligible for Medicaid were associated with lower rates of bonus payments. CONCLUSION: Neurosurgeons performed well in MIPS in 2017 and 2018, although the program may be biased against surgeons who practice in small groups or take care of socially disadvantaged patients.

The Impact of Diabetes on Outcomes and Health Care Costs Following Anterior Cervical Discectomy and Fusion.

STUDY DESIGN: Retrospective cohort study. OBJECTIVES: Anterior cervical discectomy and fusion (ACDF) is commonly used to treat an array of cervical spine pathology and is associated with good outcomes and low complication rates. Diabetes mellitus (DM) is a common comorbidity for patients undergoing ACDF, but the literature is equivocal about the impact it has on outcomes. Because DM is a highly prevalent comorbidity, it is crucial to determine if it is an associated risk factor for outcomes after ACDF procedures. METHODS: Patients at a single institution from 2008 to 2016 undergoing ACDF were compared on the basis of having a prior diagnosis of DM versus no DM. The 2 cohorts were compared utilizing univariate tests and multivariate logistic and linear regressions. RESULTS: Data for 2470 patients was analyzed. Diabetic patients had significantly higher Elixhauser scores (P < .0001). Univariate testing showed diabetic patients were more likely to suffer from sepsis (0.82% vs 0.10%, P = .03) and bleeding complications (3.0% vs 1.5%, P = .04). In multivariate analyses, diabetic patients had higher rates of non-home discharge (odds ratio [OR] = 1.37, 95% confidence interval [CI] = 1.07-1.75, P = .013) and prolonged length of stay (OR = 1.95, 95% CI = 1.25-3.05, P = .003), but similar complication (OR = 1.46, 95% CI = 0.85-2.52, P = .17), reoperation (OR = 0.77, 95% CI = 0.33-1.81, P = .55), and 90-day readmission (OR = 1.53, 95% CI = 0.97-2.43) rates compared to nondiabetic patients. Direct cost was also shown to be similar between the cohorts after adjusting for patient, surgical, and hospital-related factors (estimate = -$30.25, 95% CI = -$515.69 to $455.18, P = .90). CONCLUSIONS: Diabetic patients undergoing ACDF had similar complication, reoperation, and readmission rates, as well as similar cost of care compared to nondiabetic patients.

The Impact of American Society of Anesthesiologists Status on Cost of Care and Length of Stay Following Posterior Cervical Decompression and Fusion.

BACKGROUND: Increased posterior cervical decompression and fusion (PCDF) procedures over the past decade have raised the prospect of bundled payment plans. The American Society of Anesthesiologists (ASA) Physical Status Classification system may enable accurate estimation of health care costs, length of stay (LOS), and other postoperative outcomes in patients undergoing PCDF. METHODS: Low (I and II) versus high (III and IV) ASA class was used to evaluate 971 patients who underwent PCDF between 2008 and 2016 at a single institution. Demographics were compared using univariate analysis. Cost of care, LOS, and postoperative complications were compared using multivariable logistic and linear regression, controlling for sex, age, length of surgery, and number of segments fused. RESULTS: The high ASA class cohort was older (mean age 62 years vs. 55 years, P < 0.0001) and had higher Elixhauser comorbidity index scores (P < 0.0001). ASA class was independently associated with longer LOS (2.1 days, 95% confidence interval [CI] 1.3-2.9, P < 0.0001) and higher cost ($2936, 95% CI $1457-$4415, P < 0.0001). Patients with high ASA class were more likely to have a nonhome discharge (3.9, 95% CI 2.8-5.6, P < 0.0001), delayed extubation (3.2, 95% CI 1.4-7.3, P = 0.006), intensive care unit stay (2.4, 95% CI 1.5 3.7, P = 0.0001), in-hospital complications (1.5, 95% CI 1.0-2.2, P = 0.03), and 30-day (3.2, 95% CI 1.5-6.8, P = 0.003) and 90-day (3.2, 95% CI 1.8-5.7, P = 0.0001) readmission. CONCLUSIONS: High ASA class is strongly associated with increased costs, LOS, and adverse outcomes following PCDF and could be useful for preoperative prediction of these outcomes.

Anesthesia provider performance in the first two years of merit-based incentive payment system: Shifts in reporting and predictors of receiving bonus payments.

STUDY OBJECTIVE: The Merit-Based Incentive Payment System (MIPS) program was intended to align CMS quality and incentive programs. To date, no reports have described anesthesia clinician performance in the first two years of the program. DESIGN: Observational retrospective cohort study. SETTING: Centers for Medicare and Medicaid Services public datasets for their Quality Payment Program. PATIENTS: Anesthesia clinicians who participated in MIPS for 2017 and 2018 performance years. INTERVENTIONS: Descriptive statistics compared anesthesia clinician characteristics, practice setting, and MIPS performance between the two years to determine associations with MIPS-based payment adjustments. MEASUREMENTS: Logistic regression identified independent predictors of bonus payments for exceptional performance. MAIN RESULTS: Compared with participants in 2017 (n = 25,604), participants in 2018 (n = 54,381) had a higher proportion of reporting through groups and alternative payment models (APMs) than as individuals (p < 0.001). The proportion of clinicians earning performance bonuses increased from 2017 to 2018 except for those MIPS participants reporting as individuals. Median total MIPS scores were higher in 2018 than 2017 (84.6 vs. 82.4, p < 0.001), although median total scores fell for participants reporting as individuals (40.9 vs 75.5, p < 0.001). Among clinicians with scores in both years (n = 20,490), 10,559 (51.3%) improved their total score between 2017 and 2018, and 347 (1.7%) changed reporting from individual to APM. Reporting as an individual compared with group reporting (OR: 0.75; 95% CI: 0.71 to 0.80; p < 0.001) was associated with lower rates of bonus payments, as was having a greater proportion of patients dual-eligible for Medicaid and Medicare. Reporting through an APM (OR: 149.6; 95% CI: 110 to 203.4; p < 0.001) and increasing practice group size were associated with higher likelihood of bonus payments. CONCLUSIONS: Anesthesia clinician MIPS participation and performance were strong during 2017 and 2018 performance years. Providers who reported through groups or APMs have a higher likelihood of receiving bonus payments.

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.

The Impact of Non-Elective Admission on Cost of Care and Length of Stay in Anterior Cervical Discectomy and Fusion: A Propensity-Matched Analysis.

STUDY DESIGN: Retrospective cohort study. OBJECTIVE: To evaluate the impact of admission status on patient outcomes and healthcare costs in anterior cervical discectomy and fusion (ACDF). SUMMARY OF BACKGROUND DATA: Undergoing ACDF non-electively has been associated with higher patient comorbidity burdens. However, the impact of non-elective status on the total cost of hospital stay has yet to be quantified. METHODS: Patients undergoing ACDF at a single institution were placed into elective or non-elective cohorts. Propensity score-matching analysis in a 5:1 ratio controlling for insurance type and comorbidities was used to minimize selection bias. Demographics were compared by univariate analysis. Cost of care, length of stay (LOS), and clinical outcomes were compared between groups using multivariable linear and logistic regression with elective patients as reference cohort. All analyses controlled for sex, preoperative diagnosis, elixhauser comorbidity index (ECI), age, length of surgery, number of segments fused, and insurance type. RESULTS: Of 708 patients in the final ACDF cohort, 590 underwent an elective procedure and 118 underwent a non-elective procedure. The non-elective group was significantly younger (53.7 vs. 49.5 yr; P = 0.0007). Cohorts had similar proportions of private versus public health insurance, although elective had higher rates of commercial insurance (39.22% vs. 15.25%; P < 0.0001) and non-elective had higher rates of managed care (32.77% vs. 56.78%; P < 0.0001). Operation duration was significantly longer in non-elective patients (158 vs. 177 minutes; P = 0.01). Adjusted analysis also demonstrated that admission status independently affected cost (+$6877, 95% confidence interval [CI]: $4906-$8848; P < 0.0001) and LOS (+4.9 days, 95% CI: 3.9-6.0; P < 0.0001) for the non-elective cohort. The non-elective cohort was significantly more likely to return to the operating room (OR: 3.39; 95% CI: 1.37-8.36, P = 0.0008) and experience non-home discharge (OR: 10.95; 95% CI: 5.00-24.02, P < 0.0001). CONCLUSION: Patients undergoing ACDF non-electively had higher cost of care and longer LOS, as well as higher rates of postoperative adverse outcomes.Level of Evidence: 3.

The Price of Otologic Procedures: Variation in Markup by Surgical Procedure and Geography in the United States.

OBJECTIVE: To characterize and analyze variation in price markup of seven common otologic surgeries by procedure and geographic region. STUDY DESIGN: Retrospective Analysis of the Centers for Medicare and Medicaid Services database of 2017 Medicare Provider Utilization and Payment Public File. SETTING: Inpatient and outpatient centers delivering Medicare-reimbursed services. PATIENTS: Full sample of patients undergoing procedures with Medicare fee-for-service final action claims during 2017. INTERVENTIONS: Seven procedures (myringotomy, tympanoplasty, mastoidectomy, tympanomastoidectomy stapedotomy/stapedectomy, cochlear implant, bone-anchored hearing aid). MAIN OUTCOME MEASURES: Markup ratio (MUR) is defined as the ratio of total charges to Medicare-allowable-costs; Variation in MUR was measured using coefficient of variation (CoV). RESULTS: Among all providers, the median MUR was 2.4 (interquartile range: 1.9-3.1). MUR varied significantly by procedure, from 2.3 for myringotomy to 8.7 for mastoidectomy (p < 0.01). MUR also varied significantly within procedure, with the least variation found in myringotomy (CoV = 0.46), and the greatest in cochlear implants (CoV = 0.92). Using the national average as baseline, MUR varied 71% between states, ranging from 1.75 to 6.24. Within the same state, significant variation was also noted, varying by 4% (CoV = 0.04) in Montana compared with 138% (CoV = 1.38) in Pennsylvania. MUR was not significantly correlated with patient comorbidity or Centers for Medicare and Medicaid Services risk scores. CONCLUSIONS: There was significant variation in the price of otologic surgery across geographic regions and procedures. The MUR for otology is lower or comparable to that reported in other surgical fields.

Surgical Start Time Is Not Predictive of Microdiscectomy Outcomes.

STUDY DESIGN: Retrospective analysis of clinical data from a single institution. OBJECTIVE: The objective of this study was to assess the time of surgery as a possible predictor for outcomes, length of stay, and cost following microdiscectomy. SUMMARY OF BACKGROUND DATA: The volume of microdiscectomy procedures has increased year over year, heightening interest in surgical outcomes. Previous investigations have demonstrated an association between time of procedures and clinical outcomes in various surgeries, however, no study has evaluated its influence on microdiscectomy. METHODS: Demographic and outcome variables were collected from all patients that underwent a nonemergent microdiscectomy between 2008 and 2016. Patients were divided into 2 cohorts: those receiving surgery before 2 pm were assigned to the early group and those with procedures beginning after 2 pm were assigned to the late group. Outcomes and patient-level characteristics were compared using bivariate, multivariable logistic, and linear regression models. Adjusted length of stay and cost were coprimary outcomes. Secondary outcomes included operative complications, nonhome discharge, postoperative emergency department visits, or readmission rates. RESULTS: Of the 1261 consecutive patients who met the inclusion criteria, 792 were assigned to the late group and 469 were assigned to the early group. There were no significant differences in demographics or baseline characteristics between the 2 cohorts. In the unadjusted analysis, mean length of stay was 1.80 (SD=1.82) days for the early group and 2.00 (SD=1.70) days for the late group (P=0.054). Mean direct cost for the early cohort was $5088 (SD=$4212) and $4986 (SD=$2988) for the late cohort (P=0.65). There was no difference in adjusted length of stay or direct cost. No statistically significant differences were found in operative complications, nonhome discharge, postoperative emergency department visits, or readmission rates between the 2 cohorts. CONCLUSION: The study findings suggest that early compared with late surgery is not significantly predictive of surgical outcomes following microdiscectomy.

Comparison of Surgical Outcomes of Microdiskectomy Procedures by Patient Admission Status.

OBJECTIVE: We sought to compare the cost and in-hospital outcomes following lumbar microdiskectomy procedures by admission type. METHODS: Patients undergoing lumbar microdiskectomy at a single institution from 2008 to 2016 following an elective admission (EL) were compared against those who were admitted from the emergency department (ED) or from elsewhere within or outside the hospital system (TR) for their perioperative outcomes and cost. Multivariable modeling controlled for age, sex, self-reported race, Elixhauser comorbidity score, payer type, number of segments, and procedure length. RESULTS: Of the 1249 patients included in this study, 1116 (89.4%) were admitted electively while 123 (9.8%) were admitted from the ED and 10 (0.8%) were transferred from other hospitals. EL patients had significantly lower comorbidity burdens (P < 0.0001). Univariate and multivariable analyses revealed that transfer admission patients experienced significantly longer hospitalizations (ED: +1.7 days; P < 0.0001; TR: +5.3 days; P < 0.0001) and higher direct costs (ED: $1889; P < 0.0001; TR: $7001; P < 0.0001) compared with EL patients. Despite these risks, ED and TR patients only had increased odds of nonhome discharge compared with EL patients (ED: 3.4; P = 0.002; TR: 7.9; P = 0.02). CONCLUSIONS: Patients admitted as transfers and from the ED had significantly increased hospitalization lengths of stay and direct costs compared with electively admitted patients.

Surgeon experience influences patient characteristics and outcomes in spine deformity surgery.

PURPOSE: To characterize differences in patient demographics and outcomes by surgeon experience in a cohort of patients undergoing adult spinal deformity surgery. METHODS: Patients undergoing degenerative spinal deformity were included. Patients whose surgeons graduated from fellowship ≤ 5 years prior to surgery versus > 5 years were compared. Multivariable linear and logistic regression, controlling for age, sex, comorbidity burden, number of segments fused, blood loss and operative time were used to evaluate differences in outcomes. Characteristics of operative invasiveness were plotted against surgeons' level of experience, and trends in these measures were assessed with univariate linear regression. RESULTS: Three-hundred sixty-three patients were included. 147 patients' surgeons had ≤ 5 years of experience. Patient demographics were evenly matched. Patients with junior surgeons had more pre-existing medical complications, and senior surgeons were less likely to take care of patients with Medicare/Medicaid (p < 0.001). Junior surgeons were more likely to operate on non-elective patients (p < 0.001). Patients of junior surgeons received larger fusions (9.6 vs. 7.6 segments fused, p < 0.001). There were no differences in complication rates or death. Patients of junior surgeons had longer overall length of stays (p = 0.037) and higher rates of nonhome discharge (OR 2.0, p < 0.001), 30- and 90-day (p < 0.005) ED visits, and higher costs (+ $8548, 95% CI: $1596 to $15,502; p = 0.016). CONCLUSION: Junior surgeons tend to perform more extensive deformity operations on more medically complex patients compared to senior surgeons, associated with higher costs and more resource utilization than senior surgeons.

Surgery for spinal deformity: non-elective admission status is associated with higher cost of care and longer length of stay.

INTRODUCTION: Surgery is commonly indicated for adult spinal deformity. Annual rates and costs of spinal deformity surgery have both increased over the past two decades. However, the impact of non-elective status on total cost of hospitalization and patient outcomes has not been quantified. OBJECTIVE: To evaluate the impact of admission status on patient outcomes and healthcare costs in spinal deformity surgery. METHODS: All patients who underwent spinal deformity surgery at a single institution between 2008 and 2016 were grouped by admission status: elective, emergency (ED), or transferred. Demographics were compared by univariate analysis. Cost of care and length of stay (LOS) were compared between admission statuses using multivariable linear regression with elective admissions as reference. Multivariate logistic regression was utilized to assess in-hospital complications, discharge destination, and readmission rates. RESULTS: There were 427 spinal deformity surgeries included in this study. Compared to elective patients, ED patients had higher Elixhauser Comorbidity Index scores (p < 0.0001), longer LOS (+ 10.9 days, 97.5% CI 6.1-15.6 days, p < 0.0001), and higher costs (+ $20,076, 97.5% CI $9,073-$31,080, p = 0.0008). Transferred patients had significantly higher Elixhauser scores (p = 0.0002), longer LOS (+ 8.8 days, 97.5% CI 3.0-14.7 days, p < 0.0001), and higher rates of non-home discharge (OR = 15.8, 97.5% CI 2.3-110.0, p = 0.001). CONCLUSION: Patients admitted from the ED undergoing spinal deformity surgery had significantly higher cost of care and longer LOS compared to elective patients. Transferred patients had significantly longer LOS and a higher rate of non-home discharge compared to elective patients.

Utilization of the American Society of Anesthesiologists (ASA) classification system in evaluating outcomes and costs following deformity spine procedures.

PURPOSE: Adult spinal deformity (ASD) has increased prevalence in aging populations. Due to the high cost of surgery, studies have evaluated risk factors that predict readmissions and poor outcomes. The American Society of Anesthesiologists (ASA) classification system has been applied to patients with ASD to assess preoperative health and assess the correlation between ASA class and postoperative complications. This study evaluates the relationship between ASA and complications, length of stay (LOS), and direct costs following spine deformity surgery. METHODS: Patients undergoing spine deformity surgery at a single institution from 2008-2016 were included and stratified based upon ASA status. Primary outcomes included patient demographics, adjusted LOS, and cost of care. Secondary measures compared between cohorts included adverse events, non-home discharge, and readmission rates. RESULTS: 442 patients with ASD were included in this study. Higher ASA class was correlated with greater Elixhauser Comorbidity Index (ECI) scores (p < 0.0001) and older age (p < 0.0001). Univariate analysis showed longer LOS (p < 0.0001) and greater direct costs in patients with higher ASA class (p < 0.0001). Patients in ASA Class III or IV had the greatest incidence of ICU stay when compared to patients without systemic disease (p < 0.0001). Upon multivariable regression analysis, high ASA class was associated with higher rates of non-home discharge (OR 5.0, 95% CI 3.1-8.1). Direct costs were greater for higher ASA class (regression estimate = + $9,666, p = 0.002). CONCLUSION: This study demonstrates that ASA class is correlated with a more complicated postoperative hospital course, greater rates of non-home discharge, total direct costs in spine deformity patients.

Drivers of Prolonged Hospitalization Following Spine Surgery: A Game-Theory-Based Approach to Explaining Machine Learning Models.

BACKGROUND: Understanding the interactions between variables that predict prolonged hospital length of stay (LOS) following spine surgery can help uncover drivers of this risk in patients. This study utilized a novel game-theory-based approach to develop explainable machine learning models to understand such interactions in a large cohort of patients treated with spine surgery. METHODS: Of 11,150 patients who underwent surgery for degenerative spine conditions at a single institution, 3,310 (29.7%) were characterized as having prolonged LOS. Machine learning models predicting LOS were built for each patient. Shapley additive explanation (SHAP) values were calculated for each patient model to quantify the importance of features and variable interaction effects. RESULTS: Models using features identified by SHAP values were highly predictive of prolonged LOS risk (mean C-statistic = 0.87). Feature importance analysis revealed that prolonged LOS risk is multifactorial. Non-elective admission produced elevated SHAP values, indicating a clear, strong risk of prolonged LOS. In contrast, intraoperative and sociodemographic factors displayed bidirectional influences on risk, suggesting potential protective effects with optimization of factors such as estimated blood loss, surgical duration, and comorbidity burden. CONCLUSIONS: Meticulous management of patients with high comorbidity burdens or Medicaid insurance who are admitted non-electively or spend clinically indicated time in the intensive care unit (ICU) during their hospitalization course may be warranted to reduce their risk of unanticipated prolonged LOS following spine surgery. LEVEL OF EVIDENCE: Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

A Comparison of the Elixhauser and Charlson Comorbidity Indices: Predicting In-Hospital Complications Following Anterior Lumbar Interbody Fusions.

OBJECTIVE: The Elixhauser Comorbidity Index (ECI) and Charlson Comorbidity Index (CCI) are commonly used measures that use administrative data to characterize a patient's comorbidity burden. The purpose of this study was to compare the ability of these measures to predict outcomes following anterior lumbar interbody fusion. METHODS: The National Inpatient Sample was queried for all ALIF procedures between 2013 and 2014. The area under the receiver operating curve (AUC) was used to compare the ECI and CCI in their ability to predict postoperative complications when incorporated into a base model containing age, sex, race, and primary payer. Percent superiority was computed using AUC values for ECI, CCI, and base models. RESULTS: A total of 43,930 hospitalizations were included in this study. The ECI was superior to the CCI and baseline models in predicting minor (AUC 71 vs. 0.66, P < 0.0001) and major (AUC 0.74 vs. 0.67, P < 0.0001) complications. When evaluating individual complications, the ECI was superior to the CCI in predicting airway complications (65% superior, AUC 0.85 vs. 0.72, P = 0.0001); hemorrhagic anemia (83% superior, AUC 0.71 vs. 0.66, P < 0.0001); myocardial infarction (76% superior, AUC 0.86 vs. 0.67, P < 0.0001); cardiac arrest (75% superior, AUC 0.85 vs. 0.67, P < 0.0001); pulmonary embolism (105% superior, AUC 0.91 vs. 0.71, P < 0.0001); and urinary tract infection (43% superior, AUC 0.76 vs. 0.73, P = 0.046). CONCLUSIONS: The ECI was superior to the CCI in predicting 6 of the 15 complications analyzed in this study. Combined with previous results, the ECI may be a better predictive model in spine surgery.

Large Rises in Thoracolumbar Fusions by 2040: A Cause for Concern with an Increasingly Elderly Surgical Population.

BACKGROUND: With a growing aging population in the United States, the number of operative lumbar spine pathologies continues to grow. Therefore, our objective was to estimate the future demand for lumbar spine surgery volumes for the United States to the year 2040. METHODS: The National/Nationwide Inpatient Sample was queried for years 2003-2015 for anterior interbody and posterior lumbar fusions (ALIF, PLF) to create national estimates of procedural volumes for those years. The average age and comorbidity burden was characterized, and Poisson modeling controlling for age and sex allowed for surgical volume prediction to 2040 in 10-year increments. Age was grouped into categories (<25, 25-34, 35-44, 45-54, 55-64, 65-74, 75-84, and >85 years), and estimates of surgical volumes for each age subgroup were created. RESULTS: ALIF volume is expected to increase from 46,903 to 55,528, and PLF volume is expected to increase from 248,416 to 297,994 from 2020 to 2040. For ALIF, the largest increases are expected in the 45-54 years (10,316 to 12,216) and 75-84 years (2,898 to 5,340) age groups. Similarly the largest increases in PLF will be seen in the 65-74 years (71,087 to 77,786) and 75-84 years (28,253 to 52,062) age groups. CONCLUSIONS: The large increases in expected volumes of ALIF and PLF could necessitate training of more spinal surgeons and an examination of projected costs. Further analyses are needed to characterize the needs of this increasingly large population of surgical patients.