Predictors of discharge to an inpatient rehabilitation facility after a single-level posterior spinal fusion procedure

Predictors of Admission to Post-Acute Rehabilitation Following Multi-Level Spinal Decompression and Fusion Surgery and Its Associated Outcomes

OBJECTIVE

To investigate predictive factors and outcomes in those admitted to post-acute rehabilitation (PAR) versus those that discharged home following multi-level spinal decompression and fusion surgery.

METHODS

Retrospective case review study of adults that underwent multi-level spinal decompression and fusion surgery between 2016 and 2022 at an academic institution. Preoperative, perioperative, postoperative, and outcomes variables were compared between those discharged home versus PAR. Finally, multiple logistic regression was used to determine factors contributing to PAR admission.

RESULTS

Of 241 total patients, 89 (37%) discharged home and 152 (63%) discharged to PAR. Among home discharge patients, 45.9% used an assistive device, while among PAR patients, 61.5% used 1 (P = 0.041). Mean pre-operative Oswestry Disability Index score was significantly lower in the home discharge group compared to the PAR discharge group (40.3 vs. 45.3 respectively, P = 0.044). Females were 2.43 times more likely to be discharged to PAR compared to males (95% CI: 1.06, 5.54, P = 0.04). Patients with a mood disorder had 2.81 times higher odds of being discharged to PAR compared to those without (95% CI: 1.20, 6.60, P = 0.02). Other variables evaluated were not statistically significant.

CONCLUSIONS

Female sex and presence of a mood disorder increase the likelihood to PAR discharge following multi-level spinal decompression surgery.

The Impact of Social Determinants of Health on Discharge Disposition Following One- and Two-Level Posterior Interbody Fusion

Background Current research is limited in exploring the impact of social determinants of health (SDOH) on the discharge location within elective spine surgery. Further understanding of the influence of SDOH on disposition is necessary to improve outcomes. This study explores how SDOH influence discharge disposition for patients undergoing one- or two-level posterior interbody fusion (TLIF/PLIF). Methods This was a retrospective propensity-matched cohort study. Patients who underwent TLIF/PLIF between 2017 and 2020 at a single academic medical center were identified. The chart review gathered demographics, perioperative characteristics, intra/post-operative complications, discharge disposition, and 90-day outcomes. Discharge dispositions included subacute nursing facility (SNF), home with self-care (HSC), home with health services (HHS), and acute rehab facility (ARF). Demographic, perioperative, and disposition outcomes were analyzed by chi-square analysis and one-way ANOVA based on gender, race, and income quartiles. Results Propensity score matching for significant demographic factors isolated 326 patients. The rate of discharge to SNF was higher in females compared to males (25.00% vs 10.56%; p=0.001). Men were discharged to home at a higher rate than women (75.4% vs 61.95%; p=0.010). LatinX patients had the highest rate of home discharge, followed by Asians, Caucasians, and African Americans (83.33% vs 70.31% vs 66.45% vs 65.90%; p<0.001). The post hoc Tukey test demonstrated statistically significant differences between Asians and all other races in the context of age and BMI. Additionally, patients discharged to SNF showed the highest Charlson comorbidity index (CCI) score, followed by those at ARF, HHS, and HSC (4.36 vs 4.05 vs 2.87 vs 2.37; p<0.001). The estimated median income for the cohort ranged from $52,000 to $250,001, with no significant differences in income seen across comparisons. Conclusion Discharge disposition following one- or two-level TLIF/PLIF shows significant association with gender and race. No association was seen when comparing discharge rates among zip code-level median income quartiles.

The effect of patient age on discharge destination and complications after lumbar spinal fusion

Age is an important patient characteristic that has been correlated with specific outcomes after lumbar spine surgery. We performed a retrospective cohort study to model the effect of age on discharge destination and complications after a 1-level or multi-level lumbar spine fusion surgery. The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was used to identify patients who underwent lumbar spinal fusion surgery from 2013 through 2017. Perioperative outcomes were compared across ages 18 to 90 using multivariable nonlinear logistic regressioncontrolling for preoperative characteristics. A total of 61,315 patients were analyzed, with patients over 70 having a higher risk of being discharged to an inpatient rehabilitation center and receiving an intraoperative or postoperative blood transfusion. However, the rates of the other complications and outcomes analyzed in this study were not significantly different as patients age. In conclusion, advanced-age affects the discharge destination after a one- or multi-level fusion and intraoperative/postoperative blood transfusion after a one-level fusion. However, age alone does not significantly affect the risk of the other complications and outcomes assessed in this study. This study will help guide preoperative discussion with advanced-aged patients who are considering a 1-level or multi-level lumbar spine fusion surgery.

Drivers for nonhome discharge in a consecutive series of 1502 patients undergoing 1- or 2-level lumbar fusion

OBJECTIVE

Unexpected nonhome discharge causes additional costs in the current reimbursement models, especially to the payor. Nonhome discharge is also related to longer length of hospital stay and therefore higher healthcare costs to society. With increasing demand for spine surgery, it is important to minimize costs by streamlining discharges and reducing length of hospital stay. Identifying factors associated with nonhome discharge can be useful for early intervention for discharge planning. The authors aimed to identify the drivers of nonhome discharge in patients undergoing 1- or 2-level instrumented lumbar fusion.

METHODS

The electronic medical records from a single-center hospital administrative database were analyzed for consecutive patients who underwent 1- to 2-level instrumented lumbar fusion for degenerative lumbar conditions during the period from 2016 to 2018. Discharge disposition was determined as home or nonhome. A logistic regression analysis was used to determine associations between nonhome discharge and age, sex, body mass index (BMI), race, American Society of Anesthesiologists grade, smoking status, marital status, insurance type, residence in an underserved zip code, and operative factors.

RESULTS

A total of 1502 patients were included. The majority (81%) were discharged home. Factors associated with a nonhome discharge were older age, higher BMI, living in an underserved zip code, not being married, being on government insurance, and having more levels fused. Patients discharged to a nonhome facility had longer lengths of hospital stay (5.6 vs 3.0 days, p < 0.001) and significantly increased hospital costs ($21,204 vs $17,518, p < 0.001).

CONCLUSIONS

Increased age, greater BMI, residence in an underserved zip code, not being married, and government insurance are drivers for discharge to a nonhome facility after a 1- to 2-level instrumented lumbar fusion. Early identification and intervention for these patients, even before admission, may decrease the length of hospital stay and medical costs.

Predictive Model and Online Calculator for Discharge Disposition in Brain Tumor Patients

BACKGROUND

In the era of value-based payment models, it is imperative for neurosurgeons to eliminate inefficiencies and provide high-quality care. Discharge disposition is a relevant consideration with clinical and economic ramifications in brain tumor patients. We developed a predictive model and online calculator for postoperative non-home discharge disposition in brain tumor patients that can be incorporated into preoperative workflows.

METHODS

We reviewed all brain tumor patients at our institution from 2017 to 2019. A predictive model of discharge disposition containing preoperatively available variables was developed using stepwise multivariable logistic regression. Model performance was assessed using receiver operating characteristic curves and calibration curves. Internal validation was performed using bootstrapping with 2000 samples.

RESULTS

Our cohort included 2335 patients who underwent 2586 surgeries with a 16% non-home discharge rate. Significant predictors of non-home discharge were age >60 years (odds ratio [OR], 2.02), African American (OR, 1.73) or Asian (OR, 2.05) race, unmarried status (OR, 1.48), Medicaid insurance (OR, 1.90), admission from another health care facility (OR, 2.30), higher 5-factor modified frailty index (OR, 1.61 for 5-factor modified frailty index ≥2), and lower Karnofsky Performance Status (increasing OR with each 10-point decrease in Karnofsky Performance Status). The model was well calibrated and had excellent discrimination (optimism-corrected C-statistic, 0.82). An open-access calculator was deployed (https://neurooncsurgery.shinyapps.io/discharge_calc/).

CONCLUSIONS

A strongly performing predictive model and online calculator for non-home discharge disposition in brain tumor patients was developed. With further validation, this tool may facilitate more efficient discharge planning, with consequent improvements in quality and value of care for brain tumor patients.

Development and validation of a novel scoring tool for predicting facility discharge after elective posterior lumbar fusion

BACKGROUND CONTEXT

Discharge to acute/intermediate care facilities is a common occurrence after posterior lumbar fusion and can be associated with increased costs and complications after these procedures. This is particularly relevant with the growing popularity of bundled payment plans, creating a need to identify patients at greatest risk.

PURPOSE

To develop and validate a risk-stratification tool to identify patients at greatest risk for facility discharge after open posterior lumbar fusion.

STUDY DESIGN

Retrospective cohort study.

PATIENT SAMPLE

Patients were queried using separate databases from the institution of study and the American College of Surgeons National Surgical Quality Improvement Program (NSQIP) for all patients undergoing open lumbar fusion between 2011 and 2018.

OUTCOME MEASURES

Discharge to intermediate care and/or rehabilitation facilities.

METHODS

Using an 80:20 training and testing NSQIP data split, collected preoperative demographic and operative variables were used in a multivariate logistic regression to identify potential risk factors for postoperative facility discharge, retaining those with a p value <.05. A nomogram was generated to develop a scoring system from this model, with probability cutoffs determined for facility discharge. This model was subsequently validated within the NSQIP database, in addition to external validation at the institution of study. Overall model performance and calibration was assessed using the Brier score and calibration plots, respectively.

RESULTS

A total of 11,486 patients (10,453 NSQIP, 1,033 local cohort) were deemed eligible for study, of which 16.1% were discharged to facilities (16.7% NSQIP, 9.6% local cohort). Utilizing training data, age (p<.001), body mass index (p<.001), female sex (p<.001), diabetes (p=.043), peripheral vascular disease (p=.001), cancer (p=.010), revision surgery (p<.001), number of levels fused (p<.001), and spondylolisthesis (p=.049) were identified as significant risk factors for facility discharge. The area under the receiver operating characteristic curve (AUC) indicated a strong predictive model (AUC=0.750), with similar predictive ability in the testing (AUC=0.757) and local data sets (AUC=0.773). Using this tool, patients identified as low- and high-risk had a 7.94% and 33.28% incidence of facility discharge in the testing data set, while rates of 4.44% and 16.33% were observed at the institution of study.

CONCLUSIONS

Using preoperative variables as predictors, this scoring system demonstrated high efficiency in risk-stratifying patients with an approximate four to fivefold difference in rates of facility discharge after posterior lumbar fusion. This tool may help inform medical decision-making and guide reimbursement under bundled-care repayment plans.

Prediction calculator for nonroutine discharge and length of stay after spine surgery

BACKGROUND CONTEXT

Following spine surgery, delays in referral to rehabilitation facilities leads to increased length of hospital stay (LOS), increases costs, more risk of hospital acquired complications, and decreased patient satisfaction.

PURPOSE

We sought to create a prediction calculator to determine the expected LOS after spine surgery and identify patients most likely to need postoperative nonhome discharge. The goal would be to facilitate earlier referral to rehabilitation and thereby ultimately shorten LOS, reduce costs, and improve patient satisfaction.

STUDY DESIGN

Retrospective.

PATIENT SAMPLE

We retrospectively reviewed all adult patients who underwent spine surgery for all indications between January and June 2018.

OUTCOME MEASURES

Length of stay and discharge disposition.

METHODS

Demographic variables, insurance status, baseline comorbidities, narcotic use, operative characteristics, as well as postoperative length of stay and discharge disposition data were collected. Univariable and multivariable analyses were performed to identify independent predictors of LOS and discharge disposition.

RESULTS

Two hundred fifty-seven patients were included. Mean age was 59 years, 46% were females, and 52% had private insurance vs 7% with Medicaid and 41% with Medicare. The most commonly performed procedure was lumbar fusion (31.9%). Mean LOS after surgery was 4.8 days and 18% had prolonged LOS >7 days. Age, insurance type, marriage status, and surgical procedure were significantly associated with LOS and discharge disposition. The final model had an area under the curve of 89% with good discrimination. A web based calculator was developed: https://jhuspine1.shinyapps.io/RehabLOS/ CONCLUSIONS: This study established a novel pilot calculator to identify those patients most likely to be discharged to rehabilitation facilities and to predict LOS after spine surgery. Our calculator had a high predictive accuracy of 89% compared to others in the literature. With validation this tool may ultimately facilitate streamlining of the postoperative period to shorten LOS, optimize resource utilization, and improve patient care.

The Risk Assessment and Prediction Tool (RAPT) for Discharge Planning in a Posterior Lumbar Fusion Population

BACKGROUND

As the use of bundled care payment models has become widespread in neurosurgery, there is a distinct need for improved preoperative predictive tools to identify patients who will not benefit from prolonged hospitalization, thus facilitating earlier discharge to rehabilitation or nursing facilities.

OBJECTIVE

To validate the use of Risk Assessment and Prediction Tool (RAPT) in patients undergoing posterior lumbar fusion for predicting discharge disposition.

METHODS

Patients undergoing elective posterior lumbar fusion from June 2016 to February 2017 were prospectively enrolled. RAPT scores and discharge outcomes were recorded for patients aged 50 yr or more (n = 432). Logistic regression analysis was used to assess the ability of RAPT score to predict discharge disposition. Multivariate regression was performed in a backwards stepwise logistic fashion to create a binomial model.

RESULTS

Escalating RAPT score predicts disposition to home (P &lt; .0001). Every unit increase in RAPT score increases the chance of home disposition by 55.8% and 38.6% than rehab and skilled nursing facility, respectively. Further, RAPT score was significant in predicting length of stay (P = .0239), total surgical cost (P = .0007), and 30-d readmission (P &lt; .0001). Amongst RAPT score subcomponents, walk, gait, and postoperative care availability were all predictive of disposition location (P &lt; .0001) for both models. In a generalized multiple logistic regression model, the 3 top predictive factors for disposition were the RAPT score, length of stay, and age (P &lt; .0001, P &lt; .0001 and P = .0001, respectively).

CONCLUSION

Preoperative RAPT score is a highly predictive tool in lumbar fusion patients for discharge disposition.

Evaluation of the Risk Assessment and Prediction Tool for Postoperative Disposition Needs After Cervical Spine Surgery

BACKGROUND

Bundled care payment models are becoming more prevalent in neurosurgery. Such systems place the cost of postsurgical facilities in the hands of the discharging health system. Opportunity exists to leverage prediction tools for discharge disposition by identifying patients who will not benefit from prolonged hospitalization and facilitating discharge to post-acute care facilities.

OBJECTIVE

To validate the use of the Risk Assessment and Predictive Tool (RAPT) along with other clinical variables to predict discharge disposition in a cervical spine surgery population.

METHODS

Patients undergoing cervical spine surgery at our institution from June 2016 to February 2017 and over 50 yr old had demographic, surgical, and RAPT variables collected. Multivariable regression analyzed each variable's ability to predict discharge disposition. Backward selection was used to create a binomial model to predict discharge disposition.

RESULTS

A total of 263 patients were included in the study. Lower RAPT score, RAPT walk subcomponent, older age, and a posterior approach predicted discharge to a post-acute care facility compared to home. Lower RAPT also predicted an increased risk of readmission. RAPT score combined with age increased the predictive capability of discharge disposition to home vs skilled nursing facility or acute rehabilitation compared to RAPT alone (P < .001).

CONCLUSION

RAPT score combined with age is a useful tool in the cervical spine surgery population to predict postdischarge needs. This tool may be used to start early discharge planning in patients who are predicted to require post-acute care facilities. Such strategies may reduce postoperative utilization of inpatient resources.

Predicting discharge placement after elective surgery for lumbar spinal stenosis using machine learning methods

PURPOSE

An excessive amount of total hospitalization is caused by delays due to patients waiting to be placed in a rehabilitation facility or skilled nursing facility (RF/SNF). An accurate preoperative prediction of who would need a RF/SNF place after surgery could reduce costs and allow more efficient organizational planning. We aimed to develop a machine learning algorithm that predicts non-home discharge after elective surgery for lumbar spinal stenosis.

METHODS

We used the American College of Surgeons National Surgical Quality Improvement Program to select patient that underwent elective surgery for lumbar spinal stenosis between 2009 and 2016. The primary outcome measure for the algorithm was non-home discharge. Four machine learning algorithms were developed to predict non-home discharge. Performance of the algorithms was measured with discrimination, calibration, and an overall performance score.

RESULTS

We included 28,600 patients with a median age of 67 (interquartile range 58-74). The non-home discharge rate was 18.2%. Our final model consisted of the following variables: age, sex, body mass index, diabetes, functional status, ASA class, level, fusion, preoperative hematocrit, and preoperative serum creatinine. The neural network was the best model based on discrimination (c-statistic = 0.751), calibration (slope = 0.933; intercept = 0.037), and overall performance (Brier score = 0.131).

CONCLUSIONS

A machine learning algorithm is able to predict discharge placement after surgery for lumbar spinal stenosis with both good discrimination and calibration. Implementing this type of algorithm in clinical practice could avert risks associated with delayed discharge and lower costs. These slides can be retrieved under Electronic Supplementary Material.

Development of a machine learning algorithm predicting discharge placement after surgery for spondylolisthesis

PURPOSE

We aimed to develop a machine learning algorithm that can accurately predict discharge placement in patients undergoing elective surgery for degenerative spondylolisthesis.

METHODS

The National Surgical Quality Improvement Program (NSQIP) database was used to select patients that underwent surgical treatment for degenerative spondylolisthesis between 2009 and 2016. Our primary outcome measure was non-home discharge which was defined as any discharge not to home for which we grouped together all non-home discharge destinations including rehabilitation facility, skilled nursing facility, and unskilled nursing facility. We used Akaike information criterion to select the most appropriate model based on the outcomes of the stepwise backward logistic regression. Four machine learning algorithms were developed to predict discharge placement and were assessed by discrimination, calibration, and overall performance.

RESULTS

Nine thousand three hundred and thirty-eight patients were included. Median age was 63 (interquartile range [IQR] 54-71), and 63% (n = 5,887) were female. The non-home discharge rate was 18.6%. Our models included age, sex, diabetes, elective surgery, BMI, procedure, number of levels, ASA class, preoperative white blood cell count, and preoperative creatinine. The Bayes point machine was considered the best model based on discrimination (AUC = 0.753), calibration (slope = 1.111; intercept = - 0.002), and overall model performance (Brier score = 0.132).

CONCLUSION

This study has shown that it is possible to create a predictive machine learning algorithm with both good accuracy and calibration to predict discharge placement. Using our methodology, this type of model can be developed for many other conditions and (elective) treatments. These slides can be retrieved under Electronic Supplementary Material.

Discharge to inpatient facilities after lumbar fusion surgery is associated with increased postoperative venous thromboembolism and readmissions

BACKGROUND CONTEXT

Postdischarge care is a significant source of cost variability after posterior lumbar fusion surgery. However, there remains limited evidence associating postdischarge inpatient services and improved postoperative outcomes, despite the high cost of these services.

PURPOSE

To determine the association between posthospital discharge to inpatient care facilities and postoperative complications.

STUDY DESIGN

A retrospective review of all 1- to 3-level primary posterior lumbar fusion cases in the 2010-2014 National Surgical Quality Improvement Program registry was conducted. Propensity scores for discharge destination were determined based on observable baseline patient characteristics. Multivariable propensity-adjusted logistic regressions were performed to determine associations between discharge destination and postdischarge complications, with adjusted odds ratios (OR) and 95% confidence intervals (CI).

RESULTS

A total of 18,652 posterior lumbar fusion cases were identified, 15,234 (82%) were discharged home, and 3,418 (18%) were discharged to continued inpatient care. Multivariable propensity-adjusted analysis demonstrated that being discharged to inpatient facilities was independently associated with higher risk of thromboembolic complications (OR [95% CI]: 1.79 [1.13-2.85]), urinary complications, (1.79 [1.27-2.51]), and unplanned readmissions (1.43 [1.22-1.68]).

CONCLUSIONS

Discharge to continued inpatient care versus home after primary posterior lumbar fusion is independently associated with higher odds of certain major complications. To optimize clinical outcomes as well as cost savings in an era of value-based reimbursements, clinicians and hospitals should consider further investigation into carefully investigating which patients might be better served by home discharge after surgery.

Improving Complex Pediatric and Adult Spine Care While Embracing the Value Equation

INTRODUCTION

Value in health care is defined as the quotient of outcomes to cost. Both pediatric and adult spinal deformity surgeries are among the most expensive procedures offered today. With high variability in both outcomes and costs in spine surgery today, surgeons will be expected to consider long-term cost effectiveness when comparing treatment options.

METHODS

We summarize various methods by which value can be increased in complex spine surgery, both through the improvement of outcomes and the reduction of cost. These methods center around standardization, team-based and collaborative approaches, rigorous outcomes tracking through dashboards and registries, and continuous process improvement.

RESULTS

This manuscript reviews the expert opinion of leading spine specialists on the improvement of safety, quality and improvement of value of pediatric and adult spinal surgery.

CONCLUSION

Without surgeon leadership in this arena, suboptimal solutions may result from the isolated intervention of regulatory bodies or payer groups. The cooperative development of standardized, team-based approaches in complex spine surgery will lead to the high-quality, high-value care for patients.

Risk factors for nonroutine discharge in adult spinal deformity surgery

BACKGROUND CONTEXT

Surgery for adult spinal deformity (ASD) is increasingly common. Although outcomes of ASD surgery have been studied extensively, to our knowledge, no data exist regarding factors predicting nonroutine discharge in this population. Nonroutine discharge is defined as discharge to a health care facility after surgery rather than to home.

PURPOSE

To determine which patient and surgical factors predict nonroutine discharge after ASD surgery.

DESIGN

This is a retrospective study.

PATIENTS SAMPLE

We conducted a retrospective single-center study of 303 patients who underwent arthrodesis of five or more spinal levels to treat ASD between 2009 and 2014.

OUTCOME MEASURES

Patients were stratified into two groups according to discharge disposition: home or nonroutine.

METHODS

Objective preoperative characteristics, intraoperative course, and postoperative recovery were analyzed to identify pre- and perioperative factors associated with nonroutine discharge. Univariate analysis was performed first. All factors with P values < .2 on univariate analysis were included in a logistic regression model. Additionally, to understand the relationship between subjective patient-reported outcome measures and nonroutine discharge, we compared the two groups with respect to mean Oswestry Disability Index and Scoliosis Research Society-22r domains using Student t-tests.

RESULTS

On univariate analysis, objective measures that differed significantly (P < .05) between the two cohorts were age (≥65 years), osteoporosis, Charlson Comorbidity Index score of ≥2, prolonged hospital stay (>8 days), and blood transfusion. Given the above logistic regression inclusion criteria, we controlled for the performance, and type, of osteotomy (P = .055). On multivariate analysis, older age, osteoporosis, prolonged hospital stay, blood transfusion, and 3-column osteotomy were independently associated with nonroutine discharge. Subjective patient-reported outcome measures, including Oswestry Disability Index and Scoliosis Research Society-22r physical function and pain domain scores, were significantly worse in the nonroutine discharge cohort (P < .05).

CONCLUSION

To our knowledge, this is the first study to evaluate pre- and perioperative factors associated with nonroutine discharge after ASD surgery. Elderly patients who undergo complex surgery and receive blood transfusions are at particularly high risk of nonroutine discharge. Surgeons should consider these factors during surgical planning and preoperative patient counseling.

Continued Inpatient Care After Elective 1- to 2-level Posterior Lumbar Fusions Increases 30-day Postdischarge Readmissions and Complications

STUDY DESIGN

This was a retrospective cohort study.

OBJECTIVE

The main objective of this article was to investigate the impact of discharge destination on postdischarge outcomes following an elective 1- to 2-level posterior lumbar fusion (PLF) for degenerative pathology.

BACKGROUND DATA

Discharge to an inpatient care facility may be associated with adverse outcomes as compared with home discharge.

MATERIALS AND METHODS

The 2012-2016 American College of Surgeons-National Surgical Quality Improvement Program (ACS-NSQIP) database was used to query for patients undergoing PLFs using Current Procedural Terminology (CPT) codes (22612, 22630, and 22633). Additional levels were identified using CPT-22614, CPT-22632, and CPT-22634. Records were filtered to include patients undergoing surgery for degenerative spine pathologies. Only patients undergoing a single-level or 2-level PLF were included in the study. A total of 23,481 patients were included in the final cohort.

RESULTS

A total of 3938 (16.8%) patients were discharged to a skilled care or rehabilitation facility following the primary procedure. Following adjustment for preoperative, intraoperative, and predischarge clinical characteristics, discharge to a skilled care or rehabilitation facility was associated with higher odds of any complication [odds ratio (OR), 1.70; 95% confidence interval (CI), 1.43-2.02], wound complications (OR, 1.73; 95% CI, 1.36-2.20), sepsis-related complications (OR, 1.64; 95% CI, 1.08-2.48), deep venous thrombosis/pulmonary embolism complications (OR, 1.72; 95% CI, 1.10-2.69), urinary tract infections (OR, 1.96; 95% CI, 1.45-2.64), unplanned reoperations (OR, 1.49; 95% CI, 1.23-1.80), and readmissions (OR, 1.29; 95% CI, 1.10-1.49) following discharge.

CONCLUSIONS

After controlling for predischarge characteristics, discharge to skilled care or rehabilitation facilities versus home following 1- to 2-level PLF is associated with higher odds of complications, reoperations, and readmissions. These results stress the importance of careful patient selection before discharge to inpatient care facilities to minimize the risk of complications. Furthermore, the results further support the need for uniform and standardized care pathways to promote home discharge following hospitalization for elective PLFs.

LEVEL OF EVIDENCE

Level III.

Development of machine learning algorithms for prediction of discharge disposition after elective inpatient surgery for lumbar degenerative disc disorders

OBJECTIVE

If not anticipated and prearranged, hospital stay can be prolonged while the patient awaits placement in a rehabilitation unit or skilled nursing facility following elective spine surgery. Preoperative prediction of the likelihood of postoperative discharge to any setting other than home (i.e., nonroutine discharge) after elective inpatient spine surgery would be helpful in terms of decreasing hospital length of stay. The purpose of this study was to use machine learning algorithms to develop an open-access web application for preoperative prediction of nonroutine discharges in surgery for elective inpatient lumbar degenerative disc disorders.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program was queried to identify patients who underwent elective inpatient spine surgery for lumbar disc herniation or lumbar disc degeneration between 2011 and 2016. Four machine learning algorithms were developed to predict nonroutine discharge and the best algorithm was incorporated into an open-access web application.

RESULTS

The rate of nonroutine discharge for 26,364 patients who underwent elective inpatient surgery for lumbar degenerative disc disorders was 9.28%. Predictive factors selected by random forest algorithms were age, sex, body mass index, fusion, level, functional status, extent and severity of comorbid disease (American Society of Anesthesiologists classification), diabetes, and preoperative hematocrit level. On evaluation in the testing set (n = 5273), the neural network had a c-statistic of 0.823, calibration slope of 0.935, calibration intercept of 0.026, and Brier score of 0.0713. On decision curve analysis, the algorithm showed greater net benefit for changing management over all threshold probabilities than changing management on the basis of the American Society of Anesthesiologists classification alone or for all patients or for no patients. The model can be found here: https://sorg-apps.shinyapps.io/discdisposition/.

CONCLUSIONS

Machine learning algorithms show promising results on internal validation for preoperative prediction of nonroutine discharges. If found to be externally valid, widespread use of these algorithms via the open-access web application by healthcare professionals may help preoperative risk stratification of patients undergoing elective surgery for lumbar degenerative disc disorders.

Systematic Changes in the National Surgical Quality Improvement Program Database Over the Years Can Affect Comorbidity Indices Such as the Modified Frailty Index and Modified Charlson Comorbidity Index for Lumbar Fusion Studies

STUDY DESIGN

Retrospective cohort study of prospectively collected data.

OBJECTIVE

The aim of this study was to investigate the influence of changes in the American College of Surgeons National Surgical Quality Improvement Program (NSQIP) database over the years on the calculation of the modified Frailty Index (mFI) and the modified Charlson Comorbidity Index (mCCI) for posterior lumbar fusion studies.

SUMMARY OF BACKGROUND DATA

Multiple studies have utilized the mFI and/or mCCI and showed them to be predictors of adverse postoperative outcomes. However, changes in the NSQIP database have resulted in definition changes and/or missing data for many of the variables included in these indices. No studies have assessed the influence of different methods of treating missing values when calculating these indices on such studies.

METHODS

Elective posterior lumbar fusions were identified in NSQIP from 2005 to 2014. The mFI was calculated for each patient using three methods: treating conditions for which data was missing as not present, dropping patients with missing values, and normalizing by dividing the raw score by the number of variables collected. The mCCI was calculated by the first two of these methods. Mean American Society of Anesthesiologists (ASA) scores used for comparison.

RESULTS

In total, 19,755 patients were identified. Mean ASA score increased between 2005 and 2014 from 2.27 to 2.50 (+10.1%). For each of the methods of data handling noted above, mean mFI over the years studied increased by 33.3%, could not be calculated, and increased by 183.3%, respectively. Mean mCCI increased by 31.2% and could not be calculated respectively.

CONCLUSION

Systematic changes in the NSQIP database have resulted in missing data for many of the variables included in the mFI and the mCCI and may affect studies utilizing these indices. These changes can be understood in the context of ASA trends, and raise questions regarding the use of these indices with data available in later NSQIP years.

LEVEL OF EVIDENCE

3.