Predictive modeling of complications

Risk of spinal surgery among individuals who have been re-vascularized for coronary artery disease

HYPOTHESIS

Revascularization is a more effective intervention to reduce future postop complications.

METHODS

Patients undergoing elective spine fusion surgery were isolated in the PearlDiver database. Patients were stratified by having previous history of vascular stenting (Stent), coronary artery bypass graft (CABG), and no previous heart procedure (No-HP). Means comparison tests (chi-squared and independent samples t-tests, as appropriate) compared differences in demographics, diagnoses, and comorbidities. Binary logistic regression assessed the odds of 30-day and 90-day postoperative (postop) complications associated with each heart procedure (Odds Ratio [95 % confidence interval]). Statistical significance was set p < 0.05.

RESULTS

731,173 elective spine fusion patients included. Overall, 8,401 pts underwent a CABG, 24,037 pts Stent, and 698,735 had No-HP prior to spine fusion surgery. Compared to Stent and No-HP patients, CABG patients had higher rates of morbid obesity, chronic kidney disease, and diabetes (p < 0.001 for all). Meanwhile, stent patients had higher rates of PVD, hypertension, and hyperlipidemia (all p < 0.001). 30-days post-op, CABG patients had significantly higher complication rates including pneumonia, CVA, MI, sepsis, and death compared to No-HP (all p < 0.001). Stent patients vs. No-HF had higher 30-day post-op complication rates including pneumonia, CVA, MI, sepsis, and death. Furthermore, adjusting for age, comorbidities, and sex Stent was significantly predictive of a MI 30-days post-op (OR: 1.90 [1.53-2.34], P < 0.001). Additionally, controlling for levels fused, stent patients compared to CABG patients had 1.99x greater odds of a MI within 30-days (OR: 1.99 [1.26-3.31], p = 0.005) and 2.02x odds within 90-days postop (OR: 2.2 [1.53-2.71, p < 0.001).

CONCLUSION

With regards to spine surgery, coronary artery bypass graft remains the gold standard for risk reduction. Stenting does not appear to minimize risk of experiencing a post-procedure cardiac event as dramatically as CABG.

Predictive model for achieving good clinical and radiographic outcomes at one-year following surgical correction of adult cervical deformity

Background

For cervical deformity (CD) surgery, goals include realignment, improved patient quality of life, and improved clinical outcomes. There is limited research identifying patients most likely to achieve all three.

Objective

The objective is to create a model predicting good 1-year postoperative realignment, quality of life, and clinical outcomes following CD surgery using baseline demographic, clinical, and radiographic factors.

Methods

Retrospective review of a multicenter CD database. CD patients were defined as having one of the following radiographic criteria: Cervical sagittal vertical axis (cSVA) >4 cm, cervical kyphosis/scoliosis >10°° or chin-brow vertical angle >25°. The outcome assessed was whether a patient achieved both a good radiographic and clinical outcome. The primary analysis was stepwise regression models which generated a dataset-specific prediction model for achieving a good radiographic and clinical outcome. Model internal validation was achieved by bootstrapping and calculating the area under the curve (AUC) of the final model with 95% confidence intervals.

Results

Seventy-three CD patients were included (61.8 years, 58.9% F). The final model predicting the achievement of a good overall outcome (radiographic and clinical) yielded an AUC of 73.5% and included the following baseline demographic, clinical, and radiographic factors: mild-moderate myelopathy (Modified Japanese Orthopedic Association >12), no pedicle subtraction osteotomy, no prior cervical spine surgery, posterior lowest instrumented vertebra (LIV) at T1 or above, thoracic kyphosis >33°°, T1 slope <16 and cSVA <20 mm.

Conclusions

Achievement of a positive outcome in radiographic and clinical outcomes following surgical correction of CD can be predicted with high accuracy using a combination of demographic, clinical, radiographic, and surgical factors, with the top factors being baseline cSVA <20 mm, no prior cervical surgery, and posterior LIV at T1 or above.

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.

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

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

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.

Artificial Intelligence for Adult Spinal Deformity

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

Machine Learning Accurately Predicts Short-Term Outcomes Following Open Reduction and Internal Fixation of Ankle Fractures

Ankle fractures are common orthopedic injuries with favorable outcomes when managed with open reduction and internal fixation (ORIF). Several patient-related risk factors may contribute to poor short-term outcomes, and machine learning may be a valuable tool for predicting outcomes. The objective of this study was to evaluate machine-learning algorithms for accurately predicting short-term outcomes after ORIF for ankle fractures. The Nationwide Inpatient Sample and Nationwide Readmissions Database were queried for adult patients ≥18 years old who underwent ORIF of an ankle fracture during 2013 or 2014. Morbidity and mortality, length of stay >3 days, and 30-day all-cause readmission were the outcomes of interest. Two machine-learning models were created to identify patient and hospital characteristics associated with the 3 outcomes. The machine learning models were evaluated using confusion matrices and receiver operating characteristic area under the curve values. A total of 16,501 cases were drawn from the Nationwide Inpatient Sample and used to assess morbidity and mortality and length of stay >3 days, and 33,504 cases were drawn from the Nationwide Readmissions Database to assess 30-day readmission. Older age, Medicaid, Medicare, deficiency anemia, congestive heart failure, chronic lung disease, diabetes, hypertension, and renal failure were the variables associated with a statistically significant increased risk of developing all 3 adverse events. Logistic regression and gradient boosting had similar area under the curve values for each outcome, but gradient boosting was more accurate and more specific for predicting each outcome. Our results suggest that several comorbidities may be associated with adverse short-term outcomes after ORIF of ankle fractures, and that machine learning can accurately predict these outcomes.

Predicting Clinical Outcomes Following Surgical Correction of Adult Spinal Deformity

BACKGROUND

Deformity reconstruction surgery has been shown to improve quality of life (QOL) in cases of adult spinal deformity (ASD) but is associated with significant morbidity.

OBJECTIVE

To create a preoperative predictive nomogram to help risk-stratify patients and determine which would likely benefit from corrective surgery for ASD as measured by patient-reported health-related quality of life (HRQoL).

METHODS

All patients aged 25-yr and older with radiographic evidence of ASD and QOL data that underwent thoracolumbar fusion between 2008 and 2014 were identified. Demographic and clinical parameters were obtained. The EuroQol 5 dimensions questionnaire (EQ-5D) was used to measure HRQoL preoperatively and at 12-mo postoperative follow-up. Logistic regression of preoperative variables was used to create the prognostic nomogram.

RESULTS

Our sample included data from 191 patients. Fifty-one percent of patients experienced clinically relevant postoperative improvement in HRQoL. Seven variables were included in the final model: preoperative EQ-5D score, sex, preoperative diagnosis (degenerative, idiopathic, or iatrogenic), previous spinal surgical history, obesity, and a sex-by-obesity interaction term. Preoperative EQ-5D score independently predicted the outcome. Sex interacted with obesity: obese men were at disproportionately higher odds of improving than nonobese men, but obesity did not affect odds of the outcome among women. Model discrimination was good, with an optimism-adjusted c-statistic of 0.739.

CONCLUSION

The predictive nomogram that we developed using these data can improve preoperative risk counseling and patient selection for deformity correction surgery.

Development of a Preoperative Predictive Model for Reaching the Oswestry Disability Index Minimal Clinically Important Difference for Adult Spinal Deformity Patients

STUDY DESIGN

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

OBJECTIVE

To create a model based on baseline demographic, radiographic, health-related quality of life (HRQOL), and surgical factors that can predict patients meeting the Oswestry Disability Index (ODI) minimal clinically important difference (MCID) at the two-year postoperative follow-up.

SUMMARY OF BACKGROUND DATA

Surgical correction of ASD can result in significant improvement in disability as measured by ODI, with the goal of reaching at least one MCID. However, a predictive model for reaching MCID following ASD correction does not exist.

METHODS

ASD patients ≥18 years and baseline ODI ≥ 30 were included. Initial training of the model comprised forty-three variables including demographic data, comorbidities, modifiable surgical variables, baseline HRQOL, and coronal/sagittal radiographic parameters. Patients were grouped by whether or not they reached at least one ODI MCID at two-year follow-up. Decision trees were constructed using the C5.0 algorithm with five different bootstrapped models. Internal validation was accomplished via a 70:30 data split for training and testing each model, respectively. Final predictions from the models were chosen by voting with random selection for tied votes. Overall accuracy, and the area under a receiver operating characteristic curve (AUC) were calculated.

RESULTS

198 patients were included (MCID: 109, No-MCID: 89). Overall model accuracy was 86.0%, with an AUC of 0.94. The top 11 predictors of reaching MCID were gender, Scoliosis Research Society (SRS) activity subscore, back pain, sagittal vertical axis (SVA), pelvic incidence-lumbar lordosis mismatch (PI-LL), primary version revision, T1 spinopelvic inclination angle (T1SPI), American Society of Anesthesiologists (ASA) grade, T1 pelvic angle (T1PA), SRS pain, SRS total.

CONCLUSIONS

A successful model was built predicting ODI MCID. Most important predictors were not modifiable surgical parameters, indicating that baseline clinical and radiographic status is a critical factor for reaching ODI MCID.

LEVEL OF EVIDENCE

Level II.

Development of a validated computer-based preoperative predictive model for pseudarthrosis with 91% accuracy in 336 adult spinal deformity patients

OBJECTIVE

Pseudarthrosis can occur following adult spinal deformity (ASD) surgery and can lead to instrumentation failure, recurrent pain, and ultimately revision surgery. In addition, it is one of the most expensive complications of ASD surgery. Risk factors contributing to pseudarthrosis in ASD have been described; however, a preoperative model predicting the development of pseudarthrosis does not exist. The goal of this study was to create a preoperative predictive model for pseudarthrosis based on demographic, radiographic, and surgical factors.

METHODS

A retrospective review of a prospectively maintained, multicenter ASD database was conducted. Study inclusion criteria consisted of adult patients (age ≥ 18 years) with spinal deformity and surgery for the ASD. From among 82 variables assessed, 21 were used for model building after applying collinearity testing, redundancy, and univariable predictor importance ≥ 0.90. Variables included demographic data along with comorbidities, modifiable surgical variables, baseline coronal and sagittal radiographic parameters, and baseline scores for health-related quality of life measures. Patients groups were determined according to their Lenke radiographic fusion type at the 2-year follow-up: bilateral or unilateral fusion (union) or pseudarthrosis (nonunion). A decision tree was constructed, and internal validation was accomplished via bootstrapped training and testing data sets. Accuracy and the area under the receiver operating characteristic curve (AUC) were calculated to evaluate the model.

RESULTS

A total of 336 patients were included in the study (nonunion: 105, union: 231). The model was 91.3% accurate with an AUC of 0.94. From 82 initial variables, the top 21 covered a wide range of areas including preoperative alignment, comorbidities, patient demographics, and surgical use of graft material.

CONCLUSIONS

A model for predicting the development of pseudarthrosis at the 2-year follow-up was successfully created. This model is the first of its kind for complex predictive analytics in the development of pseudarthrosis for patients with ASD undergoing surgical correction and can aid in clinical decision-making for potential preventative strategies.

Potential of predictive computer models for preoperative patient selection to enhance overall quality-adjusted life years gained at 2-year follow-up: a simulation in 234 patients with adult spinal deformity

OBJECTIVE Patients with adult spinal deformity (ASD) experience significant quality of life improvements after surgery. Treatment, however, is expensive and complication rates are high. Predictive analytics has the potential to use many variables to make accurate predictions in large data sets. A validated minimum clinically important difference (MCID) model has the potential to assist in patient selection, thereby improving outcomes and, potentially, cost-effectiveness. METHODS The present study was a retrospective analysis of a multiinstitutional database of patients with ASD. Inclusion criteria were as follows: age ≥ 18 years, radiographic evidence of ASD, 2-year follow-up, and preoperative Oswestry Disability Index (ODI) > 15. Forty-six variables were used for model training: demographic data, radiographic parameters, surgical variables, and results on the health-related quality of life questionnaire. Patients were grouped as reaching a 2-year ODI MCID (+MCID) or not (-MCID). An ensemble of 5 different bootstrapped decision trees was constructed using the C5.0 algorithm. Internal validation was performed via 70:30 data split for training/testing. Model accuracy and area under the curve (AUC) were calculated. The mean quality-adjusted life years (QALYs) and QALYs gained at 2 years were calculated and discounted at 3.5% per year. The QALYs were compared between patients in the +MCID and -MCID groups. RESULTS A total of 234 patients met inclusion criteria (+MCID 129, -MCID 105). Sixty-nine patients (29.5%) were included for model testing. Predicted versus actual results were 50 versus 40 for +MCID and 19 versus 29 for -MCID (i.e., 10 patients were misclassified). Model accuracy was 85.5%, with 0.96 AUC. Predicted results showed that patients in the +MCID group had significantly greater 2-year mean QALYs (p = 0.0057) and QALYs gained (p = 0.0002). CONCLUSIONS A successful model with 85.5% accuracy and 0.96 AUC was constructed to predict which patients would reach ODI MCID. The patients in the +MCID group had significantly higher mean 2-year QALYs and QALYs gained. This study provides proof of concept for using predictive modeling techniques to optimize patient selection in complex spine surgery.

Development of a preoperative predictive model for major complications following adult spinal deformity surgery

OBJECTIVE The operative management of patients with adult spinal deformity (ASD) has a high complication rate and it remains unknown whether baseline patient characteristics and surgical variables can predict early complications (intraoperative and perioperative [within 6 weeks]). The development of an accurate preoperative predictive model can aid in patient counseling, shared decision making, and improved surgical planning. The purpose of this study was to develop a model based on baseline demographic, radiographic, and surgical factors that can predict if patients will sustain an intraoperative or perioperative major complication. METHODS This study was a retrospective analysis of a prospective, multicenter ASD database. The inclusion criteria were age ≥ 18 years and the presence of ASD. In total, 45 variables were used in the initial training of the model including demographic data, comorbidities, modifiable surgical variables, baseline health-related quality of life, and coronal and sagittal radiographic parameters. Patients were grouped as either having at least 1 major intraoperative or perioperative complication (COMP group) or not (NOCOMP group). An ensemble of decision trees was constructed utilizing the C5.0 algorithm with 5 different bootstrapped models. Internal validation was accomplished via a 70/30 data split for training and testing each model, respectively. Overall accuracy, the area under the receiver operating characteristic (AUROC) curve, and predictor importance were calculated. RESULTS Five hundred fifty-seven patients were included: 409 (73.4%) in the NOCOMP group, and 148 (26.6%) in the COMP group. The overall model accuracy was 87.6% correct with an AUROC curve of 0.89 indicating a very good model fit. Twenty variables were determined to be the top predictors (importance ≥ 0.90 as determined by the model) and included (in decreasing importance): age, leg pain, Oswestry Disability Index, number of decompression levels, number of interbody fusion levels, Physical Component Summary of the SF-36, Scoliosis Research Society (SRS)-Schwab coronal curve type, Charlson Comorbidity Index, SRS activity, T-1 pelvic angle, American Society of Anesthesiologists grade, presence of osteoporosis, pelvic tilt, sagittal vertical axis, primary versus revision surgery, SRS pain, SRS total, use of bone morphogenetic protein, use of iliac crest graft, and pelvic incidence-lumbar lordosis mismatch. CONCLUSIONS A successful model (87% accuracy, 0.89 AUROC curve) was built predicting major intraoperative or perioperative complications following ASD surgery. This model can provide the foundation toward improved education and point-of-care decision making for patients undergoing ASD surgery.