Explainable Machine Learning Approach to Prediction of Prolonged Intesive Care Unit Stay in Adult Spinal Deformity Patients: Machine Learning Outperforms Logistic Regression.

STUDY DESIGN: Retrospective cohort study. OBJECTIVES: Prolonged ICU stay is a driver of higher costs and inferior outcomes in Adult Spinal Deformity (ASD) patients. Machine learning (ML) models have recently been seen as a viable method of predicting pre-operative risk but are often 'black boxes' that do not fully explain the decision-making process. This study aims to demonstrate ML can achieve similar or greater predictive power as traditional statistical methods and follows traditional clinical decision-making processes. METHODS: Five ML models (Decision Tree, Random Forest, Support Vector Classifier, GradBoost, and a CNN) were trained on data collected from a large urban academic center to predict whether prolonged ICU stay would be required post-operatively. 535 patients who underwent posterior fusion or combined fusion for treatment of ASD were included in each model with a 70-20-10 train-test-validation split. Further analysis was performed using Shapley Additive Explanation (SHAP) values to provide insight into each model's decision-making process. RESULTS: The model's Area Under the Receiver Operating Curve (AUROC) ranged from 0.67 to 0.83. The Random Forest model achieved the highest score. The model considered length of surgery, complications, and estimated blood loss to be the greatest predictors of prolonged ICU stay based on SHAP values. CONCLUSIONS: We developed a ML model that was able to predict whether prolonged ICU stay was required in ASD patients. Further SHAP analysis demonstrated our model aligned with traditional clinical thinking. Thus, ML models have strong potential to assist with risk stratification and more effective and cost-efficient care.

Medicare payment trends compared to inflation for anesthesia services.

STUDY OBJECTIVE: Identify changes and trends in the real value of Medicare payments for anesthesia services between 2000 and 2020 and how it may affect practices. DESIGN: Retrospective analysis. SETTING: We utilized the Physician/Supplier Procedure Summary (PSPS) datasets of Medicare Part B claims to identify high volume anesthesia services in 2020 with 20 years of data. The Consumer Price Index was used as a measure of inflation to adjust prices. PATIENTS: The PSPS datasets contain summaries of all annual Medicare Part B claims and payment amounts by carrier and locality. INTERVENTIONS: Patients receiving anesthesia services. MEASUREMENTS: For each service, identified by Current Procedural Terminology (CPT) codes, we trended the average Medicare payment per procedure from 2000 to 2020 and calculated year to year changes and compound annual growth rate (CAGR). We also evaluated base and time units for each CPT code and the national Medicare anesthesia conversion factor (CF) for the same years. MAIN RESULTS: The average Medicare payment in the study sample increased 20.1% from 2000 to 2020. After adjusting for inflation, the average Medicare payment per anesthesia service decreased by 20.8% over that period. The Medicare anesthesia CF increased 24.9% in the same period, and after adjusting for inflation, the real value of the CF decreased 16.9%. Average CAGR across the 20 anesthesia services was 0.88%, compared to the average annual inflation at 2.06%. CONCLUSIONS: Average Medicare payment for common anesthesia services after adjusting for inflation have decreased from 2000 to 2020, consistent with findings in other physician specialties. Understanding these trends is important for practice viability and suggests significant financial implications for anesthesia practices and hospitals if the trend were to continue.

Scoping Review: Anesthesiologist Involvement in Alternative Payment Models, Value Measurement, and Nonclinical Capabilities for Success in the United States of America.

The US healthcare sector is undergoing significant payment reforms, leading to the emergence of Alternative Payment Models (APMs) aimed at improving clinical outcomes and patient experiences while reducing costs. This scoping review provides an overview of the involvement of anesthesiologists in APMs as found in published literature. It specifically aims to categorize and understand the breadth and depth of their participation, revolving around 3 main axes or "Aims": (1) shaping APMs through design and implementation, (2) gauging the value and quality of care provided by anesthesiologists within these models, and (3) enhancing nonclinical abilities of anesthesiologists for promoting more value in care. To map out the existing literature, a comprehensive search of relevant electronic databases was conducted, yielding a total of 2173 articles, of which 24 met the inclusion criteria, comprising 21 prospective or retrospective cohort studies, 2 surveys, and 1 case-control cohort study. Eleven publications (45%) discussed value-based, bundled, or episode-based payments, whereas the rest discussed non-payment-based models, such as Enhanced Recovery After Surgery (7 articles, 29%), Perioperative Surgical Home (4 articles, 17%), or other models (3 articles, 13%).The review identified key themes related to each aim. The most prominent themes for aim 1 included protocol standardization (16 articles, 67%), design and implementation leadership (8 articles, 33%), multidisciplinary collaboration (7 articles, 29%), and role expansion (5 articles, 21%). For aim 2, the common themes were Process-Based & Patient-Centric Metrics (1 article, 4%), Shared Accountability (3 articles, 13%), and Time-Driven Activity-Based Costing (TDABC) (3 articles, 13%). Furthermore, we identified a wide range of quality metrics, spanning 8 domains that were used in these studies to evaluate anesthesiologists' performance. For aim 3, the main extracted themes included Education on Healthcare Transformation and Policies (3 articles, 13%), Exploring Collaborative Leadership Skills (5 articles, 21%), and Embracing Advanced Analytics and Data Transparency (4 articles, 17%).Findings revealed the pivotal role of anesthesiologists in the design, implementation, and refinement of these emerging delivery and payment models. Our results highlight that while payment models are shifting toward value, patient-centered metrics have yet to be widely accepted for use in measuring quality and affecting payment for anesthesiologists. Gaps remain in understanding how anesthesiologists assess their direct impact and strategies for enhancing the sustainability of anesthesia practices. This review underscores the need for future research contributing to the successful adaptation of clinical practices in this new era of healthcare delivery.

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.

Clinical Considerations and Outcomes for Spine Surgery Patients with a History of Transplant: A Systematic Scoping Review.

OBJECTIVE: The objective of this study was to investigate the perioperative management and outcomes of patients with a prior history of successful transplantation undergoing spine surgery. METHODS: We searched Medline, Embase, and Cochrane Central Register of Controlled Trials for matching reports in July 2021. We included case reports, cohort studies, and retrospective analyses, including terms for various transplant types and an exhaustive list of key words for various forms of spine surgery. RESULTS: We included 45 studies consisting of 34 case reports (published 1982-2021), 3 cohort analyses (published 2005-2006), and 8 retrospective analyses (published 2006-2020). The total number of patients included in the case reports, cohort studies, and retrospective analysis was 35, 48, and 9695, respectively. The mean 1-year mortality rate from retrospective analyses was 4.6% ± 1.93%, while the prevalence of perioperative complications was 24%. Cohort studies demonstrated an 8.5% ± 12.03% 30-day readmission rate. The most common procedure performed was laminectomy (38.9%) among the case reports. Mortality after spine surgery was noted for 4 of 35 case report patients (11.4%). CONCLUSIONS: This is the first systematic scoping review examining the population of transplant patients with subsequent unrelated spine surgery. There is significant heterogeneity in the outcomes of post-transplant spine surgery patients. Given the inherent complexity of managing this group and elevated mortality and complications compared to the general spine surgery population, further investigation into their clinical care is warranted.

An 11-Year-Long Analysis of the Risks Associated With Age in Patients Undergoing Anterior Cervical Discectomy and Fusion in a Large, Urban Academic Hospital.

STUDY DESIGN: A retrospective database study of patients at an urban academic medical center undergoing an Anterior Cervical Discectomy and Fusion (ACDF) surgery between 2008 and 2019. OBJECTIVE: ACDF is one of the most common spinal procedures. Old age has been found to be a common risk factor for postoperative complications across a plethora of spine procedures. Little is known about how this risk changes among elderly cohorts such as the difference between elderly (60+) and octogenarian (80+) patients. This study seeks to analyze the disparate rates of complications following elective ACDF between patients aged 60-69 or 70-79 and 80+ at an urban academic medical center. METHODS: We identified patients who had undergone ACDF procedures using CPT codes 22,551, 22,552, and 22,554. Emergent procedures were excluded, and patients were subdivided on the basis of age. Then each cohort was propensity matched for univariate and univariate logistic regression analysis. RESULTS: The propensity matching resulted in 25 pairs in both the 70-79 and 80+ y.o. cohort comparison and 60-69 and 80+ y.o. cohort comparison. None of the cohorts differed significantly in demographic variables. Differences between elderly cohorts were less pronounced: the 80+ y.o. cohort experienced only significantly higher total direct cost (P = .03) compared to the 70-79 y.o. cohort and significantly longer operative time (P = .04) compared to the 60-69 y.o. cohort. CONCLUSIONS: Octogenarian patients do not face much riskier outcomes following elective ACDF procedures than do younger elderly patients. Age alone should not be used to screen patients for ACDF.

Analgesic options for anterior approach to scoliosis repair: a scoping review.

PURPOSE: The ideal analgesic regimen for the anterior approach to scoliosis repair is not clearly defined. The purpose of the study was to summarize and identify gaps in the current literature specific to the anterior approach to scoliosis repair. METHODS: A scoping review was conducted in July 2022 utilizing PubMed, Cochrane, and Scopus databases guided by the PRISMA-ScR framework. RESULTS: The database search generated 641 possible articles, 13 of which met all inclusion criteria. All articles focused on the effectiveness and safety of regional anesthetic techniques, while a minority also provided both opioid and non-opioid medication frameworks. CONCLUSION: Continuous Epidural Analgesia (CEA) is the most well-studied intervention for pain control in anterior scoliosis repair, but other, more novel regional anesthetic techniques offer safe and effective potential alternatives. More research is indicated to compare the effectiveness of different regional techniques and perioperative medication regimens specific to anterior scoliosis repair.

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.

Seasonal Effects on Postoperative Complications After Spinal Surgery: A National Database Analysis.

OBJECTIVE: To investigate the role of seasonality on postoperative complications after spinal surgery. METHODS: Data were obtained from the American College of Surgeons National Surgical Quality Improvement Program database from 2011 to 2018. Current Procedural Terminology codes were used to identify the following procedures: posterior cervical decompression and fusion, cervical laminoplasty, posterior lumbar fusion, lumbar laminectomy, and spinal deformity surgery. The database was queried for deep vein thrombosis (DVT), pulmonary embolism, pneumonia, sepsis, septic shock, Clostridium difficile infection, stroke, cardiac arrest, myocardial infarction, urinary tract infection (UTI), and early unplanned hospital readmission (readmission). Warm season was defined as April-September, whereas cold season was defined as October-March. Statistical analysis included computing overall complication rates and comparison between seasons using univariate analysis and multivariable logistic regression. RESULTS: A total of 208,291 individuals underwent spinal surgery from 2011 to 2018. There was a statistically significant increase in UTI (odds ratio [OR], 1.16; 95% confidence interval [CI], 1.07-1.26; P = 0.0002) and readmission (OR, 1.06; 95% CI, 1.02-1.11, P = 0.007) in the warm season compared with the cold season. An investigation into the July effect showed increases in DVT (OR, 1.24; 95% CI, 1.03-1.48; P = 0.020) and thromboembolic events (OR 1.17; 95% CI, 1.01-1.35; P = 0.032) in July-September compared with the preceding 3 months. CONCLUSIONS: The results showed a higher incidence of UTI and readmission among spine surgery patients in the warm season and a higher incidence of DVT and thromboembolic events from July to September. In both cases, the effect of seasonality is statistically significant, but the absolute difference is small and may not suggest policy changes.

Visual Analytics to Leverage Anesthesia Electronic Health Record.

BACKGROUND: Visual analytics is the science of analytical reasoning supported by interactive visual interfaces called dashboards. In this report, we describe our experience addressing the challenges in visual analytics of anesthesia electronic health record (EHR) data using a commercially available business intelligence (BI) platform. As a primary outcome, we discuss some performance metrics of the dashboards, and as a secondary outcome, we outline some operational enhancements and financial savings associated with deploying the dashboards. METHODS: Data were transferred from the EHR to our departmental servers using several parallel processes. A custom structured query language (SQL) query was written to extract the relevant data fields and to clean the data. Tableau was used to design multiple dashboards for clinical operation, performance improvement, and business management. RESULTS: Before deployment of the dashboards, detailed case counts and attributions were available for the operating rooms (ORs) from perioperative services; however, the same level of detail was not available for non-OR locations. Deployment of the yearly case count dashboards provided near-real-time case count information from both central and non-OR locations among multiple campuses, which was not previously available. The visual presentation of monthly data for each year allowed us to recognize seasonality in case volumes and adjust our supply chain to prevent shortages. The dashboards highlighted the systemwide volume of cases in our endoscopy suites, which allowed us to target these supplies for pricing negotiations, with an estimated annual cost savings of $250,000. Our central venous pressure (CVP) dashboard enabled us to provide individual practitioner feedback, thus increasing our monthly CVP checklist compliance from approximately 92% to 99%. CONCLUSIONS: The customization and visualization of EHR data are both possible and worthwhile for the leveraging of information into easily comprehensible and actionable data for the improvement of health care provision and practice management. Limitations inherent to EHR data presentation make this customization necessary, and continued open access to the underlying data set is essential.