Predicting High-Value Care Outcomes After Surgery for Skull Base Meningiomas

Machine Learning Models for Predicting Postoperative Outcomes following Skull Base Meningioma Surgery

Objective  While predictive analytic techniques have been used to analyze meningioma postoperative outcomes, to our knowledge, there have been no studies that have investigated the utility of machine learning (ML) models in prognosticating outcomes among skull base meningioma patients. The present study aimed to develop models for predicting postoperative outcomes among skull base meningioma patients, specifically prolonged hospital length of stay (LOS), nonroutine discharge disposition, and high hospital charges. We also validated the predictive performance of our models on out-of-sample testing data. Methods  Patients who underwent skull base meningioma surgery between 2016 and 2019 at an academic institution were included in our study. Prolonged hospital LOS and high hospital charges were defined as >4 days and >$47,887, respectively. Elastic net logistic regression algorithms were trained to predict postoperative outcomes using 70% of available data, and their predictive performance was evaluated on the remaining 30%. Results  A total of 265 patients were included in our final analysis. Our cohort was majority female (77.7%) and Caucasian (63.4%). Elastic net logistic regression algorithms predicting prolonged LOS, nonroutine discharge, and high hospital charges achieved areas under the receiver operating characteristic curve of 0.798, 0.752, and 0.592, respectively. Further, all models were adequately calibrated as determined by the Spiegelhalter Z -test ( p >0.05). Conclusion  Our study developed models predicting prolonged hospital LOS, nonroutine discharge disposition, and high hospital charges among skull base meningioma patients. Our models highlight the utility of ML as a tool to aid skull base surgeons in providing high-value health care and optimizing clinical workflows.

Predictors of surgical site infection in glioblastoma patients undergoing craniotomy for tumor resection

OBJECTIVE

Surgical site infections (SSIs) burden patients and healthcare systems, often requiring additional intervention. The objective of this study was to identify the relationship between preoperative predictors inclusive of scalp incision type and postoperative SSI following glioblastoma resection.

METHODS

The authors retrospectively reviewed cases of glioblastoma resection performed at their institution from December 2006 to December 2019 and noted preoperative demographic and clinical presentations, excluding patients missing these data. Preoperative nutritional indices were available for a subset of cases. Scalp incisions were categorized as linear/curvilinear, reverse question mark, trapdoor, or frontotemporal. Patients were dichotomized by SSI incidence. Multivariable logistic regression was used to determine predictors of SSI.

RESULTS

A total of 911 cases of glioblastoma resection were identified, 30 (3.3%) of which demonstrated postoperative SSI. There were no significant differences in preoperative malnutrition or number of surgeries between SSI and non-SSI cases. The SSI cases had a significantly lower preoperative Karnofsky Performance Status (KPS) than the non-SSI cases (63.0 vs 75.1, p < 0.0001), were more likely to have prior radiation history (43.3% vs 26.4%, p = 0.042), and were more likely to have received steroids both preoperatively and postoperatively (83.3% vs 54.5%, p = 0.002). Linear/curvilinear incisions were more common in non-SSI than in SSI cases (56.9% vs 30.0%, p = 0.004). Trapdoor scalp incisions were more frequent in SSI than non-SSI cases (43.3% vs 24.2%, p = 0.012). On multivariable analysis, a lower preoperative KPS (OR 1.04, 95% CI 1.02–1.06), a trapdoor scalp incision (OR 3.34, 95% CI 1.37–8.49), and combined preoperative and postoperative steroid administration (OR 3.52, 95% CI 1.41–10.7) were independently associated with an elevated risk of postoperative SSI.

CONCLUSIONS

The study findings indicated that SSI risk following craniotomy for glioblastoma resection may be elevated in patients with a low preoperative KPS, a trapdoor scalp incision during surgery, and steroid treatment both preoperatively and postoperatively. These data may help guide future operative decision-making for these patients.

Safety and Cost Savings Associated with Reduced Inpatient Hospitalization for Microvascular Decompression

OBJECTIVES

Microvascular decompression (MVD) has grown as a first-line surgical intervention for severe facial pain from trigeminal neuralgia and/or hemifacial spasm. We sought to examine the safety and cost-benefits of discharging patients with MVD within 1 day of admission.

METHODS

We retrospectively reviewed patients undergoing MVD at our institution from 2008 to 2020. Patients were sorted by 1 day, 2 days, or >2 days until discharge and by year from 2008 to 2013, 2014 to 2018, or 2019 to 2020. Patient presenting characteristics, intraoperative measures, and complications were documented. Statistical differences were calculated by one-way analysis of variance and χ2 analyses.

RESULTS

Our cohort included 976 patients undergoing MVD, with 231 (23.6%) between 2008 and 2013, 517 (52.9%) between 2014 and 2018, and 228 (23.3%) between 2019 and 2020. Over time, postoperative admission rates to the critical care unit, total inpatient hospital admission times, and Barrow Neurological Institute scores at first follow-up decreased. Postoperative complications, including cerebrospinal fluid leak, decreased significantly. In addition, patients discharged within 1 day of admission incurred a total hospital cost of $26,689, which was $3588 lower than patients discharged within more than 1 day of admission, P < 0.0001. Discharging carefully selected patients who are appropriate for discharge within 1 day of admission could translate to a potential cost-savings of $255,346 per year in our clinical practice.

CONCLUSIONS

In our experience, MVDs are a safe, elective intervention. Our findings suggest that postoperative day 1 discharge in patients with an uncomplicated postoperative course may be safe while improving hospital resource use.

Novel Predictive Models for High-Value Care Outcomes Following Glioblastoma Resection

BACKGROUND

Treating patients with glioblastoma (GBM) requires extensive medical infrastructure. Individualized risk assessment for extended length of stay (LOS), nonroutine discharge disposition, and increased total hospital charges is critical to optimize delivery of care. Our study sought to develop predictive models identifying independent risk factors for these outcomes.

METHODS

We retrospectively reviewed patients undergoing GBM resection at our institution between January 2017 and September 2020. Extended LOS and elevated hospital charges were defined as values in the upper quartile of the cohort. Nonroutine discharge was defined as any disposition other than to home. Multivariate models for each outcome included covariates demonstrating P ≤ 0.10 on bivariate analysis.

RESULTS

We identified 265 patients undergoing GBM resection, with an average age of 58.2 years. 24.5% of patients experienced extended LOS, 22.6% underwent nonroutine discharge, and 24.9% incurred elevated total hospital charges. Decreasing Karnofsky Performance Status (KPS) (P = 0.004), increasing modified 5-factor frailty (mFI-5) index (P = 0.012), lower surgeon experience (P = 0.005), emergent surgery (P < 0.0001), and larger tumor volume (P < 0.0001) predicted extended LOS. Independent predictors of nonroutine discharge included older age (P = 0.02), decreasing KPS (P < 0.0001), and emergent surgery (P = 0.048). Nonprivate insurance (P = 0.011), decreasing KPS (P = 0.029), emergent surgery (P < 0.0001), and larger tumor volume (P = 0.004) predicted elevated hospital charges. These models were incorporated into an open-access online calculator (https://neurooncsurgery3.shinyapps.io/gbm_calculator/).

CONCLUSIONS

Several factors were independent predictors for at least 1 high-value care outcome, with lower KPS and emergent admission associated with each outcome. These models and our calculator may help clinicians provide individualized postoperative risk assessment to glioblastoma patients.

Predicting High-Value Care Outcomes After Surgery for Non-Skull Base Meningiomas

OBJECTIVE

A need exists to better understand the prognostic factors that influence high-value care outcomes after meningioma surgery. The goal of the present study was to develop predictive models to determine the patients at risk of experiencing an extended hospital length of stay (LOS), nonroutine discharge disposition, and/or a 90-day hospital readmission after non-skull base meningioma resection.

METHODS

In the present study, we analyzed the data from 396 patients who had undergone surgical resection of non-skull base meningiomas at a single institution between January 1, 2005 and December 31, 2020. The Mann-Whitney U test was used for bivariate analysis of the continuous variables and the Fisher exact test for bivariate analysis of the categorical variables. A multivariate analysis was conducted using logistic regression models.

RESULTS

Most patients had had a falcine or parasagittal meningioma (66.2%), with the remainder having convexity (31.8%) or intraventricular (2.0%) tumors. Nonelective surgery (P < 0.0001) and an increased tumor volume (P = 0.0022) were significantly associated with a LOS >4 days on multivariate analysis. The independent predictors of a nonroutine discharge disposition included male sex (P = 0.0090), nonmarried status (P = 0.024), nonelective surgery (P = 0.0067), tumor location within the parasagittal or intraventricular region (P = 0.0084), and an increased modified frailty index score (P = 0.039). Hospital readmission within 90 days was independently associated with nonprivate insurance (P = 0.010) and nonmarried status (P = 0.0081). Three models predicting for a prolonged LOS, nonroutine discharge disposition, and 90-day readmission were implemented in the form of an open-access, online calculator (available at: https://neurooncsurgery3.shinyapps.io/non_skull_base_meningiomas/).

CONCLUSIONS

After external validation, our open-access, online calculator could be useful for assessing the likelihood of adverse postoperative outcomes for patients undergoing surgery of non-skull base meningioma.