Ghaith, Abdul Karim

OBJECTIVE Chordomas are rare tumors of the skull base and spine believed to arise from the vestiges of the embryonic notochord. These tumors are locally aggressive and frequently recur following resection and adjuvant radiotherapy. Proton therapy has been introduced as a tissue-sparing option because of the higher level of precision that proton-beam techniques offer compared with traditional photon radiotherapy. This study aimed to compare recurrence in patients with chordomas receiving proton versus photon radiotherapy following resection by applying tree-based machine learning models. METHODS The clinical records of all patients treated with resection followed by adjuvant proton or photon radiotherapy for chordoma at Mayo Clinic were reviewed. Patient demographics, type of surgery and radiotherapy, tumor recurrence, and other variables were extracted. Decision tree classifiers were trained and tested to predict long-term recurrence based on unseen data using an 80/20 split. RESULTS Fifty-three patients with a mean ± SD age of 55.2 ± 13.4 years receiving surgery and adjuvant proton or photon therapy to treat chordoma were identified; most patients were male. Gross-total resection was achieved in 54.7% of cases. Proton therapy was the most common adjuvant radiotherapy (84.9%), followed by conventional or external-beam radiation therapy (9.4%) and stereotactic radiosurgery (5.7%). Patients receiving proton therapy exhibited a 40% likelihood of having recurrence, significantly lower than the 88% likelihood observed in those treated with nonproton therapy. This was confirmed on logistic regression analysis adjusted for extent of tumor resection and tumor location, which revealed that proton adjuvant radiotherapy was associated with a decreased risk of recurrence (OR 0.1, 95% CI 0.01–0.71; p = 0.047) compared with photon therapy. The decision tree algorithm predicted recurrence with an accuracy of 90% (95% CI 55.5%–99.8%), with the lowest risk of recurrence observed in patients receiving gross-total resection with adjuvant proton therapy (23%). CONCLUSIONS Following resection, adjuvant proton therapy was associated with a lower risk of chordoma recurrence compared with photon therapy. The described machine learning models were able to predict tumor progression based on the extent of tumor resection and adjuvant radiotherapy modality used.

OBJECTIVE Chiari malformation type I (CM-I) is a congenital disorder occurring in 0.1% of the population. In symptomatic cases, surgery with posterior fossa decompression (PFD) is the treatment of choice. Surgery is, however, associated with peri- and postoperative complications that may require readmission or renewed surgical intervention. Given the associated financial costs and the impact on patients’ well-being, there is a need for predictive tools that can assess the likelihood of such adverse events. The aim of this study was therefore to leverage machine learning algorithms to develop a predictive model for 30-day readmissions and reoperations after PFD in pediatric patients with CM-I. METHODS This was a retrospective study based on data from the National Surgical Quality Improvement Program–Pediatric database. Eligible patients were those undergoing PFD (Current Procedural Terminology code 61343) for CM-I between 2012 and 2021. Patients undergoing surgery for tumors or vascular lesions were excluded. Unplanned 30-day readmission and unplanned 30-day reoperation were the main study outcomes. Additional outcome data considered included the length of hospital stay, 30-day complications, discharge disposition, and 30-day mortality. Training and testing samples were randomly generated (80:20) to study the 30-day readmission and reoperation using logistic regression, decision tree, random forest (RF), K-nearest neighbors, and Gaussian naive Bayes algorithms. RESULTS A total of 7106 pediatric patients undergoing PFD were included. The median age was 9.2 years (IQR 4.7, 14.2 years). Most of the patients were female (56%). The 30-day readmission and reoperation rates were 7.5% and 3.4%, respectively. Headaches (32%) and wound-related complications (30%) were the most common reasons for 30-day readmission, while wound revisions and evacuation of fluid or blood (62%), followed by CSF diversion-related procedures (28%), were the most common reasons for 30-day reoperation. RF classifiers had the highest predictive accuracy for both 30-day readmissions (area under the curve [AUC] 0.960) and reoperations (AUC 0.990) compared with the other models. On feature importance analysis, sex, developmental delay, ethnicity, respiratory disease, premature birth, hydrocephalus, and congenital/genetic anomaly were some of the variables contributing the most to both RF models. CONCLUSIONS Using a large-scale nationwide dataset, machine learning models for the prediction of both 30-day readmissions and reoperations were developed and achieved high accuracy. This highlights the utility of machine learning in risk stratification and surgical decision-making for pediatric CM-I.

Introduction The coronavirus disease 2019 (COVID‐19) pandemic has had a global impact on healthcare systems. There is limited data on the influence of COVID‐19 on treatment and outcomes in patients with intracranial aneurysms. We aimed to investigate the impact of COVID‐19 on the overall complications, including ischemic stroke and subarachnoid hemorrhage (SAH) rates in patients treated for intracranial aneurysms (IAs). Methods This national, multicenter, retrospective cohort study included patients diagnosed and treated for IAs from January 2016 to December 2020 in the National Inpatient Sample (NIS). A total of 57,715 admissions were identified. Of these, 45,979 occurred pre‐COVID and 11,736 during the COVID pandemic period. The outcome data points included the occurrence of postprocedural ischemic strokes or SAHs, death, non‐routine discharge, total charges (US dollars), and length of stay (days). A 1:1 propensity score matching protocol was applied using a K‐nearest neighbor approach to evaluate differences in the outcome data points between the pre‐COVID and during COVID periods. The trends during the study period were assessed using piecewise joinpoint regression with the Mann‐Kendall test. Results Overall, the mean age was 65 years, with most of the patients (69.9%) being females. Endovascular interventions were performed in 82.9% of pre‐COVID IAs admissions compared to 82.4% during the COVID period, while open surgical treatment was performed in 17.1% of pre‐COVID and 17.6% of the patients during COVID (p=0.625). After matching, there were no differences in length of stay (p=0.266), non‐home discharge (p=0.475), and in‐hospital mortality rates (p=0.305) between the two periods; however, the overall complication rate was significantly higher during the pandemic (31.1% vs. 28.3%; p<0.001). From 2016 to 2020, an upward trend in hospitalizations for ischemic stroke was seen among patients treated for IAs (6.1% to 7.9%; p=0.04). No trends were observed with respect to the occurrence of SAH or death (p=0.31). Patients hospitalized after treatment of IAs during the COVID pandemic had significantly higher odds of ischemic strokes (OR 1.13; 95% CI 1.05 to 1.22; p=0.03) but not SAH (OR 0.97; 95% CI 0.88 to 1.06; p=0.89). Conclusion The COVID‐19 pandemic has significantly impacted the healthcare system. In patients receiving treatment for IAs, this analysis noted a correlation between the COVID‐19 pandemic and postoperative complications, notably ischemic strokes. Unraveling the pandemic’s “black box” leads to awareness of plausible breaches within the system, which acts as a crucial component in improving situational readiness and preparedness in the event of similar large‐scale crises.

Objectives To investigate the impact of the COVID-19 pandemic as well as concomitant COVID-19 itself on stroke care, focusing on middle cerebral artery (MCA) territory infarctions. Design Registry-based study. Setting We used the National Inpatient Sample (NIS) database, which covers a wide range of hospitals within the USA. Participants The NIS was queried for patients with MCA strokes between 2016 and 2020. In total, 35 231 patients were included. Outcome measures Outcome measures were postprocedural complications, length of stays (LOSs), in-hospital mortality and non-routine discharge. Propensity score matching using all available baseline variables was performed to reduce confounders when comparing patients with and without concomitant COVID-19. Results Mechanical thrombectomy (MT) was performed in 48.4%, intravenous thrombolysis (IVT) in 38.2%, and both MT and IVT (MT+IVT) in 13.4% of patients. A gradual increase in the use of MT and an opposite decrease in the use of IVT (p<0.001) was detected during the study period. Overall, 25.0% of all patients were admitted for MCA strokes during the pandemic period (2020), of these 209 (2.4%) were concomitantly diagnosed with COVID-19. Patients with MCA strokes and concomitant COVID-19 were significantly younger (64.9 vs 70.0; p<0.001), had significantly worse NIH Stroke Severity scores, and worse outcomes in terms of LOS (12.3 vs 8.2; p<0.001), in-hospital mortality (26.3% vs 9.8%; p<0.001) and non-routine discharge (84.2% vs 76.9%; p=0.013), as compared with those without COVID-19. After matching, only in-hospital mortality rates remained significantly higher in patients with COVID-19 (26.7% vs 8.5%; p<0.001). Additionally, patients with COVID-19 had higher rates of thromboembolic (12.3% vs 7.6%; p=0.035) and respiratory (11.3% vs 6.6%; p=0.029) complications. Conclusions Among patients with MCA stroke, those with concomitant COVID-19 were significantly younger and had higher stroke severity scores. They were more likely to experience thromboembolic and respiratory complications and in-hospital mortality compared with matched controls.

BACKGROUND AND OBJECTIVES: Carotid endarterectomy (CEA) is a well-established treatment option for carotid stenosis. The choice between general anesthesia (GA) and nongeneral anesthesia (non-GA) during CEA remains a subject of debate, with concerns regarding perioperative complications, particularly myocardial infarctions. This study aimed to evaluate the outcomes associated with GA vs non-GA CEA using a large, nationwide database. METHODS: The National Surgical Quality Improvement Project database was queried for patients undergoing CEA between 2013 and 2020. Primary outcome measures including surgical outcomes and 30-day postoperative complications were compared between the 2 anesthesia methods, after 2:1 propensity score matching. RESULTS: After propensity score matching, a total of 25 356 patients (16 904 in the GA and 8452 in the non-GA group) were included. Non-GA compared with GA CEA was associated with significantly shorter operative times (101.9, 95% CI: 100.5-103.3 vs 115.8 95% CI: 114.4-117.2 minutes, P < .001), reduced length of hospital stays (2.3, 95% CI: 2.15-2.4 vs 2.5, 95% CI: 2.4-2.6 days, P < .001), and lower rates of 30-day postoperative complications, including myocardial infarctions (0.8% vs 1.2%, P = .003), unplanned intubations (0.8% vs 1.1%, P = .016), pneumonia (0.5% vs 1%, P < .001), and urinary tract infections (0.4% vs 0.7%, P = .003). These outcomes were notably more pronounced in the younger (≤70 years) and high morbidity (American Society of Anesthesiologists 3-5) cohorts. CONCLUSION: In this nationwide registry-based study, non-GA CEA was associated with better short-term outcomes in terms of perioperative complications, compared with GA CEA. The findings suggest that non-GA CEA may be a safer alternative, especially in younger patients and those with more comorbidities.

Abstract Background Although typically benign, 5% of spinal meningiomas (SMs) present with higher-grade features (World Health Organization grades 2 and 3). High-grade SMs are poorly studied and the role of adjuvant radiotherapy in their management remains controversial. We hence aimed to study the demographic characteristics of this rare tumor and investigate the outcomes associated with the use of surgery with adjuvant therapy in contrast to surgery alone. Methods The National Cancer Database was queried for patients with SMs from 2004 to 2017. Basic statistics were used to identify differences between low- and high-grade tumors in terms of baseline characteristics. Surgery with and without adjuvant radiotherapy were compared after (1:1) propensity-score matching. Kaplan–Meier survival analysis was conducted to study overall survival. All analyses were performed on R. Results A total of 13 184 patients diagnosed with SMs were included, of whom only 5% (n = 669) had high-grade SMs. Patients with high-grade SMs presented at a younger median age (57 years [IQR: 44–68] versus 65 years [54–75]; P &lt; .001) and were more commonly males (33% vs 20%; P &lt; .001). After propensity-score matching, survival analysis revealed similar overall survival outcomes in patients with high-grade SM undergoing both surgery and radiotherapy as compared to those only receiving surgery (P = .19). Conclusions This study reveals major demographic differences between high- and low-grade SMs. There were no benefits associated with the use of adjuvant radiotherapy. However, due to confounding, overall survival outcomes between patients receiving surgery alone and those receiving surgery with adjuvant radiotherapy are not causally interpretable.

BACKGROUND AND OBJECTIVES: Epilepsy is considered one of the most prevalent and severe chronic neurological disorders worldwide. Our study aims to analyze the national trends in different treatment modalities for individuals with drug-resistant epilepsy and investigate the outcomes associated with these procedural trends in the United States. METHODS: Using the National Inpatient Sample database from 2010 to 2020, patients with drug-resistant focal epilepsy who underwent laser interstitial thermal therapy (LITT), open surgical resection, vagus nerve stimulation (VNS), or responsive neurostimulation (RNS) were identified. Trend analysis was performed using piecewise joinpoint regression. Propensity score matching was used to compare outcomes between 10 years prepandemic before 2020 and the first peak of the COVID-19 pandemic. RESULTS: This study analyzed a total of 33 969 patients with a diagnosis of drug-resistant epilepsy, with 3343 patients receiving surgical resection (78%), VNS (8.21%), RNS (8%), and LITT (6%). Between 2010 and 2020, there was an increase in the use of invasive electroencephalography monitoring for seizure zone localization ( P = .003). There was an increase in the use of LITT and RNS ( P < .001), while the use of surgical resection and VNS decreased over time ( P < .001). Most of these patients (89%) were treated during the pre-COVID pandemic era (2010-2019), while a minority (11%) underwent treatment during the COVID pandemic (2020). After propensity score matching, the rate of pulmonary complications, postprocedural hematoma formation, and mortality were slightly higher during the pandemic compared with the prepandemic period ( P = .045, P = .033, and P = .026, respectively). CONCLUSION: This study indicates a relative decrease in the use of surgical resections, as a treatment for drug-resistant focal epilepsy. By contrast, newer, minimally invasive surgical approaches including LITT and RNS showed gradual increases in usage.

Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models’ effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and evaluate current research-based ML and DL models applied for spine surgery, specifically those predicting binary outcomes with a focus on their evaluation metrics. Overall, 60 papers were included, and the findings were reported according to the PRISMA guidelines. A total of 13 papers focused on lengths of stay (LOS), 12 on readmissions, 12 on non-home discharge, 6 on mortality, and 5 on reoperations. The target outcomes exhibited data imbalances ranging from 0.44% to 42.4%. A total of 59 papers reported the model’s area under the receiver operating characteristic (AUROC), 28 mentioned accuracies, 33 provided sensitivity, 29 discussed specificity, 28 addressed positive predictive value (PPV), 24 included the negative predictive value (NPV), 25 indicated the Brier score with 10 providing a null model Brier, and 8 detailed the F1 score. Additionally, data visualization varied among the included papers. This review discusses the use of appropriate evaluation schemes in ML and identifies several common errors and potential bias sources in the literature. Embracing these recommendations as the field advances may facilitate the integration of reliable and effective ML models in clinical settings.