Machine learning predicts cerebral vasospasm in patients with subarachnoid haemorrhage.

BACKGROUND: Cerebral vasospasm (CV) is a feared complication which occurs after 20-40% of subarachnoid haemorrhage (SAH). It is standard practice to admit patients with SAH to intensive care for an extended period of resource-intensive monitoring. We used machine learning to predict CV requiring verapamil (CVRV) in the largest and only multi-center study to date. METHODS: Patients with SAH admitted to UCLA from 2013 to 2022 and a validation cohort from VUMC from 2018 to 2023 were included. For each patient, 172 unique intensive care unit (ICU) variables were extracted through the primary endpoint, namely first verapamil administration or no verapamil. At each institution, a light gradient boosting machine (LightGBM) was trained using five-fold cross validation to predict the primary endpoint at various hospitalization timepoints. FINDINGS: A total of 1750 patients were included from UCLA, 125 receiving verapamil. LightGBM achieved an area under the ROC (AUC) of 0.88 > 1 week in advance and ruled out 8% of non-verapamil patients with zero false negatives. Our models predicted "no CVRV" vs "CVRV within three days" vs "CVRV after three days" with AUCs = 0.88, 0.83, and 0.88, respectively. From VUMC, 1654 patients were included, 75 receiving verapamil. VUMC predictions averaged within 0.01 AUC points of UCLA predictions. INTERPRETATION: We present an accurate and early predictor of CVRV using machine learning with multi-center validation. This represents a significant step towards optimized clinical management and resource allocation in patients with SAH. FUNDING: Robert E. Freundlich is supported by National Center for Advancing Translational Sciences federal grant UL1TR002243 and National Heart, Lung, and Blood Institute federal grant K23HL148640; these funders did not play any role in this study. The National Institutes of Health supports Vanderbilt University Medical Center which indirectly supported these research efforts. Neither this study nor any other authors personally received financial support for the research presented in this manuscript. No support from pharmaceutical companies was received.

Early Postoperative Opioid Requirement Is Associated With Later Pain Control Needs After Supratentorial Craniotomies.

BACKGROUND: Despite a renewed focus in recent years on pain management in the inpatient hospital setting, postoperative pain after elective craniotomy remains under investigated. This study aims to identify which perioperative factors associate most strongly with postoperative pain and opioid medication requirements after inpatient craniotomy. MATERIALS AND METHODS: Using an existing dataset, we selected a restricted cohort of patients who underwent elective craniotomy surgery requiring an inpatient postoperative stay during a 7-year period at our institution (n=1832). We examined pain scores and opioid medication usage and analyzed the relative contribution of specific perioperative risk factors to postoperative pain and opioid medication intake (morphine milligram equivalents). RESULTS: Postoperative pain was found to be highest on postoperative day 1 and decreased thereafter (up to day 5). Factors associated with greater postoperative opioid medication requirement were preoperative opioid medication use, duration of anesthesia, degree of pain in the preoperative setting, and patient age. Notably, the most significant factor associated with a higher postoperative pain score and Morphine milligram equivalents requirement was the time elapsed between the end of general anesthesia and a patient's first intravenous opioid medication. CONCLUSION: Postcraniotomy patients are at higher risk for requiring opioid pain medications if they have a history of preoperative opioid use, are of younger age, or undergo a longer surgery. Moreover, early requirement of intravenous opioid medications in the postoperative period should alert treating physicians that a patient's pain may require additional or alternative methods of pain control than routinely administered, to avoid over-reliance on opioid medications.

The Role of Vancomycin Powder During Spinal Cord Stimulator Implantation: A Case Series and Review of the Literature.

OBJECTIVE: We examined the role of intrawound vancomycin powder as prophylaxis against postoperative surgical site infection (SSI) after spinal cord stimulator (SCS) implantation. METHODS: We performed a retrospective analysis of 153 consecutive patients who had undergone permanent SCS implantation surgery via open laminectomy between 2014 and 2020. We queried the patients' medical records for patient age, sex, relevant medical history, and whether intrawound vancomycin had been administered. We compared the rates of SSI (primary outcome) and seroma (secondary outcome) within 3 months after surgery between the vancomycin and no-vancomycin groups. Finally, we conducted multivariable logistic regression analyses to identify independent predictors of postoperative SSI or seroma. RESULTS: Of the 153 patients, 59% were women, and the average age was 65.4 years. Overall, 3 patients (2%) had developed an SSI: 2 (methicillin-resistant Staphylococcus aureus, Klebsiella) in the vancomycin group and 1 (methicillin-sensitive Staphylococcus aureus) in the no-vancomycin group. This difference in SSI rate between the 2 groups was insignificant (P = 0.73). Three seromas, all in the no-vancomycin group, accounted for a statistically significant difference in seroma formation between the 2 groups (P = 0.04). Multivariate logistic regression failed to identify any perioperative characteristics as independent predictors of postoperative SSI or seroma. CONCLUSIONS: Our experience suggests open laminectomy for SCS implantation surgery can be performed with a low postoperative SSI rate, with or without the use of powdered vancomycin. We found no evidence suggesting that the use of powdered vancomycin is unsafe or related to postoperative seroma formation. We failed to draw any definitive conclusions regarding its efficacy, despite referencing the largest single case series of SCS implantation to date.

MR-guided delivery of AAV2-BDNF into the entorhinal cortex of non-human primates.

Brain-derived neurotrophic factor (BDNF) gene delivery to the entorhinal cortex is a candidate for treatment of Alzheimer's disease (AD) to reduce neurodegeneration that is associated with memory loss. Accurate targeting of the entorhinal cortex in AD is complex due to the deep and atrophic state of this brain region. Using MRI-guided methods with convection-enhanced delivery, we were able to accurately and consistently target AAV2-BDNF delivery to the entorhinal cortex of non-human primates; 86 ± 3% of transduced cells in the targeted regions co-localized with the neuronal marker NeuN. The volume of AAV2-BDNF (3 × 108 vg/µl) infusion linearly correlated with the number of BDNF labeled cells and the volume (mm3) of BDNF immunoreactivity in the entorhinal cortex. BDNF is normally trafficked to the hippocampus from the entorhinal cortex; in these experiments, we also found that BDNF immunoreactivity was elevated in the hippocampus following therapeutic BDNF vector delivery to the entorhinal cortex, achieving growth factor distribution through key memory circuits. These findings indicate that MRI-guided infusion of AAV2-BDNF to the entorhinal cortex of the non-human primate results in safe and accurate targeting and distribution of BDNF to both the entorhinal cortex and the hippocampus. These methods are adaptable to human clinical trials.

Cumulative Intracranial Tumor Volume Augments the Prognostic Value of Diagnosis-Specific Graded Prognostic Assessment Model for Survival in Patients with Melanoma Cerebral Metastases.

BACKGROUND: The diagnosis-specific graded prognostic assessment scale (ds-GPA) for patients with melanoma brain metastasis (BM) utilizes only 2 key prognostic variables: Karnofsky performance status and the number of intracranial metastases. We wished to determine whether inclusion of cumulative intracranial tumor volume (CITV) into the ds-GPA model for melanoma augmented its prognostic value. OBJECTIVE: To determine whether or not CITV augments the ds-GPA prognostic scale for melanoma. METHODS: We analyzed the survival pattern of 344 melanoma patients with BM treated with stereotactic radiosurgery (SRS) at separate institutions and validated our findings in an independent cohort of 201 patients. The prognostic value of ds-GPA for melanoma was quantitatively compared with and without the addition of CITV using the net reclassification index (NRI > 0) and integrated discrimination improvement (IDI) metrics. RESULTS: The incorporation of CITV into the melanoma-specific ds-GPA model enhanced its prognostic accuracy. Addition of CITV to the ds-GPA model significantly improved its prognostic value, with NRI > 0 of 0.366 (95% CI: 0.125-0.607, P = .002) and IDI of 0.024 (95% CI: 0.008-0.040, P = .004). We validated these findings that CITV improves the prognostic utility of melanoma ds-GPA in an independent cohort of 201 melanoma cohort. CONCLUSION: The prognostic value of the ds-GPA scale for melanoma BM is enhanced by the incorporation of CITV.

Depression After Spinal Surgery: A Comparative Analysis of the California Outcomes Database.

OBJECTIVE: To examine the relative incidence of newly recorded diagnosis of depression after spinal surgery as a proxy for the risk of post-spinal surgery depression. PATIENTS AND METHODS: We used the longitudinal California Office of Statewide Health Planning and Development database (January 1, 2000, through December 31, 2010) to identify patients who underwent spinal surgery during these years. Patients with documented depression before surgery were excluded. Risk of new postoperative depression was determined via the incidence of newly recorded depression on any hospitalization subsequent to surgery. For comparison, this risk was also determined for patients hospitalized during the same time period for coronary artery bypass grafting, hysterectomy, cholecystectomy, chronic obstructive pulmonary disease, congestive heart failure exacerbation, or uncomplicated vaginal delivery. RESULTS: Our review identified 1,078,639 patients. Relative to the uncomplicated vaginal delivery cohort, the adjusted hazard ratios (HRs) for newly recorded depression within 5 years after the admission of interest were 5.05 for spinal surgery (95% CI, 4.79-5.33), 2.33 for coronary artery bypass grafting (95% CI, 2.15-2.54), 3.04 for hysterectomy (95% CI, 2.88-3.21), 2.51 for cholecystectomy (95% CI, 2.35-2.69), 2.44 for congestive heart failure exacerbation (95% CI, 2.28-2.61), and 3.04 for chronic obstructive pulmonary disease (95% CI, 2.83-3.26). Among patients who underwent spinal surgery, this risk of postoperative depression was highest for patients who underwent fusion surgery (HR, 1.28; 95% CI, 1.22-1.36) or had undergone multiple spinal operations (HR, 1.22; 95% CI, 1.16-1.29) during the analyzed period. CONCLUSION: Patients who undergo spinal surgery have a higher risk for postoperative depression than patients treated for other surgical or medical conditions known to be associated with depression.

Psychiatric Disease Preceding Intracranial Tumor Diagnosis: Investigating the Association.

OBJECTIVE: Here, we examine rates of intracranial tumor diagnoses in patients with and without comorbid psychiatric diagnoses to better understand how psychiatric disease may alter risk profiles for brain tumor diagnosis. METHODS: We used a longitudinal version of the California Office of Statewide Health Planning and Development (OSHPD) database, which includes all inpatient admissions in California from 1995 to 2010. We examined patients with confirmed hospital admissions from 1997 to 2004. Patients with an intracranial tumor or psychiatric diagnosis on their first hospital admission were excluded. The primary outcome of interest was the diagnosis of intracranial tumor on any subsequent hospitalization within 5 years. Risk of tumor diagnosis was determined via Cox proportional hazard models adjusted for age, gender, race/ethnicity, and comorbidity burden. Subset analyses were performed for various tumor types. RESULTS: The risk for diagnosis of an intracranial tumor within 5 years, as determined by the hazard ratio, was 1.61 (95% CI, 1.28-2.04) for bipolar, 1.59 (95% CI, 1.41-1.72) for anxious, and 1.34 (95% CI, 1.25-1.43) for depressed cohorts relative to controls. More specifically, the risk for diagnosis of a primary benign neoplasm was elevated in depressed patients, while the risk for diagnosis of a meningioma was elevated in depressed, anxious, and bipolar disorder patients. CONCLUSIONS: Patients admitted with certain psychiatric diagnoses appear more likely to be readmitted within 5 years with specific types of intracranial tumor diagnoses. The association between certain psychiatric diagnoses and subsequent brain tumor diagnosis most likely reflects the long-held belief that slow-growing tumors may first present as psychiatric symptoms before being diagnosed. Primary care physicians should consider the possibility of an underlying intracranial tumor in patients with new psychiatric diagnoses.

Histologic Evidence for Arteriovenous Malformation-Like Vasculature Occurring within an Intracerebral Schwannoma: A Case Report and Review of the Literature.

BACKGROUND: The phenomenon of intracerebral schwannoma is exceedingly rare, and its etiology still a matter of debate. No documented cases of intracerebral schwannoma containing vascular elements consistent with those of an arteriovenous malformation (AVM) have been reported. We describe such a case here. CASE DESCRIPTION: A left temporal intraparenchymal lesion was discovered incidentally in a 34-year-old man after he suffered a mild trauma. The lesion was resected and found on histologic examination to be an intracerebral schwannoma with AVM-like vasculature. The patient made a full recovery after resection. CONCLUSIONS: To our knowledge, this is the first case of an intracerebral schwannoma with AVM-like characteristics to be reported in the literature. We hypothesize that the co-occurrence of this rare pathologic entity is caused by an interrelated etiologic process, with the tumor microenvironment of the schwannoma inciting the development of the vascular malformation.