Lanzino, Giuseppe

Purpose Aneurysmal rupture and subarachnoid hemorrhage (SAH) have an exceptionally high mortality and morbidity burden. The aim of this study was to develop interpretable machine learning models for predicting short-term poor outcomes defined by the National Inpatient Sample Subarachnoid Hemorrhage Outcome Measure (NIS-SOM). Methods The National Inpatient Sample (NIS) database was queried from 2008 to 2018 to identify patients diagnosed with SAH who had undergone endovascular coiling or clipping for intracranial aneurysm. Demographic, comorbidity, risk factor, and hospital characteristic variables were recorded. Variables were preprocessed, and the feature space was reduced to include the most important features. To predict poor outcomes, machine learning models were trained and cross-validated before being evaluated on a separate testing set. Shapley Additive exPlanations of the best performing model was used for general and local model interpretation. Results Among 18,149 admissions (mean age 55 ± 14 years, 68.8% women), 52.9% had a poor outcome. Test-set AUCs ranged 0.74–0.80; a multilayer perceptron performed best (AUC 0.80, precision 0.74, recall 0.82). SHAP ranked the ten most influential variables: age, neurological comorbidity, paralysis, Medicare insurance, smoking status, Elixhauser burden, fluid-electrolyte disorders, weight loss, arrhythmia, and heart failure. Conclusions The modeling predicted nationwide aSAH prognosis with decent accuracy and highlighted clinical, socioeconomic, and system-level drivers of determinants of poor short-term outcome. These results support the potential of explainable ML tools as complementary tools for early risk stratification, guiding resource allocation, and informing prospective multi-center validation and implementation studies.

Abstract BACKGROUND Meningiomas are the most common primary intracranial tumors, typically managed with surgical resection and/or radiation therapy. Systemic therapy options are limited and reserved for cases refractory to conventional interventions. Cyclin dependent kinase (CDK) proteins are key cell cycle regulators. CDK inhibitors are clinically available, approved for treatment of breast cancer and in clinical trials for meningioma. METHODS We present a case where a patient with incidentally-discovered intracranial meningioma undergoing CDK inhibitor therapy with ribociclib for breast cancer experienced a radiographic response. RESULTS A 73-year-old female was diagnosed with estrogen receptor (ER) positive, progesterone receptor (PR) positive, HER2 negative metastatic invasive ductal carcinoma of the breast. She was treated with estrogen receptor antagonist fulvestrant and CDK 4/6 inhibitor ribociclib. MRI of the brain performed for disease staging demonstrated an extraaxial, dural-based, homogenously enhancing mass along the left posterior petrous ridge consistent with a meningioma. Two-month interval scan demonstrated a marginal decrease in size of the mass (15.6x18.3 mm to 15.4x17.5 mm). Systemic disease related to breast cancer concurrently improved. Two years later, with ongoing fulvestrant and ribociclib therapy, a repeat MRI brain demonstrated further decrease in size of the meningioma (13.4x16.8 mm). CONCLUSIONS Hormonally-directed therapies previously demonstrated limited benefit for meningiomas despite PR/ER positivity reported for these tumors. However, CDK 4/6 inhibitors abemaciclib and ribociclib have demonstrated activity in treatment of recurrent grade 2/3 meningiomas. The radiographic response noted in our case suggests there may be a role for systemic therapy even in treatment-naive cases that may not be amenable to surgical resection or radiation therapy.

The introduction of flow diverters for treatment of intracranial aneurysms represents a major paradigm shift in the treatment of these lesions. The theoretical hallmark of flow diverters is the treatment of the diseased segment harboring the aneurysm instead of treating the aneurysm itself. Flow diverters are designed to induce disruption of flow near the aneurysm neck while preserving flow into parent vessel and adjacent branches. After flow diversion, intra-aneurysmal thrombosis occurs, followed by shrinkage of the aneurysmal sac as the thrombus organizes and retracts. Preliminary clinical series document effective treatment of wide-neck and/or large and giant aneurysms with acceptable complication rates. However, several questions remain unanswered related to the incidence and mechanisms of aneurysm rupture after treatment with flow diverters, fate of small perforating vessels, and long-term patency rates.