Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage.

To examine whether machine learning (ML) approach can be used to predict hematoma expansion in acute intracerebral hemorrhage (ICH) with accuracy and widespread applicability, we applied ML algorithms to multicenter clinical data and CT findings on admission. Patients with acute ICH from three hospitals (n = 351) and those from another hospital (n = 71) were retrospectively assigned to the development and validation cohorts, respectively. To develop ML predictive models, the k-nearest neighbors (k-NN) algorithm, logistic regression, support vector machines (SVMs), random forests, and XGBoost were applied to the patient data in the development cohort. The models were evaluated for their performance on the patient data in the validation cohort, which was compared with previous scoring methods, the BAT, BRAIN, and 9-point scores. The k-NN algorithm achieved the highest area under the receiver operating characteristic curve (AUC) of 0.790 among all ML models, and the sensitivity, specificity, and accuracy were 0.846, 0.733, and 0.775, respectively. The BRAIN score achieved the highest AUC of 0.676 among all previous scoring methods, which was lower than the k-NN algorithm (p = 0.016). We developed and validated ML predictive models of hematoma expansion in acute ICH. The models demonstrated good predictive ability, showing better performance than the previous scoring methods.

Knowledge Learning of Replacement Judgment Using Word-of-mouth Data.

The pandemic caused by COVID-19 has also affected the camera industry, and various events have been cancelled. In addition, the recent improvement in the performance of cameras installed in smartphones has reduced the demand for replacement cameras, as it is easy to take pictures without carrying a camera. For customers, online word-of-mouth is what they refer to when purchasing a product. This data is important not only for customers, but also for companies. In this research, we will use online word-of-mouth data and focus not only on numerical data but also on textual data and use text mining to learn knowledge about the decision to replace a camera.

Prolonged Cerebral Hyperperfusion and Subcortical Low Intensity on Fluid-Attenuated Inversion Recovery Images: Unusual Manifestation After Removal of Organized Chronic Subdural Hematoma.

BACKGROUND: Cerebral hyperperfusion sometimes occurs after removal of chronic subdural hematoma (CSH) and usually resolves within a few days without any symptoms. Subcortical low intensity (SCLI) on fluid-attenuated inversion recovery (FLAIR) magnetic resonance images is rare and has been reported in some diseases other than CSH. A case of organized CSH who suffered prolonged neurologic deterioration, SCLI, and cerebral hyperperfusion postoperatively is described. CASE DESCRIPTION: An 81-year-old man, presenting with left hemiparesis, underwent craniotomy for right organized CSH after 2 burr-hole surgeries. After the craniotomy, the symptoms improved, but on postoperative day 2, left hemiparesis, hemispatial neglect, and hemiasomatognosia developed. Magnetic resonance imaging revealed SCLI on FLAIR images, and single-photon emission computed tomography with N-isopropyl-p-[123I]-iodoamphetamine revealed cerebral hyperperfusion in the right hemispheric cortex. Antihypertensive treatment improved the symptoms gradually, which resolved completely 1 month postsurgery. CONCLUSIONS: A case of organized CSH, which showed postoperative neurologic deterioration associated with prolonged cerebral hyperperfusion and SCLI on FLAIR images, is reported. Prolonged cerebral hyperperfusion could be a cause of postoperative neurologic deterioration in organized CSH.

Cavernous Sinus Dural Arteriovenous Fistula Presenting with Intracerebral Hemorrhage Associated with Chronological Angiographic Demonstration of Disturbed Leptomeningeal Venous Drainage as the Sole Outflow Route.

BACKGROUND: Cavernous sinus (CS) dural arteriovenous fistula (DAVF) rarely causes intracranial hemorrhage. The authors describe a case of CS DAVF presenting with intracranial hemorrhage, focusing on the findings in digital subtraction angiography (DSA) performed before and after the onset. CASE DESCRIPTION: An 80-year-old woman, diagnosed as Borden type 3 CS DAVF on DSA 2 years before, presented with subarachnoid hemorrhage and right temporal subcortical hemorrhage. DSA findings after the onset showed that the right superficial middle cerebral vein, the sole drainage of the DAVF, had various changes including stenosis on the proximal portion, venous pouch formation, and occlusion of the distal portion compared with those 2 years before the onset. The occlusion was observed near the point where drainage of DAVF joined normal brain venous drainage, suggesting that the competition between the drainages caused impaired venous drainage, stagnation, and subsequent thrombotic occlusion. The CS DAVF was treated with evacuation of the intracerebral hematoma and surgical interruption of the right superficial middle cerebral vein at the dural origin from the CS. CONCLUSIONS: This report showed the development of thrombotic occlusion of a distal draining cortical vein as one of risk factors for CS DAVFs to cause intracranial hemorrhage on repeated DSAs.