Search

Your search keyword '"Yu-jia Jin"' showing total 2 results
Start Over Author "Yu-jia Jin" Topic hematoma
2 results on '"Yu-jia Jin"'

1. Cortical superficial siderosis, hematoma volume, and outcomes after intracerebral hemorrhage: a mediation analysis

Author

Yu-jia Jin, Jia-wen Li, Jian Wu, Yu-hui Huang, Kai-cheng Yang, Hong-na An, Chang-zheng Yuan, Feng Gao, and Lu-sha Tong

Subjects
cSS, ICH volume and outcome, mediation analysis, prospective studies, cerebral hemorrhage, hematoma, Neurology. Diseases of the nervous system, RC346-429
Abstract

BackgroundPrevious studies have shown that cortical superficial siderosis (cSS) can increase hematoma volume and predict poor outcomes following primary intracerebral hemorrhage (ICH).ObjectiveWe aimed to determine whether a large hematoma volume was the essential factor contributing to worse outcomes of cSS.MethodsPatients with spontaneous ICH underwent a CT scan within 48 h after ictus. Evaluation of cSS was performed using magnetic resonance imaging (MRI) within 7 days. The 90-day outcome was assessed using the modified Rankin Scale (mRS). In addition, we investigated the correlation between cSS, hematoma volume, and 90-day outcomes using multivariate regression and mediation analyses.ResultsAmong the 673 patients with ICH [mean (SD) age, 61 (13) years; 237 female subjects (35.2%); median (IQR) hematoma volume, 9.0 (3.0–17.6) ml], 131 (19.5%) had cSS. There was an association between cSS and larger hematoma volume (β = 4.449, 95% CI 1.890–7.009, p < 0.001) independent of hematoma location and was also related to worse 90-day mRS (β = 0.333, 95% CI 0.008–0.659, p = 0.045) in multivariable regression. In addition, mediation analyses revealed that hematoma volume was an essential factor mediating the effect of cSS on unfavorable 90-day outcomes (proportion mediated:66.04%, p = 0.01).ConclusionLarge hematoma volume was the major charge of directing cSS to worse outcomes in patients with mild to moderate ICH, and cSS was related to a larger hematoma in both lobar and non-lobar areas.Clinical trial registrationhttps://clinicaltrials.gov/ct2/show/NCT04803292, identifier: NCT04803292.

Published
2023
Full Text
View/download PDF

2. Deep learning for automatically predicting early haematoma expansion in Chinese patients

Author

Xiao-Hui Lu, Jia-Wei Zhong, Bo Lin, Fang Chen, Yu-Jia Jin, Lu-Sha Tong, and Zai-Jun Song

Subjects
China, medicine.medical_specialty, Irregular shape, 030204 cardiovascular system & hematology, Logistic regression, lcsh:RC346-429, 03 medical and health sciences, Deep Learning, 0302 clinical medicine, medicine, Humans, cardiovascular diseases, lcsh:Neurology. Diseases of the nervous system, Cerebral Hemorrhage, Original Research, Hematoma, business.industry, Deep learning, Fluid level, Predictive value, technology, Cohort, haemorrhage, Neurology (clinical), Radiology, Artificial intelligence, Tomography, X-Ray Computed, Cardiology and Cardiovascular Medicine, business, 030217 neurology & neurosurgery, CT
Abstract

Background and purposeEarly haematoma expansion is determinative in predicting outcome of intracerebral haemorrhage (ICH) patients. The aims of this study are to develop a novel prediction model for haematoma expansion by applying deep learning model and validate its prediction accuracy.MethodsData of this study were obtained from a prospectively enrolled cohort of patients with primary supratentorial ICH from our centre. We developed a deep learning model to predict haematoma expansion and compared its performance with conventional non-contrast CT (NCCT) markers. To evaluate the predictability of this model, it was also compared with a logistic regression model based on haematoma volume or the BAT score.ResultsA total of 266 patients were finally included for analysis, and 74 (27.8%) of them experienced early haematoma expansion. The deep learning model exhibited highest C statistic as 0.80, compared with 0.64, 0.65, 0.51, 0.58 and 0.55 for hypodensities, black hole sign, blend sign, fluid level and irregular shape, respectively. While the C statistics for swirl sign (0.70; p=0.211) and heterogenous density (0.70; p=0.141) were not significantly higher than that of the deep learning model. Moreover, the predictive value for the deep learning model was significantly superior to that of the logistic model of haematoma volume (0.62; p=0.042) and the BAT score (0.65; p=0.042).ConclusionsCompared with the conventional NCCT markers and BAT predictive model, the deep learning algorithm showed superiority for predicting early haematoma expansion in ICH patients.

Catalog

Books, media, physical & digital resources
See catalog results