Mohammad Shafie

Mohammad Shafie

Auto-generated profile, based on publicly available information

Mohammad Shafie

Department of Neurology, University of California, Irvine

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2018 in American Journal of Neuroradiology
Verified
Journal Article
Open access
PDF file
PCP.D. Chang
P.D. Chang
EKE. Kuoy
E. Kuoy
JGjack grinband
jack grinband
Brent WeinbergBrent Weinberg
Brent Weinberg
MTM. Thompson
M. Thompson
DCDaniel Chow
Daniel Chow
BACKGROUND AND PURPOSE: Convolutional neural networks are a powerful technology for image recognition. This study evaluates a convolutional neural network optimized for the detection and quantification of intraparenchymal, epidural/subdural, and subarachnoid hemorrhages on noncontrast CT. MATERIALS AND METHODS: This study was performed in 2 phases. First, a training cohort of all NCCTs acquired at a single institution between January 1, 2017, and July 31, 2017, was used to develop and cross-validate a custom hybrid 3D/2D mask ROI-based convolutional neural network architecture for hemorrhage evaluation. Second, the trained network was applied prospectively to all NCCTs ordered from the emergency department between February 1, 2018, and February 28, 2018, in an automated inference pipeline. Hemorrhage-detection accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative predictive value were assessed for full and balanced datasets and were further stratified by hemorrhage type and size. Quantification was assessed by the Dice score coefficient and the Pearson correlation. RESULTS: A 10,159-examination training cohort (512,598 images; 901/8.1% hemorrhages) and an 862-examination test cohort (23,668 images; 82/12% hemorrhages) were used in this study. Accuracy, area under the curve, sensitivity, specificity, positive predictive value, and negative-predictive value for hemorrhage detection were 0.975, 0.983, 0.971, 0.975, 0.793, and 0.997 on training cohort cross-validation and 0.970, 0.981, 0.951, 0.973, 0.829, and 0.993 for the prospective test set. Dice scores for intraparenchymal hemorrhage, epidural/subdural hemorrhage, and SAH were 0.931, 0.863, and 0.772, respectively. CONCLUSIONS: A customized deep learning tool is accurate in the detection and quantification of hemorrhage on NCCT. Demonstrated high performance on prospective NCCTs ordered from the emergency department suggests the clinical viability of the proposed deep learning tool.

6 January 2021 in Translational Stroke Research
Verified
Journal Article
Open access
PDF file
MSMohammad Shafie
Mohammad Shafie
WYWengui Yu
Wengui Yu
In the past 5 years, the success of multiple randomized controlled trials of recanalization therapy with endovascular thrombectomy has transformed the treatment of acute ischemic stroke with large vessel occlusion. The evidence from these trials has now established endovascular thrombectomy as standard of care. This review will discuss the chronological evolution of large vessel occlusion treatment from early medical therapy with tissue plasminogen activator to the latest mechanical thrombectomy. Additionally, it will highlight the potential areas in endovascular thrombectomy for acute ischemic stroke open to exploration and further progress in the next decade.

2 April 2024 in Journal of the American Heart Association
Verified
Journal Article
Open access
PDF file
SLSook Joung Lee
Sook Joung Lee
SLShimeng Liu
Shimeng Liu
HBHaley Blackwill
Haley Blackwill
DSDana Stradling
Dana Stradling
MSMohammad Shafie
Mohammad Shafie
WYWengui Yu
Wengui Yu
Background: Methamphetamine use has emerged as a major risk factor for cardiovascular and cerebrovascular disease in young adults. The aim of this study was to investigate a possible association of methamphetamine use with cardioembolic stroke. Methods and Results: We performed a retrospective study of patients with acute ischemic stroke admitted at our medical center between 2019 and 2022. All patients were screened for methamphetamine use and cardiomyopathy, defined as left ventricular ejection fraction ≤45%. Among 938 consecutive patients, 46 (4.9%) were identified as using methamphetamine. Compared with the nonmethamphetamine group (n=892), the methamphetamine group was significantly younger (52.8±9.6 versus 69.7±15.2 years; P <0.001), included more men (78.3% versus 52.8%; P <0.001), and had a significantly higher rate of cardiomyopathy (30.4% versus 14.0%; P <0.01). They were also less likely to have a history of atrial fibrillation (8.7% versus 33.4%; P <0.01) or hyperlipidemia (28.3% versus 51.7%; P <0.01). Compared with patients with cardiomyopathy without methamphetamine use, the patients with cardiomyopathy with methamphetamine use had significantly lower left ventricular ejection fraction (26.0±9.59% versus 32.47±9.52%; P <0.01) but better functional outcome at 3 months, likely attributable to significantly younger age and fewer comorbidities. In the logistic regression model of clinical variables, methamphetamine‐associated cardiomyopathy was found to be significantly associated with cardioembolic stroke (odds ratio, 1.79 [95% CI, 1.04–3.06]; P <0.05). Conclusions: We demonstrate that methamphetamine use is significantly associated with cardiomyopathy and cardioembolic stroke in young adults.

2 August 2026 in medRxiv
Verified
Preprint
Open access
PDF file
HTHeidi Tan
Heidi Tan
MCMichael Carrillo
Michael Carrillo
DDDiana Dench
Diana Dench
JCJefferson Chen
Jefferson Chen
MSMohammad Shafie
Mohammad Shafie
WYWengui Yu
Wengui Yu
Background: Spontaneous intracerebral hemorrhage (ICH) is the most devastating type of stroke but lacks the established time-critical treatment guidelines available for acute ischemic stroke. This study investigated the impact of Code Stroke activation and warfarin use on anticoagulation reversal times to identify opportunities for quality improvement. Methods: We retrospectively assessed patients with anticoagulation-associated ICH admitted to our medical center between January 1, 2020, and December 31, 2025. Patients with warfarin- or direct oral anticoagulant (DOAC)-associated ICH were identified from our ICH clinical trial screening log, Vizient, and AHA’s Get With The Guidelines-Stroke registry. Code Stroke activation, warfarin or DOAC use, anticoagulation reversal times, causes of delay, and clinical outcomes at hospital discharge were analyzed. Results: Of 892 ICH admissions, 50 patients had confirmed anticoagulation-associated ICH. Among those who underwent reversed at our center (n=34), Code Stroke activation (n=24) significantly reduced door-to-CT time (16.5 [12.8-22.0] vs 172.5 [49.0-261.5] minutes, p <0.001), reversal agent order-to-needle time (37.5 [24.7-56.9] vs 57.0 [39.0-85.0] minutes, p <0.001), and door-to-treatment (DTT) time (64 [48– 98] vs 277 [159–305] minutes, p <0.001) compared to non-activation (n=10). Conversely, warfarin use was associated with higher international normalized ratios (INR) (2.7 [2.2-3.6] vs 1.3 [1.2-1.9], p =0.003) and significantly longer DTT time (95 [51-108] vs 64 [48-77] minutes, p =0.007). Primary DTT delays stemmed from the absence of a time-critical treatment protocol, weight-based dosing for 4F-PCC, waiting for INR results, and a lack of Code Stroke activation for patients with mild symptoms, trauma or unexplained unresponsiveness. Conclusions: Our findings suggest that Code Stroke activation for all suspected cases of ICH, a time-critical emergency department algorithm targeting a DTT time of less than 60 minutes, and immediate anticoagulation reversal with fixed-dose 4F-PCC without waiting for INR results may optimize the acute management of anticoagulation-associated ICH.