E. V. Kuzmicheva

E. V. Kuzmicheva

Auto-generated profile, based on publicly available information

E. V. Kuzmicheva

National Research University Higher School of Economics

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
20 October 2025 in Neurology, Neuropsychiatry, Psychosomatics
Verified
Journal Article
Open access
PDF file
SKSofya Kulikova
Sofya Kulikova
IPI. Yu. Polyakova
I. Yu. Polyakova
EKE. V. Kuzmicheva
E. V. Kuzmicheva
AKAleksey Kulesh
Aleksey Kulesh
SMS. A. Mekhryakov
S. A. Mekhryakov
YKYu. V. Karakulova
Yu. V. Karakulova
Predicting the outcome of ischaemic stroke (IS) is a complex task, as mortality and disability depend on many factors, including age, gender, type and severity of stroke, and comorbidities. Survival rates also vary between countries depending on genetic characteristics and differences in the organisation of healthcare systems.Objective: to search for predictors of one-year survival after IS in a sample of patients from the Perm region.Material and methods. The study included 254 patients who had suffered an IS. Seventy-five parameters obtained during routine clinical examination were analysed, including information on the subtype and severity of the stroke, the size and location of the lesion, neurological disorders, comorbidities, and other factors. Relevant features were selected using the WEKA programme, and the selected features were used in a predictive model based on logistic regression.Results. The following factors have been identified as significant predictors of annual survival in patients who have undergone IS (the sign of the coefficient reflects the relative contribution of the factor to the model and its positive or negative effect): age (-0.02), degree of neurological deficit on the NIHSS scale at discharge (-0.06), haemoglobin level (0.01), infarction in the anterior choroidal artery basin (0.74), recurrent stroke within the following year (-0.02) and cardioembolic stroke subtype (-0.32). The accuracy of the logistic model was 84% with 10-fold cross-validation.Conclusion. In the model predicting one-year survival after IS, other factors have been identified in addition to age, which is usually associated with a less favourable prognosis. Further multicentre studies are needed to confirm the reliability of the proposed model.

1 August 2024 in Scientific Visualization
Verified
Journal Article
Open access
PDF file
APA. Provorova
A. Provorova
IPI. Polyakova
I. Polyakova
EKE. Kuzmicheva
E. Kuzmicheva
Machine methods of image analysis are gaining popularity in various fields of life. However, the question remains as to how effective such algorithms are on low-quality data, such as those that can be used in the field of telemedicine. The work provides a comparative analysis of various approaches to object detection in MRI brain images taken from a computer screen. For the recognition of brain contours in the image, a classical morphometric approach (OpenCV library), the Viola-Jones algorithm, and two deep learning algorithms, YOLOv8 and EfficientDet, were used. The comparison of these methods was conducted in terms of the quality of object detection in the image. To assess the quality, we used the IoU metric, as well as measured the amount of memory used and the speed of algorithm execution. As a result of the comparison, we found that the YOLOv8 model demonstrated the best performance in terms of object detection quality. However, its performance was unstable in cases of low-quality images with high levels of noise. Among the considered approaches, YOLOv8 is also the most memory-intensive. The YOLOv8 network architecture can be considered the best candidate for further practical application in terms of average performance and resistance to noise.