Liudmyla Bashkirova

Liudmyla Bashkirova

Auto-generated profile, based on publicly available information

Liudmyla Bashkirova

SHUPYK NATIONAL HEALTHCARE UNIVERSITY OF UKRAINE, KYIV, UKRAINE

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
10 July 2024 in Futurity Medicine
Verified
Journal Article
Open access
PDF file
RYRayisa Yuriy
Rayisa Yuriy
OTOlha Tatarina
Olha Tatarina
VKValery Kaminskyy
Valery Kaminskyy
TSTetyana Silina
Tetyana Silina
LBLiudmyla Bashkirova
Liudmyla Bashkirova
Aims: Assess AI methodologies in early disease detection, identify application areas like imaging and prognosis, determine key findings and clinical impacts, explore AI's prospects for accuracy and personalization, and analyze implementation challenges. Methodology: This narrative review examines AI's role in medical diagnostics by analyzing peer-reviewed articles from 2019-2024 from PubMed. A comprehensive search strategy identified 338 publications, which were filtered for relevance, resulting in 10 key studies. Focus areas include AI techniques like machine learning and their applications and challenges in disease diagnosis. Results: Results showed that in 2024, notable AI studies included a large experimental study with 27,558 samples, a comparative study with 1,653 samples, and a cross-sectional study with 20 samples. Previous years saw a retrospective cross-sectional study with 90,000 samples, an observational study with 1,052 samples, and a retrospective study with 219 samples. AI techniques featured EfficientNet-B2, CNNs, VGG-16, and ResNet variants, with transfer learning models like VER-Net and methods such as COVID-DSNet. Advancements highlighted EfficientNet-B2's 97.57% accuracy in malaria detection, VER-Net's superior lung cancer detection, and AI’s effectiveness in diagnosing retinal diseases, heart conditions, diabetic nephropathy, and COVID-19. Challenges included computational demands and dataset needs, with recommendations for model optimization and clinical integration. Scientific Novelty: This review is about the integration of advanced AI techniques in disease diagnostics, showing new algorithms and machine learning models that improve accuracy, speed, and personalized treatment strategies in medical practice. Conclusion: This study has shown that there has been a significant progress in AI-based disease diagnostics, with examples of high performing models such as EfficientNet-B2 and VER-Net. Despite challenges like computational requirement and interpretability of the model, AI has the potential to revolutionize diagnosis.

10 July 2024 in Futurity Medicine
Verified
Journal Article
Open access
PDF file
LBLiudmyla Bashkirova
Liudmyla Bashkirova
IKIryna Kit
Iryna Kit
YHYury Havryshchuk
Yury Havryshchuk
AKAnatolija Krasnova
Anatolija Krasnova
SVSvitlana Vasylyuk-Zaitseva
Svitlana Vasylyuk-Zaitseva
In recent years, medicine has faced the serious challenge of the covid pandemic, due to which representatives of the health care sector had to mobilize forces and resources to jointly overcome these problems. The rapid development of artificial intelligence, its learning capabilities, and in recent years the creation of a neural network opens up wide possibilities for the use of AI in medicine. Aims: To analyze the modern literature on the use of AI for diagnosis and treatment and to analyze what problems may arise with the uncontrolled introduction of artificial intelligence Methodology: When conducting a literature review, an analysis and generalization of data on the research topic from 2019 to 2024 was carried out. The literature search was carried out by keywords using the PubMed search engine. Results: The literature review demonstrated the use of artificial intelligence in medicine, which has grown significantly in recent years and continues its rapid development, which is associated with the improvement of innovative technologies. The use of artificial intelligence in diagnostics is associated with the use of a neural network, which makes it possible to identify digitized images for rapid diagnosis. The use of artificial intelligence in surgery is reflected in the application of da Vinci. Artificial intelligence has been widely used in anesthesiology. Scientific Novelty: The literature search established that the implementation of artificial intelligence in medicine creates certain challenges related to the protection of personal data, and the possibility of error is not excluded when using AI. Conclusion: The use of AI is promising for diagnosis and treatment and helps doctors quickly make a diagnosis and prescribe treatment, but certain challenges created by artificial intelligence must be solved by implementing more reliable personal data protection systems, as well as control over the information reproduced by artificial intelligence.

22 August 2024 in Salud, Ciencia y Tecnología - Serie de Conferencias
Verified
Journal Article
Open access
PDF file
VBViktoriia Bati
Viktoriia Bati
DTDmytro Teslenko
Dmytro Teslenko
OYOlha Yuryk
Olha Yuryk
YAYevhenii Avtomieienko
Yevhenii Avtomieienko
LBLiudmyla Bashkirova
Liudmyla Bashkirova
Clinical studies can be relied on as a powerful engine of medical advancement in terms of developing new solutions for better life treatment. This paper reviews research approaches that are critical for the establishment of the safety and efficacy of various treatment methods. Even though research is becoming more advanced day by day, still a gap exists between the research findings and their real application. The purpose of this review is to identify barriers that stand in the way of translation and to provide means for overcoming them. A comprehensive search of online databases identified studies on clinical research methodologies and evidence-based practice (EBP) promotion. Thematic analysis was used to synthesize key themes. This paper demonstrates how clinical research particularly matters. It denotes problems like expenses limits as well as clinicians’ unawareness that do not allow the translation of research results into practice. Nevertheless, efforts are made to provide solutions, including education on EBP, adoption of practice guidelines and leveraging technology to share research findings. These problems should be tackled by EBP promotion in order to guarantee optimum and updated treatment of patients and better population health.

15 August 2025 in Futurity Medicine
Verified
Journal Article
Open access
PDF file
APArtem Posunko
Artem Posunko
MCMykhaylo Chavarha
Mykhaylo Chavarha
LBLiudmyla Bashkirova
Liudmyla Bashkirova
SVSvitlana Vasylyuk-Zaitseva
Svitlana Vasylyuk-Zaitseva
OAOlga Abramchuk
Olga Abramchuk
The continuous advancement of information technologies and artificial intelligence is rapidly transforming the diagnostic, therapeutic, and prognostic capabilities of modern medicine. These developments offer unprecedented opportunities for analyzing large volumes of clinical data, which form the foundation of personalized medicine and evidence-based clinical practice. This systematic review aims to assess the current state of machine learning implementation in clinical settings, synthesize the experience of applying artificial intelligence algorithms across various medical domains, and identify promising directions for the further evolution of this innovative paradigm. Study design: A systematic analytical review was conducted using scientific literature focused on clinical and experimental studies, as well as on developed and predictive projects in the field of machine learning applications in medicine. Methodology: A comprehensive search and analysis of publications in the PubMed, Scopus, Web of Science, and Google Scholar databases over the past 15 years were performed. A total of 93 original studies were selected, comprising 65 systematic reviews and 28 meta-analyses. Content analysis, systematization, and generalization of empirical data were employed to evaluate the effectiveness of machine learning algorithms in clinical diagnostics. Results: Machine learning algorithms demonstrated high diagnostic accuracy in radiology (87–94%), pathology (91–96%), cardiology (83–89%), and oncology (88–93%). Neural networks showed significant advantages in medical image recognition, achieving diagnostic accuracy comparable to that of experienced specialists. The application of algorithms for predicting disease progression proved effective, contributing to the optimization of therapeutic strategies and a reduction in mortality rates by 12–18%. Conclusion: Machine learning is shaping a new paradigm in medical practice by enhancing diagnostic accuracy, optimizing treatment protocols, and enabling personalized therapeutic approaches. The integration of artificial intelligence technologies requires a comprehensive strategy that includes the training of healthcare professionals, the development of suitable infrastructure, and the refinement of regulatory frameworks.

22 December 2025 in INTERNATIONAL NEUROLOGICAL JOURNAL
Verified
Journal Article
Open access
TNT.I. Nasonova
T.I. Nasonova
VGV.A. Gryb
V.A. Gryb
ASA.M. Sinhaivskyi
A.M. Sinhaivskyi
LBL.M. Bashkirova
L.M. Bashkirova
TKT.V. Kolosova
T.V. Kolosova
NKN.V. Khanenko
N.V. Khanenko
Background. Polyneuropathies are a common group of neurological disorders characterized by variable clinical manifestations and involvement of motor, sensory or autonomic peripheral nerve fibers. The most prevalent variant is diabetic polyneuropathy, which develops in roughly 30 to 50 % of diabetes mellitus patients. Neuropathic pain has a profound negative impact on quality of life or daytime activity, so controlling it becomes an important task for physicians. Conventional treatments such as antidepressants and gabapentinoids often provide only partial relief of symptoms, ma­king doctors and scientists turn to research for other pathogenetic and neuromodulatory therapy choices. The objective of this article is to explore evidence-based strategies for managing diabetic polyneuropathy. Materials and methods. A literature review was conducted in PubMed, Scopus, and Cochrane Library databases over the past 10 years. It includes randomized control trials, systematic reviews, and meta-analyses on the efficacy and safety of metabolic and neuromodulatory therapy for patients with diabetic polyneuropathy. Results. Modern studies show that in addition to first-line drugs (gabapentinoids, selective serotonin reuptake inhibitors, etc.), alpha-lipoic acid, gamma-linolenic acid, acetyl-L-carnitine and B vitamins such as methylcobalamin (B12), pyridoxine (B6) and thiamine (B1), which have neuroprotective and antioxidant properties, are often used in treatment. These substances participate in energy metabolism and remyelination processes, which can lead to reduction and improvement of neurological symptoms. Research data show their effectiveness in reducing the intensity of pain and improving overall nerve conduction in patients with diabetic polyneuropathy, so these agents can be effectively used in combination with antidepressants and gabapentinoids to maximize symptomatic and pathogenetic benefit. Conclusions. An individualized, evidence-based and multicomponent approach contributes to better treatment of diabetic polyneuropathy. The combination of sympto­matic therapy (antidepressants or gabapentinoids) with pathogenetic agents is the optimal treatment choice.