Keyword: Diagnosis

ABSTRACT: Precision medicine aims to deliver the right treatment to the right patient at the right time, yet its widespread clinical adoption remains limited by challenges in accurate diagnosis, slow drug development processes and the difficulty of translating complex biological data into actionable clinical decisions. Conventional diagnostic and therapeutic approaches often rely on population averages, which can overlook individual genetic, molecular and clinical differences, leading to variable treatment responses and high drug development failure rates. In recent years, Artificial Intelligence (AI) and Machine Learning (ML) have gained increasing attention as clinical support tools capable of analyzing complex and large-scale biomedical data, improving diagnostic accuracy, accelerating drug development and enabling more personalized approaches to patient care. This study presents a systematic literature review conducted in accordance with the PRISMA guidelines, examining recent evidence on how AI and ML act as catalysts for precision medicine, particularly in diagnosis and drug development. Peer-reviewed studies published between 2019 and 2025 were systematically identified from major academic databases and screened using predefined inclusion and exclusion criteria. The selected studies were analyzed to assess clinical applications, AI techniques employed and their implications for personalized healthcare and pharmaceutical innovation. The findings indicate that AI and ML significantly enhance diagnostic accuracy through applications in medical imaging, genomics and electronic health record analysis, supporting earlier and more precise disease detection. In drug development, AI-driven methods improve target identification, lead optimization, toxicity prediction and clinical trial design, contributing to reduced development time and cost. Furthermore, the integration of multi-omics and clinical data through AI enables more personalized treatment strategies, improving therapeutic selection and dosing. This study concludes that AI and ML are powerful catalysts for precision medicine and capable of bridging the gap between complex biomedical data and clinical decision-making. With appropriate validation, explainable models and robust ethical and regulatory frameworks, these technologies have the potential to accelerate drug development and support clinicians in delivering more accurate diagnoses, more effective treatments and safer patient-centered, precision-based healthcare.

ABSTRACT: Castleman disease (CD) is a rare lymphoproliferative disorder with heterogeneous clinical manifestations. This article presents a clinical case of HHV-8–associated multicentric Castleman disease (MCD) in an HIV-negative patient treated at the National Scientific Oncology Center. Diagnostic methods included histological and immunohistochemical evaluation, laboratory investigations, and imaging studies. The choice of therapy is discussed. The patient demonstrated resistance to rituximab monotherapy but achieved a favorable response to R-CHOP chemotherapy. This case highlights the importance of early assessment of HHV-8 status and an individualized approach to treatment selection.

ABSTRACT: Summary: The article presents the results of evaluating the diagnostic efficiency of ultrasound (US) in determining the extent of pathological processes in lymphoma patients. The study included 48 patients with Hodgkin’s and non-Hodgkin’s lymphoma who were hospitalized at the National Scientific Oncology Center from 2021 to 2024. All participants underwent comprehensive ultrasound of the abdominal parenchymal organs and lymph nodes using B-mode and Doppler imaging. The obtained data indicate high sensitivity and specificity of US in detecting liver, spleen, and abdominal lymph node involvement. Characteristic echographic signs of lymphatic conglomerates and associated complications such as ascites and exudative pleuritis were noted. Given the availability and safety of the method, US can be considered a key tool for primary diagnosis and lymphoma monitoring in clinical practice.
The purpose of the study: To evaluate the diagnostic efficiency of ultrasound (US) in assessing the extent of the disease in lymphoma.
Methods: A retrospective analysis of 48 medical records of patients with confirmed diagnoses of Hodgkin’s lymphoma (HL) and non-Hodgkin’s malignant lymphoma (NHL) who were treated at the National Scientific Oncology Center between 2021 and 2024. All patients underwent comprehensive abdominal ultrasound, pleural ultrasound, and lymph node imaging with Doppler.
Results: Pathological changes in lymph nodes, spleen, liver, and pleura were detected in all patients. In 60% of cases, the lymph node conglomerates appeared echonegative, while 5% showed signs of aggressive progression (undefined capsules, liquefaction). Typical echographic signs of diffuse and focal organ changes were observed.