[Left ventricular dysfunction in patients following high-dose chemotherapy and autologous hematopoietic stem cell transplantation].

AIM: To evaluate the dynamics of LV global longitudinal strain (GLS) and other EchoCG parameters after high-dose chemotherapy (HDCT) and autologous hematopoietic stem cell transplantation (aHSCT). MATERIAL AND METHODS: The risk of LV dysfunction in patients after HDCT followed by aHSCT has not been sufficiently studied. This study included 74 patients with hemoblastosis aged 20 to 65 years who had undergone HDCT followed by aHSCT. All patients had a history of antitumor treatment. EchoCG with assessment of LV GLS and measurements of troponin T and N-terminal pro-brain natriuretic peptide (NT-proBNP) were performed for all patients before and after the treatment. RESULTS: A decrease in GLS by 15 % or more from the baseline was detected in 6 (8.1 %) patients. The decrease in GLS was associated with increased NT-proBNP >125 pg / ml at baseline (odds ratio, 8.667; 95 % confidence interval, 1.419-52.942; p=0.022). CONCLUSION: The decrease in LV GLS in patients after aHSCT was associated with increased NT-proBNP before the intervention.

[The future of computer-aided diagnostics in chest computed tomography]. / Perspektivy ispol'zovaniia kompleksnoi komp'iuter-assistirovannoi diagnostiki v otsenke struktur grudnoi kletki.

Recently, more and more attention has been paid to the utility of artificial intelligence in medicine. Radiology differs from other medical specialties with its high digitalization, so most software developers operationalize this area of medicine. The primary condition for machine learning is met because medical diagnostic images have high reproducibility. Today, the most common anatomic area for computed tomography is the thorax, particularly with the widespread lung cancer screening programs using low-dose computed tomography. In this regard, the amount of information that needs to be processed by a radiologist is snowballing. Thus, automatic image analysis will allow more studies to be interpreted. This review is aimed at highlighting the possibilities of machine learning in the chest computed tomography.