Holter monitoring, a long-term ECG recording (24-hours and more), contains a large amount of valuable diagnostic information about the patient. Its interpretation becomes a difficult and time-consuming task for the doctor who analyzes them because every heartbeat needs to be classified, thus requiring highly accurate methods for automatic interpretation. In this paper, we present a three-stage process for analysing Holter recordings with robustness to noisy signal. First stage is a segmentation neural network (NN) with encoderdecoder architecture which detects positions of heartbeats. Second stage is a classification NN which will classify heartbeats as wide or narrow. Third stage in gradient boosting decision trees (GBDT) on top of NN features that incorporates patient-wise features and further increases performance of our approach. As a part of this work we acquired 5095 Holter recordings of patients annotated by an experienced cardiologist. A committee of three cardiologists served as a ground truth annotators for the 291 examples in the test set. We show that the proposed method outperforms the selected baselines, including two commercial-grade software packages and some methods previously published in the literature.

Analysis of chest CT scans can be used in detecting parts of lungs that are affected by infectious diseases such as COVID-19. Determining the volume of lungs affected by lesions is essential for formulating treatment recommendations and prioritizing patients by severity of the disease. In this article we adopted an approach based on using an ensemble of deep convolutional neural networks for segmentation of slices of lung CT scans. Using our models, we are able to segment the lesions, evaluate patients’ dynamics, estimate relative volume of lungs affected by lesions, and evaluate the lung damage stage. Our models were trained on data from different medical centers. We compared predictions of our models with those of six experienced radiologists, and our segmentation model outperformed most of them. On the task of classification of disease severity, our model outperformed all the radiologists.

Background. In relation with the COVID-19 new coronavirus infection epidemic that began in Russia in the spring of 2020, a completely new group of patients appeared: patients whose coronavirus infection was combined with the proximal femur fractures. In the course of practical work, hospital doctors had to gain experience in treating these complex patients, solve new organizational and medical tasks. The aim of the study was to evaluate the results of treatment of patients with the proximal femur fractures in combination with coronavirus infection in a covid hospital at the hospital stage, 30-day and 6-month terms. Materials and Methods. The retrospective study is based on the collection and generalization of data from 64 patients with the proximal femur fractures in combination with confirmed coronavirus infection who underwent inpatient treatment from 16.03.2020 to 31.05.2021. 38 (59.4%) patients had a femoral neck fracture, 26 (40.6%) had a fracture of the trochanter region. Forty (62.5%) patients underwent surgical treatment (hip replacement was performed in 23 cases, osteosynthesis was performed in 17 cases), 24 (37.5%) patients did not undergo surgery. Results. With conservative treatment, the hospital mortality rate was 41.6%, the 30-day mortality rate was 72.7%, and the 6 month mortality rate was 95.5%. During surgical treatment, the hospital mortality rate was 5.0% (2 patients died). Early postoperative complications were detected in 5 (12.5%) patients. Thirty-one (77.5%) patients walked or stood with a walker on their own at the time of discharge; 7 (17.5%) patients could not be activated. The thirty-day mortality rate in the group of patients who underwent surgical treatment was 8.6%, and the 6-month mortality rate was 32.1%. Conclusion. Surgical treatment of patients with the proximal femur fractures in combination with coronavirus infection is much more difficult than the treatment of patients without infectious pathology. However, despite number of unresolved problems, surgical treatment of such patients is possible with good results and should be actively applied.