Background Large observational clinical datasets are becoming increasingly available for mining associations between various disease traits and administered therapy. These datasets can be considered as representations of the landscape of all possible disease conditions, in which a concrete disease state develops through stereotypical routes, characterized by “points of no return" and “final states" (such as lethal or recovery states). Extracting this information directly from the data remains challenging, especially in the case of synchronic (with a short-term follow-up) observations. Results Here we suggest a semi-supervised methodology for the analysis of large clinical datasets, characterized by mixed data types and missing values, through modeling the geometrical data structure as a bouquet of bifurcating clinical trajectories. The methodology is based on application of elastic principal graphs, which can address simultaneously the tasks of dimensionality reduction, data visualization, clustering, feature selection, and quantifying the geodesic distances (pseudo-time) in partially ordered sequences of observations. The methodology allows a patient to be positioned on a particular clinical trajectory (pathological scenario) and the degree of progression along it to be characterized with a qualitative estimate of the uncertainty of the prognosis. We developed a tool ClinTrajan for clinical trajectory analysis implemented in the Python programming language. We test the methodology in 2 large publicly available datasets: myocardial infarction complications and readmission of diabetic patients data. Conclusions Our pseudo-time quantification-based approach makes it possible to apply the methods developed for dynamical disease phenotyping and illness trajectory analysis (diachronic data analysis) to synchronic observational data.

This article discusses the issue of assessing the quality of predicting the dynamics of the human body in conditions of cardiovascular disease using intelligent software systems. To improve the forecast accuracy, the voting method of 3 competing systems was used, as well as the elimination of sparse data columns. Assessment of the quality of the prognosis of complications of cardiovascular diseases is carried out in terms of the accuracy and specificity of the diagnosis. The constructed system for 10 predicted diagnoses out of 12 showed a prediction accuracy of more than 90% with a specificity of more than 85%. This result shows a fairly high predictive ability of the created system when solving the problem of predicting the reaction of the human body to the onset of cardiovascular diseases (for example, complications of myocardial infarction).

The article solves the problem of creating models for predicting the course and complications of cardiovascular diseases. Artificial neural networks based on the Keras library are used. The original dataset includes 1700 case histories. In addition, the dataset augmentation procedure was used. As a result, the overall accuracy exceeded 84%. Furthermore, optimizing the network architecture and dataset has increased the overall accuracy by 17% and precision by 7%.

No abstract

In order to terminate atrial flutter (AF) overdrive transesophageal left atrial pacing (TELAP) was performed in 760 patients with paroxysmal AF. There were 315 women and 415 men (mean age 59 years). In 260 patients, TELAP was used in an outpatient setting. Approximately half of the patients (51%) had coronary artery disease and/or arterial hypertension, and 23% of the patients had no structural heart disease. The duration of AF ranged between 1 hour and 1 month. TELAP was performed in 312 patients without any antiarrhythmic drug (AAD) administration (group I) and in 448 patients after administration of AAD (procainamide and/or amiodarone) in conventional doses (group II). TELAP resulted in immediate return of sinus rhythm in 85 patients (27%) of group I and in 222 patients (50%) of group II (P < 0.001). TELAP converted AF to atrial fibrillation (AFIB) in 185 of group I and in 214 (48%) of the group II patients (P < 0.01). In addition, within 1-2 days after TELAP AFIB converted to sinus rhythm spontaneously or after AAD in 87 patients of group I (28%) and in 84 (19%) of the group II patients (P < 0.01). In general sinus rhythm was restored in 172 (55%) of the group I and in 306 (68%) of the group II patients (P < 0.005). AF was converted to AFIB in 98 (31%) of the group I and in 130 (29%) of the patients in group II patients (NS). TELAP was ineffective in 42 (13.5%) of the group I and in 12 (3%) of the group II patients (P < 0.001). TELAP was an effective noninvasive method for the treatment of recent onset AF. Our experience showed that after TELAP, sinus rhythm was restored in most of the patients with paroxysmal AF within 1-2 days. In some patients TELAP converted AF to AFIB, making it easier to control the heart rate with AAD. Treatment with AAD before TELAP increased its effectiveness.