For early detection and timely correction of imbalances in the body that can lead to the development of various diseases, personalized devices are needed with which one can control the current state of the body at home. The purpose of the article is to develop a universal approach to the construction of such tools and, using examples of solving urgent problems, to demonstrate its effectiveness. A distinctive feature of the proposed approach is that the user at home has the ability to form a training sample of observations of his physiological indicators, according to which two integral characteristics are automatically calculated: the reference result, which is closest to all other observations, and the value, characterizing the average deviation of the results. Personalized diagnostic rules are proposed that ensure an increase in the reliability of decisions about the current functional state of the user and an assessment of the risk of a possible development of pathology. The proposed rules form the basis of original preventive medicine for home use, including the intelligent PHASEGRAPH® electrocardiograph for diagnosing myocardial ischemia at early stages, AI-RHYTHMOGRAPH software applications for determining heart rate variability parameters and AI-ARTERIOGRAPH for integral assessment of properties blood vessels, an intelligent blood pressure monitor that measures the long-term variability in blood pressure between doctor visits, and an intelligent stethoscope for detecting respiratory distress at home. Further development of the proposed approach will make it possible to create personalized means of assessing visual acuity and hearing acuity at home, control of the vestibular apparatus, essential tremor and other means.

Introduction. An important area of modern information technology application is medical diagnostics, which is based on computer processing of biomedical signals The purpose of the article is to provide information on the results of basic and applied research that has ensured the practical implementation of the ECG method (fasegraphy method) in various fields of application and to outline further prospects for these studies. Methods. The technology is based on a stochastic model of generating an artificial signal of complex shape in terms of internal and external distortions. Results. It is shown that the efficiency in extracting diagnostic information from biomedical signals in conditions of the real distortions, which are not always additive in nature, can be increased by switching from a scalar signal in the time domain to a cognitive image in the phase plane. Original algorithms of adaptive filtering and smoothing have been developed, which made it possible to obtain a numerical estimate of the first derivative of the distorted signal. Recovery of the useful signal (reference cycle) for distorted implementations is carried out by averaging the phase trajectories with the subsequent return to the time domain. To increase the reliability of additional diagnostic features of the ECG in the phase space is proposed and clinical data have proven their usefulness in terms of reducing the risk of misdiagnosis. The practical results of the implementation of the diagnostic complex FASEGRAF® have confirmed the effectiveness of fasegraphy in various fields of application. Plans for further prospective research are presented. Conclusions. Continuation of research allow to create new competitive information technologies and digital medicine devices.

Introduction. The linguistic approach, based on the transition from the observed cyclic signal to a sequence of symbols (codeword), which characterize the dynamics of indicators from cycle to cycle, makes it possible to use the procedures of mathematical linguistics to increase the reliability of decisions. The purpose of the article is to expand the diagnostic capabilities of the linguistic approach to the analysis and interpretation of electrocardiograms (ECG). Methods. Each ECG cycle is encoded with one of four symbols characterizing changes in two indicators: traditional (cycle duration) and original (symmetry of the repolarization area). Results. Based on the processing of real clinical data of verified patients and healthy volunteers, standards of patients with chronic coronary artery disease (СAD) and healthy patients. The standards are developed using computational procedures of mathematical linguistics – the Levenshtein distance, which is the minimum number of editing operations (insertion, deletion and replacement of a character), ensuring the transition from one word to another and the frequency of occurrence of substrings in the analyzed word. On the basis of these procedures, decision rules that have been developed allow making diagnostic decisions based on the Levenshtein distance to the standards and the frequency of occurrence of one-, two- and three-symbol patterns in code words. It was found that the combination of these two methods expands the diagnostic capabilities of the linguistic approach to the analysis and interpretation of the ECG. Conclusions. It has been shown that using of the developed decision rules makes it possible to increase the sensitivity and specificity of diagnostics even in cases when the ECG does not show traditional electrocardiological signs of myocardial ischemia.

When solving a number of applied problems of medical and technical diagnostics, the designing of diagnostic models is carried out under the conditions of insufficient knowledge of physical regularities occurring in the studied objects. It is necessary to create models only based on "common case" and intuition, relying on the available experimental material (precedents). However, here erroneous solutions are possible that lead to the inefficiency of the diagnostic system. We consider examples of some considerations, which turn to be scientifically insolvent. It is shown that the linear classifier, to which the method of decision-making on the distance to standards is reduced according to the method of reference images, can lead to absurd results. Such an effect occurs if the independence condition for the preferences of individual characteristics is not fulfilled, which foresees the "worsening" of the value of one attribute can be compensated by the "improvement" of another, and vice versa, which is not always true. It is shown that the unjustified expansion of the space of diagnostic attributes impairs the effectiveness of the diagnostic rule. Therefore, it is important to get rid of unnecessary signs even before the training stage. We analyzed the inconsistency of the argumentation that when constructing diagnostic models it is expedient to use only statistically independent attributes. For showing the fallibility of such an argumentation it is proved that under a statistical dependence between attributes, a combination of individually non-informative attributes can be not only useful but also capable of providing unmistakable recognition of classes. Therefore, it is important in every definite case to investigate the question of conditional statistical dependence between attributes before making decision on their exclusion from a description. By the example of constructing a model of indirect estimation of the carbon content in a liquid metal by the temperature of crystallization onset, it is shown that it is impossible to restore the true diagnostic model using only self-organization methods without using additional algorithms.

The purpose of the article is to expand the intellectual capabilities of digital blood pressure monitors, which will increase the efficiency of their use at home.The proposed approach boils down to simple computational procedures that can be implemented on the internal processor of a home blood pressure monitor.It is shown that to assess long-term variability of indicators, it is enough to use the recurrence formulas for each current measurement to correct the range of recorded values, refine the mean and standard deviation, calculate the Pearson coefficient of variation and the index characterizing the percentage of measurements that exceed established medical standards.

модиФиЦированныЙ метод оптималЬноЙ остановКи в ЗадаЧе последователЬноГо аналиЗа алЬтернативПредложен метод, обобщающий классическую постановку задачи оптимальной остановки принятия решений при последовательном просмотре ранжированных альтернатив в случайном порядке.Отличительная особенность метода состоит в том, что правильным считается решение о появлении претендента, который по

A new method for evaluating subtle changes in biomedical signals, caused by external influences on the human organism, is proposed. The method is based on the analysis of chaoticness of the studied parameter, which is calculated in a sliding window along an array of observed values using different entropy estimations. A distinctive feature of the method is the transition from the calculated entropies to their mapping on the phase plane and estimation of the integral parameters of the obtained graphic image (the entropy phase portrait), in particular, the area of the convex hull. The diagnostic value of the proposed approach in the processing of real clinical data was demonstrated, obtained under conditions of increasing physical activity, coronary artery bypass surgery and intravenous drip infusion

ИНТЕЛЛЕКТУАЛЬНЫЕ ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ -ГЛАВНЫЙ ИНСТРУМЕНТ ПОСТРОЕНИЯ СРЕДСТВ ЦИФРОВОЙ МЕДИЦИНЫСформóлировано определение интеллеêтóальной ИТ обработêи сиãналов сложной формы.Описаны вычислительные процедóры, обладающие свойствами естественноãо интеллеêта -способностью приспосабливаться ê изменяющимся ситóациям, распознавать êлассы ситóаций внешней среды и совершенствовать собственные потребительсêие свойства по мере эêсплóатации.Эффеêтивность предложенных процедóр продемонстрирована на примере фазаãра

The method of detecting the electrical alternation effect of the heart, based on the permutation entropy analysis, which is calculated from the array of single-channel electrocardiogram parameters in sliding windows, is considered. The results of the research method on model and real data are presented. Figs.: 3. Tabl.: 1. Refs.: 10 titles.Keywords: electric alternation of the heart; electrocardiogram; permutation entropy.

Образное мышлениеУДК 616.12-07В.И.Гриценко, Л

Предложен метод анализа основных электрокардиографических признаков ЭКГ на основе построения конструктивного алгоритма описания циклов сигнала совокупностью несимметричных гауссовых функций. Разработан конструктивный алгоритм решения задачи аналитическим методом, основанный на модификации критерия оптимальности метода наименьших квадратов и введения ограничения на интервал аппроксимации элементов сигнала. Представлены результаты численных экспериментов на модельных и реальных данных, подтвердившие эффективность предложенного алгоритма. Ключевые слова: диагностический признак ЭКГ, гауссова функция, аппроксимация, критерий оптимальности Запропоновано метод аналізу основних електрокардіограмних ознак ЕКГ на основі побудови конструктивного алгоритму опису циклів сигналу сукупністю несиметричних гаусових функцій. Розроблено конструктивний алгоритм розв’язання задачі аналітичним методом, заснований на модифікації критерію оптимальності методу найменших квадратів і введення обмежень на інтервал апроксимації елементів сигналу. Представлено результати чисельних експериментів на модельних та реальних даних, котрі підтвердили ефективність запропонованого алгоритму. Ключові слова: діагностична ознака ЕКГ, гаусова функція, апроксимація, критерій оптимальності.

The original approach to the analysis, interpretation and economical coding of cyclic signals of a complex form is developed. The approach is based on the transition from the observed signal to the phase portrait in the multidimensional space of parameters that uniquely describe the form of the signal fragments. It is shown that the proposed approach allows one to solve effectively different tasks of ECG computer processing based on unified methodological principles.

Aim. To study a diagnostic value of the parameters characterizing phasic ECG portrait of the first standard lead in assessment of efficiency of cardiovascular system functioning in persons with different level of adaptation potential. Material and methods. Totally, 825 persons participated of the age 17-70 y.o. The group with cardiovascular pathology consisted with 99 persons of 50-70 y.o. with diagnoses CHD, PICS. In almost healthy group we included volunteers 17-50 y.o. (n=726), of those 35 soccer players (sports mastery) and 15 train drivers of 30-35 y.o. Registration and analysis of ECG in phasic area and defining of the original parameters βT , STR, αQRS and σQRS of phasic portrait of ECG was done via diagnostic complex PHASAGRAPH® . In train drivers the mentioned parameters of phasic portrait were recorded before and after six-hour shift. In almost healthy persons, young men and male sportsmen additionally we recorded the studied parameters continuing exercise test with gradually increasing load. Additionally, with PHASAGRAPH® we assessed the parameters of cardiointervalogram with automatic calculation of tension index (TI, u.). Before this,, in all groups the parameter of relative MOC was defined, mL/min/kg. Results. Diagnostic efficacy of βT was assessed with AUC square under experimental ROC-curve. It was found, that in threshold βT0≈0,788 there is sensitivity SE =78,8% and specificity SP =80,3% By the results of measurement of STR, αQRS, σQRS in group of almost healthy volunteers the reference diapasons defined for these parameters, which were 110 0,02 units. The scheme invented for diagnostic conclusions with the use of collected βT , STR, αQRS and σQRS. It was found that “sizes” and direction of the motions of pairs in areas of phasic portrait bring the information on compensational-adaptational mechanisms in urgent, as in long-term adaptation. Conclusion. Diagnostic ECG signs are more visible in the signal visualization in phasic coordinates z(t), z’(t), than in time zone z(t), and collection of phasic parameters of the phasic portrait, that are automatically calculated by the PHASAGRAPH® complex, make it to improve the power of one-channel ECG in prognostic reasons, as for the assessment of functional condition of cardiovascular system in screenings.

The basic principles of information technology FASEGRAPH® focuses on mass preventive examinations for early detection of abnormalities of the heart are discribed. Results of clinical trials are given

We construct the generative model for creation of artificial electrocardiogram with realistic form of informative fragments. Mechanism of creation of sequence of cycles, distorted by internal and external perturbations is considered. On the basis of model experiments we reconstruct dependencies between electrocardiogram parameters in time domain and phase coordinates.

In paper the results of study of method of analyzing electrocardiogram (ECG) in the phase space based on the original mathematical model of signal generation under conditions of internal and external disturbances are considered. Dependencies between the characteristics of the phase portrait of the ECG and ECG parameters in time domain are received. Figs.: 3. Refs.: 10 titles.

The present study aimed to develop a computerized classification of magnetocardiograms (MCG) on the basis of current density vectors (CDV) map analysis for the diagnosis of coronary artery disease (CAD). The study included 123 patients with angina and angiographically documented CAD but with normal ECG at rest and normal left ventricular function. The control group consisted of 124 normals. 4-channel SQUID-magnetometer systems located in an unshielded hospital environment was used. MCG recordings were taken at 36 pre-thoracic sites over the pericardial area and reconstruction of CDV maps within the ST–T interval was applied. Each CDV map was classified automatically with a scale from 0 (normal) to 4 (grossly abnormal). The classification number depends on the number of large vectors directed left–downward and the presence of additional clusters. The mean class was calculated for each subject in order to discriminate between groups. Using a mean class value of 1.75 as threshold for the discrimination between healthy persons and CAD patients, 76% sensitivity and 81% specificity were achieved. The computerized classification of CDV maps seems to be a useful tool for the diagnosis of CAD.

A stochastic model of generation of a signal with locally concentrated features, distorted by internal and external perturbation, and also efficient algorithms of restoring useful signal by phase trajectories of distorted observations, are suggested. Advantages of the suggested approach are demonstrated on examples of derivation of new information technologies for diagnosis of state of technical and biological objects.