PSU research team presented a report at the International Conference in China: they found a way to diagnose CHF from a drop of blood

At the International Conference on Artificial Intelligence and Human-Computer Interaction, the research team of Penza State University presented a report on October 28, “Application of a machine learning approach to classify the results of a tensiometric blood test for diagnosing chronic heart failure.” The conference took place in Wuhan (China).

The authors of the report are: Mukhi Alkezuini, Candidate of Engineering Sciences, a PSU postgraduate student (scientific supervisor Vladimir Gorbachenko), employee of the University of Kerbala (Iraq); Vladimir Gorbachenko, Head of the Department of Computer Technologies; Dmitry Gribkov , PSU post-graduate student (scientific supervisor Vladimir Gorbachenko); Oleg Zenin, Professor of the Department of Human Anatomy, PSU; Ilya Miltykh, student of the Medical Institute (scientific supervisor Professor Oleg Zenin); Vladimir Potapov, Candidate of Medical Sciences, assistant at Maxim Gorky Donetsk National Medical University.

The report develops a new approach, proposed by the authors, to the early diagnosis of chronic heart failure (CHF) based on tensiometry methods with subsequent neural network processing. “The report presents a solution to the problem of time series classification that arises when analyzing the results of tensiometric analysis. To classify time series, we propose to use a recurrent neural network,” said Vladimir Gorbachenko.

The research team analyzed neural network methods for classifying time series. “The presented approach demonstrated better accuracy rates compared to the existing machine learning approaches. The use of the developed neural network model in medical practice will significantly increase the reliability of the diagnosis of coronary heart disease,” added Oleg Zenin.

In addition, the results of the study indicate the possibility of modernizing tensiometers by eliminating the technical elements that provide forced vibrations of the drop. This will significantly reduce the cost of the device and reduce the time of the experiment.
Let us recall that we previously reported that medical scientists and IT specialists at PSU have developed neural networks capable of determining the authenticity of medications and diagnosing the early development of CHF.