Machine Learning of the Biotechnic System for Gastroesophageal Reflux Disease Monitoring

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17610%2F23%3AA2402GZX" target="_blank" >RIV/61988987:17610/23:A2402GZX - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-16203-9_23" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-16203-9_23</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-16203-9_23" target="_blank" >10.1007/978-3-031-16203-9_23</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Machine Learning of the Biotechnic System for Gastroesophageal Reflux Disease Monitoring

Popis výsledku v původním jazyce

The article is devoted to the study of gastroesophageal reflux disease development. The main research contribution is that the study implements prognostic, morpho-functional models to automate the differential diagnostics process. Also, the research developed a special methodology for automating the differential diagnostics process using artificial neural networks based on predictive morpho-functional models. The system analysis method was applied. This method allows you to study analyzed problems and diseases at various systems organization levels, including macro and micro levels to highlight the characteristics, symptoms, syndromes, and signs necessary for private diagnosis, and in the study, the use of algorithms for evaluating the dispersion of the results was further developed, which made it possible to assess the informativeness of signs about the corresponding nosological disease form. The methods and techniques for treating the disease were analyzed. A faster and more reliable method was proposed for monitoring the food effect on the gastroesophageal reflux disease reaction. Statistical processing of the research results is carried out. The reliability of the data is shown. Machine learning of the biotechnical disease monitoring system was carried out for a more reliable further diagnosis. The machine is properly trained and classifies the image. Regression analysis showed the model reliability built using machine learning. After conducting experiments and subsequent analysis of the results, we obtained an accuracy of 99%. The system has correctly learned to classify data. Regression analysis showed an almost linear regression.

Název v anglickém jazyce

Machine Learning of the Biotechnic System for Gastroesophageal Reflux Disease Monitoring

Popis výsledku anglicky

The article is devoted to the study of gastroesophageal reflux disease development. The main research contribution is that the study implements prognostic, morpho-functional models to automate the differential diagnostics process. Also, the research developed a special methodology for automating the differential diagnostics process using artificial neural networks based on predictive morpho-functional models. The system analysis method was applied. This method allows you to study analyzed problems and diseases at various systems organization levels, including macro and micro levels to highlight the characteristics, symptoms, syndromes, and signs necessary for private diagnosis, and in the study, the use of algorithms for evaluating the dispersion of the results was further developed, which made it possible to assess the informativeness of signs about the corresponding nosological disease form. The methods and techniques for treating the disease were analyzed. A faster and more reliable method was proposed for monitoring the food effect on the gastroesophageal reflux disease reaction. Statistical processing of the research results is carried out. The reliability of the data is shown. Machine learning of the biotechnical disease monitoring system was carried out for a more reliable further diagnosis. The machine is properly trained and classifies the image. Regression analysis showed the model reliability built using machine learning. After conducting experiments and subsequent analysis of the results, we obtained an accuracy of 99%. The system has correctly learned to classify data. Regression analysis showed an almost linear regression.

Druh

C - Kapitola v odborné knize

CEP obor

—

OECD FORD obor

10102 - Applied mathematics

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název knihy nebo sborníku

Lecture Notes in Data Engineering, Computational Intelligence, and Decision Making

ISBN

978-3-031-16202-2

Počet stran výsledku

20

Strana od-do

387-406

Počet stran knihy

721

Název nakladatele

Springer Cham

Místo vydání

Cham, Switzerland

Kód UT WoS kapitoly

—