Journal influence
Higher Attestation Commission (VAK) - К1 quartile
Russian Science Citation Index (RSCI)
Bookmark
Next issue
№3
Publication date:
16 September 2025
Data analysis and processing to predict patients’ health status
Date of submission article: 24.12.2015
UDC: 004.658.6
The article was published in issue no. № 1, 2016 [ pp. 180-185 ]Abstract:Development of information technologies made people to pay more attention to automated methods of data analysis and processing. This article describes two interconnected methods for data processing: multifactor data analysis using the major components method and neural networks. The work showed a necessity to process data from patients’ tests and to predict a target parameter value through time based on this data. Prediction of a certain target parameter makes medical treatment easier due to doctor’s faster decision-making regarding a way of treatment. The authors used a multifactor analysis method (major components method). It allowed decreasing a problem scale, showed requirements to educational and test sets to design a mathematical model based on a neural network. It also allowed identifying key factors, which can be used as initial parameters for a neural-network model. The article contains load diagrams and graphical interpretation of a correlation between patients’ test values, as well as authors’ conclusions about correlation. Further, a neural network trained using a training sample (an amount of experiments for training was about 200). Training quality was controlled using a test set (an amount of experiments for a test was about 50). The article also contains a comparison of calculated and experimental data. An error of the neural network is 8 %. The authors developed software using C# and Visual Studio to implement the described methods.
Аннотация:С развитием информационных технологий все больше внимания уделяется автоматизированным способам анализа и обработки информации. В данной статье описаны два связанных способа обработки данных: многофакторный анализ данных с использованием метода главных компонент и нейронные сети. В ходе работы возникла необходимость обрабатывать данные об анализах пациентов и на их основе предсказывать значение целевого параметра во времени. Предсказание целевого параметра упрощает процесс лечения за счет более оперативного принятия врачом решения о способе лечения. Использованный метод многофакторного анализа (метод главных компонент) позволил сократить размерность задачи, выявил требования к формированию обучающей и тестовой выборок для построения математической модели на основе нейронной сети, а также дал возможность определять ключевые факторы, которые должны использоваться в качестве входных параметров в нейросетевой модели. В работе представлены графики нагрузок и графическое отображение корреляции между значениями анализов пациентов, сделаны выводы о силе корреляции между значениями анализов. В дальнейшем были проведены обучение нейронной сети на обучающей выборке (количество экспериментов для обучения – около 200) и проверка качества обучения на тестовой выборке (количество экспериментов в тестовой выборке – около 50). В работе приведено сравнение расчетных и экспериментальных данных, определена ошибка работы нейронной сети, которая составила 8 %. Для реализации вышеописанных методов разработано ПО на языке программирования C# в среде разработки Visual Studio.
Authors: Ivanov S.I. (patephon2009@yandex.ru) - D. Mendeleev University of Chemical Technology of Russian Federation, Moscow, Russia, Ph.D, Gordienko M.G. (chemcom@muctr.ru) - International Science and Education Centre for Transfer of Biopharmaceutical Technologies D. Mendeleev University of Chemical Technology of Russian Federation (Leading Researcher), Moscow, Russia, Ph.D, Matasov A.V. (mats@muctr.ru) - International Science and Education Centre for Transfer of Biopharmaceutical Technologies D. Mendeleev University of Chemical Technology of Russian Federation (Head of Information Technologies Department), Moscow, Russia, Ph.D, Menshutina N.V. (chemcom@muctr.ru) - D. Mendeleev University of Chemical Technology of Russian Federation, Moscow, Russia, Ph.D | |
Keywords: software development, data analysis, data processing, neural network, multivariate analysis |
|
Page views: 17523 |
Print version Full issue in PDF (8.31Mb) Download the cover in PDF (1.24Мб) |
Анализ и обработка данных для прогнозирования состояния больных
DOI: 10.15827/0236-235X.113.180-185
Date of submission article: 24.12.2015
UDC: 004.658.6
The article was published in issue no. № 1, 2016. [ pp. 180-185 ]
Development of information technologies made people to pay more attention to automated methods of data analysis and processing. This article describes two interconnected methods for data processing: multifactor data analysis using the major components method and neural networks. The work showed a necessity to process data from patients’ tests and to predict a target parameter value through time based on this data. Prediction of a certain target parameter makes medical treatment easier due to doctor’s faster decision-making regarding a way of treatment. The authors used a multifactor analysis method (major components method). It allowed decreasing a problem scale, showed requirements to educational and test sets to design a mathematical model based on a neural network. It also allowed identifying key factors, which can be used as initial parameters for a neural-network model. The article contains load diagrams and graphical interpretation of a correlation between patients’ test values, as well as authors’ conclusions about correlation. Further, a neural network trained using a training sample (an amount of experiments for training was about 200). Training quality was controlled using a test set (an amount of experiments for a test was about 50).
The article also contains a comparison of calculated and experimental data. An error of the neural network is 8 %. The authors developed software using C# and Visual Studio to implement the described methods.
Ivanov S.I. (patephon2009@yandex.ru) - D. Mendeleev University of Chemical Technology of Russian Federation, Moscow, Russia, Ph.D, Gordienko M.G. (chemcom@muctr.ru) - International Science and Education Centre for Transfer of Biopharmaceutical Technologies D. Mendeleev University of Chemical Technology of Russian Federation (Leading Researcher), Moscow, Russia, Ph.D, Matasov A.V. (mats@muctr.ru) - International Science and Education Centre for Transfer of Biopharmaceutical Technologies D. Mendeleev University of Chemical Technology of Russian Federation (Head of Information Technologies Department), Moscow, Russia, Ph.D, Menshutina N.V. (chemcom@muctr.ru) - D. Mendeleev University of Chemical Technology of Russian Federation, Moscow, Russia, Ph.D
Ссылка скопирована!
Permanent link: http://swsys.ru/index.php?page=article&id=4129&lang=en |
Print version Full issue in PDF (8.31Mb) Download the cover in PDF (1.24Мб) |
The article was published in issue no. № 1, 2016 [ pp. 180-185 ] |
The article was published in issue no. № 1, 2016. [ pp. 180-185 ]
Perhaps, you might be interested in the following articles of similar topics:Perhaps, you might be interested in the following articles of similar topics:
- Разработка базы данных и конвертера для извлечения и анализа специализированных данных, получаемых с медицинского аппарата
- Методы автоматической классификации текстов
- Учебная распределенная система управления мобильной колесной платформой с использованием видео- и сенсорной информации
- Структуризация сущностей естественного текста с использованием нейронных сетей для генерации трехмерных сцен
- Решение задачи прогнозирования с использованием нейронных сетей прямого распространения на примере построения прогноза роста курса акций
Back to the list of articles