Some Mathematical Approaches to Develop Models for Prediction of Compensation and Decompensation Stages of Diabetes Mellitus among Children and Adolescents
Abstract
The problem of prediction of compensation and decompensation stages of diabetes mellitus among children and adolescents using methods of machine learning is considered in the paper. There are several mathematical models used in the study: logistic regression, decision trees and gradient boosting.
The “de-identified” data of medical examination of children and adolescents of the Altai region suffering from diabetes mellitus are used to train the models in this study.
The output parameter of the models is the stage of diabetes mellitus compensation encoded with the following values: 0 — compensation of diabetes mellitus, 1 — decompensation of diabetes mellitus. This way, the prediction is the problem of binary classification.
The results of the conducted research are the following: models to predict the stages of compensation and decompensation of diabetes mellitus among children and adolescents are developed using the high-level Python programming language; optimal parameters are obtained for each model; prediction quality is estimated for each model using the following metrics: accuracy, completeness, F-measure, sensitivity, and specificity.
Professionals can use the obtained results for the supplementary diagnosis of children and adolescents of the Altay region who suffer from diabetes mellitus.
DOI 10.14258/izvasu(2018)4-15
Downloads
Metrics
References
Дедов И.И.‚ Кураева Т.Л.‚ Петеркова В.А.‚ Щербачёва А.Н. Сахарный диабет у детей и подростков. — М., 2002.
Дедов И.И., Кураева Т.Л., Петеркова В.А. Инсулинотерапия сахарного диабета 1 типа у детей и подростков. — М., 2003.
Медик В.А.‚ Токмачев В.С., Фишман Б.Б. Теоретическая статистика // Статистика в медицине и биологии. — М.‚ 2002.
Флах П. Машинное обучение. Наука и искусство построения алгоритмов, которые извлекают знания из данных. — М., 2015.
Вьюгин В.В. Математические основы машинного обучения и прогнозирования. — М., 2013.
Бринк Х., Ричардс Д., Феверолф М. Машинное обучение. — СПб., 2017.
Пиянзин А.И., Сидун Д.Ю., Назаркина О.М., Хворова Л.А., Малахова Т.И., Шарлаева Е.А., Левич К.А., Сапкина М.Р., Назаровская О.В. Информационные технологии в оценке липидного обмена у детей и подростков с сахарным диабетом 1 типа // Медицинский алфавит. — 2017.
Рашка С. Python и машинное обучение. — М., 2017.
Коэльо Л., Ричарт В. Построение систем машинного обучения на языке Python. — М., 2016.
Виндер П. Python для сложных задач: наука о данных и машинное обучение. — СПб., 2018.
Кротова О.С., Хворова Л.А. Применение нейронных сетей для диагностики заболевания сахарным диабетом детей и подростков на территории Алтайского края // МАК: Математики — Алтайскому краю : сборник трудов
всерос. конф. по математике. — Барнаул, 2017.
Кротова О.С., Сидун Д.Ю. Современные компьютерные технологии в изучении сахарного диабета у детей и подростков // Молодежь — Барнаулу : материалы XVIII—XIX городской научно-практической конференции молодых ученых. — Ч. XIX. — Барнаул, 2018.
Концепция создания единой государственной информационной системы в сфере здравоохранения : приказ Минздравсоцразвития России от 28.04.2011 № 364 [Электронный ресурс]. — URL: http://www.consultant.ru/.
Copyright (c) 2018 О.С. Кротова, А.И. Пиянзин, Л.А. Хворова, А.В. Жариков
This work is licensed under a Creative Commons Attribution 4.0 International License.
Izvestiya of Altai State University is a golden publisher, as we allow self-archiving, but most importantly we are fully transparent about your rights.
Authors may present and discuss their findings ahead of publication: at biological or scientific conferences, on preprint servers, in public databases, and in blogs, wikis, tweets, and other informal communication channels.
Izvestiya of Altai State University allows authors to deposit manuscripts (currently under review or those for intended submission to Izvestiya of Altai State University) in non-commercial, pre-print servers such as ArXiv.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
