The use of ridge regression for estimating the severity of acute pancreatitis

Purpose. Increasing of treatment efficiency for patients with acute pancreatitis by improving objective means of determining the severity of acute pancreatitis.Materials and method. The study was based on a retrospective analysis of 130 cases of acute pancreatitis: 47 cases from «Krasnoyarsk Regiona...

Full description

Bibliographic Details
Main Authors: D. V. Cherdantsev, A. V. Stroev, E. S. Mangalova, N. V. Kononova, O. V. Chubarova
Format: Article
Language:English
Published: Siberian State Medical University (Tomsk) 2019-10-01
Series:Bûlleten' Sibirskoj Mediciny
Subjects:
Online Access:https://bulletin.tomsk.ru/jour/article/view/2408
id doaj-42075d036257403ca7eeb1619662d6b1
record_format Article
spelling doaj-42075d036257403ca7eeb1619662d6b12021-07-29T08:38:07ZengSiberian State Medical University (Tomsk)Bûlleten' Sibirskoj Mediciny1682-03631819-36842019-10-0118310711510.20538/1682-0363-2019-3-107-1151544The use of ridge regression for estimating the severity of acute pancreatitisD. V. Cherdantsev0A. V. Stroev1E. S. Mangalova2N. V. Kononova3O. V. Chubarova4Krasnoyarsk State Medical University (KrasSMU) named after Prof. V.F. Voino-YasenetskyKrasnoyarsk State Medical University (KrasSMU) named after Prof. V.F. Voino-YasenetskyRD Science Ltd.Siberian Federal UniversityReshetnev Siberian State University of Science and TechnologyPurpose. Increasing of treatment efficiency for patients with acute pancreatitis by improving objective means of determining the severity of acute pancreatitis.Materials and method. The study was based on a retrospective analysis of 130 cases of acute pancreatitis: 47 cases from «Krasnoyarsk Regional Clinical Hospital» and 83 cases from «Regional Interdistrict Clinical Hospital No 20 named after I.S. Berzon» in the period from 2015 to 2017. The raw data was pre-processed. In particular, different methods (median, linear regression) were used to fill the missing values in the observation matrix. The initial dataset contained features measured in various quantitative and categorical scales. For some features with a pronounced asymmetric distribution, a quantile transformation was applied to initial values. The quantile transformation allows features to be brought to a uniform distribution in order to reduce the risk of excluding significant features. Ridge regression was used in combination with an algorithm for sequential reduction of attribute space.Results. The classifier of three degrees of acute pancreatitis severity was developed. This classifier can help to determine better treatment tactics. During validation, the method of determining the severity of acute pancreatitis classification has proven to be effective. The average accuracy was 92% compared to the experts’ decisions. This procedure for constructing a classifier can be used as part of the basis to the medical decision support system.Conclusion. The results of this study will help to make the choice of a necessary starting therapy, assess the need for surgical intervention and in severe cases, prescribe enhanced antibacterial and detoxification therapy. This will predictably reduce the percentage of septic complications of acute pancreatitis, and consequently will reduce the frequency of fatal outcomes.https://bulletin.tomsk.ru/jour/article/view/2408acute pancreatitisseverity, classifiercategorical signssignificant indicatorsrecovery of gapsridge regressionauc (area under curve)
collection DOAJ
language English
format Article
sources DOAJ
author D. V. Cherdantsev
A. V. Stroev
E. S. Mangalova
N. V. Kononova
O. V. Chubarova
spellingShingle D. V. Cherdantsev
A. V. Stroev
E. S. Mangalova
N. V. Kononova
O. V. Chubarova
The use of ridge regression for estimating the severity of acute pancreatitis
Bûlleten' Sibirskoj Mediciny
acute pancreatitis
severity, classifier
categorical signs
significant indicators
recovery of gaps
ridge regression
auc (area under curve)
author_facet D. V. Cherdantsev
A. V. Stroev
E. S. Mangalova
N. V. Kononova
O. V. Chubarova
author_sort D. V. Cherdantsev
title The use of ridge regression for estimating the severity of acute pancreatitis
title_short The use of ridge regression for estimating the severity of acute pancreatitis
title_full The use of ridge regression for estimating the severity of acute pancreatitis
title_fullStr The use of ridge regression for estimating the severity of acute pancreatitis
title_full_unstemmed The use of ridge regression for estimating the severity of acute pancreatitis
title_sort use of ridge regression for estimating the severity of acute pancreatitis
publisher Siberian State Medical University (Tomsk)
series Bûlleten' Sibirskoj Mediciny
issn 1682-0363
1819-3684
publishDate 2019-10-01
description Purpose. Increasing of treatment efficiency for patients with acute pancreatitis by improving objective means of determining the severity of acute pancreatitis.Materials and method. The study was based on a retrospective analysis of 130 cases of acute pancreatitis: 47 cases from «Krasnoyarsk Regional Clinical Hospital» and 83 cases from «Regional Interdistrict Clinical Hospital No 20 named after I.S. Berzon» in the period from 2015 to 2017. The raw data was pre-processed. In particular, different methods (median, linear regression) were used to fill the missing values in the observation matrix. The initial dataset contained features measured in various quantitative and categorical scales. For some features with a pronounced asymmetric distribution, a quantile transformation was applied to initial values. The quantile transformation allows features to be brought to a uniform distribution in order to reduce the risk of excluding significant features. Ridge regression was used in combination with an algorithm for sequential reduction of attribute space.Results. The classifier of three degrees of acute pancreatitis severity was developed. This classifier can help to determine better treatment tactics. During validation, the method of determining the severity of acute pancreatitis classification has proven to be effective. The average accuracy was 92% compared to the experts’ decisions. This procedure for constructing a classifier can be used as part of the basis to the medical decision support system.Conclusion. The results of this study will help to make the choice of a necessary starting therapy, assess the need for surgical intervention and in severe cases, prescribe enhanced antibacterial and detoxification therapy. This will predictably reduce the percentage of septic complications of acute pancreatitis, and consequently will reduce the frequency of fatal outcomes.
topic acute pancreatitis
severity, classifier
categorical signs
significant indicators
recovery of gaps
ridge regression
auc (area under curve)
url https://bulletin.tomsk.ru/jour/article/view/2408
work_keys_str_mv AT dvcherdantsev theuseofridgeregressionforestimatingtheseverityofacutepancreatitis
AT avstroev theuseofridgeregressionforestimatingtheseverityofacutepancreatitis
AT esmangalova theuseofridgeregressionforestimatingtheseverityofacutepancreatitis
AT nvkononova theuseofridgeregressionforestimatingtheseverityofacutepancreatitis
AT ovchubarova theuseofridgeregressionforestimatingtheseverityofacutepancreatitis
AT dvcherdantsev useofridgeregressionforestimatingtheseverityofacutepancreatitis
AT avstroev useofridgeregressionforestimatingtheseverityofacutepancreatitis
AT esmangalova useofridgeregressionforestimatingtheseverityofacutepancreatitis
AT nvkononova useofridgeregressionforestimatingtheseverityofacutepancreatitis
AT ovchubarova useofridgeregressionforestimatingtheseverityofacutepancreatitis
_version_ 1721253234691014656