A clinical model for highly accurate prediction of blood glucose depression after continuous intravenous insulin therapy in hyperglycemic emergencies, a multicenter retrospective cohort study

IF 3 3区 医学 Q2 ENDOCRINOLOGY & METABOLISM
Yuichiro Iwamoto, Tomohiko Kimura, Masashi Shimoda, Yuichi Morimoto, Kazunori Dan, Hideyuki Iwamoto, Junpei Sanada, Yoshiro Fushimi, Yukino Katakura, Hayato Isobe, Fuminori Tatsumi, Yukiko Kimura, Fumiko Kawasaki, Mizuho Yamabe, Michihiro Matsuki, Shuhei Nakanishi, Tomoatsu Mune, Kohei Kaku, Hideaki Kaneto
{"title":"A clinical model for highly accurate prediction of blood glucose depression after continuous intravenous insulin therapy in hyperglycemic emergencies, a multicenter retrospective cohort study","authors":"Yuichiro Iwamoto,&nbsp;Tomohiko Kimura,&nbsp;Masashi Shimoda,&nbsp;Yuichi Morimoto,&nbsp;Kazunori Dan,&nbsp;Hideyuki Iwamoto,&nbsp;Junpei Sanada,&nbsp;Yoshiro Fushimi,&nbsp;Yukino Katakura,&nbsp;Hayato Isobe,&nbsp;Fuminori Tatsumi,&nbsp;Yukiko Kimura,&nbsp;Fumiko Kawasaki,&nbsp;Mizuho Yamabe,&nbsp;Michihiro Matsuki,&nbsp;Shuhei Nakanishi,&nbsp;Tomoatsu Mune,&nbsp;Kohei Kaku,&nbsp;Hideaki Kaneto","doi":"10.1111/jdi.70109","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Hyperglycemic emergencies are broadly classified into diabetic ketoacidosis and hyperosmotic hyperglycemic state. The purpose of this study was to develop a clinical model for predicting treatment of hyperglycemic emergencies.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>This study is a multicenter, retrospective cohort study. We used information on patients admitted to four medical institutions for treatment for hyperglycemic emergencies by diabetologists between April 1, 2010, and March 31, 2024, as the machine learning's training data. Multiple regression analysis was performed to find parameters that correlated with the difference between blood glucose levels before and after treatment initiation (ΔGlu), and a gradient boosting decision tree (GBDT) was created to predict ΔGlu.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>Patients with type 1 diabetes (<i>n</i> = 47) and type 2 diabetes (<i>n</i> = 116) were included in the analysis of this study. We created a GBDT model using the following parameters as features: blood glucose level at the start of continuous intravenous insulin therapy, bicarbonate concentration, insulin flow rate, time elapsed since the start of continuous insulin therapy, and drip flow, which are important parameters for continuous intravenous insulin therapy for hyperglycemic emergencies. As a result, the correlation coefficient between predicted ΔGlu and actual ΔGlu was 0.83, showing a strong positive correlation.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>A GBDT model was developed to predict treatment after continuous intravenous insulin therapy using several variables during emergency care of patients with hyperglycemic emergencies. It is hoped that the application of this GBDT will allow appropriate provision of initial treatment, especially in nonspecialized medical facilities.</p>\n </section>\n </div>","PeriodicalId":51250,"journal":{"name":"Journal of Diabetes Investigation","volume":"16 10","pages":"1820-1828"},"PeriodicalIF":3.0000,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/jdi.70109","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Diabetes Investigation","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/jdi.70109","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

Abstract

Background

Hyperglycemic emergencies are broadly classified into diabetic ketoacidosis and hyperosmotic hyperglycemic state. The purpose of this study was to develop a clinical model for predicting treatment of hyperglycemic emergencies.

Methods

This study is a multicenter, retrospective cohort study. We used information on patients admitted to four medical institutions for treatment for hyperglycemic emergencies by diabetologists between April 1, 2010, and March 31, 2024, as the machine learning's training data. Multiple regression analysis was performed to find parameters that correlated with the difference between blood glucose levels before and after treatment initiation (ΔGlu), and a gradient boosting decision tree (GBDT) was created to predict ΔGlu.

Results

Patients with type 1 diabetes (n = 47) and type 2 diabetes (n = 116) were included in the analysis of this study. We created a GBDT model using the following parameters as features: blood glucose level at the start of continuous intravenous insulin therapy, bicarbonate concentration, insulin flow rate, time elapsed since the start of continuous insulin therapy, and drip flow, which are important parameters for continuous intravenous insulin therapy for hyperglycemic emergencies. As a result, the correlation coefficient between predicted ΔGlu and actual ΔGlu was 0.83, showing a strong positive correlation.

Conclusions

A GBDT model was developed to predict treatment after continuous intravenous insulin therapy using several variables during emergency care of patients with hyperglycemic emergencies. It is hoped that the application of this GBDT will allow appropriate provision of initial treatment, especially in nonspecialized medical facilities.

Abstract Image

一项多中心回顾性队列研究,高度准确预测高血糖急诊患者持续静脉注射胰岛素治疗后血糖下降的临床模型。
背景:高血糖紧急情况大致分为糖尿病酮症酸中毒和高渗性高血糖状态。本研究的目的是建立一个预测高血糖紧急情况治疗的临床模型。方法:本研究为多中心、回顾性队列研究。我们使用了2010年4月1日至2024年3月31日期间四家医疗机构接受糖尿病专家治疗的高血糖急诊患者的信息作为机器学习的训练数据。进行多元回归分析,寻找与治疗开始前后血糖水平差异相关的参数(ΔGlu),并创建梯度增强决策树(GBDT)预测ΔGlu。结果:本研究纳入了1型糖尿病患者(n = 47)和2型糖尿病患者(n = 116)。我们以以下参数为特征建立了GBDT模型:持续静脉注射胰岛素治疗开始时的血糖水平、碳酸氢盐浓度、胰岛素流速、开始持续胰岛素治疗的时间、滴注流量,这些参数是持续静脉注射胰岛素治疗高血糖紧急情况的重要参数。结果,预测值ΔGlu与实际值ΔGlu的相关系数为0.83,呈较强的正相关。结论:我们建立了一个GBDT模型来预测持续静脉注射胰岛素治疗后高血糖紧急情况患者急诊护理中的几个变量。希望这一GBDT的应用将允许适当提供初步治疗,特别是在非专业医疗设施中。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Diabetes Investigation
Journal of Diabetes Investigation ENDOCRINOLOGY & METABOLISM-
CiteScore
6.50
自引率
9.40%
发文量
218
审稿时长
6-12 weeks
期刊介绍: Journal of Diabetes Investigation is your core diabetes journal from Asia; the official journal of the Asian Association for the Study of Diabetes (AASD). The journal publishes original research, country reports, commentaries, reviews, mini-reviews, case reports, letters, as well as editorials and news. Embracing clinical and experimental research in diabetes and related areas, the Journal of Diabetes Investigation includes aspects of prevention, treatment, as well as molecular aspects and pathophysiology. Translational research focused on the exchange of ideas between clinicians and researchers is also welcome. Journal of Diabetes Investigation is indexed by Science Citation Index Expanded (SCIE).
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信