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