预测低钠血症治疗反应的机器学习方法

IF 1.3 4区 医学 Q4 ENDOCRINOLOGY & METABOLISM Endocrine journal Pub Date : 2024-02-02 DOI:10.1507/endocrj.ej23-0561
Tamaki Kinoshita, Shintaro Oyama, Daisuke Hagiwara, Yoshinori Azuma, Hiroshi Arima
{"title":"预测低钠血症治疗反应的机器学习方法","authors":"Tamaki Kinoshita, Shintaro Oyama, Daisuke Hagiwara, Yoshinori Azuma, Hiroshi Arima","doi":"10.1507/endocrj.ej23-0561","DOIUrl":null,"url":null,"abstract":"</p><p>Hyponatremia leads to severe central nervous system disorders and requires immediate treatment in some cases. However, a rapid increase in serum sodium (s-Na) concentration could cause osmotic demyelination syndrome. To achieve a safety hyponatremia treatment, we develop a prediction model of s-Na concentration using a machine learning. Among the 341 and 47 patients admitted to two tertiary hospitals for hyponatremia treatment (s-Na &lt;130 mEq/L), those who were admitted to the general unit with urine sodium &lt;20 mEq/L or treated with desmopressin were excluded. Ultimately, 74 and 15 patients (342 and 146 6-hourly datasets) were included in the learning and validation data, respectively. We trained the prediction model using three regression algorithms for shallow machine learning to predict s-Na every 6 h during treatment with the data of patients with hyponatremia (median s-Na: 112.5 mEq/L; range: 110.0–116.8 mEq/L) from one hospital. The model was validated externally using the data of patients with hyponatremia (median s-Na: 117.0 mEq/L; range: 112.9–120.0 mEq/L) from another hospital. Using 5–7 predictors (water intake, sodium intake, potassium intake, urine volume, s-Na concentration, serum potassium concentration, serum chloride concentration), the support vector regression model showed the best performance overall (root mean square error = 0.05396; R<sup>2</sup> = 0.92), followed by the linear regression and regression tree models. The predicted s-Na levels, using explainable machine learning algorithms and clinically accessible parameters, correlated well with the actual levels. Thus, our model could be applied to the treatment of hyponatremia in clinical practice.</p>\n<p></p>","PeriodicalId":11631,"journal":{"name":"Endocrine journal","volume":"7 1","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2024-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A machine learning approach for predicting treatment response of hyponatremia\",\"authors\":\"Tamaki Kinoshita, Shintaro Oyama, Daisuke Hagiwara, Yoshinori Azuma, Hiroshi Arima\",\"doi\":\"10.1507/endocrj.ej23-0561\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"</p><p>Hyponatremia leads to severe central nervous system disorders and requires immediate treatment in some cases. However, a rapid increase in serum sodium (s-Na) concentration could cause osmotic demyelination syndrome. To achieve a safety hyponatremia treatment, we develop a prediction model of s-Na concentration using a machine learning. Among the 341 and 47 patients admitted to two tertiary hospitals for hyponatremia treatment (s-Na &lt;130 mEq/L), those who were admitted to the general unit with urine sodium &lt;20 mEq/L or treated with desmopressin were excluded. Ultimately, 74 and 15 patients (342 and 146 6-hourly datasets) were included in the learning and validation data, respectively. We trained the prediction model using three regression algorithms for shallow machine learning to predict s-Na every 6 h during treatment with the data of patients with hyponatremia (median s-Na: 112.5 mEq/L; range: 110.0–116.8 mEq/L) from one hospital. The model was validated externally using the data of patients with hyponatremia (median s-Na: 117.0 mEq/L; range: 112.9–120.0 mEq/L) from another hospital. Using 5–7 predictors (water intake, sodium intake, potassium intake, urine volume, s-Na concentration, serum potassium concentration, serum chloride concentration), the support vector regression model showed the best performance overall (root mean square error = 0.05396; R<sup>2</sup> = 0.92), followed by the linear regression and regression tree models. The predicted s-Na levels, using explainable machine learning algorithms and clinically accessible parameters, correlated well with the actual levels. Thus, our model could be applied to the treatment of hyponatremia in clinical practice.</p>\\n<p></p>\",\"PeriodicalId\":11631,\"journal\":{\"name\":\"Endocrine journal\",\"volume\":\"7 1\",\"pages\":\"\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2024-02-02\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Endocrine journal\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1507/endocrj.ej23-0561\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"ENDOCRINOLOGY & METABOLISM\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Endocrine journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1507/endocrj.ej23-0561","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENDOCRINOLOGY & METABOLISM","Score":null,"Total":0}
引用次数: 0

摘要

低钠血症会导致严重的中枢神经系统紊乱,在某些情况下需要立即治疗。然而,血清钠(s-Na)浓度的快速增加会导致渗透性脱髓鞘综合征。为了实现安全的低钠血症治疗,我们利用机器学习建立了一个 s-Na 浓度预测模型。在两家三甲医院分别收治的 341 名和 47 名低钠血症治疗患者(s-Na <130 mEq/L)中,排除了尿钠 <20 mEq/L 或接受去氨加压素治疗的普通病房患者。最终,分别有 74 名和 15 名患者(342 个和 146 个 6 小时数据集)被纳入学习数据和验证数据。我们利用一家医院的低钠血症患者数据(中位数 s-Na:112.5 mEq/L;范围:110.0-116.8 mEq/L),使用浅层机器学习的三种回归算法训练了预测模型,以预测治疗期间每 6 小时的 s-Na。利用另一家医院的低钠血症患者数据(中位数 s-Na:117.0 mEq/L;范围:112.9-120.0 mEq/L)对该模型进行了外部验证。使用 5-7 个预测因子(水摄入量、钠摄入量、钾摄入量、尿量、s-Na 浓度、血清钾浓度、血清氯浓度),支持向量回归模型的总体性能最佳(均方根误差 = 0.05396;R2 = 0.92),其次是线性回归模型和回归树模型。使用可解释的机器学习算法和临床可用参数预测的 s-Na 水平与实际水平相关性良好。因此,我们的模型可用于临床低钠血症的治疗。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A machine learning approach for predicting treatment response of hyponatremia

Hyponatremia leads to severe central nervous system disorders and requires immediate treatment in some cases. However, a rapid increase in serum sodium (s-Na) concentration could cause osmotic demyelination syndrome. To achieve a safety hyponatremia treatment, we develop a prediction model of s-Na concentration using a machine learning. Among the 341 and 47 patients admitted to two tertiary hospitals for hyponatremia treatment (s-Na <130 mEq/L), those who were admitted to the general unit with urine sodium <20 mEq/L or treated with desmopressin were excluded. Ultimately, 74 and 15 patients (342 and 146 6-hourly datasets) were included in the learning and validation data, respectively. We trained the prediction model using three regression algorithms for shallow machine learning to predict s-Na every 6 h during treatment with the data of patients with hyponatremia (median s-Na: 112.5 mEq/L; range: 110.0–116.8 mEq/L) from one hospital. The model was validated externally using the data of patients with hyponatremia (median s-Na: 117.0 mEq/L; range: 112.9–120.0 mEq/L) from another hospital. Using 5–7 predictors (water intake, sodium intake, potassium intake, urine volume, s-Na concentration, serum potassium concentration, serum chloride concentration), the support vector regression model showed the best performance overall (root mean square error = 0.05396; R2 = 0.92), followed by the linear regression and regression tree models. The predicted s-Na levels, using explainable machine learning algorithms and clinically accessible parameters, correlated well with the actual levels. Thus, our model could be applied to the treatment of hyponatremia in clinical practice.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Endocrine journal
Endocrine journal 医学-内分泌学与代谢
CiteScore
4.30
自引率
5.00%
发文量
224
审稿时长
1.5 months
期刊介绍: Endocrine Journal is an open access, peer-reviewed online journal with a long history. This journal publishes peer-reviewed research articles in multifaceted fields of basic, translational and clinical endocrinology. Endocrine Journal provides a chance to exchange your ideas, concepts and scientific observations in any area of recent endocrinology. Manuscripts may be submitted as Original Articles, Notes, Rapid Communications or Review Articles. We have a rapid reviewing and editorial decision system and pay a special attention to our quick, truly scientific and frequently-citable publication. Please go through the link for author guideline.
期刊最新文献
A parent and child with Liddle syndrome diagnosed correctly with the child as the proband: a case report with review of literature. Effects of breaking up prolonged sitting via exercise snacks intervention on the body composition and plasma metabolomics of sedentary obese adults: a randomized controlled trial. Associations between muscle quality and whole-body vibration exercise-induced changes in plasma hypoxanthine following an oral glucose load in healthy male subjects. Dose-response relationship between the fatty liver index and asthma risk: NHANES 2001~2018. Updates on WHO 5th edition classification, molecular characteristics and tumor microenvironment of adrenocortical carcinomas.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1