Artificial intelligence for improved decision-making in diabetic emergency survival: A cross-sectional study

IF 1.8 4区医学 Q2 NURSING

International Emergency Nursing Pub Date : 2025-10-04 DOI:10.1016/j.ienj.2025.101700

Lintang Arum Nikentari , Heri Kristianto , Laily Yuliatun , Ali Haedar , Paulus Lucky Tirma Irawan

{"title":"Artificial intelligence for improved decision-making in diabetic emergency survival: A cross-sectional study","authors":"Lintang Arum Nikentari , Heri Kristianto , Laily Yuliatun , Ali Haedar , Paulus Lucky Tirma Irawan","doi":"10.1016/j.ienj.2025.101700","DOIUrl":null,"url":null,"abstract":"<div><h3>Aims</h3><div>This study aims to develop and validate an artificial intelligence -driven survival prediction model using the Random Forest algorithm to support clinical decision-making in diabetic emergency cases. The model is designed to assist emergency nurses in triage prioritization and resource allocation to improve patient outcomes.</div></div><div><h3>Methods</h3><div>A retrospective cross-sectional study was conducted using medical records of 1,047 diabetic emergency patients treated at regional hospital in Indonesia, from 2019 to 2024. Key clinical variables, including age, gender, blood glucose levels, Glasgow Coma Scale, triage classification, and insulin use, were analyzed. Logistic regression identified significant survival predictors, and random forest model was developed for survival prediction. Model performance was evaluated using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic AUC (Area Under Curve).</div></div><div><h3>Results</h3><div>The random forest model identified GCS and triage classification as the most significant predictors of survival. Patients with higher GCS scores and immediate triage classification (P1) had a greater likelihood of survival. The model demonstrated high predictive performance, achieving an accuracy of 94.9 %, sensitivity of 95.6 %, specificity of 93.7 %, and an AUC of 0.96.</div></div><div><h3>Conclusion</h3><div>The AI-based random forest model demonstrated excellent predictive accuracy, supporting its integration into emergency nursing workflows. Implementing AI-driven decision-support systems in emergency departments may enhance triage accuracy, to improve survival outcomes in diabetic emergencies, future studies should focus on external validation and the integration of additional clinical parameters to further refine model performance.</div></div>","PeriodicalId":48914,"journal":{"name":"International Emergency Nursing","volume":"83 ","pages":"Article 101700"},"PeriodicalIF":1.8000,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Emergency Nursing","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1755599X25001314","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NURSING","Score":null,"Total":0}

引用次数: 0

Abstract

Aims

This study aims to develop and validate an artificial intelligence -driven survival prediction model using the Random Forest algorithm to support clinical decision-making in diabetic emergency cases. The model is designed to assist emergency nurses in triage prioritization and resource allocation to improve patient outcomes.

Methods

A retrospective cross-sectional study was conducted using medical records of 1,047 diabetic emergency patients treated at regional hospital in Indonesia, from 2019 to 2024. Key clinical variables, including age, gender, blood glucose levels, Glasgow Coma Scale, triage classification, and insulin use, were analyzed. Logistic regression identified significant survival predictors, and random forest model was developed for survival prediction. Model performance was evaluated using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic AUC (Area Under Curve).

Results

The random forest model identified GCS and triage classification as the most significant predictors of survival. Patients with higher GCS scores and immediate triage classification (P1) had a greater likelihood of survival. The model demonstrated high predictive performance, achieving an accuracy of 94.9 %, sensitivity of 95.6 %, specificity of 93.7 %, and an AUC of 0.96.

Conclusion

The AI-based random forest model demonstrated excellent predictive accuracy, supporting its integration into emergency nursing workflows. Implementing AI-driven decision-support systems in emergency departments may enhance triage accuracy, to improve survival outcomes in diabetic emergencies, future studies should focus on external validation and the integration of additional clinical parameters to further refine model performance.

查看原文本刊更多论文

人工智能改善糖尿病紧急生存决策：一项横断面研究

本研究旨在利用随机森林算法开发和验证人工智能驱动的生存预测模型，以支持糖尿病急诊病例的临床决策。该模型旨在帮助急诊护士在分类优先级和资源分配，以改善病人的结果。方法对2019 - 2024年在印尼地区医院就诊的1047例糖尿病急诊患者的病历进行回顾性横断面研究。分析主要临床变量，包括年龄、性别、血糖水平、格拉斯哥昏迷量表、分诊分类和胰岛素使用。Logistic回归发现显著的生存预测因子，并建立随机森林模型进行生存预测。使用准确性、灵敏度、特异性和接收器工作特征AUC下面积（曲线下面积）来评估模型的性能。结果随机森林模型确定GCS和分诊分类是最显著的生存预测因子。GCS评分较高且立即分诊分类（P1）的患者生存的可能性较大。该模型具有较高的预测性能，准确率为94.9%，灵敏度为95.6%，特异性为93.7%，AUC为0.96。结论基于人工智能的随机森林模型具有良好的预测准确性，支持其集成到急诊护理工作流程中。在急诊科实施人工智能驱动的决策支持系统可以提高分诊准确性，改善糖尿病急诊患者的生存结果，未来的研究应侧重于外部验证和整合其他临床参数，以进一步完善模型的性能。

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

International Emergency Nursing NURSING-

CiteScore

3.20

自引率

11.10%

发文量

期刊介绍： International Emergency Nursing is a peer-reviewed journal devoted to nurses and other professionals involved in emergency care. It aims to promote excellence through dissemination of high quality research findings, specialist knowledge and discussion of professional issues that reflect the diversity of this field. With an international readership and authorship, it provides a platform for practitioners worldwide to communicate and enhance the evidence-base of emergency care. The journal publishes a broad range of papers, from personal reflection to primary research findings, created by first-time through to reputable authors from a number of disciplines. It brings together research from practice, education, theory, and operational management, relevant to all levels of staff working in emergency care settings worldwide.