Artificial intelligence for improved decision-making in diabetic emergency survival: A cross-sectional study.
• The Random Forest model accurately predicted survival in diabetic emergency patients, achieving an AUC of 0.96 • Patients categorized under immediate triage (P1) had significantly better survival outcomes • Integrating AI-driven predictive tools into emergency nursing workflows may enhance triage...
| Published in: | International Emergency Nursing Vol. 83 |
|---|---|
| Main Authors: | , , , , |
| Format: | research Journal Article |
| Published: |
Elsevier B.V.
Dec2025
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=189517824&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 189517824 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 1755599X 6395 jtl: International Emergency Nursing issn: 1755599X maglogo: N pubinfo: dt: Dec2025 vid: 83 pid: 467 pub: Elsevier B.V. place: New York, New York artinfo: ui: 189517824 189517824 189517824 10.1016/j.ienj.2025.101700 189517824 ppct: 1 formats: tig: atl: Artificial intelligence for improved decision-making in diabetic emergency survival: A cross-sectional study. aug: au: Nikentari, Lintang Arum Kristianto, Heri Yuliatun, Laily Haedar, Ali Tirma Irawan, Paulus Lucky affil: Nursing Department, Faculty of Health Sciences, Brawijaya University, Malang, Indonesia sug: subj: Artificial Intelligence Decision Making, Clinical Diabetes Mellitus Mortality Mortality Risk Factors Emergency Service Prediction Models Evaluation Overall Survival Human Indonesia Retrospective Design Cross Sectional Studies Record Review Logistic Regression ROC Curve Glasgow Coma Scale Random Forest Algorithms Triage Emergency Nursing Emergency Nurses Psychosocial Factors Workflow Blood Glucose Insulin Resource Allocation Validation Studies ab: • The Random Forest model accurately predicted survival in diabetic emergency patients, achieving an AUC of 0.96 • Patients categorized under immediate triage (P1) had significantly better survival outcomes • Integrating AI-driven predictive tools into emergency nursing workflows may enhance triage accuracy 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. 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). 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. 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. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|