Predicting Mortality and the Need for Early Intubation in Intensive Care Patients Using Machine Learning: A Pilot Study
Open Access
- 2 August 2026
- journal article
- Published by Istanbul Gelisim University in İstanbul Gelişim Üniversitesi Sağlık Bilimleri Dergisi
- No. 29,p. 26-36
Abstract
Aim: This pilot study aimed to assess the feasibility and preliminary performance of machine learning models for predicting ICU mortality and the need for intubation within 48 hours using routinely collected admission data.Method: Ten adult intensive care patients were included in this single-center, retrospective observational pilot study. For ANN development, 13 prespecified clinical and laboratory features per patient were restructured in long format, yielding 130 feature-level records. These records represented feature entries derived from 10 patients rather than independent patient-level observations. Demographic characteristics, primary diagnosis, APACHE II and SOFA scores, arterial blood gas parameters, oxygenation indicators (FiO₂, PaO₂/FiO₂), and routine metabolic–biochemical variables were analyzed. ML-based classification models predicted ICU mortality and the need for intubation within the first 48 hours.Results: In the exploratory feature-level internal assessment, both the ICU mortality and early-intubation classifications yielded an AUC of 1.00, sensitivity of 100%, specificity of 100%, and an F1-score of 1.00. These estimates were derived from records originating from 10 patients and should be interpreted cautiously.Conclusion: This pilot study demonstrates the feasibility of applying machine learning methods to routinely collected ICU admission data. The findings are preliminary and hypothesis-generating and should not be interpreted as established clinical predictive performance. Validation in larger, independent, prospective, and multicenter cohorts is required.Keywords
Funding Information
- The authors declare that no financial support was received during the conduct of this study.
This publication has 19 references indexed in Scilit:
- Improving Sepsis Mortality Prediction With Machine Learning Using Full Region Synthetic Sampling ApproachHealth Science Reports, 2025
- Machine Learning for Predicting Mortality in Intensive Care Unit Patients: A Prognostic Performance Systematic Review and Meta‐AnalysisNursing in Critical Care, 2025
- Machine Learning-Based Prediction Model for ICU Mortality After Continuous Renal Replacement Therapy Initiation in ChildrenCritical Care Explorations, 2024
- Prediction of prolonged mechanical ventilation in the intensive care unit via machine learning: a COVID-19 perspectiveScientific Reports, 2024
- Multitask multilayer-prediction model for predicting mechanical ventilation and the associated mortality rateNeural Computing and Applications, 2024
- Development and external validation of an interpretable machine learning model for the prediction of intubation in the intensive care unitScientific Reports, 2024
- Intelligent alert system for predicting invasive mechanical ventilation needs via noninvasive parameters: employing an integrated machine learning method with integration of multicenter databasesMedical & Biological Engineering & Computing, 2024
- Predicting intubation for intensive care units patients: A deep learning approach to improve patient managementInternational Journal of Medical Informatics, 2024
- Predicting time-to-intubation after critical care admission using machine learning and cured fraction informationArtificial Intelligence in Medicine, 2024
- Prediction algorithm for ICU mortality and length of stay using machine learningScientific Reports, 2022