Machine learning modelling for predicting the utilization of invasive and non‐invasive ventilation throughout the ICU duration

• Published in: Healthcare technology letters 2024-08, Vol.11 (4), p.252-257
• Main Authors: Schwager, Emma, Nabian, Mohsen, Liu, Xinggang, Feng, Ting, French, Robin, Amelung, Pam, Atallah, Louis, Badawi, Omar
• Format: Article
• Language: English
• Subjects: Letter; medical computing; medical information systems; medical signal processing; patient care; patient monitoring; pattern classification
• ISSN: 2053-3713; 2053-3713
• DOI: 10.1049/htl2.12081

The goal of this work is to develop a Machine Learning model to predict the need for both invasive and non‐invasive mechanical ventilation in intensive care unit (ICU) patients. Using the Philips eICU Research Institute (ERI) database, 2.6 million ICU patient data from 2010 to 2019 were analyzed. This data was randomly split into training (63%), validation (27%), and test (10%) sets. Additionally, an external test set from a single hospital from the ERI database was employed to assess the model's generalizability. Model performance was determined by comparing the model probability predictions with the actual incidence of ventilation use, either invasive or non‐invasive. The model demonstrated a prediction performance with an AUC of 0.921 for overall ventilation, 0.937 for invasive, and 0.827 for non‐invasive. Factors such as high Glasgow Coma Scores, younger age, lower BMI, and lower PaCO2 were highlighted as indicators of a lower likelihood for the need for ventilation. The model can serve as a retrospective benchmarking tool for hospitals to assess ICU performance concerning mechanical ventilation necessity. It also enables analysis of ventilation strategy trends and risk‐adjusted comparisons, with potential for future testing as a clinical decision tool for optimizing ICU ventilation management. This study developed a Machine Learning model using the Philips eICU Research Institute database to predict the need for invasive and non‐invasive mechanical ventilation in intensive care unit (ICU) patients. Analyzing data from 2.6 million ICU patients from 2010 to 2019, the model achieved high accuracy in performance, indicated by AUC values. Notably, factors such as Glasgow Coma Scores, age, BMI, and PaCO2 influenced the likelihood of ventilation necessity.