Machine learning prediction of the total duration of invasive and non-invasive ventilation During ICU Stay

• Published in: PLOS digital health Vol. 2; no. 9; p. e0000289
• Main Authors: Schwager, Emma, Liu, Xinggang, Nabian, Mohsen, Feng, Ting, French, Robin MacDonald, Amelung, Pam, Atallah, Louis, Badawi, Omar
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 01.09.2023; Public Library of Science (PLoS)
• Subjects: Computer and Information Sciences; Datasets; Heart rate; Intensive care; Machine learning; Medicine and Health Sciences; Mortality; Oxygenation; Patients; Physical Sciences; Research and Analysis Methods; Resource allocation; Risk assessment; Ventilation; Ventilators; Vital signs; United States > US
• ISSN: 2767-3170; 2767-3170
• DOI: 10.1371/journal.pdig.0000289

Predicting the duration of ventilation in the ICU helps in assessing the risk of ventilator-induced lung injury, ensuring sufficient oxygenation, and optimizing resource allocation. Prior models provided a prediction of total duration without distinguishing between invasive and non-invasive ventilation. This work proposes two independent gradient boosting regression models for predicting the duration of invasive and non-invasive ventilation based on commonly available ICU features. These models are trained on 2.6 million patient stays across 350 US hospitals between 2010 to 2019. The mean absolute error (MAE) for the prediction of duration was 2.08 days for invasive ventilation and 0.36 days for non-invasive ventilation. The total ventilation duration predicted by our model had MAE of 2.38 days, which outperformed the gold standard (APACHE) with MAE of 3.02 days. The feature importance analysis of the trained models showed that, for invasive ventilation, high average heart rate, diagnosis of respiratory infection and admissions from locations other than the operating room were associated with longer ventilation durations. For non-invasive ventilation, higher respiratory rates and having any GCS measurement were associated with longer durations.