article · Neural Computing and Applications
Mechanical ventilation is a vital intensive care intervention, yet it carries risks of lung damage. Accurately anticipating which patients will require ventilation and forecasting mortality can assist intensive care units. Using clinical records from the MIMIC-III database across 6, 12, and 24-hour observation windows, a two-layer predictive system was developed. The first layer uses multitask long short-term memory networks to forecast ventilation needs and mortality over the following 48 hours. The second layer applies a multilayer perceptron neural network to estimate the duration of ventilation. Particle swarm optimisation identifies the best subset of features, while relationships between ventilation and mortality are evaluated across patients with and without acute respiratory distress syndrome. Model performance peaked when utilising 24 hours of data, achieving high accuracy, precision, and recall across both prediction tasks.
Mechanical ventilation is essential for severely ill patients but can cause lung trauma. Accurate predictive tools allow clinical staff to anticipate equipment requirements and identify deteriorating patients sooner. This can support clinical decision-making, improve patient outcomes, and help healthcare managers allocate critical care resources more effectively during periods of high demand.
This technology could support clinical decision-support software used by hospital intensive care teams and healthcare administrators for patient monitoring and equipment planning. Because the model was trained and tested retrospectively on the MIMIC-III database, it represents early-stage to applied computational research that requires clinical validation and prospective testing before real-world deployment.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Mechanical ventilation (MV) is a crucial intervention in the intensive care unit (ICU) for severely ill patients. However, it can potentially contribute to lung damage due to the opening and closing of small airways and alveoli. This study aims to enhance the accuracy of mechanical ventilation prediction using a comprehensive dataset from the Medical Information Mart for Intensive Care (MIMIC-III). The data were extracted with three time frames, 6, 12, and 24 h. Then, 6 h left as a time gap and the ventilation as well as the mortality during the next 48 h. The proposed model consists of two layers: Layer 1 predicts ventilation and mortality in the ICU, while Layer 2 predicts the duration of ventilation. Classification techniques are applied to identify patients in need of ventilators, employing multilayer multitask long short-term memory (LSTM) models. Regression tasks use neural networks (multilayer perception). The optimum feature subset was obtained using particle swarm optimization (PSO). Additionally, this study examines the correlation between ventilation and mortality among patients with and without acute respiratory distress syndrome (ARDS). The findings of this research can enhance health-care outcomes and inform policymakers about resource allocation in overwhelmed health services. The best results were obtained when utilizing the first 24 h for prediction. The proposed MTL model achieved promising performance of 0.944, 0.923, 0.951, and 0.921 for the first task and 0.971, 0.961, 0.963, and 0.970 for the second task for accuracy, precision, recall, score, and AUC, respectively.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-024-10468-9
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
