Using weak signals to predict spontaneous breathing trial success: a machine learning approach.

Background: Weaning from mechanical ventilation (MV) is a key phase in the management of intensive care unit (ICU) patient. According to the WEAN SAFE study, weaning from MV initiation is defined as the first attempt to separate a patient from the ventilator and the success is the absence of reintubation (or death) within 7 days of extubation. Mortality rates increase with the difficulty of weaning, reaching 38% for the most challenging cases. Predicting the success of weaning is difficult, due to the complexity of factors involved. The many biosignals that are measured in patients during ventilation may be considered "weak signals", a concept rarely used in medicine. The aim of this research is to investigate the performance of machine learning (ML) models based on biosignals to predict spontaneous breathing trial success (SBT) using biosignals and to identify the most important variables.

Methods: This retrospective study used data from two centers (Nice University Hospital, Archet and Pasteur) collected from 232 intensive care patients who underwent MV (149 successfully and 83 unsuccessfully) between January, 2020 and April, 2023. The study focuses on the development of ML algorithms to predict the success of the spontaneous breathing trial based on a combination of discrete variables and biosignals (time series) recorded during the 24 h prior to the SBT.

Results: For the models tested, the best results were obtained with Support Vector Classifier model: AUC-PR 0.963 (0.936-0.970, p = 0.001), AUROC 0.922 (0.871-0.940, p < 0.001).

Conclusions: We found that ML models are effective in predicting the success of SBT based on biosignals. Predicting weaning from mechanical ventilation thus appears to be a promising area for the application of AI, through the development of multidimensional models to analyze weak signals.