Medical Support System for Spontaneous Breathing Trial Prediction Using Nonuniform Discrete Fourier Transform

Spontaneous breathing trials (SBTs) represent a pivotal phase in the weaning process of mechanically ventilated patients. The objective of these trials is to assess patients’ readiness to resume independent breathing, thereby facilitating timely weaning and reducing the duration of mechanical ventilation (MV). Nevertheless, accurately predicting the success or failure of SBT remains a significant challenge in clinical practice. This study proposes a healthcare system that employs machine learning techniques to predict the outcome of SBT. The model is trained on respiratory flow and electrocardiogram (ECG) signals, employing the non-uniform discrete Fourier transform (NUDFT) for frequency domain analysis. The SBT prediction model has the potential to significantly enhance clinical decision-making by enabling the early identification of patients at risk for SBT failure, achieving an accuracy of 84.4 ± 3.2%.