Entropy analysis of diaphragmatic EMG signals as an indicator of extubation viability in mechanically ventilated patients

Abstract

© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

javascript:dpEsborraDadesFormAbstract();Surface electromyographic (sEMG) signals from the diaphragm has become a valuable tool for monitoring muscle activity during the weaning process from mechanical ventilation. However, EMG signals are inherently nonlinear and susceptible to noise contamination, which poses challenges for traditional signal processing methods. In this study, we propose the use of entropy metrics to evaluate the dynamic complexity and irregularity of surface electromyographic (EMG) signals of patients assisted with mechanical ventilation. Shannon entropy and spectral entropy were computed to analyze EMG signals from two surface diaphragm channels recorded in mechanically ventilated patients during extubation preparation. According to clinical criteria, the patients were classified into the successful group (GE) – 19 patients with successful extubation after 48 hours, and the failure group (GF) – 21 patients who required reconnection to the ventilator within 48 hours. sEMG signals were recorded using 5-channel surface electrodes placed around the diaphragm muscle. Shannon and spectral entropies were calculated using a 0.5-minute window with an overlap of 80%. The results presented a greater complexity of the EMG signal in the SG group. This group shows higher peaks in Shannon entropy and elevated spectral entropy values compared to the FG group. Channels 2 and 3 presented the largest statistically significant differences.Clinical Relevance— Analyzing diaphragm EMG signals using entropy metrics could improve patient outcomes by optimizing the timing of extubation. These metrics would serve as a key indicator of readiness for extubation, providing an objective basis for more informed clinical decision-making.

Research supported in part by the Universidad UNAB, Bucaramanga, Colombia, in part by the CERCA Program/ Generalitat de Catalunya, in part by the Secretaria d’Universitats i Recerca de la Generalitat de Catalunya GRC 2021 SGR 01390, and in part by the Spanish Ministry of Science and Innovation (PID2021-126455OB-I00 MCIN/AEI/FEDER).

Peer Reviewed

Postprint (author's final draft)