Defining predictors for successful mechanical ventilation weaning, using a data-mining process and artificial intelligence

Abstract

Mechanical ventilation weaning within intensive care units (ICU) is a difficult process, while crucial when considering its impact on morbidity and mortality. Failed extubation and prolonged mechanical ventilation both carry a significant risk of adverse events. We aimed to determine predictive factors of extubation success using data-mining and artificial intelligence. A prospective physiological and biomedical signal data warehousing project. A 21-beds medical Intensive Care Unit of a University Hospital. Adult patients undergoing weaning from mechanical ventilation. Hemodynamic and respiratory parameters of mechanically ventilated patients were prospectively collected and combined with clinical outcome data. One hundred and eight patients were included, for 135 spontaneous breathing trials (SBT) allowing to identify physiological parameters either measured before or during the trial and considered as predictive for extubation success. The Early-Warning Score Oxygen (EWSO2) enables to discriminate patients deemed to succeed extubation, at 72-h and 7-days. Cut-off values for EWSO2 (AUC = 0.80; Se = 0.75; Sp = 0.76), mean arterial pressure and heart-rate variability parameters were determined. A predictive model for extubation success was established including body-mass index (BMI) on inclusion, occlusion pressure at 0,1 s. (P0.1) and heart-rate analysis parameters (LF/HF) both measured before SBT, and heart rate during SBT (global performance 62%; 83%). The data-mining process enabled to detect independent predictive factors for extubation success and to develop a dynamic predictive model using artificial intelligence. Such predictive tools may help clinicians to better discriminate patients deemed to succeed extubation and thus improve clinical performance.

Using Artificial Intelligence to Predict Mechanical Ventilation Weaning Success in Patients with Respiratory Failure, Including Those with Acute Respiratory Distress Syndrome

“…The prognosis for patients in the first group, constituting 69% of those undergoing weaning, is favorable, with ICU and in-hospital mortality rates of 5% and 12%, respectively. The remaining 31% of patients, representing groups 2 and 3, have ICU mortality rates as high as 25% [ 8 , 9 ].…”

“…The essential clinical parameters include the resolution of, or a significant improvement in, the underlying cause for ventilation and ensuring adequate gas exchange, typically reflected by an arterial oxygen saturation > 90% with FiO 2 < 0.4 or PaO 2 /FiO 2 > 200 with PEEP ≤ 5 cmH 2 O. Additional criteria include: the absence of fever, satisfactory neurological and muscular status, stable cardiovascular function, appropriate hemoglobin concentrations, and the correction of metabolic and/or electrolyte disturbances [ 1 , 7 , 9 ]. Factors predicting extubation failure include but are not limited to excessive secretions, a mechanical ventilation duration exceeding 72 h, and upper airway disorders.…”

“…Successful completion of the SBT, as evidenced by successful extubation, is achieved in some patients. However, approximately 25–40% of patients fail the first SBT, and 10–25% experience extubation failure, which necessitates re-intubation [ 9 , 22 , 23 ].…”

“…Menguy et al [ 9 ] used a data-mining process and AI on a prospective database of 108 medical ICU patients in order to find predictors of a successful SBT and weaning from MV for at least 72 h after extubation. In their analysis, cardiovascular parameters (reflected in heart rate variability) had a substantial impact on SBT success in addition to respiratory and systemic parameters (respiratory drive and BMI, respectively).…”

“…The weaning process, a crucial step in MV management, involves the process of liberating the patient from mechanical support and removing the endotracheal tube, commonly known as extubation [ 2 ]. This process can involve a substantial portion, up to 40–50%, of the overall duration of MV [ 7 , 8 , 9 ]. Several risk factors for respiratory weaning failure have been investigated over time, including co-morbidities, acute disease severity, and problems involving physiological systems, such as respiratory pump failure and cardiovascular instability [ 7 , 10 ].…”