Intelligent Alarm System of Mechanical Ventilation: Innovative Pressure Alarm for Immediate Clinical Management

Yang, Shih‐Hsing; Yeh, Tsung-Wu; Fang, Yang-Lin; Shyu, Kuo-Kai; Huang, Chung Chien; Wu, Chin-Pyng

doi:10.1109/icbeb.2012.252

Cited by 2 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prediction using machine learning and statistical techniques has been proposed (Papaioannou et al 2011, Arcentales et al 2015, based also on physiological time-series analysis, to help clinical decision-making concerning ventilator weaning, namely discontinuing ventilation support from a patient. Other studies have focused on the prediction of an increase in the PEEP parameter to reduce incidents of ventilator-induced lung injury (VILI) (Langdon et al 2017), and on an intelligent alarm system for the ventilator pressure to provide information and alarms (Yang 2012).…”

mentioning

confidence: 99%

Smart alarms towards optimizing patient ventilation in intensive care: the driving pressure case

et al. 2019

View full text Add to dashboard Cite

Objective: Alarms are a substantial part of clinical practice, warning clinicians of patient complications. In this paper, we focus on alarms in the intensive care unit and especially on the use of machine learning techniques for the creation of alarms for the ventilator support of patients. The aim is to study a method to enable timely interventions for intubated patients and prevent complications induced by high driving pressure (ΔP) and lung strain during mechanical ventilation. Approach: The relation between the ΔP and the total set of the ventilator parameters was examined and resulted in a predictive model with bimodal implementation for the short-term prediction of the ΔP level (high/low). The proposed method includes two sub-models for the prediction of future ΔP level based on the current level being high or low, named cH and cL, respectively. Based on this method, for both sub-models, an alarm will be triggered when the predicted ΔP level is considered to be high. In this vein, three classifiers (the random forest, linear support vector machine, and kernel support vector machine methods) were tested for each sub-model. To adjust the highly unbalanced classes, four different sampling methods were considered: downsampling, upsampling, synthetic minority over-sampling technique (SMOTE) sampling, and random over-sampling examples (ROSE) sampling. Main results: For the cL sub-model the combination of linear support vector machine with SMOTE sampling showed the best performance, resulting in accuracy of 93%, while the cH sub-model reached the best performance, with accuracy of 73%, with kernel support vector machine combined with the downsampling method. Significance: The results are positive in terms of the generation of new alarms in mechanical ventilation. The technical and organizational possibility of integrating data from multiple modalities is expected to further advance this line of work.

show abstract

mentioning

confidence: 99%