Automatic Classification of Sedation Levels in ICU Patients Using Heart Rate Variability

Nagaraj, Sunil Belur; McClain, Lauren; Biswal, Siddharth; Rosenthal, Eric S.; Purdon, Patrick L.; Westover, M. Brandon

doi:10.1097/ccm.0000000000001708

Cited by 30 publications

(29 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In a previous investigation we found that HRV features showed promise for distinguishing between different levels of sedation in mechanically ventilated ICU patients (12). Our present results extend these findings by demonstrating that HRV-based classification of sedation levels can be accomplished with an accuracy substantially above chance at the level of individual patients.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Patient-Specific Classification of ICU Sedation Levels From Heart Rate Variability*

Nagaraj

Biswal

Boyle

et al. 2017

Critical Care Medicine

Self Cite

View full text Add to dashboard Cite

Rationale Intensive care unit (ICU) patients are at risk for both over- and under sedation, presently. An automated, physiologically-based method for monitoring sedation levels might help reduce this risk by allowing more precise titration of sedation in critically ill individuals. Objective To develop a peronsalizable algorithm to discriminate between sedation levels in ICU patients based on heart rate variability (HRV). Methods We gathered 21,912 hours of routine electrocardiogram (ECG) recordings from a heterogenous group of 70 adult ICU patients. All patients included in the study were mechanically ventilated and were receiving sedatives. As “ground truth” for developing our method we used Richmond agitation-sedation scale (RASS) scores grouped into four levels denoted “comatose” (−5), “deeply sedated” (−4 to −3), “lightly sedated” (−2 to 0), and “agitated” (+1 to +4). We trained a support vector machine learning algorithm to calculate the probability of each sedation level from HRV measures derived from the ECG. To estimate algorithm performance we calculated leave-one-subject-out cross-validated accuracy. Measurements and Main Results The patient-independent version of the proposed system discriminated between the 4 sedation levels with an overall accuracy of 59%. Upon personalizing the system supplementing the training data with patient-specific calibration data, consisting of an individual’s labeled HRV epochs from the preceding 24 hours, accuracy improved to 67%. The personalized system discriminated between light- and deep-sedation states with an average accuracy of 75%. Conclusions Our results suggest that HRV information can be used to monitor sedation levels in medical and surgical ICU patients with varied pathophysiologies. Future work incorporating disease pathology, pharmacological information and other physiological variables may further improve the accuracy of this model.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In preliminary work we found that HRV measures show potential value as features in an automated monitoring system to predict the level of consciousness of ICU patients (12). Here we extend our previous work by developing a sedation level assessment system based on HRV measures that is patient-specific .…”

Section: Introductionmentioning

confidence: 99%

Patient-Specific Classification of ICU Sedation Levels From Heart Rate Variability*

Nagaraj

Biswal

Boyle

et al. 2017

Critical Care Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…This paper extends the preliminary work demonstrating the potential of HRV features to predict patient's sedation level [11] into an automated patient specific sedation level classification system. Several HRV features involving time, frequency and complexity domain were used in this work.…”

Section: Discussionmentioning

confidence: 86%

“…Based on our previous work, 14 features were extracted from the NN interval [11], shown in Table 2. All features were normalized using the box-cox transformation to have uniform mean and standard deviation before feeding it to the SVM classifier for classification.…”

Section: Preprocessing and Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Personalized Sedation Level Monitoring in ICU Patients Using Heart Rate Variability

Nagaraj

Biswal

Valdery

et al. 2016

2016 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

Aim: To develop an automated system to monitor sedation levels in intensive care unit patients using heart rate variability (HRV).Methods: We developed an automatic sedation level prediction system using HRV as input to a support vector machine learning algorithm. Our data consisted of electrocardiogram recordings from a heterogeneous group of 50 mechanically ventilated adults receiving sedatives in an ICU setting. The target variable was the Richmond agitation-sedation scale score, grouped into four levels: "comatose" (-5), "deeply sedated" (-4 to -3), "lightly sedated" (-2 to 0), and "agitated" (+1 to +4). As input we used 14 features derived from the normalized-RR (NN) interval. We used leave-one-subject-out cross-validated accuracy to measure system performance.Results: A patient-independent version of the proposed system discriminated between the 4 sedation levels with an overall accuracy of 52%. A patient-specific version, where the training data was supplemented with the patient's labeled HRV epochs from the preceding 24 hours, improved classification accuracy to 60%.Conclusions: Our preliminary results suggest that the HRV varies systematically with sedation levels and has potential to supplement current clinical sedation level assessment methods. With additional variables such as disease pathology, and pharmacological data, the proposed system could lead to a fully automated system for depth of sedation monitoring IntroductionAccurate administration and optimization of sedatives dosing is important in intensive care units (ICU) [1]. Patients are often sedated in the ICU to increase their level of comfortness, tolerate several procedures and facilitate mechanical ventilation and analgesia [2,3]. Therefore, it is critical to maintain patient's optimal sedation level since both over-and under sedation could lead to adverse patient outcomes including prolonged mechanical ventilation and ICU stay, increased risk of pneumonia and delirium [4,5]. Currently, subjective methods such as the Riker sedation agitation scale (SAS), Richmond agitation sedation scale (RASS), Ramsay sedation scale are used to score the level of sedation in ICUs. These scoring systems rely mainly on patient's response to external and noxious stimulation, which are subjective and are less discriminative during over-sedated state [6].Several electroencephalogram (EEG) based methods have been developed to assess patient's level of consciousness during general anesthesia based on spectral and entropy measures [7,8]. However, several studies have demonstrated their ineffectiveness in monitoring patients sedation level in the ICU environment [9,10]. Therefore, a more robust and reliable objective method is crucial to assess the depth of sedation in the ICU.Heart rate variability (HRV) is a popular noninvasive method that can provide information about the functioning of the autonomous nervous system using electrocardiogram (ECG). We recently investigated the potential of HRV for automatically predicting level of sedation using machine l...

show abstract

Using Deep Learning to Characterize Persistent Physiological Parameters in Patient Monitoring Systems

Jain,

Gupta,

Pandey

et al. 2024

Reshaping Intelligent Business and Industry

View full text Add to dashboard Cite

Automatic Classification of Sedation Levels in ICU Patients Using Heart Rate Variability

Cited by 30 publications

References 40 publications

Patient-Specific Classification of ICU Sedation Levels From Heart Rate Variability*

Patient-Specific Classification of ICU Sedation Levels From Heart Rate Variability*

Personalized Sedation Level Monitoring in ICU Patients Using Heart Rate Variability

Using Deep Learning to Characterize Persistent Physiological Parameters in Patient Monitoring Systems

Contact Info

Product

Resources

About