A comparison of patients’ heart rate variability and blood flow variability during surgery based on the Hilbert–Huang Transform

Fan, Shou-Zen; Qin, Wei; Shi, Pei-Fung; Chen, Yu-Jen; Liu, Quan; Shieh, Jiann-Shing

doi:10.1016/j.bspc.2011.11.006

Cited by 11 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further efforts need to be taken in order for the method described herein to be effective enough for real-world deployment. Long-term anesthetic infusion often results in drug habituation, and hence, a patient's pharmacologic response may change over the course of their treatment ( 44 ); future approaches may need to account for the effects of habituation. Additionally, future work in this domain would benefit by accounting for other factors that confound sedation in the ICU environment including adjunct therapies such as clonidine, ketamine, volatile anesthetics, and neuromuscular blockers.…”

Section: Discussionmentioning

confidence: 99%

“…Propofol administration lowers sympathetic tone and causes vasodilation, which may decrease preload and cardiac output and consequently lower the MAP and other interrelated hemodynamic parameters. Therefore, ensuring a desired range of MAP is an essential consideration of propofol infusion ( 7 , 44 ). Moreover, efforts should be made to minimize the sedative dosage ( 17 ).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Patient-Specific Sedation Management via Deep Reinforcement Learning

Eghbali

Alhanai

Ghassemi

2021

Front. Digit. Health

View full text Add to dashboard Cite

Introduction: Developing reliable medication dosing guidelines is challenging because individual dose–response relationships are mitigated by both static (e. g., demographic) and dynamic factors (e.g., kidney function). In recent years, several data-driven medication dosing models have been proposed for sedatives, but these approaches have been limited in their ability to assess interindividual differences and compute individualized doses.Objective: The primary objective of this study is to develop an individualized framework for sedative–hypnotics dosing.Method: Using publicly available data (1,757 patients) from the MIMIC IV intensive care unit database, we developed a sedation management agent using deep reinforcement learning. More specifically, we modeled the sedative dosing problem as a Markov Decision Process and developed an RL agent based on a deep deterministic policy gradient approach with a prioritized experience replay buffer to find the optimal policy. We assessed our method's ability to jointly learn an optimal personalized policy for propofol and fentanyl, which are among commonly prescribed sedative–hypnotics for intensive care unit sedation. We compared our model's medication performance against the recorded behavior of clinicians on unseen data.Results: Experimental results demonstrate that our proposed model would assist clinicians in making the right decision based on patients' evolving clinical phenotype. The RL agent was 8% better at managing sedation and 26% better at managing mean arterial compared to the clinicians' policy; a two-sample t-test validated that these performance improvements were statistically significant (p < 0.05).Conclusion: The results validate that our model had better performance in maintaining control variables within their target range, thereby jointly maintaining patients' health conditions and managing their sedation.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Patient-Specific Sedation Management via Deep Reinforcement Learning

Eghbali

Alhanai

Ghassemi

2021

Front. Digit. Health

View full text Add to dashboard Cite

show abstract

“…Thus, the brain stem function that is related to the deep anesthesia should be evaluated to improve the DOA monitoring without the EEG [25]. The most common method of determining the activity of the brain stem is to quantify the spectrum of heart rate variability (HRV), which reflects the activity of sympathetic and parasympathetic nervous systems that are controlled by the brain stem [26]. Therefore, ECG, SpO 2 and respiration of patients should be integrated into analysis and measurement of DOA.…”

Section: Offline Analysismentioning

confidence: 99%

A critical care monitoring system for depth of anaesthesia analysis based on entropy analysis and physiological information database

Wei

Fan

et al. 2014

Australas Phys Eng Sci Med

Self Cite

View full text Add to dashboard Cite

Diagnosis of depth of anaesthesia (DoA) plays an important role in treatment and drug usage in the operating theatre and intensive care unit. With the flourishing development of analysis methods and monitoring devices for DoA, a small amount of physiological data had been stored and shared for further researches. In this paper, a critical care monitoring (CCM) system for DoA monitoring and analysis was designed and developed, which includes two main components: a physiologic information database (PID) and a DoA analysis subsystem. The PID, including biologic data and clinical information was constructed through a browser and server model so as to provide a safe and open platform for storage, sharing and further study of clinical anaesthesia information. In the analysis of DoA, according to our previous studies on approximate entropy, sample entropy (SampEn) and multi-scale entropy (MSE), the SampEn and MSE were integrated into the subsystem for indicating the state of patients underwent surgeries in real time because of their stability. Therefore, this CCM system not only supplies the original biological data and information collected from the operating room, but also shares our studies for improvement and innovation in the research of DoA.

show abstract

“…Propofol administration lowers sympathetic tone and causes vasodilation, which can decrease preload and cardiac output and consequently lower the mean arterial pressure and other interrelated hemodynamic parameters. This can lead to blood pressure instability, overdose, and cardiovascular collapse [20]. Therefore, ensuring a desired range for MAP as one of the important hemodynamic parameters is vital during propofol infusion [21,22].…”

Section: Introductionmentioning

confidence: 99%