Event-based MPC for propofol administration in anesthesia

Online and personalised control of the Depth of hypnosis during induction using fractional order PID

INTRODUCTION

The integration of information technology and control engineering has significantly increased in clinical practice research, especially in the management of drug dosing for general anaesthesia.

OBJECTIVE

The main focus of the research is to achieve a personalised control of the Depth of Hypnosis based on a novel approach. The primary objective is to regulate the Bispectral Index by administering Propofol during the hypnotic phase of anaesthesia.

METHODS

A fractional order time delay model is proposed to replace the conventional PK-PD model. This model is estimated online during the induction phase. A fractional order Proportional-Integral-Derivative (PID) controller is then individually tuned for each patient.

RESULTS

The closed loop simulation results demonstrate that the proposed controllers effectively minimise undershoot and achieve a short time to reach the desired time-to-target for the majority of the patients. The analysis indicates that the proposed controller is capable of maintaining the BIS signal within a safe range. Comparative analyses with similar research are provided to effectively contextualise this study within the existing literature. Disturbance rejection tests during the maintenance phase are performed to demonstrate the effectiveness of personalised control.

CONCLUSION

The online adaptation that this research brings, compared to the previous attempts, allows for significantly improved results for the hypnosis phase.

Feature selection integrating Shapley values and mutual information in reinforcement learning: An application in the prediction of post-operative outcomes in patients with end-stage renal disease

BACKGROUND

In predicting post-operative outcomes for patients with end-stage renal disease, our study faced challenges related to class imbalance and a high-dimensional feature space. Therefore, with a focus on overcoming class imbalance and improving interpretability, we propose a novel feature selection approach using multi-agent reinforcement learning.

METHODS

We proposed a multi-agent feature selection model based on a comprehensive reward function that combines classification model performance, Shapley additive explanations values, and the mutual information. The definition of rewards in reinforcement learning is crucial for model convergence and performance improvement. Initially, we set a deterministic reward based on the mutual information between variables and the target class, selecting variables that are highly dependent on the class, thus accelerating convergence. We then prioritized variables that influence the minority class on a sample basis and introduced a dynamic reward distribution strategy using Shapley additive explanations values to improve interpretability and solve the class imbalance problem.

RESULTS

Involving the integration of electronic medical records, anesthesia records, operating room vital signs, and pre-operative anesthesia evaluations, our approach effectively mitigated class imbalance and demonstrated superior performance in ablation analysis. Our model achieved a 16% increase in the minority class F1 score and an 8.2% increase in the overall F1 score compared to the baseline model without feature selection.

CONCLUSION

This study contributes important research findings that show that the multi-agent-based feature selection method can be a promising approach for solving the class imbalance problem.

Development, Validation, and Comparison of a Novel Nociception/Anti-Nociception Monitor against Two Commercial Monitors in General Anesthesia

In this paper, we present the development and the validation of a novel index of nociception/anti-nociception (N/AN) based on skin impedance measurement in time and frequency domain with our prototype AnspecPro device. The primary objective of the study was to compare the Anspec-PRO device with two other commercial devices (Medasense, Medstorm). This comparison was designed to be conducted under the same conditions for the three devices. This was carried out during total intravenous anesthesia (TIVA) by investigating its outcomes related to noxious stimulus. In a carefully designed clinical protocol during general anesthesia from induction until emergence, we extract data for estimating individualized causal dynamic models between drug infusion and their monitored effect variables. Specifically, these are Propofol hypnotic drug to Bispectral index of hypnosis level and Remifentanil opioid drug to each of the three aforementioned devices. When compared, statistical analysis of the regions before and during the standardized stimulus shows consistent difference between regions for all devices and for all indices. These results suggest that the proposed methodology for data extraction and processing for AnspecPro delivers the same information as the two commercial devices.