Tailored Pharmacokinetic model to predict drug trapping in long-term anesthesia

Fractal Kinetic Implementation in Population Pharmacokinetic Modeling

Compartment modeling is a widely accepted technique in the field of pharmacokinetic analysis. However, conventional compartment modeling is performed under a homogeneity assumption that is not a naturally occurring condition. Since the assumption lacks physiological considerations, the respective modeling approach has been questioned, as novel drugs are increasingly characterized by physiological or physical features. Alternative approaches have focused on fractal kinetics, but evaluations of their application are lacking. Thus, in this study, a simulation was performed to identify desirable fractal-kinetics applications in conventional modeling. Visible changes in the profiles were then investigated. Five cases of finalized population models were collected for implementation. For model diagnosis, the objective function value (OFV), Akaike's information criterion (AIC), and corrected Akaike's information criterion (AICc) were used as performance metrics, and the goodness of fit (GOF), visual predictive check (VPC), and normalized prediction distribution error (NPDE) were used as visual diagnostics. In most cases, model performance was enhanced by the fractal rate, as shown in a simulation study. The necessary parameters of the fractal rate in the model varied and were successfully estimated between 0 and 1. GOF, VPC, and NPDE diagnostics show that models with the fractal rate described the data well and were robust. In the simulation study, the fractal absorption process was, therefore, chosen for testing. In the estimation study, the rate application yielded improved performance and good prediction-observation agreement in early sampling points, and did not cause a large shift in the original estimation results. Thus, the fractal rate yielded explainable parameters by setting only the heterogeneity exponent, which reflects true physiological behavior well. This approach can be expected to provide useful insights in pharmacological decision making.

Feasibility of intelligent drug control in the maintenance phase of general anesthesia based on convolutional neural network

Background

The growth and aging process of the human population has accelerated the increase in surgical procedures. Yet, the demand for increasing operations can be hardly met since the training of anesthesiologists is usually a long-term process. Closed-loop artificial intelligence (AI) model provides the possibility to solve intelligent decision-making for anesthesia auxiliary control and, as such, has allowed breakthroughs in closed-loop control of clinical practices in intensive care units (ICUs). However, applying an open-loop artificial intelligence algorithm to build up personalized medication for anesthesia still needs to be further explored. Currently, anesthesiologists have selected doses of intravenously pumped anesthetic drugs mainly based on the blood pressure and bispectral index (BIS), which can express the depth of anesthesia. Unfortunately, BIS cannot be monitored at some medical centers or operational procedures and only be regulated by blood pressure. As a result, here we aim to inaugurally explore the feasibility of a basic intelligent control system applied to drug delivery in the maintenance phase of general anesthesia, based on a convolutional neural network model with open-loop design, according to AI learning of existing anesthesia protocols.

Methods

A convolutional neural network, combined with both sliding window sampling method and residual learning module, was utilized to establish an "AI anesthesiologist" model for intraoperative dosing of personalized anesthetic drugs (propofol and remifentanil). The fitting degree and difference in pumping dose decision, between the AI anesthesiologist and the clinical anesthesiologist, for these personalized anesthetic drugs were examined during the maintenance phase of anesthesia.

Results

The medication level established by the "AI anesthesiologist" was comparable to that obtained by the clinical anesthesiologist during the maintenance phase of anesthesia.

Conclusion

The application of an open-loop decision-making plan by convolutional neural network showed that intelligent anesthesia control is consistent with the actual anesthesia control, thus providing possibility for further evolution and optimization of auxiliary intelligent control of depth of anesthesia.