An automatic deep reinforcement learning bolus calculator for automated insulin delivery systems.

In hybrid automatic insulin delivery (HAID) systems, meal disturbance is compensated by feedforward control, which requires the announcement of the meal by the patient with type 1 diabetes (DM1) to achieve the desired glycemic control performance. The calculation of insulin bolus in the HAID system is based on the amount of carbohydrates (CHO) in the meal and patient-specific parameters, i.e. carbohydrate-to-insulin ratio (CR) and insulin sensitivity-related correction factor (CF). The estimation of CHO in a meal is prone to errors and is burdensome for patients. This study proposes a fully automatic insulin delivery (FAID) system that eliminates patient intervention by compensating for unannounced meals. This study exploits the deep reinforcement learning (DRL) algorithm to calculate insulin bolus for unannounced meals without utilizing the information on CHO content. The DRL bolus calculator is integrated with a closed-loop controller and a meal detector (both previously developed by our group) to implement the FAID system. An adult cohort of 68 virtual patients based on the modified UVa/Padova simulator was used for in-silico trials. The percentage of the overall duration spent in the target range of 70-180 mg/dL was 71.2 % and 76.2 % , < 70 mg/dL was 0.9 % and 0.1 % , and > 180 mg/dL was 26.7 % and 21.1 % , respectively, for the FAID system and HAID system utilizing a standard bolus calculator (SBC) including CHO misestimation. The proposed algorithm can be exploited to realize FAID systems in the future.

Bolus Insulin calculation without meal information. A reinforcement learning approach.

In continuous subcutaneous insulin infusion and multiple daily injections, insulin boluses are usually calculated based on patient-specific parameters, such as carbohydrates-to-insulin ratio (CR), insulin sensitivity-based correction factor (CF), and the estimation of the carbohydrates (CHO) to be ingested. This study aimed to calculate insulin boluses without CR, CF, and CHO content, thereby eliminating the errors caused by misestimating CHO and alleviating the management burden on the patient. A Q-learning-based reinforcement learning algorithm (RL) was developed to optimise bolus insulin doses for in-silico type 1 diabetic patients. A realistic virtual cohort of 68 patients with type 1 diabetes that was previously developed by our research group, was considered for the in-silico trials. The results were compared to those of the standard bolus calculator (SBC) with and without CHO misestimation using open-loop basal insulin therapy. The percentage of the overall duration spent in the target range of 70-180 mg/dL was 73.4% and 72.37%, <70 mg/dL was 1.96 and 0.70%, and >180 mg/dL was 23.40 and 24.63%, respectively, for RL and SBC without CHO misestimation. The results revealed that RL outperformed SBC in the presence of CHO misestimation, and despite not knowing the CHO content of meals, the performance of RL was similar to that of SBC in perfect conditions. This algorithm can be incorporated into artificial pancreas and automatic insulin delivery systems in the future.

Hypnosis regulation in propofol anaesthesia employing super-twisting sliding mode control to compensate variability dynamics.

Regulation of hypnosis level on bi-spectral index monitor (BIS) during a surgical procedure in propofol anaesthesia administration is a challenging task for an anaesthesiologist in multi-tasking environment of the operation theater. Automation in anaesthesia has the potential to solve issues arising from manual administration. Automation in anaesthesia is based on developing the three-compartmental model including pharmacokinetics and pharmacodynamic of the silico patients. This study focuses on regulation of the hypnosis level in the presence of surgical stimulus including skin incision, surgical diathermy and laryngoscopy as well as inter-patient variability by designing super-twisting sliding mode control (STSMC). The depth of the hypnosis level is maintained to 50 on the BIS level in the maintenance phase after improving the induction phase to 60 s using the conventional sliding mode control and 30 s with STSMC. The proposed scheme also compensates the inter-patient variability dynamics including height, age and weight of the different silico patients. Moreover, the surgical stimuli direct the hypnosis level towards the state of consciousness and stimulate the controller to provide continuous drug infusion during the interval 80-90 s. Simulation results witness that the oscillatory behaviour is observed in drug infusion to ensure the moderate level of hypnosis (40-60) for general surgery.