The combined effect of optimal control and swarm intelligence on optimization of cancer chemotherapy

Deep reinforcement learning-based control of chemo-drug dose in cancer treatment

BACKGROUND AND OBJECTIVE

Advancement in the treatment of cancer, as a leading cause of death worldwide, has promoted several research activities in various related fields. The development of effective treatment regimens with optimal drug dose administration using a mathematical modeling framework has received extensive research attention during the last decades. However, most of the control techniques presented for cancer chemotherapy are mainly model-based approaches. The available model-free techniques based on Reinforcement Learning (RL), commonly discretize the problem states and variables, which other than demanding expert supervision, cannot model the real-world conditions accurately. The more recent Deep Reinforcement Learning (DRL) methods, which enable modeling the problem in its original continuous space, are rarely applied in cancer chemotherapy.

METHODS

In this paper, we propose an effective and robust DRL-based, model-free method for the closed-loop control of cancer chemotherapy drug dosing. A nonlinear pharmacological cancer model is used for simulating the patient and capturing the cancer dynamics. In contrast to previous work, the state variables and control action are modeled in their original infinite spaces to avoid expert-guided discretization and provide a more realistic solution. The DRL network is trained to automatically adjust the drug dose based on the monitored states of the patient. The proposed method provides an adaptive control technique to respond to the special conditions and diagnosis measurements of different categories of patients.

RESULTS AND CONCLUSIONS

The performance of the proposed DRL-based controller is evaluated by numerical analysis of different diverse simulated patients. Comparison to the state-of-the-art RL-based method, which uses discretized state and action spaces, shows the superiority of the approach in the process and duration of cancer chemotherapy treatment. In the majority of the studied cases, the proposed model decreases the medication period and the total amount of administrated drug, while increasing the rate of reduction in tumor cells.

Optimizing chemotherapy treatment outcomes using metaheuristic optimization algorithms: A case study

BACKGROUND

This study explores the dynamics of a mathematical model, utilizing ordinary differential equations (ODE), to depict the interplay between cancer cells and effector cells under chemotherapy. The stability of the equilibrium points in the model is analysed using the Jacobian matrix and eigenvalues. Additionally, bifurcation analysis is conducted to determine the optimal values for the control parameters.

OBJECTIVE

To evaluate the performance of the model and control strategies, benchmarking simulations are performed using the PlatEMO platform.

METHODS

The Pure Multi-objective Optimal Control Problem (PMOCP) and the Hybrid Multi-objective Optimal Control Problem (HMOCP) are two different forms of optimal control problems that are solved using revolutionary metaheuristic optimisation algorithms. The utilization of the Hypervolume (HV) performance indicator allows for the comparison of various metaheuristic optimization algorithms in their efficacy for solving the PMOCP and HMOCP.

RESULTS

Results indicate that the MOPSO algorithm excels in solving the HMOCP, with M-MOPSO outperforming for PMOCP in HV analysis.

CONCLUSION

Despite not directly addressing immediate clinical concerns, these findings indicates that the stability shifts at critical thresholds may impact treatment efficacy.

Uncovering personal circadian responses to light through particle swarm optimization

BACKGROUND AND OBJECTIVES

Kronauer's oscillator model of the human central pacemaker is one of the most commonly used approaches to study the human circadian response to light. Two sources of error when applying it to a personal light exposure have been identified: (1) as a populational model, it does not consider inter-individual variability, and (2) the initial conditions needed to integrate the model are usually unknown, and thus subjectively estimated. In this work, we evaluate the ability of particle swarm optimization (PSO) algorithms to simultaneously uncover the optimal initial conditions and individual parameters of a pre-defined Kronauer's oscillator model.

METHODS

A Canonical PSO, a Dynamic Multi-Swarm PSO and a novel modification of the latter, namely Hierarchical Dynamic Multi-Swarm PSO, are evaluated. Two different target models (under a regular and an irregular schedule) are defined, and the same realistic light profile is fed to them. Based on their output, a fitness function is proposed, which is minimized by the algorithms to find the optimum set of parameters and initial conditions of the model.

RESULTS

We demonstrate that Dynamic Multi-Swarm and Hierarchical Dynamic Multi-Swarm algorithms can accurately uncover personal circadian parameters under both regular and irregular schedules, but as expected, optimization is easier under a regular schedule. Circadian parameters play the most important role in the optimization process and should be prioritized over initial conditions, although assessment of the impact of misestimating the latter is recommended. The log-log linear relationship between mean absolute error and computational cost shows that the number of particles to use is at the discretion of the user.

CONCLUSIONS

The robustness and low errors achieved by the algorithms support their further testing, validation and systematic application to empirical data under a regular or irregular schedule. Uncovering personal circadian parameters can improve the assessment of the circadian status of a person and the applicability of personalized light therapies, as well as help to discover other factors that may lie behind the interindividual variability in the circadian response to light.

Optimal control design for drug delivery of immunotherapy in chemoimmunotherapy treatment

BACKGROUND AND OBJECTIVE

There are various approaches to control a mathematical dynamic of cancer, each of which is suitable for a special goal. Optimal control is considered as an applicable method to calculate the minimum necessary drug delivery in such systems.

METHODS

In this paper, a mathematical dynamic of cancer is proposed considering tumor cells, natural killer cells, CD8+T cells, circulating lymphocytes, IL-2 cytokine and Regulatory T cells as the system states, and chemotherapy, IL-2 and activated CD8+T cells injection rate as the control signals. After verifying the proposed mathematical model, the importance of the drug delivery timing and the effect of cancer cells initial condition are discussed. Afterwards, an optimal control is designed by defining a proper cost function with the goal of minimizing the number of tumor cells, and two immunotherapy drug amounts during treatment CONCLUSIONS: Results show that inappropriate injection of immunotherapy time schedule and the number of initial conditions of cancer cells might result in chemoimmunotherapy failure and auxiliary treatment must be prescribed to decrease tumor size before any treatment takes place. The obtained optimal control signals show that with lower amount of drug delivery and a suitable drug injection time schedule, tumor cells can be eliminated while a fixed immunotherapy time schedule protocol fails with larger amount of drug injection. This conclusion can be utilized with the aim of personalizing drug delivery and designing more accurate clinical trials based on the improved model simulations in order to save cost and time.

Cancerous Tumor Controlled Treatment Using Search Heuristic (GA)-Based Sliding Mode and Synergetic Controller

Simple Summary

Cancer is basically a tough condition on a patient’s body where cell grows uncontrollably. Normal cells are affected, which destroys the health of the patient. The main problem in cancer is spreading from one part to another. Therefore, the mathematical modeling of cancerous tumors integrates to check overall stability. A novel approach is introduced such as Bernstein polynomial with combination of genetic algorithm, sliding mode controller, and synergetic control. The proposed solution has easily eliminated cancerous cells within five days using synergetic control. In addition, five cases are incorporated to evaluate error function. In addition, a brief comparative study is added to contrast the simulation results with theoretical modeling.

Abstract

Cancerous tumor cells divide uncontrollably, which results in either tumor or harm to the immune system of the body. Due to the destructive effects of chemotherapy, optimal medications are needed. Therefore, possible treatment methods should be controlled to maintain the constant/continuous dose for affecting the spreading of cancerous tumor cells. Rapid growth of cells is classified into primary and secondary types. In giving a proper response, the immune system plays an important role. This is considered a natural process while fighting against tumors. In recent days, achieving a better method to treat tumors is the prime focus of researchers. Mathematical modeling of tumors uses combined immune, vaccine, and chemotherapies to check performance stability. In this research paper, mathematical modeling is utilized with reference to cancerous tumor growth, the immune system, and normal cells, which are directly affected by the process of chemotherapy. This paper presents novel techniques, which include Bernstein polynomial (BSP) with genetic algorithm (GA), sliding mode controller (SMC), and synergetic control (SC), for giving a possible solution to the cancerous tumor cells (CCs) model. Through GA, random population is generated to evaluate fitness. SMC is used for the continuous exponential dose of chemotherapy to reduce CCs in about forty-five days. In addition, error function consists of five cases that include normal cells (NCs), immune cells (ICs), CCs, and chemotherapy. Furthermore, the drug control process is explained in all the cases. In simulation results, utilizing SC has completely eliminated CCs in nearly five days. The proposed approach reduces CCs as early as possible.

Lanthanide (Eu3+/Tb3+)-Loaded γ-Cyclodextrin Nano-Aggregates for Smart Sensing of the Anticancer Drug Irinotecan

The clinical use of anticancer drugs necessitates new technologies for their safe, sensitive, and selective detection. In this article, lanthanide (Eu³⁺ and Tb³⁺)-loaded γ-cyclodextrin nano-aggregates (ECA and TCA) are reported, which sensitively detects the anticancer drug irinotecan by fluorescence intensity changes. Fluorescent lanthanide (Eu³⁺ and Tb³⁺) complexes exhibit high fluorescence intensity, narrow and distinct emission bands, long fluorescence lifetime, and insensitivity to photobleaching. However, these lanthanide (Eu³⁺ and Tb³⁺) complexes are essentially hydrophobic, toxic, and non-biocompatible. Lanthanide (Eu³⁺ and Tb³⁺) complexes were loaded into naturally hydrophilic γ-cyclodextrin to form fluorescent nano-aggregates. The biological nontoxicity and cytocompatibility of ECA and TCA fluorescent nanoparticles were demonstrated by cytotoxicity experiments. The ECA and TCA fluorescence nanosensors can detect irinotecan selectively and sensitively through the change of fluorescence intensity, with detection limits of 6.80 μM and 2.89 μM, respectively. ECA can safely detect irinotecan in the cellular environment, while TCA can detect irinotecan intracellularly and is suitable for cell labeling.

Intelligent automated drug administration and therapy: future of healthcare

In the twenty-first century, the collaboration of control engineering and the healthcare sector has matured to some extent; however, the future will have promising opportunities, vast applications, and some challenges. Due to advancements in processing speed, the closed-loop administration of drugs has gained popularity for critically ill patients in intensive care units and routine life such as personalized drug delivery or implantable therapeutic devices. For developing a closed-loop drug delivery system, the control system works with a group of technologies like sensors, micromachining, wireless technologies, and pharmaceuticals. Recently, the integration of artificial intelligence techniques such as fuzzy logic, neural network, and reinforcement learning with the closed-loop drug delivery systems has brought their applications closer to fully intelligent automatic healthcare systems. This review's main objectives are to discuss the current developments, possibilities, and future visions in closed-loop drug delivery systems, for providing treatment to patients suffering from chronic diseases. It summarizes the present insight of closed-loop drug delivery/therapy for diabetes, gastrointestinal tract disease, cancer, anesthesia administration, cardiac ailments, and neurological disorders, from a perspective to show the research in the area of control theory.