Deep reinforcement learning control of combined chemotherapy and anti-angiogenic drug delivery for cancerous tumor treatment

By virtue of the chronic and dangerous nature of cancer, researchers have explored various approaches to managing the abnormal cell growth associated with this disease using novel treatment methods. This study introduces a control system based on normalized advantage function reinforcement learning. It aims to boost the body's immune response against cancer cell proliferation. This control approach is applied to provide a combination of both chemotherapy and anti-angiogenic drugs for the first time without the need for complex, predefined mathematical models. It employs a model-free reinforcement learning technique that adaptively adjusts to individual patients to determine optimal drug administration with minimum injection rates. In this regard, a comprehensive and realistic simulation and training environment is employed, with the concentrations of normal cells, cancer cells, and endothelial cells, as well as the levels of chemotherapy and anti-angiogenic agents, as state variables. Furthermore, high levels of disturbances are considered in the simulation to investigate the robustness of the proposed method against probable uncertainties in the treatment process or patient parameters. A practical reward function has also been devised in alignment with medical objectives to ensure effective and safe treatment outcomes. The results demonstrate robustness and superior performance compared to the existing methods. Simulations show that the proposed approach is a dependable strategy for effectively reducing the concentration of cancer cells in the shortest duration using minimal doses of chemotherapy and anti-angiogenic drugs.

Design and implementation of an adaptive fuzzy sliding mode controller for drug delivery in treatment of vascular cancer tumours and its optimisation using genetic algorithm tool

In this paper, the side effects of drug therapy in the process of cancer treatment are reduced by designing two optimal non-linear controllers. The related gains of the designed controllers are optimised using genetic algorithm and simultaneously are adapted by employing the Fuzzy scheduling method. The cancer dynamic model is extracted with five differential equations, including normal cells, endothelial cells, cancer cells, and the amount of two chemotherapy and anti-angiogenic drugs left in the body as the engaged state variables, while double drug injection is considered as the corresponding controlling signals of the mentioned state space. This treatment aims to reduce the tumour cells by providing a timely schedule for drug dosage. In chemotherapy, not only the cancer cells are killed but also other healthy cells will be destroyed, so the rate of drug injection is highly significant. It is shown that the simultaneous application of chemotherapy and anti-angiogenic therapy is more efficient than single chemotherapy. Two different non-linear controllers are employed and their performances are compared. Simulation results and comparison studies show that not only adding the anti-angiogenic reduce the side effects of chemotherapy but also the proposed robust controller of sliding mode provides a faster and stronger treatment in the presence of patient parametric uncertainties in an optimal way. As a result of the proposed closed-loop drug treatment, the tumour cells rapidly decrease to zero, while the normal cells remain healthy simultaneously. Also, the injection rate of the chemotherapy drug is very low after a short time and converges to zero.

TUMOR VOLUME GROWTH CONTROL USING BIFURCATION APPROACH

A tumor growth system with immune response and chemotherapy is put in a nonlinear dynamical system whose solutions are relative to the initial data. This study presents a phase space analysis of the system. Here, the basin of equilibrium points attraction is determined for a particular class of systems and is subjected to input and state constraints in which all points in phase space would be close to the equilibrium points according to the region of attraction it starts. The addition of a drug term to the system can move the solution trajectory to the desirable basin of attraction. The proposed method gives static output feedback controllers that guarantee the convergence of the generic solutions. Although such a set-point regulation problem is too challenging for general nonlinear systems, the standard surface is found by the proposed approach, which is called separatrix for the controller. This criterion of separating border can perform well even when the mentioned system has limited change parameters. The control is set by separatrix in which the output feedback controller therapy can take all solutions to the healthy state through a constrained chemotherapy protocol. Moreover, this protocol can enable globalization of healthy equilibria.

Optimal control methods for drug delivery in cancerous tumour by anti-angiogenic therapy and chemotherapy

There are numerous mathematical models simulating the behaviour of cancer by considering variety of states in different treatment strategies, such as chemotherapy. Among the models, one is developed which is able to consider the blood vessel‐production (angiogenesis) in the vicinity of the tumour and the effect of anti‐angiogenic therapy. In the mentioned‐model, normal cells, cancer cells, endothelial cells, chemotherapy and anti‐angiogenic agents are taking into account as state variables, and the rate of injection of the last two are considered as control inputs. Since controlling the cancerous tumour growth is a challenging matter for patient's life, the time schedule design of drug injection is very significant. Two optimal control strategies, an open‐loop (calculus of variations) and a closed‐loop (state‐dependent Riccati equation), are applied on the system in order to find an optimal time scheduling for each drug injection. By defining a proper cost function, an optimal control signal is designed for each one. Both obtained control inputs have reasonable answers, and the system is controlled eventually, but by comparing them, it is concluded that both methods have their own benefits which will be discussed in details in the conclusion section.

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.

Pseudo-spectral method for controlling the drug dosage in cancer

A mixed chemotherapy-immunotherapy treatment protocol is developed for cancer treatment. Chemotherapy pushes the trajectory of the system towards the desired equilibrium point, and then immunotherapy alters the dynamics of the system by affecting the parameters of the system. A co-existing cancerous equilibrium point is considered as the desired equilibrium point instead of the tumour-free equilibrium. Chemotherapy protocol is derived using the pseudo-spectral (PS) controller due to its high convergence rate and simple implementation structure. Thus, one of the contributions of this study is simplifying the design procedure and reducing the controller computational load in comparison with Lyapunov-based controllers. In this method, an infinite-horizon optimal control problem is proposed for a non-linear cancer model. Then, the infinite-horizon optimal control of cancer is transformed into a non-linear programming problem. The efficient Legendre PS scheme is suggested to solve the proposed problem. Then, the dynamics of the system is modified by immunotherapy is another contribution. To restrict the upper limit of the chemo-drug dose based on the age of the patients, a Mamdani fuzzy system is designed, which is not present yet. Simulation results on four different dynamics cases how the efficiency of the proposed treatment strategy.

Sliding mode controller-observer pair for p53 pathway

A significant loss of p53 protein, an anti-tumour agent, is observed in early cancerous cells. Induction of small molecules based drug is by far the most prominent technique to revive and maintain wild-type p53 to the desired level. In this study, a sliding mode control (SMC) based robust non-linear technique is presented for the drug design of a control-oriented p53 model. The control input generated by conventional SMC is discontinuous; however, depending on the physical nature of the system, drug infusion needs to be continuous. Therefore, to obtain a smooth control signal, a dynamic SMC (DSMC) is designed. Moreover, the boundedness of the zero-dynamics is also proved. To make the model-based control design possible, the unknown states of the system are estimated using an equivalent control based, reduced-order sliding mode observer. The robustness of the proposed technique is assessed by introducing input disturbance and parametric uncertainty in the system. The effectiveness of the proposed control scheme is witnessed by performing in-silico trials, revealing that the sustained level of p53 can be achieved by controlled drug administration. Moreover, a comparative quantitative analysis shows that both controllers yield similar performance. However, DSMC consumes less control energy.