Reinforcement learning-based control of drug dosing for cancer chemotherapy treatment

Padmanabhan, Regina; Meskin, Nader; Haddad, Wassim M.

doi:10.1016/j.mbs.2017.08.004

Cited by 83 publications

(44 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such models are promising for the development of mathematical models of cancer mechanisms and treatment (Figure 1). Another advantage of representing cancer mechanisms in terms of mathematical models is that it enables easy design and implementation of algorithms for optimizing drug dose and effective treatment schedules [35,186]. Even though many such optimization results are reported for various cancers [31,158], only a few studies are reported specifically for BC [36].…”

Section: Mathematical Models Used For Breast Cancer Managementmentioning

confidence: 99%

See 1 more Smart Citation

Crosstalk between HER2 and PD-1/PD-L1 in Breast Cancer: From Clinical Applications to Mathematical Models

Padmanabhan

Kheraldine

Meskin

et al. 2020

Cancers

Self Cite

View full text Add to dashboard Cite

Breast cancer is one of the major causes of mortality in women worldwide. The most aggressive breast cancer subtypes are human epidermal growth factor receptor-positive (HER2+) and triple-negative breast cancers. Therapies targeting HER2 receptors have significantly improved HER2+ breast cancer patient outcomes. However, several recent studies have pointed out the deficiency of existing treatment protocols in combatting disease relapse and improving response rates to treatment. Overriding the inherent actions of the immune system to detect and annihilate cancer via the immune checkpoint pathways is one of the important hallmarks of cancer. Thus, restoration of these pathways by various means of immunomodulation has shown beneficial effects in the management of various types of cancers, including breast. We herein review the recent progress in the management of HER2+ breast cancer via HER2-targeted therapies, and its association with the programmed death receptor-1 (PD-1)/programmed death ligand-1 (PD-L1) axis. In order to link research in the areas of medicine and mathematics and point out specific opportunities for providing efficient theoretical analysis related to HER2+ breast cancer management, we also review mathematical models pertaining to the dynamics of HER2+ breast cancer and immune checkpoint inhibitors.

show abstract

Section: Mathematical Models Used For Breast Cancer Managementmentioning

confidence: 99%

“…Even though many such optimization results are reported for various cancers [31,158], only a few studies are reported specifically for BC [36]. Even though many such optimization results are reported for various cancers [31,35,158,186], only a few studies are reported specifically for BC [36].…”

Section: Mathematical Models Used For Breast Cancer Managementmentioning

confidence: 99%

Crosstalk between HER2 and PD-1/PD-L1 in Breast Cancer: From Clinical Applications to Mathematical Models

Padmanabhan

Kheraldine

Meskin

et al. 2020

Cancers

Self Cite

View full text Add to dashboard Cite

show abstract

“…ReLe-based approaches and their combination with DL models will be increasingly applied to precision oncology. Recent examples include: a deep reinforcement learning algorithm for the early detection of pulmonary nodes in computed tomography images; 48 a ReLe model for controlling chemotherapy dosing in cancer patients; 49 and a deep reinforcement learning for the estimation and adaptation of radiation protocols for lung cancer patients. 50 Although these and other examples reviewed in detail by Mahmud et al 51 provide evidence of the potential of ReLe in precision oncology, deeper investigations involving different and larger patient cohorts will be needed.…”

Section: Challenge D—alternative Learning Approaches: Hybrid Models Amentioning

confidence: 99%

Artificial intelligence for precision oncology: beyond patient stratification

Azuaje

2019

npj Precision Onc

116

View full text Add to dashboard Cite

The data-driven identification of disease states and treatment options is a crucial challenge for precision oncology. Artificial intelligence (AI) offers unique opportunities for enhancing such predictive capabilities in the lab and the clinic. AI, including its best-known branch of research, machine learning, has significant potential to enable precision oncology well beyond relatively well-known pattern recognition applications, such as the supervised classification of single-source omics or imaging datasets. This perspective highlights key advances and challenges in that direction. Furthermore, it argues that AI’s scope and depth of research need to be expanded to achieve ground-breaking progress in precision oncology.

show abstract

“…Moreover, four optimal control problems (OCPs) for chemotherapy schedule are investigated by Engelhart et al, 11 and different choices of the objective functions in the framework of chemotherapy are compared. The combination of chemotherapy and radiotherapy to eradicate the cancer with metastasis is discussed by Ghaffari et al 12 An adaptive robust control is proposed to adjust the drug dosages with an extended Kalman filter observer by Rokhforoz et al 13 An optimal control strategy based on a linear time-varying approximation technique is proposed by Itik et al 14 On the other hand, an OCP with a free final time is solved for tumor-immune interactions with the aim of minimizing not only the tumor population but also the treatment period by Alkama et al 15 A model-free method for chemotherapy based on reinforcement learning is proposed by Padmanabhan et al 16 using the closed-loop control. In particular, they developed an optimal controller using Q-learning algorithm for cancer chemotherapy treatment.…”

Section: Introductionmentioning

confidence: 99%

Optimal chemotherapy and immunotherapy schedules for a cancer‐obesity model with Caputo time fractional derivative

Yıldız

Arshad

Băleanu

2018

Math Methods in App Sciences

View full text Add to dashboard Cite

Communicated by: M. Kirane MSC Classification: 49K99; 34A08; 37N25; 92B05; 65L07This work presents a new mathematical model to depict the effect of obesity on cancerous tumor growth when chemotherapy and immunotherapy have been administered. We consider an optimal control problem to destroy the tumor population and minimize the drug dose over a finite time interval. The constraint is a model including tumor cells, immune cells, fat cells, and chemotherapeutic and immunotherapeutic drug concentrations with the Caputo time fractional derivative. We investigate the existence and stability of the equilibrium points, namely, tumor-free equilibrium and coexisting equilibrium, analytically. We discretize the cancer-obesity model using the L1 method. Simulation results of the proposed model are presented to compare three different treatment strategies: chemotherapy, immunotherapy, and their combination. In addition, we investigate the effect of the differentiation order and the value of the decay rate of the amount of chemotherapeutic drug to the value of the cost functional. We find out the optimal treatment schedule in case of chemotherapy and immunotherapy. KEYWORDS chemotherapy, fractional differential equations, immunotherapy, optimal control, stability 9390

show abstract

Reinforcement learning-based control of drug dosing for cancer chemotherapy treatment

Cited by 83 publications

References 19 publications

Crosstalk between HER2 and PD-1/PD-L1 in Breast Cancer: From Clinical Applications to Mathematical Models

Crosstalk between HER2 and PD-1/PD-L1 in Breast Cancer: From Clinical Applications to Mathematical Models

Artificial intelligence for precision oncology: beyond patient stratification

Optimal chemotherapy and immunotherapy schedules for a cancer‐obesity model with Caputo time fractional derivative

Contact Info

Product

Resources

About