Reinforcement learning strategies in cancer chemotherapy treatments: A review.

BACKGROUND AND OBJECTIVE: Cancer is one of the major causes of death worldwide and chemotherapies are the most significant anti-cancer therapy, in spite of the emerging precision cancer medicines in the last 2 decades. The growing interest in developing the effective chemotherapy regimen with optimal drug dosing schedule to benefit the clinical cancer patients has spawned innovative solutions involving mathematical modeling since the chemotherapy regimens are administered cyclically until the futility or the occurrence of intolerable adverse events. Thus, in this present work, we reviewed the emerging trends involved in forming a computational solution from the aspect of reinforcement learning. METHODS: Initially, this survey in-depth focused on the details of the dynamic treatment regimens from a broad perspective and then narrowed down to inspirations from reinforcement learning that were advantageous to chemotherapy dosing, including both offline reinforcement learning and supervised reinforcement learning. RESULTS: The insights established in the chemotherapy-planning problem associated with the Reinforcement Learning (RL) has been discussed in this study. It showed that the researchers were able to widen their perspectives in comprehending the theoretical basis, dynamic treatment regimens (DTR), use of the adaptive control on DTR, and the associated RL techniques. CONCLUSIONS: This study reviewed the recent researches relevant to the topic, and highlighted the challenges, open questions, possible solutions, and future steps in inventing a realistic solution for the aforementioned problem.

Supervised Optimal Chemotherapy Regimen Based on Offline Reinforcement Learning.

In recent years, reinforcement learning (RL) has achieved a remarkable achievement and it has attracted researchers' attention in modeling real-life scenarios by expanding its research beyond conventional complex games. Prediction of optimal treatment regimens from observational real clinical data is being popularized, and more advanced versions of RL algorithms are being implemented in the literature. However, RL-generated medications still need careful supervision of expertise parties or doctors in healthcare. Hence, in this paper, a Supervised Optimal Chemotherapy Regimen (SOCR) approach to investigate optimal chemotherapy-dosing schedule for cancer patients was presented by using Offline Reinforcement Learning. The optimal policy suggested by the RL approach was supervised by incorporating previous treatment decisions of oncologists, which could add clinical expertise knowledge on algorithmic results. Presented SOCR approach followed a model-based architecture using conservative Q-Learning (CQL) algorithm. The developed model was tested using a manually constructed database of forty Stage-IV colon cancer patients, receiving line-1 chemotherapy treatments, who were clinically classified as 'Bevacizumab based patient' and 'Cetuximab based patient'. Experimental results revealed that the supervision from the oncologists has considered the effect to stabilize chemotherapy regimen and it was suggested that the proposed framework could be successfully used as a supportive model for oncologists in deciding their treatment decisions.