A New Fuzzy Reinforcement Learning Method for Effective Chemotherapy
A key challenge for drug dosing schedules is the ability to learn an optimal control policy even when there is a paucity of accurate information about the systems. Artificial intelligence has great potential for shaping a smart control policy for the dosage of drugs for any treatment. Motivated by t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/2/477 |
| _version_ | 1797438934460923904 |
|---|---|
| author | Fawaz E. Alsaadi Amirreza Yasami Christos Volos Stelios Bekiros Hadi Jahanshahi |
| author_facet | Fawaz E. Alsaadi Amirreza Yasami Christos Volos Stelios Bekiros Hadi Jahanshahi |
| author_sort | Fawaz E. Alsaadi |
| collection | DOAJ |
| description | A key challenge for drug dosing schedules is the ability to learn an optimal control policy even when there is a paucity of accurate information about the systems. Artificial intelligence has great potential for shaping a smart control policy for the dosage of drugs for any treatment. Motivated by this issue, in the present research paper a Caputo–Fabrizio fractional-order model of cancer chemotherapy treatment was elaborated and analyzed. A fix-point theorem and an iterative method were implemented to prove the existence and uniqueness of the solutions of the proposed model. Afterward, in order to control cancer through chemotherapy treatment, a fuzzy-reinforcement learning-based control method that uses the State-Action-Reward-State-Action (SARSA) algorithm was proposed. Finally, so as to assess the performance of the proposed control method, the simulations were conducted for young and elderly patients and for ten simulated patients with different parameters. Then, the results of the proposed control method were compared with Watkins’s Q-learning control method for cancer chemotherapy drug dosing. The results of the simulations demonstrate the superiority of the proposed control method in terms of mean squared error, mean variance of the error, and the mean squared of the control action—in other words, in terms of the eradication of tumor cells, keeping normal cells, and the amount of usage of the drug during chemotherapy treatment. |
| first_indexed | 2024-03-09T11:45:28Z |
| format | Article |
| id | doaj.art-634441a54138444aa84e3274668ba61a |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T11:45:28Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-634441a54138444aa84e3274668ba61a2023-11-30T23:22:45ZengMDPI AGMathematics2227-73902023-01-0111247710.3390/math11020477A New Fuzzy Reinforcement Learning Method for Effective ChemotherapyFawaz E. Alsaadi0Amirreza Yasami1Christos Volos2Stelios Bekiros3Hadi Jahanshahi4Communication Systems and Networks Research Group, Department of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi ArabiaDepartment of Mechanical Engineering, University of Alberta, Edmonton, AB T6G 1H9, CanadaNonlinear Laboratory of Nonlinear Systems, Circuits Complexity (LaNSCom), Department of Physics, Aristotle University of Thessaloniki, 54124 Thessaloniki, GreeceFEMA, University of Malta, MSD 2080 Msida, MaltaDepartment of Mechanical Engineering, University of Manitoba, Winnipeg, MB R3T 5V6, CanadaA key challenge for drug dosing schedules is the ability to learn an optimal control policy even when there is a paucity of accurate information about the systems. Artificial intelligence has great potential for shaping a smart control policy for the dosage of drugs for any treatment. Motivated by this issue, in the present research paper a Caputo–Fabrizio fractional-order model of cancer chemotherapy treatment was elaborated and analyzed. A fix-point theorem and an iterative method were implemented to prove the existence and uniqueness of the solutions of the proposed model. Afterward, in order to control cancer through chemotherapy treatment, a fuzzy-reinforcement learning-based control method that uses the State-Action-Reward-State-Action (SARSA) algorithm was proposed. Finally, so as to assess the performance of the proposed control method, the simulations were conducted for young and elderly patients and for ten simulated patients with different parameters. Then, the results of the proposed control method were compared with Watkins’s Q-learning control method for cancer chemotherapy drug dosing. The results of the simulations demonstrate the superiority of the proposed control method in terms of mean squared error, mean variance of the error, and the mean squared of the control action—in other words, in terms of the eradication of tumor cells, keeping normal cells, and the amount of usage of the drug during chemotherapy treatment.https://www.mdpi.com/2227-7390/11/2/477Caputo-Fabrizio derivativecancer chemotherapy drug dosingfuzzy-reinforcement learningoptimal controlSARSA algorithmartificial intelligence |
| spellingShingle | Fawaz E. Alsaadi Amirreza Yasami Christos Volos Stelios Bekiros Hadi Jahanshahi A New Fuzzy Reinforcement Learning Method for Effective Chemotherapy Mathematics Caputo-Fabrizio derivative cancer chemotherapy drug dosing fuzzy-reinforcement learning optimal control SARSA algorithm artificial intelligence |
| title | A New Fuzzy Reinforcement Learning Method for Effective Chemotherapy |
| title_full | A New Fuzzy Reinforcement Learning Method for Effective Chemotherapy |
| title_fullStr | A New Fuzzy Reinforcement Learning Method for Effective Chemotherapy |
| title_full_unstemmed | A New Fuzzy Reinforcement Learning Method for Effective Chemotherapy |
| title_short | A New Fuzzy Reinforcement Learning Method for Effective Chemotherapy |
| title_sort | new fuzzy reinforcement learning method for effective chemotherapy |
| topic | Caputo-Fabrizio derivative cancer chemotherapy drug dosing fuzzy-reinforcement learning optimal control SARSA algorithm artificial intelligence |
| url | https://www.mdpi.com/2227-7390/11/2/477 |
| work_keys_str_mv | AT fawazealsaadi anewfuzzyreinforcementlearningmethodforeffectivechemotherapy AT amirrezayasami anewfuzzyreinforcementlearningmethodforeffectivechemotherapy AT christosvolos anewfuzzyreinforcementlearningmethodforeffectivechemotherapy AT steliosbekiros anewfuzzyreinforcementlearningmethodforeffectivechemotherapy AT hadijahanshahi anewfuzzyreinforcementlearningmethodforeffectivechemotherapy AT fawazealsaadi newfuzzyreinforcementlearningmethodforeffectivechemotherapy AT amirrezayasami newfuzzyreinforcementlearningmethodforeffectivechemotherapy AT christosvolos newfuzzyreinforcementlearningmethodforeffectivechemotherapy AT steliosbekiros newfuzzyreinforcementlearningmethodforeffectivechemotherapy AT hadijahanshahi newfuzzyreinforcementlearningmethodforeffectivechemotherapy |