Learning and Assessing Optimal Dynamic Treatment Regimes Through Cooperative Imitation Learning

Abstract

Dynamic Treatment Regimes (DTRs) are sets of sequential decision rules that can be adapted over time to treat patients with a specific pathology. DTR consists of alternative treatment paths and any of these treatments can be adapted depending on the patient's characteristics. Reinforcement Learning (RL) and Imitation Learning (IL) approaches have been deployed for obtaining optimal treatment for a patient but, these approaches rely only on positive trajectories (i.e., treatments that concluded with positive responses of the patient). In contrast, negative trajectories (i.e., samples of non-responding treatments) are discarded, although these have valuable information content. We propose a Cooperative Imitation Learning (CIL) method that exploits information from both negative and positive trajectories to learn the optimal DTR. The proposed method reduces the chance of selecting any treatment which results in a negative outcome (negative response of the patient) during the medical examination. To validate our approach, we have considered a well-known DTR which is defined for the treatment of patients with alcohol addiction. Results show that our approach outperforms those that rely only on positive trajectories.

Impact of AI-Powered Solutions in Rehabilitation Process: Recent Improvements and Future Trends

“…5 The applications of AI in mental health extend beyond diagnosis and drug recommendation. 6 Virtual therapy sessions using AI chatbots or virtual reality platforms have shown promising results in providing accessible support thus, offering a safe environment for patients to express their thoughts and emotions, facilitating effective therapy without geographical barriers. 7 One of the primary advantages of technology-based interventions is their enhanced accessibility.…”

Improving Adherence to Medication in an Intelligent Environment Using Reinforcement Learning

“…Therefore, the role of a patient engagement system is broader than the exercise routines and diets [20]. care solutions such as in risk management in nuclear medicine department [19], in personalized medication (e.g., [11,7], in dynamic treatment regimes [18]. Concerning the engagement of patients during medications, some studies have proposed medication reminder systems that we report here by highlighting their contributions and limitations concerning our work.…”

Cloud-Based Monitoring System for Personalized Home Medication

“…AI has significant application in many areas including:healthcare [8,25], UAVs, 5G and autonomous control [15], risk management [20,26], communication [14,11].…”