Intelligent Agents for Rehabilitation and Care of Disabled and Chronic Patients
Authors: Sarit Kraus
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | One of the main difficulties in the development of intelligent agents for rehabilitation and care of the disabled and of chronic patients is the time and effort it takes to evaluate the proposed techniques. I am involved in a project on personalized reinforcement for rehabilitation of patients in an inpatient rehabilitation center. Our goal is to develop and evaluate a personalized reinforcement treatment, based on the atti-tude of Strategic Behavioral Treatment. The objective of this treatment is to improve the patient s motivation for rehabilitation and for participation in a neurological rehabilitation inpatient program, ultimately improving the outcome of the rehabilitation. This proposed reinforcement plan is designed according to the patient s responses and the staff s reports. Positive reinforcement will be fitted to the patient s functional improvement. More than two years into the project, we are still collecting data for a baseline group. The main algorithmic development will begin only after another experiment with a naive agent that will send participants daily text messages on their cellular phones according to the fulfillment of their tasks. Those who fulfilled the tasks over the entire week will receive a monetary reward (vouchers) from the agent. This is an extreme case, but it will provide a good indication concerning the main problem; running experiments with patients is extremely time consuming and computer scientists should adjust their research expectations accordingly. |
| Researcher Affiliation | Academia | Sarit Kraus Department of Computer Science Bar-Ilan University, Ramat-Gan, Israel 92500 sarit@cs.biu.ac.il |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions 'Cindy is a virtual speech therapist; a development in which I am involved that uses the combined methods (http://www.gertnerinst.org.il/e/well\ being\ e/Tele\ rehabilitation)', which points to a project the author is involved in, but this is not an explicit statement or link to the open-source code for the methodology presented in *this* paper. |
| Open Datasets | No | The paper discusses collecting data for a baseline group and building models from data, but does not provide concrete access information (link, DOI, citation) for any specific dataset used or discussed in the context of training for *this* paper's primary conceptual contribution. |
| Dataset Splits | No | The paper does not specify dataset split information (e.g., percentages, sample counts, or predefined splits) for training, validation, or test sets, as it is a conceptual paper discussing challenges and opportunities rather than reporting on specific experimental results with its own models. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running experiments. |
| Software Dependencies | No | The paper discusses various types of agents (negotiation, advice, persuasion) and machine learning methods, but does not list specific software dependencies with version numbers (e.g., Python 3.8, TensorFlow 2.x) that would be needed to reproduce any specific implementation. |
| Experiment Setup | No | The paper does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings, as it is a conceptual paper discussing challenges and opportunities rather than presenting a concrete experimental system. |