Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards RehabCoach: Design and Preliminary Evaluation of a Conversational Agent Supporting Unsupervised Therapy after Stroke

Giada Devittori, Mehdi Akeddar, Alexandra Retevoi, Fabian Schneider, Viktoria Cvetkova, Daria Dinacci, Antonella Califfi, Paolo Rossi, Claudio Petrillo, Tobias Kowatsch, Olivier Lambercy

TL;DR

The initial prototype of RehabCoach, a novel smartphone-based app with conversational agent to support unsupervised therapy and to increase patients' engagement and adherence to therapy and to provide information in an interactive and user-friendly manner is presented.

Abstract

Unsupervised therapy after stroke is a promising way to boost therapy dose without significantly increasing the workload on healthcare professionals. However, it raises important challenges, such as lower adherence to therapy in the absence of social interaction with therapists. We present the initial prototype of RehabCoach, a novel smartphone-based app with conversational agent to support unsupervised therapy. RehabCoach is designed to increase patients engagement and adherence to therapy and to provide information (e.g., about stroke, health) in an interactive and user-friendly manner. We report on the design and usability evaluation of the first prototype of RehabCoach, assessed by four stroke patients and five healthcare professionals, who interacted with the app in a single testing session. Task completion time and success rates were measured for 15 representative tasks, and participants assessed usability via questionnaires and a semi-structured interview. Results show that it was feasible for stroke patients to successfully interact with RehabCoach (task success $\geq$ 93 $\%$) without requiring extensive training. Participants positively rated the usability of RehabCoach (mean mHealth App Usability Questionnaire score: 1.3 for primary users, 1.4 for healthcare professionals, on a scale from 1 (positive evaluation) to 7). The feedback collected in this work opens the door to further enhance RehabCoach as an interactive digital tool to support unsupervised rehabilitation.

Towards RehabCoach: Design and Preliminary Evaluation of a Conversational Agent Supporting Unsupervised Therapy after Stroke

TL;DR

The initial prototype of RehabCoach, a novel smartphone-based app with conversational agent to support unsupervised therapy and to increase patients' engagement and adherence to therapy and to provide information in an interactive and user-friendly manner is presented.

Abstract

Unsupervised therapy after stroke is a promising way to boost therapy dose without significantly increasing the workload on healthcare professionals. However, it raises important challenges, such as lower adherence to therapy in the absence of social interaction with therapists. We present the initial prototype of RehabCoach, a novel smartphone-based app with conversational agent to support unsupervised therapy. RehabCoach is designed to increase patients engagement and adherence to therapy and to provide information (e.g., about stroke, health) in an interactive and user-friendly manner. We report on the design and usability evaluation of the first prototype of RehabCoach, assessed by four stroke patients and five healthcare professionals, who interacted with the app in a single testing session. Task completion time and success rates were measured for 15 representative tasks, and participants assessed usability via questionnaires and a semi-structured interview. Results show that it was feasible for stroke patients to successfully interact with RehabCoach (task success 93 ) without requiring extensive training. Participants positively rated the usability of RehabCoach (mean mHealth App Usability Questionnaire score: 1.3 for primary users, 1.4 for healthcare professionals, on a scale from 1 (positive evaluation) to 7). The feedback collected in this work opens the door to further enhance RehabCoach as an interactive digital tool to support unsupervised rehabilitation.
Paper Structure (10 sections, 3 figures, 1 table)

This paper contains 10 sections, 3 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. METHODS
  3. RehabCoach design
  4. Preliminary usability evaluation
  5. Data analysis
  6. RESULTS
  7. Task success and completion time
  8. MAUQ and custom questionnaire
  9. Semi-structured interview
  10. DISCUSSION

Figures (3)

  • Figure 1: Screenshot of the main menu of the RehabCoach app.
  • Figure 2: Excerpts from representative chat-based daily interactions between a user and RehabCoach. Grey boxes correspond to the messages sent by the virtual coach, while dark blue boxes are messages sent by the user. Depending on the question, the user can answer either by choosing between predefined answers and clicking on the corresponding button (e.g., light blue buttons with different time options in the planning interaction) or by typing an answer in a predefined field (e.g., light blue box in the training interaction). While the planning interaction and the summary interaction are always at a fixed time (8 am and 7 pm, respectively), the time for the training interaction and the learning interaction can vary depending on the patient’s answers.
  • Figure 3: Tasks performed by the participants with the RehabCoach app during the usability evaluation (a), heat map representing task success for both primary users (P1-P4) and healthcare professionals (H1-H5) (b), and boxplots of the time taken to complete the different tasks for the group of primary users and for the one of healthcare professionals (c).