The objective of the user study was to evaluate the usability of the dialogue protocol. The protocol is supposed to facilitate collaborative decision making between medical experts. Usability evaluation has been done to assess whether and how much the protocol enables transfer of learning, conflict resolution, agreement on explanations and collaborative decision making.
Due to the highly specialised profile (i.e. medical experts) required for the test subjects in this user study, it was difficult to recruit test subjects. So discount testing was done with the minimum number of participants for the formative study (5 participants). The goal of the study was to elicit user’s perspectives on effectiveness, efficiency and satisfaction of the platform and the underlying protocol in meeting their professional communication needs. The participants were final year medical students from a medical university in Barcelona, Spain. They were volunteers who responded to a call for participation after reading the advertised information sheet through their University’s human resource department.
Participants were given scenarios (medical cases) based on anonymous patient data taken from the publicly available Thyroid dataset from the Machine Learning repository (https://archive.ics.uci.edu/ml/datasets/Thyroid+Disease, DOI: https://doi.org/10.24432/C5D010). For each session of the usability testing, participants were divided into groups of three. They were then tasked with collaboratively deciding on the best possible diagnosis and advice for an anonymous patient with a thyroid disorder. Each scenario asked the participants to diagnose and prescribe treatments for test examples taken from the dataset. Each participant needed a computer to access the web application. The researcher in charge moderated each session and conducted the interview at the end of each session. Each session took 45 minutes in total.
The post session interviews from the user study were recorded with the consent of participants, transcribed and the interview data was thematically analysed to discover key insights. Openly available are the experimental cases (original Thyroid dataset) used as an experimental material discussed during interviews and the questions asked during the interviews (both attached to this repository). Due to the decision of The Bioethics Commission of the University of Barcelona, full transcripts of interviews could not be publicly shared. The special requests and inquiries about this data can be send to the Authors of the study: Qurat-ul-ain Shaheen (qurat@iiia.csic.es), Katarzyna Budzynska (Katarzyna.Budzynska@pw.edu.pl), and Carles Sierra (sierra@iiia.csic.es). A detailed description of the results from the analysis of this data is available in the research paper: Shaheen Q, Budzynska K, Sierra C. An explanation-oriented inquiry dialogue game for expert collaborative recommendations. Argument & Computation. 2024;15(3):355-390. doi:10.3233/AAC-230010.
• data types: Free text
• date of data collection: 2023-April
• location of data collection: medical university computer science lab in Barcelona, IIIA
• format of data storage: .TXT
• language of collected data: English
• location of data storage: IIIA Institute, Barcelona, Spain
The data is provided with plain text formats, so they can be opened with:
- Notepad,
- VS Code,
- Any text editor,
as well as loaded and processed with tools like:
- Python (pandas),
- Excel / LibreOffice Calc (after converting to .csv),
- R,
- Jupyter Notebook.