Developing of Q&A bots for medicinal disclosure for CKD-patients

Berchtold, Jan

doi:10.21256/zhaw-29324

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-29324

Publication type:	Master thesis
Title:	Developing of Q&A bots for medicinal disclosure for CKD-patients
Authors:	Berchtold, Jan
Advisors / Reviewers:	Keller, Thomas de Spindler, Alexandre
DOI:	10.21256/zhaw-29324
Extent:	61
Issue Date:	2023
Publisher / Ed. Institution:	ZHAW Zürcher Hochschule für Angewandte Wissenschaften
Publisher / Ed. Institution:	Winterthur
Language:	English
Subject (DDC):	410.285: Computational linguistics 616: Internal medicine and diseases
Abstract:	This thesis was a subproject of the RealCo project by Prof. Dr. Thomas Keller at ZHAW which provides information about a medication called SGLT2 inhibitors to patients with chronic kidney disease (CKD). While the goal of the project is to improve patient health literacy and compliance, this thesis rather focused on developing a chatbot to answer questions related to the use of SGLT2 inhibitors to CKD patients. Chatbots, as software components that communicate with users via natural language, are considered as an appropriate instrument for improving health literacy. The developed chatbots were implemented using natural language understanding (NLU) platforms, which, due to their structure, enable rapid prototyping, deployment and simple integrations. This thesis addressed the question of which NLU platform is most suitable for the use case. In this thesis, two artefacts were built with over 800 training questions about SGLT2 inhibitors to answer the question above. The developed chatbots were tested with physicians and pharmacists for correctness. The results showed that DialogFlow and Watson Assistant are the most popular and widely used NLU platforms were therefore selected for the chatbot development. The tests conducted and the feedback gathered from physicians and pharmacists showed that the answers were medically correct and the chatbot was perceived as friendly and appealing. Also, in the majority of cases, users received an answer that was relevant to their question. The implementation of the chatbots in these two platforms demonstrated that Watson Assistant was superior to DialogFlow in terms of latency as well as the delivery of the correct answer to the question asked. Future studies using the existing chatbots within the RealCo project should involve patients for testing and further development.
URI:	https://digitalcollection.zhaw.ch/handle/11475/29324
License (according to publishing contract):	CC BY-NC-ND 4.0: Attribution - Non commercial - No derivatives 4.0 International
Departement:	School of Management and Law
Appears in collections:	MSc Wirtschaftsinformatik

Files in This Item:

File	Description	Size	Format
2023_Berchtold_Jan_MSc_IWI.pdf		881.43 kB	Adobe PDF	View/Open

Show full item record

Berchtold, J. (2023). Developing of Q&A bots for medicinal disclosure for CKD-patients [Master’s thesis, ZHAW Zürcher Hochschule für Angewandte Wissenschaften]. https://doi.org/10.21256/zhaw-29324

Berchtold, J. (2023) Developing of Q&A bots for medicinal disclosure for CKD-patients. Master’s thesis. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. Available at: https://doi.org/10.21256/zhaw-29324.

J. Berchtold, “Developing of Q&A bots for medicinal disclosure for CKD-patients,” Master’s thesis, ZHAW Zürcher Hochschule für Angewandte Wissenschaften, Winterthur, 2023. doi: 10.21256/zhaw-29324.

BERCHTOLD, Jan, 2023. Developing of Q&A bots for medicinal disclosure for CKD-patients. Master’s thesis. Winterthur: ZHAW Zürcher Hochschule für Angewandte Wissenschaften

Berchtold, Jan. 2023. “Developing of Q&A Bots for Medicinal Disclosure for CKD-Patients.” Master’s thesis, Winterthur: ZHAW Zürcher Hochschule für Angewandte Wissenschaften. https://doi.org/10.21256/zhaw-29324.

Berchtold, Jan. Developing of Q&A Bots for Medicinal Disclosure for CKD-Patients. ZHAW Zürcher Hochschule für Angewandte Wissenschaften, 2023, https://doi.org/10.21256/zhaw-29324.