Author(s)
Term
4. Term
Publication year
2024
Submitted on
2024-05-31
Pages
54 pages
Abstract
Paradokset at komplekse patienttilfælde kræver mere tid og efterlader mindre tid til dokumentation og behandling sammenlignet med enklere tilfælde i fysioterapeutisk praksis, motiverer vores forskning. Studiet havde til formål at undersøge anvendelsen af en virtuel assistent i til at indsamle patienternes sygehistorie (anamnese). Vi ønskede at lette fysioterapeuternes dokumentationsansvar og muliggøre hurtigere igangsættelse af nødvendige tests og behandling i praksis. For at teste, om patienter ville svare anderledes til et system sammenlignet med en fysioterapeut, blev der udviklet en selv-anamnese prototype, indeholdende både talegenkendelse og talesyntese teknologier. Evalueringen involverede deltagernes interaktion med systemet, efterfulgt af et spørgeskema og semi-struktureret interview for at indsamle deres perspektiver på teknologien. En gruppe på syv fysioterapeuter blev derefter præsenteret for et udvalg af svar fra konventionelle anamnesisoptagelser og svar givet til systemet. De blev bedt om at skelne mellem de to, hvis muligt. Generelt kunne fysioterapeuterne ikke skelne mellem anamnese data indsamlet af den virtuelle assistent og dem, der blev indsamlet gennem konventionelle metoder, hvilket understøtter, at patienter ikke svarer anderledes, når de bliver spurgt af et system, der er specifikt designet til formålet. Derudover gav både fysioterapeuter og potentielle brugere generelt positiv feedback på systemet, mens de også fremhævede nogle udfordringer. De primære bekymringer var manglen på personliggørelse af dialogen og logistiske udfordringer, der kunne hindre en vellykket implementering i praksis.
The paradox of complex patient cases requiring more time and leaving less for documentation and treatment compared to simpler cases in physiotherapy practice, motivates our research. The study aimed to investigate the use of a virtual assistant in physiotherapy practice to gather patients’ medical histories (anamnesis). We sought to alleviate the physiotherapists’ responsibility of documentation and enable quicker initiation of necessary tests and treatment in practice. For testing whether patients would respond differently to a system compared to a physiotherapist, a self-anamnesis prototype was developed, incorporating both speech recognition and speech synthesis technologies. The evaluation involved potential patients interacting with the system, followed by a survey and semi-structured interviews to gather their perspectives on the technology. A group of seven physiotherapists were then presented with a selection of answers from conventional anamnesis recordings and answers provided to the system. They were asked to distinguish between the two if possible. Overall, physiotherapists could not distinguish between anamnesis data collected by the VA and that obtained through conventional methods, supporting that patients do not respond differently when prompted by a system specifically designed for the purpose. Additionally, both physiotherapists and potential patients provided overall positive feedback on the system, while also highlighting some drawbacks. The primary concerns were the lack of customization and logistical challenges that could hinder successful implementation in practice.
Keywords
fysioterapi ; anamnese ; virtuel assistent ; AI ; data ; NLP
Documents
Colophon: This page is part of the AAU Student Projects portal, which is run by Aalborg University. Here, you can find and download publicly available bachelor's theses and master's projects from across the university dating from 2008 onwards. Student projects from before 2008 are available in printed form at Aalborg University Library.
If you have any questions about AAU Student Projects or the research registration, dissemination and analysis at Aalborg University, please feel free to contact the VBN team. You can also find more information in the AAU Student Projects FAQs.