Javascript must be enabled to continue!
ChatGPT for tinnitus information and support: response accuracy and retest after three months (Preprint)
View through CrossRef
BACKGROUND
ChatGPT – a conversational tool based on artificial intelligence – has recently been tested on a range of topics. However most of the testing has involved broad domains of knowledge.
OBJECTIVE
Here we test ChatGPT’s knowledge of tinnitus, an important but specialized aspect of audiology and otolaryngology. Testing involved evaluating ChatGPT’s answers to a defined set of 10 questions on tinnitus. Furthermore, given the technology is advancing quickly, we re-evaluated the responses to the same 10 questions 3 months later.
METHODS
ChatGPT (free version 3.5) was asked 10 questions on tinnitus at two points of time – August 2023 and November 2023. The accuracy of the responses was rated by 6 experts using a Likert scale ranging from 1 to 5. The number of words in each response was also counted, and responses were specifically examined for whether references were provided or whether consultation with a specialist was suggested.
RESULTS
Most of ChatGPT’s responses were rated as satisfactory or better. However, we did detect a few instances where the responses were not accurate and might be considered somewhat misleading. The responses from ChatGPT were quite long (averaging over 400 words) and they occasionally tended to stray off-topic. No solid references to sources of information were ever supplied, and when references were specifically asked for the sources were artificial. For most responses consultation with a specialist was suggested. It is worth noting that after 3 months the responses generally improved (p = 0.0031).
CONCLUSIONS
ChatGPT provided surprisingly good responses, given that the questions were quite specific. Although no potentially harmful errors were identified, some mistakes could be seen as somewhat misleading. No solid references were ever supplied. ChatGPT shows great potential if further developed by experts in specific areas, but for now it is not yet ready for serious application.
JMIR Publications Inc.
Title: ChatGPT for tinnitus information and support: response accuracy and retest after three months (Preprint)
Description:
BACKGROUND
ChatGPT – a conversational tool based on artificial intelligence – has recently been tested on a range of topics.
However most of the testing has involved broad domains of knowledge.
OBJECTIVE
Here we test ChatGPT’s knowledge of tinnitus, an important but specialized aspect of audiology and otolaryngology.
Testing involved evaluating ChatGPT’s answers to a defined set of 10 questions on tinnitus.
Furthermore, given the technology is advancing quickly, we re-evaluated the responses to the same 10 questions 3 months later.
METHODS
ChatGPT (free version 3.
5) was asked 10 questions on tinnitus at two points of time – August 2023 and November 2023.
The accuracy of the responses was rated by 6 experts using a Likert scale ranging from 1 to 5.
The number of words in each response was also counted, and responses were specifically examined for whether references were provided or whether consultation with a specialist was suggested.
RESULTS
Most of ChatGPT’s responses were rated as satisfactory or better.
However, we did detect a few instances where the responses were not accurate and might be considered somewhat misleading.
The responses from ChatGPT were quite long (averaging over 400 words) and they occasionally tended to stray off-topic.
No solid references to sources of information were ever supplied, and when references were specifically asked for the sources were artificial.
For most responses consultation with a specialist was suggested.
It is worth noting that after 3 months the responses generally improved (p = 0.
0031).
CONCLUSIONS
ChatGPT provided surprisingly good responses, given that the questions were quite specific.
Although no potentially harmful errors were identified, some mistakes could be seen as somewhat misleading.
No solid references were ever supplied.
ChatGPT shows great potential if further developed by experts in specific areas, but for now it is not yet ready for serious application.
Related Results
Exploring Large Language Models Integration in the Histopathologic Diagnosis of Skin Diseases: A Comparative Study
Exploring Large Language Models Integration in the Histopathologic Diagnosis of Skin Diseases: A Comparative Study
Abstract
Introduction
The exact manner in which large language models (LLMs) will be integrated into pathology is not yet fully comprehended. This study examines the accuracy, bene...
Impact of Tinnitus on Quality of Life and Cognitive Function in Adults: A Systematic Review
Impact of Tinnitus on Quality of Life and Cognitive Function in Adults: A Systematic Review
Background: Tinnitus is often associated with cognitive difficulties, especially in attention and executive functioning. However, it remains unclear how much tinnitus itself contri...
Assessment of Chat-GPT, Gemini, and Perplexity in Principle of Research Publication: A Comparative Study
Assessment of Chat-GPT, Gemini, and Perplexity in Principle of Research Publication: A Comparative Study
Abstract
Introduction
Many researchers utilize artificial intelligence (AI) to aid their research endeavors. This study seeks to assess and contrast the performance of three sophis...
Development of a tinnitus sound generator that matches the sound of tinnitus patient
Development of a tinnitus sound generator that matches the sound of tinnitus patient
Background: Tinnitus is the perception of sound heard by a person in the absence of an external stimulus. About 10-14.5% of the world's population experience tinnitus, with the mos...
Sound-Evoked Plasticity Differentiates Tinnitus from Non-Tinnitus Mice
Sound-Evoked Plasticity Differentiates Tinnitus from Non-Tinnitus Mice
AbstractTinnitus is the perception of non-meaningful sound in the absence of external stimuli. Although tinnitus behavior in animal models is associated with altered central nervou...
Tinnitus treatment: an experimental study
Tinnitus treatment: an experimental study
Abstract
Objective
The objective of the present study was to compare the effectiveness of the selected tinnitus management protocols for the experim...
The Relation of Sound Level Tolerance to Tinnitus Ears in Human
The Relation of Sound Level Tolerance to Tinnitus Ears in Human
BACKGROUND: The aim of this study was to evaluate the relationship between sound level tolerance and tinnitus in humans.
METHODS: We compared the loudness discomfort levels at 500...
CHATGPT ASSISTANCE ON BIOCHEMISTRY LEARNING OUTCOMES OF PRE-SERVICE TEACHERS
CHATGPT ASSISTANCE ON BIOCHEMISTRY LEARNING OUTCOMES OF PRE-SERVICE TEACHERS
This research investigates the effect of ChatGPT on the learning outcomes of pre-service biology teachers. Sampling was done by purposive sampling in class A (treated with ChatGPT)...

