ChatGPT as a decision-support tool for better self-monitoring of hearing DOI Creative Commons
Małgorzata Pastucha, Anna Ratuszniak, Małgorzata Ganc

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 16, 2024

Abstract Background The rapid development of large language model chatbots, such as ChatGPT, has created new possibilities for healthcare support. This study investigates the feasibility integrating self-monitoring hearing (via a mobile app) with ChatGPT’s decision-making capabilities to assess whether specialist consultation is required. In particular, evaluated how accuracy make recommendation changed over periods up 12 months. Methods ChatGPT-4.0 was tested on dataset 1,000 simulated cases, each containing monthly threshold measurements Its recommendations were compared opinions 5 experts using percent agreement and Cohen’s Kappa. A multiple-response strategy, selecting most frequent from trials, also analyzed. Results ChatGPT aligned strongly experts’ judgments, scores ranging 0.80 0.84. Accuracy improved 0.87 when multiple-query strategy employed. those cases where all unanimously agreed, achieved near-perfect score 0.99. It adapted its criteria extended observation periods, seemingly accounting potential random fluctuations in thresholds. Conclusions significant decision-support tool monitoring hearing, able match expert adapting effectively time-series data. Existing self-testing apps lack tracking evaluating changes time; could fill this gap. While not without limitations, offers promising complement self-monitoring. can enhance processes potentially encourage patients seek clinical expertise needed. Graphical abstract

Language: Английский

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices DOI Creative Commons
Marcin Masalski

Medical Devices Evidence and Research, Journal Year: 2024, Volume and Issue: Volume 17, P. 151 - 163

Published: April 1, 2024

Abstract: The popularity of mobile devices, combined with advances in electronic design and internet technology, has enabled home-based hearing tests recent years. purpose this article is to highlight the distinctive aspects pure-tone audiometry performed on a device by means Hearing Test app for Android devices. first version was released decade ago, since then been systematically improved, which required addressing many issues common majority apps testing. discusses techniques calibration, outlines testing procedure how it differs from traditional audiometry, explores potential bone conduction testing, provides considerations interpreting including test duration background noise. concludes detailing clinically relevant requiring special attention during interpretation results are substantial value hundreds thousands active users worldwide, as well other apps. Keywords: self-testing, threshold,

Language: Английский

Citations

6

Development and Comparison of Machine Learning and Deep Learning Models for Speech Audiometry Prediction DOI Creative Commons
Jaeyoung Shin, Jun Ma, Makara Mao

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(6), P. 3071 - 3071

Published: March 12, 2025

Hearing loss significantly impacts daily communication, making accurate speech audiometry (SA) assessment essential for diagnosis and treatment. However, SA testing is time-consuming resource-intensive, limiting its accessibility in clinical practice. This study aimed to develop a multi-class classification model that predicts results using pure-tone (PTA) data, enabling more efficient automated assessment. To achieve this, we implemented compared MLP, RNN, gradient boosting, XGBoost models, evaluating their performance accuracy, F1 score, log loss, confusion matrix analysis. Experimental showed boosting achieved the highest 86.22%, while demonstrated balanced performance. The MLP 85.77% RNN 85.41%, exhibiting relatively low with showing limitations due temporal dependency of PTA data. Additionally, all models faced challenges predicting class 2 (borderline hearing levels) overlapping data distributions. These findings suggest machine learning particularly XGBoost, outperform deep prediction. Future research should focus on feature engineering, hyperparameter optimization, ensemble approaches enhance validate real-world applicability. proposed could contribute automating prediction improving efficiency patient care.

Language: Английский

Citations

0

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices [Letter] DOI Creative Commons
Triwiyanto Triwiyanto

Medical Devices Evidence and Research, Journal Year: 2024, Volume and Issue: Volume 17, P. 213 - 214

Published: May 1, 2024

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices" by M. Masalski, published in Medical Evidence and Research. 1 article reveals the innovative use mobile devices home hearing tests, which represents a remarkable advance given growing prevalence loss worldwide.The app devices, developed offers practical solution early identification loss, particularly resource-constrained environments.The continuous development since its release 2013 impressive number downloads over two million demonstrates importance to users around world.However, this paper also recognizes some limitations weaknesses inherent audiometry.One primary concerns is reliability calibration coefficients, are crucial generation accurate test results.The notes that although pre-determined coefficients most reliable, there degree variability can affect precision test.In addition, testing environment, such as background noise level, significantly results, potentially leading an overestimated threshold.Based these observations, it recommended future research area should explore more advanced techniques adapt diverse headphones used consumers.It would be beneficial develop algorithms compensate environmental effectively, improve accuracy audiometry tests. 2,3Finally, user education proper interpretation tests improved.This will help reduce risk misdiagnosis ensure serves reliable tool professional audiologists.

Language: Английский

Citations

1

The multilingual digits-in-noise (DIN) test: development and evaluation DOI Creative Commons
Marcin Masalski, Krzysztof Morawski

International Journal of Audiology, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 11

Published: Aug. 29, 2024

To develop a methodologically uniform digits-in-noise (DIN) test in 17 different languages.

Language: Английский

Citations

0

The Hearing Test App for Android Devices: Distinctive Features of Pure-Tone Audiometry Performed on Mobile Devices [Response to Letter] DOI Creative Commons
Marcin Masalski

Medical Devices Evidence and Research, Journal Year: 2024, Volume and Issue: Volume 17, P. 215 - 216

Published: June 1, 2024

The objective of this response is to

Language: Английский

Citations

0

ChatGPT as a decision-support tool for better self-monitoring of hearing DOI Creative Commons
Małgorzata Pastucha, Anna Ratuszniak, Małgorzata Ganc

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 16, 2024

Abstract Background The rapid development of large language model chatbots, such as ChatGPT, has created new possibilities for healthcare support. This study investigates the feasibility integrating self-monitoring hearing (via a mobile app) with ChatGPT’s decision-making capabilities to assess whether specialist consultation is required. In particular, evaluated how accuracy make recommendation changed over periods up 12 months. Methods ChatGPT-4.0 was tested on dataset 1,000 simulated cases, each containing monthly threshold measurements Its recommendations were compared opinions 5 experts using percent agreement and Cohen’s Kappa. A multiple-response strategy, selecting most frequent from trials, also analyzed. Results ChatGPT aligned strongly experts’ judgments, scores ranging 0.80 0.84. Accuracy improved 0.87 when multiple-query strategy employed. those cases where all unanimously agreed, achieved near-perfect score 0.99. It adapted its criteria extended observation periods, seemingly accounting potential random fluctuations in thresholds. Conclusions significant decision-support tool monitoring hearing, able match expert adapting effectively time-series data. Existing self-testing apps lack tracking evaluating changes time; could fill this gap. While not without limitations, offers promising complement self-monitoring. can enhance processes potentially encourage patients seek clinical expertise needed. Graphical abstract

Language: Английский

Citations

0