Combination of static and dynamic neural imaging features to distinguish sensorineural hearing loss: a machine learning study

Frontiers in Neuroscience, Journal Year: 2024, Volume and Issue: 18

Published: June 12, 2024

Sensorineural hearing loss (SNHL) is the most common form of sensory deprivation and often unrecognized by patients, inducing not only auditory but also nonauditory symptoms. Data-driven classifier modeling with combination neural static dynamic imaging features could be effectively used to classify SNHL individuals healthy controls (HCs).

Language: Английский

---

Changing Knowledge, Principles, and Technology in Contemporary Clinical Audiological Practice: A Narrative Review

Journal of Clinical Medicine, Journal Year: 2024, Volume and Issue: 13(15), P. 4538 - 4538

Published: Aug. 2, 2024

The field of audiology as a collection auditory science knowledge, research, and clinical methods, technologies, practices has seen great changes. A deeper understanding psychological, cognitive, behavioural interactions led to growing range variables interest measure track in diagnostic rehabilitative processes. Technology-led changes practices, including teleaudiology, have heralded call action order recognise the role impact autonomy agency on practice, engagement, outcomes. Advances new information loudness models, tinnitus, psychoacoustics, deep neural networks, machine learning, predictive adaptive algorithms, PREMs/PROMs enabled innovations technology revolutionise principles for following: (i) assessment, (ii) fitting programming hearing devices, (iii) rehabilitation. This narrative review will consider how rise teleaudiology increasingly fundamental element contemporary adult audiological practice affected based era knowledge capability. What areas grown? How shifted priorities audiology? technological been combined with these change practices? Above all, where is loss now consequently positioned its journey health medicine?

Language: Английский

---

Applications of Machine Learning in Meniere's Disease Assessment Based on Pure‐Tone Audiometry

Otolaryngology, Journal Year: 2024, Volume and Issue: 172(1), P. 233 - 242

Published: Aug. 28, 2024

Abstract Objective To apply machine learning models based on air conduction thresholds of pure‐tone audiometry for automatic diagnosis Meniere's disease (MD) and prediction endolymphatic hydrops (EH). Study Design Retrospective study. Setting Tertiary medical center. Methods Gadolinium‐enhanced magnetic resonance imaging sequences data were collected. Subsequently, basic multiple analytical features engineered the audiometry. Later, 5 classical trained to diagnose MD using features. The demonstrating excellent performance also selected predict EH. model's effectiveness in was compared with experienced otolaryngologists. Results First, winning light gradient boosting (LGB) model by demonstrates a remarkable MD, achieving an accuracy rate 87%, sensitivity 83%, specificity 90%, robust area under receiver operating characteristic curve 0.95, which compares favorably clinicians. Second, LGB model, 78% EH prediction, outperformed other 3 models. Finally, feature importance analysis reveals pivotal role specific that are essential both prediction. Highlighted include standard deviation mean whole‐frequency hearing, peak audiogram, hearing at low frequencies, notably 250 Hz. Conclusion An efficient produced showed potential subtypes innovative approach demonstrated game‐changing strategy screening promising cost‐effective benefits health care enterprise.

Language: Английский

---

The Earphone Project pilot: a tele-otology study for remote Aboriginal communities

Australian Journal of Otolaryngology, Journal Year: 2024, Volume and Issue: 7, P. 38 - 38

Published: Sept. 3, 2024

Language: Английский

---

Test-retest reliability of remote home-based audiometry in differing ambient noise conditions

Frontiers in Audiology and Otology, Journal Year: 2024, Volume and Issue: 2

Published: March 27, 2024

Background Home-based remote audiometry has been emerging due to the increasing accessibility of mobile technology and need for healthcare solutions that are available worldwide. However, challenges presented by uncontrolled conditions, such as noisy environments, could compromise reliability hearing assessment. Method In this study, we evaluate Jacoti Hearing Center (JHC) smartphone application in differing ambient noise environments. test data were synchronized from JHC earCloud database (JEC). We collected, de-identified, analyzed real-world, home-based audiometric spanning 2015 2023, extracted JEC database. A set exclusion criteria was defined perform cleaning, ensuring removal incomplete unreliable data, well as, users who had completed a large number tests. The final dataset comprised 9,421 retest threshold pairs 1,115 users. tests conducted under relatively quiet conditions categorized based on threshold-to-noise ratio. Results test-retest demonstrated an average absolute difference 4.7 dB within range 20 75 dB, ranging 3.7 6.2 across frequencies. strong positive correlation 0.85 found between thresholds. Moreover, pure tone differences 5 84.6% audiograms. No clinically significant effects observed thresholds determined HL. Conclusions Our results demonstrate can provide reliable loss, even non-ideal acoustic conditions. This highlights potential assessment, reinforcing idea that, with continuous monitoring noise-aware control testing procedure, be reliable.

Language: Английский

---