Development of a Predictive Model for Individualized Hearing Aid Benefit

Suresh, Krish; Franck, Kevin H.; Arenberg, Julie G.; Song, Yohan; Lee, Dong Hoon; Crowson, Matthew G.

doi:10.1097/mao.0000000000003739

Cited by 3 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ProtoSound [22] is one step towards personalization as it allows DHH users to experience a customized sound experience and the algorithm requires few training examples to scale across many different types of sounds. Because of these individual differences, technology designers should strive to accommodate personal needs and preferences of individual users making their experience more user friendly and positive [23]. Not only should this effort involve tackling additional barriers to communication with the wearable devices but also it should aim for convenience in wearing the devices along with handling users cultural preferences [24,25].…”

Section: Variability In User Preferencesmentioning

confidence: 99%

See 1 more Smart Citation

Socio-Technical Trust For Multi-Modal Hearing Assistive Technology

Williams

Azim

Piskopani

et al. 2023

2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

View full text Add to dashboard Cite

The landscape of opportunity is rapidly changing for audio-visual (AV) hearing assistive technology. While hearing assistive devices, such as hearing aids, have traditionally been developed for populations of deaf and hard of hearing (DHH) communities, the ubiquitous use of in-ear technology and recent advances in edge computing are reformulating what drives research and development in this domain. With that comes new challenges to consider from the perspective of multiple different stakeholders. In this position paper, we elaborate on seven key socio-technical challenges that may impede the adoption of trustworthy multi-modal hearing assistive technologies. We also draw upon a recent survey being piloted in the UK to examine perceptions of trust for audio systems in the context of human rights. We strongly encourage the research community to consider trust as a factor in developing new AV assistive hearing technologies, as trust may ultimately drive adoption of this technology within broader society.

show abstract

Section: Variability In User Preferencesmentioning

confidence: 99%

“…In order to improve the power and understanding of AI algorithms that are integrated with hearing aids, deep learning based models are being used to amplify the performance and experience of the technology [4,10,23]. However, these deep models are black boxes and do not offer explanations for the decisions made by the device.…”

Section: Integrated Explainabilitymentioning

confidence: 99%

Socio-Technical Trust For Multi-Modal Hearing Assistive Technology

Williams

Azim

Piskopani

et al. 2023

2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)

View full text Add to dashboard Cite

show abstract

Predicting patient reported outcome measures: a scoping review for the artificial intelligence-guided patient preference predictor

Balch,

Chatham,

Hong

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

BackgroundThe algorithmic patient preference predictor (PPP) has been proposed to aid in decision making for incapacitated patients in the absence of advanced directives. Ethical and legal challenges aside, multiple practical barriers exist for building a personalized PPP. Here, we examine previous work using machine learning to predict patient reported outcome measures (PROMs) for capacitated patients undergoing diverse procedures, therapies, and life events. Demonstrating robust performance in predicting PROMs for capacitated patients could suggest opportunities for developing a model tailored to incapacitated ones.MethodsWe performed a scoping review of PubMed, Embase, and Scopus using the PRISMA-ScR guidelines to capture studies using machine learning to predict PROMs following a medical event alongside qualitative studies exploring a theoretical PPP.ResultsSixty-eight studies used machine learning to evaluate PROMs; an additional 20 studies focused on a theoretical PPP. For PROMs, orthopedic surgeries (n = 33) and spinal surgeries (n = 12) were the most common medical event. Studies used demographic (n = 30), pre-event PROMs (n = 52), comorbidities (n = 29), social determinants of health (n = 30), and intraoperative variables (n = 124) as predictors. Thirty-four different PROMs were used as the target outcome. Evaluation metrics varied by task, but performance was overall poor to moderate for the best reported scores. In models that used feature importance, pre-event PROMs were the most predictive of post-event PROMs. Fairness assessments were rare (n = 6). These findings reinforce the necessity of the integrating patient values and preferences, beyond demographic factors, to improve the development of personalized PPP models for incapacitated patients.ConclusionThe primary objective of a PPP is to estimate patient-reported quality of life following an intervention. Use of machine learning to predict PROMs for capacitated patients introduces challenges and opportunities for building a personalized PPP for incapacitated patients without advanced directives.

show abstract

Client Oriented Scale of Improvement in First-Time and Experienced Hearing Aid Users: An Analysis of Five Predetermined Predictability Categories through Audiometric and Speech Testing

Salvago,

Vaccaro,

Plescia

et al. 2024

JCM

View full text Add to dashboard Cite

Objectives: The aim of our investigation was to explore the relationship between unaided pure-tone and speech audiometry and self-reported aided performance measured according to five predetermined COSI categories among first-time hearing aid users and experienced hearing aid users. Methods: Data from 286 patients were retrospectively evaluated. We divided the sample into first-time hearing aid users (G1) and experienced hearing aid users (G2). The correlation between unaided tonal and speech audiometry and five preliminary selected client-oriented scale of improvement (COSI) categories was studied. Results: A greater percentage of hearing aid users aged >80 years and a higher prevalence of severe-to-profound hearing loss in G2 group were observed (p < 0.05). For the total cohort, a mean hearing threshold of 60.37 ± 18.77 db HL emerged in the right ear, and 59.97 ± 18.76 db HL was detected in the left ear (p > 0.05). A significant statistical difference was observed in the group of first-time hearing aid users for the “Television/Radio at normal volume” item, where patients with a lower speech intellection threshold (SIT) were associated with higher COSI scores (p = 0.019). Studying the relationship between the speech reception threshold (SRT) and the COSI item “conversation with 1 or 2 in noise” evidenced worse speech audiometry in patients who scored ≤2 among experienced hearing aid users (p = 0.00012); a higher mean 4–8 kHz frequencies threshold for the better ear was found within the G2 group among those who scored ≤2 in the COSI item “conversation with 1 or 2 in quiet” (p = 0.043). Conclusions: Our study confirms a poor correlation between unaided tonal and speech audiometry and self-reported patient assessment. Although we included only five COSI categories in this study, it is clear that unaided audiometric tests may drive the choice of proper hearing rehabilitation, but their value in predicting the benefit of hearing aids remains limited.

show abstract

Development of a Predictive Model for Individualized Hearing Aid Benefit

Cited by 3 publications

References 24 publications

Socio-Technical Trust For Multi-Modal Hearing Assistive Technology

Socio-Technical Trust For Multi-Modal Hearing Assistive Technology

Predicting patient reported outcome measures: a scoping review for the artificial intelligence-guided patient preference predictor

Client Oriented Scale of Improvement in First-Time and Experienced Hearing Aid Users: An Analysis of Five Predetermined Predictability Categories through Audiometric and Speech Testing

Contact Info

Product

Resources

About