Computer-Guided Electrode Selection for Hearing Loss

Overseen By Elad Sagi

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: NYU Langone Health

Disqualifiers: Communicative, cognitive disorders, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 8

Duration: 24 weeks

45 Participants Needed

Trial Summary

What is the purpose of this trial?

The goal of the present study is to use computationally driven models of speech understanding in CI users to guide the search for which combination of active electrodes can yield the best speech understanding for a specific patient. It is hypothesized that model-recommended settings will result in significantly better speech understanding than standard-of-care settings.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the treatment Cochlear implant?

Research shows that using a computer-guided method to select which electrodes in a cochlear implant are active can significantly improve hearing outcomes. This method helps avoid overlapping stimulation of nerve pathways, which can otherwise reduce the effectiveness of the implant. ^{1 2 3 4 5}

Is the computer-guided electrode selection for hearing loss generally safe for humans?

Cochlear implants, which are similar to the treatment being studied, have been associated with some adverse events like patient injury and device malfunction, but serious events like death are rare. Safety data from various studies suggest that while there are risks, they are generally well understood and managed. ^{6 7 8 9 10}

How does the computer-guided electrode selection for cochlear implants differ from other treatments for hearing loss?

This treatment is unique because it uses computer-guided technology to automatically select which electrodes in a cochlear implant should be active, based on imaging techniques. This helps avoid overlapping stimulation of nerve pathways, which can improve hearing outcomes compared to traditional methods where an expert manually selects the electrodes. ^{2 3 4 11 12}

Research Team

Elad Sagi, MD

Principal Investigator

NYU Langone Health

Eligibility Criteria

This trial is for adults over 18 with hearing loss who have had a cochlear implant for at least one year. Participants must speak English, be able to give informed consent, and not have other communication or cognitive disorders.

Inclusion Criteria

I am over 18, speak English, have normal hearing, and can consent.

I am over 18, have a cochlear implant for at least a year, speak English, and can consent.

Exclusion Criteria

Not meeting the inclusion criteria above

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Baseline

Initial assessments and baseline measurements are conducted

1 day

1 visit (in-person)

Treatment

Participants undergo testing with model-recommended and standard CI settings over multiple visits

24 weeks

7 visits (in-person)

Follow-up

Participants are monitored for safety and effectiveness after treatment

4 weeks

Treatment Details

Interventions

• Cochlear implant

Trial Overview The study is testing a computer model that suggests the best settings for cochlear implants in individuals. It aims to see if these personalized settings improve speech understanding more than standard settings do.

Participant Groups

Group I: Cochlear implant subjects Experimental Treatment 1 Intervention

Participates in 7 visits over a six-month duration. Subjects will be given several tests that require them to listen to sounds presented to their cochlear implant and answer questions about those sounds.

Group II: Normal hearing subjects Active Control 1 Intervention

Participates in 1 visit lasting 3 hours. Will be given several tests that require you to listen to sounds and answer questions about those sounds. The sounds will be distorted in ways that approximate how a cochlear implant sounds.

Who Is Running the Clinical Trial?

NYU Langone Health

Lead Sponsor

Trials

1,431

Recruited

838,000+

National Institute on Deafness and Other Communication Disorders (NIDCD)

Collaborator

Trials

377

Recruited

190,000+

Findings from Research

A machine learning-based referral guideline for cochlear implant candidacy evaluation demonstrated higher sensitivity (0.96) and specificity (1.00) compared to the traditional 60/60 guideline, which had a sensitivity of 0.91 and specificity of 0.42, based on a study of 772 adults.

The machine learning model showed consistent accuracy (0.96) across multiple bootstrapped iterations, indicating its potential for generalizability and effectiveness in identifying candidates for cochlear implants.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Machine Learning Approach for Screening Cochlear Implant Candidates: Comparing With the 60/60 Guideline. Patro, A., Perkins, EL., Ortega, CA., et al.[2023]

An automated technique for selecting cochlear implant electrodes has been developed, which can identify and deactivate electrodes that cause competing stimulation, leading to improved hearing outcomes.

In tests with various electrode array models from three manufacturers, this automated method successfully generated effective electrode sets in 98.3% of subjects, indicating its potential for clinical use in enhancing cochlear implant programming.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Automatic selection of the active electrode set for image-guided cochlear implant programming. Zhao, Y., Dawant, BM., Noble, JH.[2020]

An automatic method for measuring cochlear duct length (CDL) using CT images was evaluated in 309 ears, showing that manual measurements by experts often underestimate cochlea size and have high variability, with a mean difference of 1.15 mm between observers.

The automatic measurement approach provides more consistent and reliable results, which could improve the selection of cochlear implant electrode arrays, ultimately optimizing hearing outcomes for patients.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Automatic Cochlear Duct Length Estimation for Selection of Cochlear Implant Electrode Arrays. Rivas, A., Cakir, A., Hunter, JB., et al.[2022]

The proposed image-guided cochlear implant programming (IGCIP) system uses CT images to identify and reduce cross-electrode neural stimulation overlap, leading to significantly improved hearing outcomes for patients with cochlear implants.

An automated technique for selecting electrode configurations has been developed, which performs as well as previous methods but is more generic and requires fewer parameters, enhancing the efficiency of the programming process.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Selecting electrode configurations for image-guided cochlear implant programming using template matching. Zhang, D., Zhao, Y., Noble, JH., et al.[2020]

Cochlear implants, which send electrical impulses directly to the cochlear nerve, are a significant advancement for patients with severe hearing loss who cannot benefit from traditional hearing aids, and they are now being used in pediatric patients as well.

A multidisciplinary team approach is crucial for the successful implantation and follow-up care of cochlear implants, with 29 patients having received implants using a preferred multi-channel intracochlear system, demonstrating a positive impact on their quality of life.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

[Cochlear implants in children]. Garabedian, EN., Moatti, L., Roger, G., et al.[2006]

In a review of 38 studies involving 3177 cochlear implant cases, the occurrence rate of electrode tip fold-over was found to be 1.57%, primarily associated with pre-curved electrodes.

The review also revealed a significant rate of electrode scalar deviation at 22.38%, with pre-curved electrodes showing a much higher occurrence (32%) compared to lateral-wall electrodes (6.7%), suggesting a need to reconsider the use of pre-curved electrodes in clinical practice for better patient outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Review on cochlear implant electrode array tip fold-over and scalar deviation. Dhanasingh, A., Jolly, C.[2022]

A retrospective analysis of cochlear implant adverse events over a 10-year period revealed a significant increase in cases with multiple or unknown causes, particularly gradual idiopathic loss of performance, indicating a shift in the nature of reported issues.

Despite improvements in manufacturing and surgical techniques, the rise in complex adverse events suggests a need for further research to understand and address these idiopathic cases to enhance cochlear implant outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Trends in cochlear implant complications: implications for improving long-term outcomes. Causon, A., Verschuur, C., Newman, TA.[2013]

A study analyzing adverse event reports for cochlear implants found that most incidents involved patient injury (16,736 cases) and device malfunction (10,760 cases), highlighting areas for potential safety improvements.

Using machine learning algorithms, researchers achieved high prediction accuracy (up to 88.6%) in identifying the cochlear implant manufacturer and type of adverse event based on the descriptions, suggesting that data analysis can enhance understanding of device performance and safety.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Machine learning for pattern detection in cochlear implant FDA adverse event reports. Crowson, MG., Hamour, A., Lin, V., et al.[2021]

A review of 31,857 adverse events from cochlear implants revealed that implants from manufacturer C had a higher incidence of complications, including infection (0.97%), cerebrospinal fluid leak (0.07%), extrusion (0.44%), and facial nerve stimulation (0.11%).

Manufacturer B's implants were linked to a higher rate of meningitis (0.07%), highlighting the importance of considering both patient risk factors and the specific manufacturer when evaluating the safety of cochlear implants.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Complications of cochlear implants: a MAUDE database study. Jinka, S., Wase, S., Jeyakumar, A.[2023]

This study introduces a new evaluation protocol for research platforms (RPs) used in cochlear implants (CIs) and hearing aids (HAs) to ensure their operational safety and reliability, which is crucial for advancing hearing restoration technologies.

The proposed two-phase analysis includes an acoustic phase to assess sound output safety and a parameter phase to evaluate the reliability of electrical stimulation, providing a structured approach to improve the design and testing of hearing devices.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

An evaluation framework for research platforms to advance cochlear implant/hearing aid technology: A case study with CCi-MOBILE. Shekar, RCMC., Hansen, JHL.[2022]

Cochlear implantation (CI) is a widely successful procedure, and the development of computational models can significantly enhance surgical planning by predicting patient-specific outcomes based on neural responses.

The study found that the positioning of the electrode within the cochlea greatly influences the performance of the CI, with lateral insertion being more effective, especially in cases of auditory nerve degeneration, suggesting tailored approaches for individual patients.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Towards a Complete In Silico Assessment of the Outcome of Cochlear Implantation Surgery. Mangado, N., Ceresa, M., Benav, H., et al.[2022]

The study evaluated a method for predicting the angular insertion depth of cochlear implants in 50 patients, finding a theoretical prediction error of 5 degrees, but a much larger clinical prediction error of 70 degrees when including cases with extracochlear electrodes.

While the prediction method can assist in preoperative planning for cochlear implants, it has limitations, such as not being able to accurately predict extracochlear electrode placements and requiring training for effective use.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Clinical Applicability of a Preoperative Angular Insertion Depth Prediction Method for Cochlear Implantation. Rathgeb, C., Demattè, M., Yacoub, A., et al.[2020]

References

1. United States pubmed.ncbi.nlm.nih.gov

Machine Learning Approach for Screening Cochlear Implant Candidates: Comparing With the 60/60 Guideline. [2023]

2. United States pubmed.ncbi.nlm.nih.gov

Automatic selection of the active electrode set for image-guided cochlear implant programming. [2020]

3. United States pubmed.ncbi.nlm.nih.gov

Automatic Cochlear Duct Length Estimation for Selection of Cochlear Implant Electrode Arrays. [2022]

4. United States pubmed.ncbi.nlm.nih.gov

Selecting electrode configurations for image-guided cochlear implant programming using template matching. [2020]

5. France pubmed.ncbi.nlm.nih.gov

[Cochlear implants in children]. [2006]

6. China pubmed.ncbi.nlm.nih.gov

Review on cochlear implant electrode array tip fold-over and scalar deviation. [2022]

7. United States pubmed.ncbi.nlm.nih.gov

Trends in cochlear implant complications: implications for improving long-term outcomes. [2013]

8. England pubmed.ncbi.nlm.nih.gov

Machine learning for pattern detection in cochlear implant FDA adverse event reports. [2021]

9. England pubmed.ncbi.nlm.nih.gov

Complications of cochlear implants: a MAUDE database study. [2023]

10. United States pubmed.ncbi.nlm.nih.gov

An evaluation framework for research platforms to advance cochlear implant/hearing aid technology: A case study with CCi-MOBILE. [2022]

11. United States pubmed.ncbi.nlm.nih.gov

Towards a Complete In Silico Assessment of the Outcome of Cochlear Implantation Surgery. [2022]

12. United States pubmed.ncbi.nlm.nih.gov

Clinical Applicability of a Preoperative Angular Insertion Depth Prediction Method for Cochlear Implantation. [2020]