Prediction of Cochlear Implant Fitting by Machine Learning Techniques.

Otol Neurotol

Department of Otorhinolaryngology and Head and Neck Surgery, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.

Published: July 2024

Objective: This study aimed to evaluate the differences in electrically evoked compound action potential (ECAP) thresholds and postoperative mapping current (T) levels between electrode types after cochlear implantation, the correlation between ECAP thresholds and T levels, and the performance of machine learning techniques in predicting postoperative T levels.

Study Design: Retrospective case review.

Setting: Tertiary hospital.

Patients: We reviewed the charts of 124 ears of children with severe-to-profound hearing loss who had undergone cochlear implantation.

Interventions: We compared ECAP thresholds and T levels from different electrodes, calculated correlations between ECAP thresholds and T levels, and created five prediction models of T levels at switch-on and 6 months after surgery.

Main Outcome Measures: The accuracy of prediction in postoperative mapping current (T) levels.

Results: The ECAP thresholds of the slim modiolar electrodes were significantly lower than those of the straight electrodes on the apical side. However, there was no significant difference in the neural response telemetry thresholds between the two electrodes on the basal side. Lasso regression achieved the most accurate prediction of T levels at switch-on, and the random forest algorithm achieved the most accurate prediction of T levels 6 months after surgery in this dataset.

Conclusion: Machine learning techniques could be useful for accurately predicting postoperative T levels after cochlear implantation in children.

Download full-text PDF

Source
http://dx.doi.org/10.1097/MAO.0000000000004205DOI Listing

Publication Analysis

Top Keywords

ecap thresholds
20
machine learning
12
learning techniques
12
thresholds levels
12
postoperative mapping
8
mapping current
8
levels
8
cochlear implantation
8
predicting postoperative
8
levels switch-on
8

Similar Publications

Background: Pediatric cochlear implant (CI) recipients with cochlear malformations face challenges due to variable speech recognition outcomes.

Aims/objectives: This study assesses the predictive value of intraoperative electrically evoked compound action potential (eCAP) thresholds, residual hearing, age at implantation, Intelligent Quotient (IQ), and malformation type for speech recognition outcomes.

Material And Methods: A prospective cohort of 52 children (aged 1-4 years) with cochlear malformations who underwent CI between 2016 and 2024 was analyzed.

View Article and Find Full Text PDF

Unlabelled: The article is devoted to the problem of the rehabilitation stage of cochlear implantation in patients with inner ear abnormalities. It provides a detailed analysis of the audiological characteristics of such patients and draws conclusions about approaches to interpreting diagnostic data and speech processors fitting.

Material And Methods: The track records of 80 patients with abnormalities of the inner ear development were retrospectively studied, of which 10 had abnormal structure of the auditory nerve.

View Article and Find Full Text PDF

Studies have reported a varied correlation strength between the electrically evoked compound action potential (ECAP) and electrically evoked stapedial reflex thresholds (ESRT) in cochlear implant recipients. However, there is a lack of information on the relationship between the two measures in paediatric cochlear implant users. This study was aimed to compare the ESRT and ECAP measures and determine where ECAP thresholds fall within the dynamic range of ESRT-based Maps in paediatric cochlear implant users.

View Article and Find Full Text PDF
Article Synopsis
  • Spiral ganglion neuron (SGN) degeneration may lead to poorer hearing outcomes in cochlear implant (CI) users, but there's no existing method to locate these degenerated areas in patients.
  • Research on guinea pigs showed that small cochlear micro-lesions significantly increased electrical thresholds and lowered eCAP amplitudes, with effects noticeable up to 3.5 mm away from the lesions.
  • A new electrophysiological marker called the Failure Index (FI) was developed, which accurately indicates the presence and proximity of SGN degeneration and demonstrates a high classification accuracy in identifying affected areas, making it a promising tool for clinical applications.
View Article and Find Full Text PDF

Retrograde evoked compound action potentials as an alternative for close-loop spinal cord stimulation.

Sci Rep

December 2024

Beijing Key Laboratory of Bioelectromagnetism, Institute of Electrical Engineering, Chinese Academy of Sciences, Beijing, 100190, China.

Evoked compound action potential (ECAP) is an important parameter in close-loop spinal cord stimulation (SCS). The recording electrode is typically positioned proximal to the stimulation electrode to capture the antegrade ECAP signals generated by ascending fibers. However, relatively little research has been conducted on retrograde ECAPs.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!