Dataset Information

Cochlear Implantation in Postlingually Deaf Adults is Time-sensitive Towards Positive Outcome: Prediction using Advanced Machine Learning Techniques.

ABSTRACT: Given our aging society and the prevalence of age-related hearing loss that often develops during adulthood, hearing loss is a common public health issue affecting almost all older adults. Moderate-to-moderately severe hearing loss can usually be corrected with hearing aids; however, severe-to-profound hearing loss often requires a cochlear implant (CI). However, post-operative CI results vary, and the performance of the previous prediction models is limited, indicating that a new approach is needed. For postlingually deaf adults (n de120) who received CI with full insertion, we predicted CI outcomes using a Random-Forest Regression (RFR) model and investigated the effect of preoperative factors on CI outcomes. Postoperative word recognition scores (WRS) served as the dependent variable to predict. Predictors included duration of deafness (DoD), age at CI operation (ageCI), duration of hearing-aid use (DoHA), preoperative hearing threshold and sentence recognition score. Prediction accuracy was evaluated using mean absolute error (MAE) and Pearson's correlation coefficient r between the true WRS and predicted WRS. The fitting using a linear model resulted in prediction of WRS with r = 0.7 and MAE = 15.6 ± 9. RFR outperformed the linear model (r = 0.96, MAE = 6.1 ± 4.7, p < 0.00001). Cross-hospital data validation showed reliable performance using RFR (r = 0.91, MAE = 9.6 ± 5.2). The contribution of DoD to prediction was the highest (MAE increase when omitted: 14.8), followed by ageCI (8.9) and DoHA (7.5). After CI, patients with DoD < 10 years presented better WRSs and smaller variations (p < 0.01) than those with longer DoD. Better WRS was also explained by younger age at CI and longer-term DoHA. Machine learning demonstrated a robust prediction performance for CI outcomes in postlingually deaf adults across different institutes, providing a reference value for counseling patients considering CI. Health care providers should be aware that the patients with severe-to-profound hearing loss who cannot have benefit from hearing aids need to proceed with CI as soon as possible and should continue using hearing aids until after CI operation.

SUBMITTER: Kim H

PROVIDER: S-EPMC6301958 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The benefits of cochlear implantation for children with developmental delays (DD) often are unclear. We compared cognition, adaptive behavior, familial stress, and communication in children with and without DD.Retrospective review.Two tertiary care pediatric hospitals.Two hundred four children who underwent cochlear implantation assessed before and more than 1 year after implantation.The Mullen Scales of Early Learning (MSEL), vineland adaptive behavior scales (VABS), Parental Stress Index, and Preschool Language Scale.We developed a specific definition of DD for hearing-impaired children based upon diagnostic and statistical manual of mental disorders, fourth edition, criteria for mental retardation; 60 children met the criteria for DD, and 144 children did not. Before implantation, multiple linear regression demonstrated that children with DD had lower scores in every domain of the MSEL and VABS (p < 0.05), but no differences in any domains of the parental stress index and preschool language scale (p > 0.1) compared with children without DD. After implantation, children without DD demonstrated significant improvements in intelligence as measured by the MSEL and age-appropriate improvements in adaptive behavior as evaluated by the VABS, and their familial stress levels were not increased after cochlear implantation. In contrast, children with DD underwent implantation at a later age and demonstrated less comprehensive developmental improvements after cochlear implantation and higher stress levels. However, when the age differences were taken into account using multiple linear regression analyses, the differences between the 2 cohorts were reduced.These data indicate that our definition of DD is a reliable method of stratifying deaf children. Although children with DD have a normal developmental rate of adaptive behavior after cochlear implantation, their developmental rate of intelligence is lower, and they have higher stress levels than children without DD. However, our data suggest that if children with DD could be implanted as early as children without DD, their intelligence and stress outcomes would be improved.

Project description:Currently, it is not possible to accurately predict how well a deaf individual will be able to understand speech when hearing is (re)introduced via a cochlear implant. Differences in brain organisation following deafness are thought to contribute to variability in speech understanding with a cochlear implant and may offer unique insights that could help to more reliably predict outcomes. An emerging optical neuroimaging technique, functional near-infrared spectroscopy (fNIRS), was used to determine whether a pre-operative measure of brain activation could explain variability in cochlear implant (CI) outcomes and offer additional prognostic value above that provided by known clinical characteristics. Cross-modal activation to visual speech was measured in bilateral superior temporal cortex of pre- and post-lingually deaf adults before cochlear implantation. Behavioural measures of auditory speech understanding were obtained in the same individuals following 6 months of cochlear implant use. The results showed that stronger pre-operative cross-modal activation of auditory brain regions by visual speech was predictive of poorer auditory speech understanding after implantation. Further investigation suggested that this relationship may have been driven primarily by the inclusion of, and group differences between, pre- and post-lingually deaf individuals. Nonetheless, pre-operative cortical imaging provided additional prognostic value above that of influential clinical characteristics, including the age-at-onset and duration of auditory deprivation, suggesting that objectively assessing the physiological status of the brain using fNIRS imaging pre-operatively may support more accurate prediction of individual CI outcomes. Whilst activation of auditory brain regions by visual speech prior to implantation was related to the CI user's clinical history of deafness, activation to visual speech did not relate to the future ability of these brain regions to respond to auditory speech stimulation with a CI. Greater pre-operative activation of left superior temporal cortex by visual speech was associated with enhanced speechreading abilities, suggesting that visual speech processing may help to maintain left temporal lobe specialisation for language processing during periods of profound deafness.

Dataset Information

Cochlear Implantation in Postlingually Deaf Adults is Time-sensitive Towards Positive Outcome: Prediction using Advanced Machine Learning Techniques.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets