Further Evidence for Individual Ear Consideration in Cochlear Implant Candidacy Evaluation

Improved Postoperative Speech Recognition and Processor Use With Early Cochlear Implant Activation

OBJECTIVE

To report speech recognition outcomes and processor use based on timing of cochlear implant (CI) activation.

STUDY DESIGN

Retrospective cohort.

SETTING

Tertiary referral center.

PATIENTS

A total of 604 adult CI recipients from October 2011 to March 2022, stratified by timing of CI activation (group 1: ≤10 d, n = 47; group 2: >10 d, n = 557).

MAIN OUTCOME MEASURES

Average daily processor use; Consonant-Nucleus-Consonant (CNC) and Arizona Biomedical (AzBio) in quiet at 1-, 3-, 6-, and 12-month visits; time to peak performance.

RESULTS

The groups did not differ in sex ( p = 0.887), age at CI ( p = 0.109), preoperative CNC ( p = 0.070), or preoperative AzBio in quiet ( p = 0.113). Group 1 had higher median daily processor use than group 2 at the 1-month visit (12.3 versus 10.7 h/d, p = 0.017), with no significant differences at 3, 6, and 12 months. The early activation group had superior median CNC performance at 3 months (56% versus 46%, p = 0.007) and 12 months (60% versus 52%, p = 0.044). Similarly, the early activation group had superior median AzBio in quiet performance at 3 months (72% versus 59%, p = 0.008) and 12 months (75% versus 68%, p = 0.049). Both groups were equivalent in time to peak performance for CNC and AzBio. Earlier CI activation was significantly correlated with higher average daily processor use at all follow-up intervals.

CONCLUSION

CI activation within 10 days of surgery is associated with increased early device usage and superior speech recognition at both early and late follow-up visits. Timing of activation and device usage are modifiable factors that can help optimize postoperative outcomes in the CI population.

Impact of unilateral vs. bilateral evaluation on cochlear implant candidacy

BACKGROUND

The indication criteria for cochlear implantation differ considerably across regions.

OBJECTIVES

To estimate the effects of different candidacy criteria on the number of cochlear implant (CI) candidates.

METHODS

We analysed a very large clinical audiological database comprising pure-tone thresholds and speech-audiometric data in order to identify CI candidates on the basis of different audiometric candidacy criteria. In particular, we simulated the effects of three different CI candidacy criteria.

RESULTS

The bilateral evaluation of CI candidacy has the strongest influence on the number of potential CI candidates. Additionally, the cut-off criteria for middle-ear implants have a large effect on numbers of candidates when air conduction has deteriorated.Conclusions and Significance: Expanding the indication criteria opens up the possibility of improving the accurate identification of individual cases suitable for cochlear-implant provision.

Investigation of Maximum Monosyllabic Word Recognition as a Predictor of Speech Understanding with Cochlear Implant

Background: The cochlear implant (CI) is an established treatment option for patients with inadequate speech understanding and insufficient aided scores. Nevertheless, reliable predictive models and specific therapy goals regarding achievable speech understanding are still lacking. Method: In this retrospective study, 601 cases of CI fittings between 2005 and 2021 at the University Medical Center Freiburg were analyzed. We investigated the preoperative unaided maximum word recognition score (mWRS) as a minimum predictor for post-interventional scores at 65 dB SPL, WRS65(CI). The WRS65(CI) was compared with the preoperative-aided WRS, and a previously published prediction model for the WRS65(CI) was reviewed. Furthermore, the effect of duration of hearing loss, duration of HA fitting, and etiology on WRS65(CI) were investigated. Results: In 95.5% of the cases, a significant improvement in word recognition was observed after CI. WRS65(CI) achieved or exceeded mWRS in 97% of cases. Etiology had a significant impact on WRS65(CI). The predicted score was missed by more than 20 percentage points in 12.8% of cases. Discussion: Our results confirmed the minimum prediction via mWRS. A more precise prediction of the expected WRS65(CI) is possible. The etiology of hearing loss should be considered in the indication and postoperative care to achieve optimal results.

Comparison of Speech Recognition and Hearing Preservation Outcomes Between the Mid-Scala and Lateral Wall Electrode Arrays

OBJECTIVE

To assess speech recognition and hearing preservation (HP) outcomes with the Advanced Bionics Mid-Scala and SlimJ electrodes.

STUDY DESIGN

Retrospective cohort.

SETTING

Tertiary referral center.

PATIENTS

A total of 237 adult patients implanted between 2013 and 2020 (Mid-Scala, n = 136; SlimJ, n = 101).

MAIN OUTCOME MEASURES

Consonant-nucleus-consonant (CNC) and AzBio (Arizona Biomedical) scores at 6 and 12 months; postoperative HP, defined as low-frequency pure-tone average ≤ 80 dB HL; scalar position.

RESULTS

Mean CNC scores did not significantly differ between Mid-Scala and SlimJ recipients at 6 (45.8% versus 46.0%, p = 0.962) and 12 (51.9% versus 48.8%, p = 0.363) months. Similarly, mean AzBio in quiet scores were equivalent for both groups at 6 (55.1% versus 59.2%, p = 0.334) and 12 (60.6% versus 62.3%, p = 0.684) months. HP rates were significantly higher with the SlimJ (48.4%) than the Mid-Scala (30.8%; p = 0.033). Scalar translocations were 34.8 and 16.1% for the Mid-Scala and SlimJ groups, respectively ( p = 0.019). Ears with postoperative HP had significantly fewer scalar translocations (16.7% versus 37.2%, p = 0.048), and postoperative HP was associated with higher AzBio in noise scores at the most recent follow-up interval (38.7% versus 25.1%, p = 0.042). CNC, AzBio in quiet and noise, low-frequency pure-tone average shifts, and PTA at 6 and 12 months were not significantly different between patients with scala tympani insertions of the SlimJ versus the Mid-Scala ( p > 0.05).

CONCLUSIONS

Compared with the Mid-Scala, the lateral wall electrode has superior HP rates and fewer scalar translocations, whereas speech recognition scores are equivalent between both electrode arrays. These findings can help providers with electrode selection and patient counseling.

Machine Learning Approach for Screening Cochlear Implant Candidates: Comparing With the 60/60 Guideline

OBJECTIVE

To develop a machine learning-based referral guideline for patients undergoing cochlear implant candidacy evaluation (CICE) and to compare with the widely used 60/60 guideline.

STUDY DESIGN

Retrospective cohort.

SETTING

Tertiary referral center.

PATIENTS

772 adults undergoing CICE from 2015 to 2020.

INTERVENTIONS

Variables included demographics, unaided thresholds, and word recognition score. A random forest classification model was trained on patients undergoing CICE, and bootstrap cross-validation was used to assess the modeling approach's performance.

MAIN OUTCOME MEASURES

The machine learning-based referral tool was evaluated against the 60/60 guideline based on ability to identify CI candidates under traditional and expanded criteria.

RESULTS

Of 587 patients with complete data, 563 (96%) met candidacy at our center, and the 60/60 guideline identified 512 (87%) patients. In the random forest model, word recognition score; thresholds at 3000, 2000, and 125; and age at CICE had the largest impact on candidacy (mean decrease in Gini coefficient, 2.83, 1.60, 1.20, 1.17, and 1.16, respectively). The 60/60 guideline had a sensitivity of 0.91, a specificity of 0.42, and an accuracy of 0.89 (95% confidence interval, 0.86-0.91). The random forest model obtained higher sensitivity (0.96), specificity (1.00), and accuracy (0.96; 95% confidence interval, 0.95-0.98). Across 1,000 bootstrapped iterations, the model yielded a median sensitivity of 0.92 (interquartile range [IQR], 0.85-0.98), specificity of 1.00 (IQR, 0.88-1.00), accuracy of 0.93 (IQR, 0.85-0.97), and area under the curve of 0.96 (IQR, 0.93-0.98).

CONCLUSIONS

A novel machine learning-based screening model is highly sensitive, specific, and accurate in predicting CI candidacy. Bootstrapping confirmed that this approach is potentially generalizable with consistent results.