Lost to follow up: Exploring patients who initially fail cochlear implant evaluation

Postoperative optimization of cochlear implantation for single sided deafness and asymmetric hearing loss: a systematic review

OBJECTIVE

Identify and evaluate the effectiveness of methods for improving postoperative cochlear implant (CI) hearing performance in subjects with single-sided deafness (SSD) and asymmetric hearing loss (AHL).

DATA SOURCES

Embase, PubMed, Scopus.

REVIEW METHODS

Systematic review and narrative synthesis. English language studies of adult CI recipients with SSD and AHL reporting a postoperative intervention and comparative audiometric data pertaining to speech in noise, speech in quiet and sound localization were included.

RESULTS

32 studies met criteria for full text review and 6 (n = 81) met final inclusion criteria. Interventions were categorized as: formal auditory training, programming techniques, or hardware optimization. Formal auditory training (n = 10) found no objective improvement in hearing outcomes. Experimental CI maps did not improve audiologic outcomes (n = 9). Programed CI signal delays to improve synchronization demonstrated improved sound localization (n = 12). Hardware optimization, including multidirectional (n = 29) and remote (n = 11) microphones, improved sound localization and speech in noise, respectively.

CONCLUSION

Few studies meeting inclusion criteria and small sample sizes highlight the need for further study. Formal auditory training did not appear to improve hearing outcomes. Programming techniques, such as CI signal delay, and hardware optimization, such as multidirectional and remote microphones, show promise to improve outcomes for SSD and AHL CI users.

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.

A Five-Year Update on the Profile of Adults Undergoing Cochlear Implant Evaluation and Surgery-Are We Doing Better?

OBJECTIVE

To characterize the influence of expanding indications on the profile of adults undergoing cochlear implantation (CI) at a high-volume CI center.

STUDY DESIGN

Retrospective review.

SETTING

Tertiary referral center.

PATIENTS

774 adults undergoing CI evaluation from August 2015 to August 2020.

MAIN OUTCOME MEASURES

Demographics; audiometry; speech recognition; speech, spatial, and qualities of hearing scale (SSQ-12).

RESULTS

Of 745 (96.3%) patients qualifying for implantation, 642 (86.6%) pursued surgery. Median age at evaluation was 69 years; 56.3% were men; 88.2% were Caucasian. Median distance to our center was 95 miles. The majority (51.8%) had public insurance (Medicare, Medicaid), followed by private (47.8%) and military (0.4%). Mean PTA, CNC, and AzBio in quiet and noise for the ear to be implanted were 85.2 dB HL, 15.0%, and 19.2% and 3.5%, respectively. Hybrid/EAS criteria were met by 138 (18.5%) CI candidates, and 436 (77.0%) unilateral CI recipients had aidable contralateral hearing for bimodal hearing configurations. Younger age (odds ratio [OR], 0.96; 95% confidence interval, 0.93-0.99) and non-Caucasian race (OR, 6.95; 95% confidence interval, 3.22-14.98) predicted candidacy. Likelihood of surgery increased for Caucasian (OR, 8.08; 95% confidence interval, 4.85-13.47) and married (OR, 2.28; 95% confidence interval, 1.50-3.47) patients and decreased for those with public insurance (OR, 0.45; 95% confidence interval, 0.29-0.69). A lower SSQ-12 score predicted both candidacy and surgery.

CONCLUSION

Despite expansions in criteria, speech understanding remained extremely low at CI evaluation. Younger age and non-Caucasian race predicted candidacy, and Caucasian, married patients with private insurance and lower SSQ scores were more likely to pursue surgery.

External Validation of Cochlear Implant Screening Tools Demonstrates Modest Generalizability

OBJECTIVE

To assess the clinical application of five recently published cochlear implant (CI) candidacy evaluation (CICE) referral screening tools through external validation.

STUDY DESIGN

Retrospective cohort study.

SETTING

Tertiary otology/neurotology practice.

PATIENTS

Adults who underwent CICE between December 2020 and September 2021.

INTERVENTIONS

CICE referral screening tools versus CI candidacy criteria.

MAIN OUTCOME MEASURES

CICE screening tool performance, based on the ability to identify patients who met the CI candidacy criteria, was evaluated. CI candidacy criteria were defined as best-aided AzBio sentences at +10 signal-to-noise ratio and either 60% or less accuracy to reflect traditional criteria used in clinical settings or 40% or less accuracy (only patients 65 years or older) to reflect Medicare-eligible criteria.

RESULTS

Screening criteria of proposed CICE referral tools vary widely across pure-tone average and word recognition scores. When screened by traditional criteria, the sensitivities and specificities of these referral tools varied from 40 to 77% and from 22 to 86%, respectively. When screened by Medicare-eligible criteria, sensitivities and specificities varied from 41 to 81% and from 24 to 91%, respectively. The screening tool proposed by Zwolan et al. ( Otol Neurotol 2020;41(7):895-900) demonstrated the best overall performance for traditional (Youden's J , 0.37; sensitivity, 62%; specificity, 75%) and Medicare-eligible patients (Youden's J , 0.44; sensitivity, 66%; specificity, 78%). All screening tools performed worse on the validation cohort compared with their respective development cohorts.

CONCLUSIONS

Current tools for determining CICE referral have diverse screening criteria. These combinations of pure-tone average and word recognition score are modestly successful at identifying CI candidates.