Cochlear Implant Candidacy Support Tool Using Conjunctive Consolidation

Area of Science:

• Audiology
• Otolaryngology
• Biomedical Engineering

Background:

• Cochlear implant (CI) utilization remains suboptimal despite proven benefits.
• Current screening relies on binary classification, hindering personalized patient counseling and shared decision-making.

Purpose of the Study:

• To develop a risk stratification system for CI candidacy using routine audiometric data.
• To enable individualized estimates of CI candidacy likelihood and improve shared decision-making.

Main Methods:

• Retrospective cohort study at a tertiary academic center.
• Developed a 4-stage audiometric severity classification combining pure tone average (PTA) and word recognition score (WRS) using consonant-nucleus-consonant (CNC) criteria.
• Assessed discriminative power using the C statistic; secondary analysis used AzBio sentence scores.

Main Results:

• 782 of 1312 (59.6%) adults met CI candidacy criteria (CNC ≤50%).
• The 4-stage system demonstrated a clear gradient of candidacy likelihood (2.8%–88.5%) with strong discrimination (C=0.83).
• Similar strong discrimination was observed using AzBio scores (C=0.80); demographic factors did not improve model performance.

Conclusions:

• Routine audiometric data can effectively stratify patients by likelihood of cochlear implant candidacy.
• The 4-level classification system provides a simple, intuitive method for estimating candidacy probability.
• This system facilitates personalized, data-driven decision-making beyond binary screening.