AI-FOX: Clinical results

The development of FOX has been documented in the scientific literature. However, almost all of the published clinical results refer to the previous rule-based generation. The Eargroup, the CI clinic led by Prof. Govaerts, has carefully analyzed their internal results with the current AI-FOX generation.

Tonal Audiometry

On average tone audiometric thresholds are 20 dB HL at octave frequencies from 250 to 4000 Hz with only very little variation. At all frequencies the P95 lies at 30 dB HL (PJ Govaerts, unpublished data).

Distribution of audiometric thresholds in all Eargroup’s Nucleus CI recipients assessed at an age of at least 6 years in 2015 or later.  Cases with cochlear anomalies were excluded. (PJ Govaerts, unpublished data).

Speech Audiometry

It has been shown that the average results (phoneme score on CVC open set speech audiometry) with AI-FOX are 20% better than 8 years ago, when all fitting was still done manually (Eargroup, unpublished results).

Average phoneme scores on open set monosyllable word lists at different presentation levels (40, 55, 70, 85 dBSPL) in all postlingual adults assessed in 2008 and 2016.  Similar results were obtained in a cohort of patients who obtained their CI before 2007 and who were assessed in the same two years 2008 and 2016 (Eargroup, unpublished results).

A similar result is illustrated in the graph below, taken from Meeuws et al., showing the improvement in speech in quiet scores, obtained in a cohort of experienced CI users coming back for an annual visit. In this session their maps were tuned with the current AI-FOX version, leading to an acute improvement in speech understanding by several percentages.

To go further

Meeuws M, et al.  Computer assisted CI fitting: is the learning capacity of the intelligent agent FOX beneficial for speech understanding? Cochlear Implants Intl. 2017; DOI:10.1080/14670100.2017.1325093