Harnessing the Power of Artificial Intelligence in Otolaryngology and the Communication Sciences

Use of artificial intelligence (AI) is a burgeoning field in otolaryngology and the communication sciences. A virtual symposium on the topic was convened from Duke University on October 26, 2020, and was attended by more than 170 participants worldwide. This review presents summaries of all but one of the talks presented during the symposium; recordings of all the talks, along with the discussions for the talks, are available at https://www.youtube.com/watch?v=ktfewrXvEFg and https://www.youtube.com/watch?v=-gQ5qX2v3rg . Each of the summaries is about 2500 words in length and each summary includes two figures. This level of detail far exceeds the brief summaries presented in traditional reviews and thus provides a more-informed glimpse into the power and diversity of current AI applications in otolaryngology and the communication sciences and how to harness that power for future applications.

Radiological and surgical aspects of round window visibility during cochlear implantation: a retrospective analysis

Purpose

The round window approach has become the most preferred option for cochlear implant (CI) insertion, however, sometimes it may not be possible due to the (in)visibility of the round window membrane (RWM). We addressed the prevalence, consequences and indicators of difficult detection of the RWM in cochlear implant surgery.

Methods

This study retrospectively analysed the operative reports and preoperative high resolution axial-computed tomography (CT) scans of a consecutive cohort of patients who underwent a CI insertion. The main outcomes were surgical outcomes of the RW approach, and assessment of radiological markers.

Results

The operative reports showed that RWM insertion was feasible in 151 out of 153 patients. In 18% of the patients the RWM was difficult to visualize. All these patients had at least one intraoperative event. The chorda tympani nerve (CTN) or posterior canal wall was affected in 8% of the 153 patients and the fallopian canal in 6%. These patients had a facial-chorda tympani nerve distance on the CT scan that was considerably smaller than normal patients (1.5 mm vs 2.3 mm). In addition, a prediction line towards the anterolateral side of the RWM was found to be more prevalent in these patients’ CT scans (sensitivity 81%, specificity 63%).

Conclusion

The RW approach is feasible in almost all patients undergoing CI surgery. Difficult visualisation of the RWM seems to lead to at least one intraoperative event. Radiological measures showed that these patients had a smaller facial recess and a more anteriorly placed facial nerve, which can be used to better plan a safe insertion approach.