Development of a machine learning model for prognostic prediction of severe sudden sensorineural hearing loss with hyperbaric oxygen therapy.

What Researchers Did

Researchers developed and evaluated a machine learning model to predict recovery in 231 patients with severe sudden sensorineural hearing loss (SSNHL) treated with hyperbaric oxygen therapy (HBOT) in a single-center retrospective study.

What They Found

The custom model achieved 89.36% test accuracy and an AUC of 0.8716, outperforming several conventional methods. Key predictors included age, diabetes, dizziness, and HBOT exposure, with "≥10 HBOT sessions" showing high importance for prognostic relevance.

What This Means for Canadian Patients

This model could help Canadian clinicians predict recovery for patients with severe SSNHL, potentially guiding individualized treatment plans. The findings also suggest that sufficient cumulative hyperbaric oxygen therapy exposure may be prognostically relevant.

Canadian Relevance

There is no direct Canadian connection mentioned in this study.

Study Limitations

A limitation is that this was a single-center retrospective study, and the model does not infer causal treatment effects of HBOT.