Table 2 Qualitative comparison between the different clusters identified in the Royal National ear, nose and throat (RNENT) and Massachusetts eye and ear (MEE) datasets. Clusters with similar audiogram profiles are described as overlapping. Audiogram profiles with no clear counterpart in the other dataset are described as not overlapping. M is the prefix used to identify the different clusters in the MEE dataset.

From: Identification of sensorineural hearing loss subtypes using unsupervised machine learning and assessment of their replicability