Integrating audiological datasets via federated merging of Auditory Profiles

TL;DR

This paper presents a method to merge audiological patient profiles from multiple datasets using similarity measures, enhancing the understanding of hearing loss patterns while maintaining clinical relevance.

Contribution

It introduces a novel AP merging pipeline that combines profiles from different datasets based on feature similarity, improving population analysis.

Findings

Merged APs provide distinct, detailed patient profiles.

Classification performance is satisfactory across combined profiles.

Best results achieved with combined audiological measures.

Abstract

Audiological datasets contain valuable knowledge about hearing loss in patients, which can be uncovered using data-driven, federated learning techniques. Our previous approach summarized patient information from one audiological dataset into distinct Auditory Profiles (APs). To obtain a better estimate of the audiological patient population, however, patient patterns must be analyzed across multiple, separated datasets, and finally, be integrated into a combined set of APs. This study aimed at extending the existing profile generation pipeline with an AP merging step, enabling the combination of APs from different datasets based on their similarity across audiological measures. The 13 previously generated APs (NA=595) were merged with 31 newly generated APs from a second dataset (NB=1272) using a similarity score derived from the overlapping densities of common features across the two datasets. To ensure clinical applicability, random forest models were created for various scenarios, encompassing different combinations of audiological measures. A new set with 13 combined APs is proposed, providing separable profiles, which still capture detailed patient information from various test outcome combinations. The classification performance across these profiles is satisfactory. The best performance was achieved using a combination of loudness scaling, audiogram and speech test information, while single measures performed worst. The enhanced profile generation pipeline demonstrates the feasibility of combining APs across datasets, which should generalize to all datasets and could lead to an interpretable global profile set in the future. The classification models maintain clinical applicability.