Hereditary hearing loss (HL) is one of the most common sensory disorders worldwide, with an incidence of 1–2 per 1000 newborns [1]. In 2004 the World Health Organization reported that over 5% of the world population (cca. 360 million people) had a disabling hearing impediment greater than 40 decibels (measured average for 0.5, 1, 2, 4 kHz (dB)) [2]. Genetic factors account for more than 50% of cases, where the majority exhibit autosomal recessive (AR) inheritance (75–80%) followed by 20–25% autosomal dominant (AD) and 1–1.5% X-linked or of mitochondrial inheritance [3]. It is estimated that just over 200 genes are involved in the process of hearing, which comprises about 1% of all coding genes in the human genome [4].

About 70% of all congenital hereditary HL is non-syndromic (nsHL) [5]. Thus far, 59 autosomal dominant, 78 autosomal recessive and 6 X-linked loci have been identified with 36, 66, and 5 causative genes, respectively [4]. Furthermore, some of these HL genes have been associated with both recessive and dominant forms of HL. There are examples of digenic interactions that cause deafness [1], mitochondrial pathogenic variants as well as certain genetic-environmental interactions that cause HL.

The remaining 30% of HL cases are considered to be syndromic (sHL), wherein the patients exhibit clinical features in at least one other organ system. HL is a feature of between 300 and 400 different syndromes, in which hardness of hearing commonly represents a mild and/or inconsistent feature and many of these syndromes are extremely rare. Nonetheless, HL is also a frequent and/or consistent clinical feature in many syndromes such as Usher syndrome, Pendred syndrome, Waardenburg, Branchio-Oto-Renal and Jarvell, Lange-Nielsen syndromes [6].

This extreme genetic heterogeneity of hereditary nsHL and sHL can often present challenges in its clinical and genetic evaluation. Traditionally, genetic diagnosis of nsHL patients has been carried out for the most common genetic cause of recessive nsHL (the c.35delG variant of the GJB2 gene) using PCR or Sanger sequencing of the entire GJB2 gene. Pathogenic variants in this gene are responsible for an estimated 50% of all prelingual, nsHL cases and the carrier rate of the c.35delG variant in the Caucasian population is 1 in 33 [7]. However, considering the great overall number of possible genetic causes for HL, these two methods have proven to be inefficient, costly and very time consuming when dealing with cascade sequencing of coding regions in a large number of genes. Recently, with the advent of next generation sequencing (NGS) in medical molecular laboratories, high-throughput sequencing of a large set of HL-associated genes has become possible. Massively parallel sequencing of a large number of exons in a single experiment has increased the diagnostic yield and contributed to better characterization of known genes associated with HL [8,9].

The majority of studies published (reviewed in [10]) on the usage of NGS technologies for genetic testing of HL included only individuals with nsHL and have used panels with different types and numbers of genes, while data on the utility of exome sequencing and the utility of NGS technologies in individuals with sHL are sparse.

In the present work we used exome sequencing to seek a genetic cause in a group of 56 patients with either syndromic HL or non-syndromic non-GJB2 HL. This work illustrates genetic heterogeneity of HL and added value of exome sequencing approach in patients with complex phenotypes.

We conducted comprehensive gene analysis using clinical exome sequencing in a group of probands with non-syndromic non-GJB2 HL and in a group with syndromic HL from the Slovene and Bosnian populations. The strength of our approach is the inclusion of individuals with syndromic HL and the usage of a clinical exome instead of targeted panels, which enabled us to identify not only the cause of non-syndromic and syndromic HL phenotypes but also to decipher whether HL is part of a syndrome or a separate clinical feature.

There are three important findings from our study.

First, we found the genetic cause for HL in 15 of the 49 probands evaluated (30%). These included individuals with nsHL and individuals with apparently sHL. In the subgroup of nsHL, the diagnostic yield reached 21.8% (7/32). It should be noted, that this group of patients was prescreened for GJB2 mutations, which account for up to 50% of all prelingual, non-syndromic HL cases in Caucasian populations [7][22]. Our diagnostic yield coincides well with results published in 2016 by Sloan-Heggen et al.[33], where they reported the analysis of the largest nsHL patient cohort to date with 1119 probands of mixed ethnicity, almost half of whom were of Caucasian origin. Their non-GJB2 diagnostic yield reached 17.4%, which is comparable to the diagnostic yield in our nsHL study cohort. While several studies evaluated the diagnostic yield of non-syndromic HL [10], implementation of NGS technologies in syndromic HL has not been systematically studied. In the present group of 17 individuals with apparently syndromic HL, according to clinical examination and medical history, the disease-causing variant for HL was found in 8 individuals (47%). In a recent study, where children with syndromic HL had undergone genetic testing with a disease-targeted NGS panel for syndromic and non-syndromic HL genes, a diagnostic yield of 58.3% (28/48) was achieved, however the diagnosis of syndromic HL was not pinpointed solely on a clinical bases but determined after the results of genetic testing were known [34].

Second, clinical exome sequencing proved to be a useful tool in distinguishing between nsHL, sHL and HL as a separate feature of a complex phenotype.

Usually, when probands are found to have HL as the only presenting feature, a mutation in nsHL genes is suspected. However, in some syndromes special tests are required to detect secondary features or the penetrance of the secondary features is either incomplete or age dependent. These may lead to a false clinical categorization of patients with sHL into a group of apparently nsHL patients. In such cases the identification of the cause of HL would not be possible using disease-targeted panels for nsHL alone while clinical exome sequencing enables screening of non-syndromic and syndromic genes. One of the most common syndromic forms of HL, Usher syndrome, presents as a nsHL mimic early in life [33] as the onset of the secondary symptom (retinitis pigmentosa) does not appear until puberty. Two probands in the present cohort were found to have pathogenic USH2A variants; the older one (P852) presented with HL with retinal changes, while HL was the only clinical feature in the younger one (P584). Genetic testing enabled an early diagnosis of Usher syndrome, which is important in order to implement appropriate visual rehabilitation and to optimize learning and communication strategies. Waardenburg syndrome type 2A (OMIM193510), caused by pathogenic variants in the MITF gene, can also present as non-syndromic SNHL or as sHL with heterochromia iridum being the most common secondary feature. Two present probands had the same pathogenic variant in MITF. One presented as HL (P2091) and the other as HL with heterochromia (P045).

In patients with HL accompanied by clinical features in at least one other organ system, a syndromic diagnosis is suspected. As such, mutations of non-syndromic genes are often neglected during genetic testing. The clinical distinction between HL as a feature of a syndrome and HL as a separate feature of a complex phenotype can be difficult. The clinical exome sequencing approach can yield information concerning causes of nsHL, sHL, and a non-HL phenotype in the case of complex phenotypes. cES can aid in deciphering cases of syndromic HL (P584) and cases with complex phenotypes where HL is a separate feature (P144, P314, P555). As an example, proband P144, who suffered from mild high frequency HL and presented with clinical features of congenital myopathy, was found to have a novel, missense variant in a hotspot domain of the RYR1 gene, explaining his primary diagnosis, but not the cause of HL. Proband P314, who was born after a twin pregnancy and presented with moderately severe HL, a complex clinical picture of major abnormalities (microphtalmia, solitary kidney, omphalocoele) and normal development, indicating a suspicion of a syndromic diagnosis. She was found to have a compound heterozygous variant in GJB2, explaining her HL, while the cause of the congenital anomalies remained unknown. Proband P555, with a family history of suspected Usher syndrome, was found to have the most common pathogenic homozygous variant in GJB2, while the cause of familial retinitis pigmentosa remained unknown as the father declined further testing. In families with complex pedigrees with several members presenting with HL, the application of trio analysis enabled us to detect that members from a single family had different genetic causes for HL (P453).

Lastly, 14 different non-GJB2 HL disease causing variants in 10 genes (CHD7, HDAC8, MITF, NEFL, OTOF, SF3B4, SLC26A4, TECTA, TMPRSS3, and USH2A) were found among 13 patients confirming the extreme genetic heterogeneity of hereditary HL. Half (50%; 7/14) of the HL disease causing variants were novel and unique to a family, with only two variants in the USH2A and MITF genes, detected in two probands. Variant c.11864G>A in USH2A is one of the two most common pathogenic variants found in patients with Usher syndrome type 2A in Europe [28]. The distribution of the variant was shown to differ greatly among EU countries, with the lowest proportion found in France (4.5%) and the highest in Slovenia (82.5%) [28]. This coincides well with our findings of both patients with Usher syndrome having the homozygous c.11864G>A variant. Contrary to the small range of USH2A pathogenic variants, MITF pathogenic variants causing Waardenburg syndrome type 2 are diverse and usually private, with only a small number of exceptions [18], [35]. One of them is a pathogenic variant c.943C>T (p.Arg315*), which was detected in two unrelated families in our study, and has already been reported in three families originating from Northern Europe [16], India [17], and Togo [18].

The frequency of variants in some causative genes was high, with nearly half (6 of 13, 46%) of the non-GJB2 causes attributable to four genes (SLC26A4, USH2A, TECTA, and OTOF). In the study by Sloan-Heggen et al. (2016) [33] these four genes were among the top 11 most common, non-GJB2 identified genetic causes for hereditary HL (STRC, SLC26A4, TECTA, MYO15A, MYO7A, USH2A, CDH23, ADCRV1, TMC1, PCDH15 and OTOF) that made up 67% of all successful diagnoses.

In summary, the clinical exome sequencing approach allowed us to comprehensively address the genetic heterogeneity of HL, to detect clinically unrecognized HL syndromes, and to distinguish between non-syndromic HL, syndromic HL, and HL as a separate feature of a complex phenotype.