Tackling hidden hearing loss with digital twins
Almost 60 million Europeans live with hearing loss, which becomes more prevalent with age. Typically this is diagnosed with a test that identifies the quietest tones that can be detected at different pitches. Yet even those who score normally may experience difficulty understanding speech in noisy environments such as crowded restaurants. This ‘hidden hearing loss’ is thought to be driven by damage to the connection between the hair cells and the hearing nerve, known as cochlear synaptopathy (CS). “In 2009, researchers at Harvard found that the first aspect of hearing loss is not losing hair cells in the inner ear, but rather a decrease in the number of synapses,” explains EarDiTech(opens in new window) project coordinator Sarah Verhulst, from Ghent University(opens in new window) in Belgium. “This means that the hair cells may still be intact, but the signals that they send to the brain are not as clear as they should be.”
Non-invasive diagnostic CS test
There is currently no clinical diagnosis for CS and no treatment. To address this, Verhulst set out to find ways of better diagnosing this condition. Prior to the EarDiTech project, her team had successfully built the CochSyn test, a non-invasive prototype diagnostic to identify CS. It consists of a digital signal processing model of the auditory system – a digital twin in effect – that replicates normal hearing function in silico. By tweaking this model to make it hearing impaired, the team was able to find a specific sound that reveals synapse function. “This specific sound is very good at driving the available synapses at the same time,” says Verhulst. “When we play that sound, EEG responses (recordings of the brain’s electrical activity) are very large when there are lots of functional synapses. As people start to lose synapses, the EEG signal also starts to decrease.”
Applicability in real-world clinical contexts
The EarDiTech project builds on earlier work funded by the European Research Council(opens in new window) through the CochSyn project. Supported by the European Innovation Council(opens in new window), the EarDiTech project enabled Verhulst and her team to take this diagnostic test out of the lab and into clinical settings, supporting the EU’s strategy to empower people and businesses with a new generation of digital technologies(opens in new window) with human-centric artificial intelligence(opens in new window). Clinical trials provided valuable evidence of patient benefits, as well as the applicability of the test in real-world clinical contexts. “These medical trials enabled us to gather results and build a strong business case,” she notes. Results have been published and the sound stimulus patented. Next steps include establishing a spin-off company to bring this diagnostic innovation to market. In addition to diagnostics, EarDiTech also wanted to bring forward solutions to improve patient lives. “The aim here was to not only diagnose, but to actively help people who have hidden hearing loss to hear better,” adds Verhulst. Digital models were used to represent patients and tasked with processing speech using advanced machine learning. This created unique individualised audio processing algorithms. These algorithms will eventually be used in personalised next-generation hearing devices to individually compensate for CS. Next steps include establishing collaborations with hardware experts and testing the technology in the high-performance world of hearable devices. “We are currently having conversations with partners in the hearing aid and audio chip industry,” says Verhulst. “Hopefully we can work towards a licensing strategy to get this innovation to market.”