Eavesdropping on Tinnitus Using MEG: Lessons Learned and Future Perspectives

Chronic tinnitus is associated with aging but not dementia

AIM

Aging is related to deterioration of bodily and neural functions, leading to various disorders and symptoms, including the development of dementia, hearing loss, or tinnitus. Understanding how these phenomena are intertwined and how aging affects those is crucial for prevention and the future development of interventions.

METHODS

We utilized the UK Biobank which includes a total of 502,382 participants between 40 and 70 years old. We used logistic regression models and cox proportional hazard models and compared hazard ratios.

RESULTS

The odds of reporting tinnitus in the older age group (i.e., older than 58 years) were increased by 53.6 % and a one decibel increase in the speech-reception thresholds enhanced the odds for tinnitus by 13.0 %. For our second analysis regarding hearing loss, the risk of dementia increased by 14.0 % with an increase by one decibel in the speech-reception threshold score. In terms of aging, each additional year increased the risk by 17.3 %. Tinnitus alone showed a significant influence with a hazard ratio of 52.1 %, however, when adding hearing loss, age and various covariates, the effect vanished.

CONCLUSION

Findings confirm that tinnitus is indeed related to aging, but presumably independent of the aging processes accompanying the development of dementia. This highlights the urge to further investigate the impact of aging on neural processes that are relevant for alterations in the auditory systems (e.g., leading to the development of tinnitus or hearing loss) as well as for increased vulnerability in terms of neurodegenerative diseases.

Tinnitus classification based on resting-state functional connectivity using a convolutional neural network architecture

OBJECTIVES

Many studies have investigated aberrant functional connectivity (FC) using resting-state functional MRI (rs-fMRI) in subjective tinnitus patients. However, no studies have verified the efficacy of resting-state FC as a diagnostic imaging marker. We established a convolutional neural network (CNN) model based on rs-fMRI FC to distinguish tinnitus patients from healthy controls, providing guidance and fast diagnostic tools for the clinical diagnosis of subjective tinnitus.

METHODS

A CNN architecture was trained on rs-fMRI data from 100 tinnitus patients and 100 healthy controls using an asymmetric convolutional layer. Additionally, a traditional machine learning model and a transfer learning model were included for comparison with the CNN, and each of the three models was tested on three different brain atlases.

RESULTS

Of the three models, the CNN model outperformed the other two models with the highest area under the curve, especially on the Dos_160 atlas (AUC = 0.944). Meanwhile, the model with the best classification performance highlights the crucial role of the default mode network, salience network, and sensorimotor network in distinguishing between normal controls and patients with subjective tinnitus.

CONCLUSION

Our CNN model could appropriately tackle the diagnosis of tinnitus patients using rs-fMRI and confirmed the diagnostic value of FC as measured by rs-fMRI.