Earwax Becomes Weapon Against Parkinson's: New Test Has 94% Accuracy

Scientists have developed an innovative method that can help identify Parkinson's disease early on by analyzing earwax. They discovered four substances in the wax that are different in people with the disease. With the help of artificial intelligence, the system was able to correctly identify 94% of cases. This technique may, in the future, allow for simpler, cheaper and faster diagnosis, helping in the early treatment of Parkinson's.

Parkinson's disease (PD) is a degenerative neurological disorder that affects millions of people around the world. It occurs when brain cells responsible for the production of dopamine, a neurotransmitter essential for controlling movement, begin to die progressively.

The most well-known symptoms include tremors, muscle stiffness and slowness of movement, but the disease can also affect mood, sleep and memory.

Unfortunately, most treatments available today only alleviate symptoms or slow the progression of the disease, without offering a cure. Therefore, early diagnosis is considered essential: the earlier the disease is detected, the greater the chances that treatment will help preserve the patient's quality of life.

However, current tools for diagnosing Parkinson’s, such as imaging tests and clinical assessments, are often expensive, complex and, in some cases, subjective.

With the goal of developing simpler, more accessible ways to identify Parkinson’s early on, scientists have been looking for clues in unexpected places, like earwax. That’s right: the recent study we’re presenting investigated whether secretions from the ear canal, known as earwax, could contain chemical signals that indicate the presence of the disease.

The idea arose because earwax is made up primarily of sebum, an oily substance produced by the skin. Previous research has shown that the sebum of people with Parkinson’s releases different compounds than the sebum of people without the disease.

These compounds, called volatile organic compounds (or VOCs), can change due to neuronal degeneration, inflammation, and oxidative stress caused by Parkinson’s. Because earwax is protected from environmental factors like pollution and humidity, it proved to be a more reliable material for analysis than sebum from skin exposed to the air.

To test this hypothesis, the researchers collected earwax samples from 209 volunteers, 108 of whom had been diagnosed with Parkinson’s and 101 of whom did not have the disease. The samples were analyzed using an advanced technique called gas chromatography coupled with mass spectrometry, which allows the substances present in the wax to be accurately identified.

The study found four compounds that were present in different concentrations in the earwax of people with Parkinson’s compared to people without the disease: ethylbenzene, 4-ethyltoluene, pentanal and 2-pentadecyl-1,3-dioxolane. These compounds were highlighted as potential biomarkers, or chemical signals that could indicate the presence of the disease.

To turn this discovery into a practical tool, the scientists created an artificial intelligence-based screening system. They fed data from the compounds they found into a computer program and trained the system to distinguish between earwax samples from Parkinson’s patients and healthy people.

Gas chromatography machine

The result was a model capable of correctly identifying the disease in 94% of the cases tested, a very high rate. The method combines gas-sensitive sensors with neural network technology (a type of artificial intelligence that learns from examples) and could, in the future, be used in doctors' offices as a fast, cheap and non-invasive tool for screening Parkinson's.

For now, this new technique is still in the early stages of research, having been tested in a single center in China. The authors of the study themselves acknowledge that more experiments need to be carried out in different regions, involving people from different ethnic groups and at different stages of the disease, before the method can be applied in clinical practice on a large scale.

Even so, the work paves the way for new possibilities for early diagnosis, which could help doctors intervene earlier and, therefore, offer more effective treatments for Parkinson's patients.

Comparison of typical differential frequency signals in biomarker detection between patients with and without Parkinson’s.

READ MORE:

An Artificial Intelligence Olfactory-Based Diagnostic Model for Parkinson’s Disease Using Volatile Organic Compounds from Ear Canal Secretions

Xing Chen, Yi Li, Chenying Pan, Shenda Weng, Xiaoya Xie, Bangjie Zhou, Hao Dong, and Danhua Zhu

Analytical Chemistry. May 28, 2025

https://doi.org/10.1021/acs.analchem.5c00908

Abstract: 

Parkinson’s Disease (PD), a frequently diagnosed neurodegenerative condition, poses a major global challenge. Early diagnosis and intervention are crucial for PD treatment. This study proposes a diagnostic model for PD that analyzes volatile organic compounds (VOCs) from ear canal secretions (ECS). Using gas chromatography–mass spectrometry (GC-MS) to examine ECS samples from patients, four VOC components (ethylbenzene, 4-ethyltoluene, pentanal, and 2-pentadecyl-1,3-dioxolane) were identified as biomarkers with statistically significant differences between PD and non-PD patients. Diagnostic models based on these VOC components demonstrate strong capability in identifying and classifying PD patients. To enhance the accuracy and efficiency of the PD diagnostic model, this study introduces a protocol for extracting features from chromatographic data. By integrating gas chromatography–surface acoustic wave sensors (GC-SAW) with a convolutional neural network (CNN) model, the system achieves an accuracy of up to 94.4%. Further enhancements to the diagnostic model could pave the way for a promising new PD diagnostic solution and the clinical use of a bedside PD diagnostic device.