Scientists Develop 'E-Nose' That Could Diagnose Parkinson's Disease By Smelling Patient’s Skin

Scientists Develop 'E-Nose' That Could Diagnose Parkinson's Disease By Smelling Patient’s Skin

Currently, there's no cure for Parkinson's disease. But early diagnosis and treatment can lessen symptoms, improve one's quality of life, and prolong survival.

Written by Longjam Dineshwori |Updated : February 24, 2022 3:30 PM IST

Parkinson's disease (PD) is recognised as the second most common neurodegenerative disorder after Alzheimer's disease, with more than 10 million people worldwide estimated to be living with the condition. It is a lifelong condition which occurs when nerve cells in the brain don't produce enough of a brain chemical called dopamine. Among its many functions, dopamine helps regulate body movements. Parkinson's disease mainly affects the motor system and causes tremors, stiffness, and difficulty walking and maintaining your balance and coordination, as well as non-motor symptoms, including depression and dementia. Unfortunately, there is no specific test to diagnose this disorder. Neurologists review your medical history, signs and symptoms, and a neurological and physical examination for diagnosis of Parkinson's disease. The good news is - researchers have developed a portable AI-based device, dubbed as e-nose, that could someday diagnose the disease by smelling the patient's skin.

The new portable, artificially intelligent olfactory system, or "e-nose," could someday diagnose the disease in a doctor's office, the researchers stated in an article published in ACS Omega.

People withParkinson'sproduce specific body odors

Even though there's no cure for Parkinson's disease, early diagnosis and treatment can lessen symptoms, improve one's quality of life, and prolong survival. However, it is difficult to diagnose the disease in its early stage. In most cases, PD isn't identified until patients develop motor symptoms, and when they've already experienced irreversible neuron loss.

Also Read

More News

It was recently discovered that people with Parkinson's disease secrete more sebum (an oily, waxy substance produced by the skin's sebaceous glands), yeast, enzymes and hormones - the combination of which produce certain odors. Following this discovery, scientists around the world have been trying to build devices that could diagnose Parkinson's disease through odor compounds on the skin.

Some scientists have tried using gas chromatography (GC)-mass spectrometry to analyze odor compounds in the sebum of people with PD. But the instruments are bulky, slow and expensive.

So, Jun Liu, Xing Chen and colleagues started their study to develop a fast, easy to use, portable and inexpensive GC system to diagnose Parkinson's disease through smell, which would be suitable for point-of-care testing.

Finally, they came up with the e-nose by combining GC with a surface acoustic wave sensor -- which measures gaseous compounds through their interaction with a sound wave -- and machine learning algorithms.

E-nose could facilitate early diagnosis and treatment

To test the efficacy of e-nose, the scientists collected sebum samples from 31 PD patients and 32 healthy controls by swabbing their upper backs with gauze. Using the device, they analyzed volatile organic compounds emanating from the gauze and found three odor compounds (octanal, hexyl acetate and perillic aldehyde) significantly different between the two groups.

Further, they analyzed sebum from an additional 12 PD patients and 12 healthy controls, and confirmed that the device had an accuracy of 70.8 per cent in predicting PD.

While the model was 91.7 per cent sensitive in identifying true PD patients, but its specificity was only 50 per cent, which suggests a high rate of false positives. When machine learning algorithms were used to analyze the entire odor profile, the accuracy of diagnosis improved to 79.2 per cent, the researchers said.

The team said that they would be testing the e-nose on many more people to improve the accuracy of the models, before it is ready for the clinic. They also stressed the need to consider other factors such as race in their future study.