In the year In 1991, the world was shocked when she learned to be an actress. Michael J. Fox He was diagnosed with Parkinson’s disease.
He was just 29 years old and at the height of his Hollywood fame, a year after the release of the blockbuster Back to the Future III. This week, a documentary Still: Michael J. Fox movie It will be released. It features interviews with Fox, his friends, family and experts.
Parkinson’s is a debilitating neurological disease. Motor signs including slow movements, body tremors, decreased muscle strength and balance. Fox already has Broken His hands, elbows, face and hands fall from many.
It is not genetic, does not have a specific diagnosis and cannot be diagnosed before motor symptoms appear. The cause is still there. UnknownAlthough Fox is one of those who think Chemical exposure can play a central roleAssuming “genetics loads the gun and environment pulls the trigger”.
Research published today ACS Central Sciencewe have built an artificial intelligence (AI) tool that can predict Parkinson’s disease up to 15 years before clinical diagnosis based on analysis of blood chemicals with up to 96% accuracy.
While this AI tool showed promise for accurate early diagnosis, it also revealed chemicals strongly associated with accurate prediction.
More common than ever
Parkinson’s is global. Rapidly developing neurological diseases with 38 Australians Daily examination.
For people over the age of 50, Parkinson’s disease is more likely. Higher than many cancers including breast, colorectal, ovarian and pancreatic cancer.
as signs Depression, loss of smell and sleep problems It can predict clinical activity or cognitive symptoms for decades.
However, the prevalence of such symptoms in many other medical conditions may lead to the early signs of Parkinson’s disease being missed and the condition being treated incorrectly, contributing to increased hospitalizations and ineffective treatments.
Our research
At UNSW, we collaborated with experts at Boston University to develop an AI tool that analyzes mass spectrometry datasets (a Technique which detects chemicals) from blood samples.
For this study, we looked at the Spanish European Prospective Investigation into Cancer and Nutrition (EPIC) study involving more than 41,000 participants. About 90 of them developed Parkinson’s within 15 years.
What we used to train the AI model was a Data subset It included a random selection of 39 participants who later developed Parkinson’s disease. They were matched with 39 control participants. The AI tool was fed blood data from participants, all of whom were healthy at the time of donating blood. This means that the blood can present the first symptoms of the disease.
Drawing on blood data from the EPIC study, the AI tool was used to run 100 “experiments” and evaluate the accuracy of 100 different models for predicting Parkinson’s disease.
Overall, AI can diagnose Parkinson’s disease with up to 96% accuracy. The AI tool helps us to identify which chemicals or metabolites are associated with those who develop the disease later.
Key metabolites
Metabolites are chemicals produced or used during the breakdown of substances such as food, drugs, and other substances from environmental exposures.
Our bodies can contain thousands of metabolites and their concentrations can vary greatly between healthy people and those with disease.
Our research has identified a chemical, possibly a triterpenoid, as a key metabolite to prevent Parkinson’s disease. Triterpenoid levels in the blood of people with Parkinson’s disease have been found to be lower than those without.
Triterpenoids are known Neuroprotective agents It can be controlled Oxidative stress – a major factor involved in Parkinson’s disease – and prevents cell death in the brain. Like many foods Apples and tomatoes They are rich sources of triterpenoids.
Synthetic chemicals (A Polyfluorinated alkyl substance) has been associated with an increased risk of disease. This chemical was later found in large amounts in people who developed Parkinson’s.
Further research using different methods and looking at larger populations is needed to further confirm these results.
A heavy financial and personal burden.
Every year in Australia, the average person with Parkinson’s disease dies 14,000 dollars Out-of-pocket medical expenses.
The burden of living with the disease can be unbearable.
Fox admits the disease can be a “nightmare” and a “living hell,” but “Thankfully, optimism is sustainableHe said.
As researchers, we see hope that AI technologies can be used to improve patient quality of life and reduce healthcare costs by accurately diagnosing diseases.
We’re excited to have the research community test our AI tool, which it is. Available publicly..
This study was conducted with Mr Chonghua Xue and A/Prof Vijaya Kolachalama (Boston University).
Article written by Diana ZhangFulbright and Scientia PhD Scholar; UNSW Sydney And William Alexander DonaldAssociate Professor, ARC Future Fellow and UNSW Scientia Fellow, UNSW Sydney
This article was reprinted from The conversation Under a Creative Commons license. Read Original article.
