Parkinson’s disease (PD) is a progressive disease of the nervous system that affects movement, causing tremors, stiffness, difficulty walking, balance and coordination. PD is the second most common chronic progressive neurodegenerative disease in the elderly after Alzheimer’s disease, affecting 1% to 2% of all individuals aged 65 and over worldwide. . Currently, there are no blood or laboratory tests to diagnose nonhereditary PD cases, and the diagnosis is based primarily on medical history and neurological examination. Recently, machine learning (ML) has been used to analyze a patient’s medical and laboratory history and predict the probability of PD. If ML technology develops the ability to predict her PD with reasonable accuracy before symptoms develop, it would be a major advance for early diagnosis and management of PD.
According to a study conducted by J Diana Zhang et al. ACS Central Scientific Journal In May 2023, ML tools will be able to predict PD up to 15 years before clinical diagnosis by analyzing chemicals in blood. The researchers also claimed to be able to predict PD with up to 96% accuracy. The study, a collaboration between Boston University and the University of Sydney, analyzed blood samples from 39 healthy individuals from the European Prospective Cancer and Nutrition Registry in Spain. They used a tool called CRANK-MS (Classification and Ranking Analysis Using Neural Network Generated Knowledge from Mass Spectrometry) to analyze detailed information about the metabolites present in the blood. Analysis of changes in PD-specific biomarkers such as triterpenoids, diacylglycerols, and polyfluoroalkyls prior to clinical PD diagnosis has enabled early prediction of disease.
PD is a significant health burden, with GlobalData epidemiologists now prevalent in more than 2.4 million people across seven major drug markets (7MM: US, France, Germany, Italy, Spain, UK, Japan) I’m assuming you’ve been diagnosed with Combining 7MM, prevalent cases diagnosed with PD are expected to rise to 2.9 million cases in 2029 with an annual growth rate of 2.30%. Based on historical data analyzed by GlobalData, the prevalence of PD has remained unchanged over the past decade, so the increase in the number of cases can be attributed to projected population growth.
PD is difficult to diagnose early, especially in the preclinical stage. The findings of this study are important because early diagnosis using ML tools can lead to better treatments and improve patients’ quality of life. Further studies on large populations are needed to validate the results of this ML study.
