Researchers Use AI to Predict Parkinson Disease Up to 7 Years

Since Parkinson disease (PD) progresses from the pre-motor stage to the disabling motor stage, a group of researchers sought to develop a method to intervene at the early/pre-motor stage and slow the neurodegenerative process. In a recent study, they developed a blood test using artificial intelligence (AI) to predict PD up to 7 years.

For the study, researchers used mass spectrometry-based proteomic phenotyping to identify a panel of blood biomarkers in 99 newly diagnosed patients with PD, including those with de novo PD (48 men, 50%, mean age 67 years), pre-motor individuals with isolated REM sleep behavior disorder (iRBD) (two cohorts: n = 18 and n = 54 longitudinally), and 36 healthy controls (20 men, 57%, mean age 64 years). In addition to this main cohort, the authors added further samples for validation that consisted of a heterogeneous group of 41 patients with other neurological diseases (OND), which included 29 men (71%, mean age 70 years) and 18 patients with video-polysomnography (vPSG)-confirmed iRBD (10 men, 56%, mean age 67 years). By using a panel of eight blood biomarkers identified in a machine-learning approach, the researchers we were able to differentiate between PD and HC with a specificity of 100%. They were also able to identify 79% of the iRBD patients up to 7 years before the development of either dementia with Lewy bodies (DLB) or motor PD.

“Our identified panel of biomarkers significantly advances neuronal synuclein disease (NSD) research by providing potential screening and detection markers for use in the earliest stages of NSD for subject identification/stratification for the upcoming prevention trials,” said the authors.

“In summary, instead of single biomarkers in a univariate approach, we have created a pipeline using a targeted proteomic test of a multiplexed panel of proteins, together with machine learning… Most importantly, this blood panel can, in the future, upon further validation help identify subjects at risk of developing PD/DLB and stratify them for upcoming prevention trials,” concluded the authors.

Reference

Hällqvist J, Bartl M, Dakna M, et al. Plasma proteomics identify biomarkers predicting Parkinson’s disease up to 7 years before symptom onset. Nat Commun. 2024;15(1):4759. doi: 10.1038/s41467-024-48961-3.