Algorithm IDs symptoms that increase future risk of Parkinson’s

Algorithm spots those who are more likely to develop motor problems years later

Marisa Wexler, MS avatar

by Marisa Wexler, MS |

Share this article:

Share article via email
A roll of the dice illustrates the risk of developing disease.

An algorithm can accurately identify people who are at increased risk of developing Parkinson’s-like motor problems in coming years, a new study shows.

The study, “The Emergence and Progression of Motor Dysfunction in Individuals at Risk of Parkinson’s Disease,” was published in Movement Disorders.

The causes of Parkinson’s disease remain poorly understood, but researchers are developing better methods for predicting the risk of developing the disease. PREDICT-PD is a research project funded by Parkinson’s UK that aims to test and refine an algorithm to predict Parkinson’s risk.

Recommended Reading
A person is shown being given a vaccination.

Vaccine trial for early Parkinson’s meets primary objectives

In this study, researchers in the United Kingdom evaluated long-term outcomes for 128 people participating in PREDICT-PD. All of these participants underwent an initial evaluation in 2012. At that time, they all were more than 60 years old, but did not have a diagnosis of Parkinson’s. Based on the algorithm used in the study, 33 of the patients were rated as high-risk for Parkinson’s, while the other 95 were low-risk.

Participants then completed a second assessment six years later. By that time, two of them had received a formal diagnosis of Parkinson’s; both were in the high-risk group.

Given that very few patients were formally diagnosed, the researchers assessed rates of sub-threshold parkinsonism — meaning patients showed some Parkinson’s-like symptoms, but not enough to facilitate a formal diagnosis.

The proportion of patients with sub-threshold parkinsonism was higher in the high-risk group compared to the low-risk group (18.2% vs. 7.4%). This difference did not reach statistical significance in the initial analysis. However, when the researchers conducted a follow-up analysis that also included data collected in two other large studies, results suggested that patients in the high-risk group were more than twice as likely to develop sub-threshold parkinsonism.

Parkinson’s-like symptoms were assessed using part three of the Unified Parkinson’s Disease Rating Scale (UPDRS). In the high-risk group, nearly a third (30.3%) of patients experienced an increase of at least five points on this scale, indicating more severe problems after six years of follow-up. By comparison, only 12.5% of patients in the low-risk group had such an increase.

Significant increases

Analyses of individual parts of the UPDRS score showed that patients in the high-risk group had significantly higher rates of new-onset motor problems like slow movement (57.6% vs 28.4%) and action tremor (75.7% vs. 46.3%). Statistical models indicated that patients in the high-risk group were significantly more likely to develop these issues, especially for slow movement, known as bradykinesia.

“Our algorithm seems to be able to estimate the occurrence of motor disturbances in the future, in particular [sub-threshold parkinsonism] and bradykinesia,” the researchers wrote.

The team noted this study is limited by its use of only two assessments six years apart, which makes it hard to say with certainty how motor function trends changed over time.

They also highlighted that broadly classifying patients as either high or low risk is likely too simplistic, and refinement of the algorithm is needed to more granularly understand the risk of Parkinson’s for individual patients.