Can Cognitive Decline Be Predicted 10 Years Before Parkinson Onset?

A newly developed algorithm can predict cognitive impairment within 10 years of the onset of Parkinson disease, according to a recent analysis. The algorithm may be able to test for future cognitive health or impairment in patients with the condition.

Cognitive decline is a debilitating manifestation of disease progression in Parkinson disease. In order to better predict cognitive decline in patients with Parkinson disease, the researchers built a prediction algorithm for global cognitive impairment, defined as a Mini Mental State Examination (MMSE) score of 25 or lower.
______________________________________________________________________________________________________

RELATED CONTENT
Diabetes Drug Could Help Treat Parkinson Disease
How Do Statins Affect Parkinson Disease Risk?
______________________________________________________________________________________________________

To build the algorithm, the researchers assessed 3200 patients with Parkinson in 9 cohorts over 27,022 study visits in North America and Europe from 1986 to 2016. The researchers also evaluated a discovery population of 1350 patients from 6 cohorts with a total of 5165 longitudinal visits over 12.8 years. Furthermore, the researchers assessed a replication population of 1132 patients from 3 cohorts with 19,127 follow-up visits over 8.6 years

The researchers used a backward eliminated Cox’s proportional hazards analysis using the Akaike’s information criterion to determine candidate predictors of cognitive decline. These criteria were then used to calculate multivariable predictors based on data from 6 cohorts in the discovery population. The predictive score was rebuilt and retested in 10,000 training and test sets that were randomly generated from the whole study population.

Age at onset, baseline MMSE, years of education, motor examination score, sex, depression, and β-glucocerebrosidase (GBA) mutation status were included in the prediction model.

Results indicated that the cognitive risk score predicted cognitive impairment within 10 years of disease onset with an area under the curve (AUC) of more than 0.85 in both the discovery and replication populations. An increased risk for global cognitive impairment was observed among patients scoring in the highest quartile for cognitive risk score, compared with those in the lowest quartile. Dementia or disabling cognitive impairment was predicted with an AUC of 0.88 and a negative predictive value of 0.92 at the predefined cutoff of 0.196.

The researchers noted that the algorithm’s performance was stable in 10,000 randomly resampled subsets.

“Our predictive algorithm provides a potential test for future cognitive health or impairment in patients with Parkinson's disease,” the researchers concluded. “This model could improve trials of cognitive interventions and inform on prognosis.”

—Christina Vogt

Reference:

Liu G, Locascio JJ, Corvol JC, et al. Prediction of cognition in Parkinson’s disease with a clinical-genetic score: a longitudinal analysis of nine cohorts. Lancet Neurol. 2017;16(8):620-629. doi:10.1016/S1474-4422(17)30122-9.