Predicting Cognition in Parkinson's - Another risk score

The development of tools to predict risk of neurological disease is an ever expanding field. In PREDICT the algorithm used to predict risk of Parkinson's disease was based on a meta-analysis of symptoms preceding a diagnosis of Parkinson's in both cohort and case-control studies. Here the authors take a slightly different approach to look at the development of dementia in patients with Parkinson's Disease and use only longitudinal cohort studies to both develop and test a risk prediction model.

We already know from smaller studies that, similar to alzheimer's, factors such as age and lower educational attainment are associated with development of cognitive impairment in Parkinson's but this study took a far more robust approach, using a huge data set, looking at the significance of 9 clinical and genetic biomarkers and then replicating their findings in a further large data set. They found that 7 markers were informative or valid for use in the model and of these, age at onset of Parkinson's disease was responsible for over half the variance, followed by cognitive score (MMSE) at baseline. The score generated was highly accurate for prediction of global cognitive decline and for dementia. As an example, of participants scoring in the highest quartile, 51.7% had developed dementia at 10 years compared to 1.1% in the lowest quartile.

Clearly this score captures many of the important factors predictive of dementia in Parkinson's and is likely to be helpful in risk stratifying; but it doesn't tell us everything. The focus on only 9 factors from the outset probably limits the predictive value of the model. Further exploratory work in such large cohorts will take us even further. 

https://www.ncbi.nlm.nih.gov/pubmed/28629879

Prediction of cognition in Parkinson's disease with a clinical-genetic score: a longitudinal analysis of nine cohorts.

Liu G, Locascio JJ, Corvol JC, Boot B, Liao Z, Page K, Franco D, Burke K, Jansen IE, Trisini-Lipsanopoulos A, Winder-Rhodes S, Tanner CM, Lang AE, Eberly S, Elbaz A, Brice A, Mangone G, Ravina B, Shoulson I, Cormier-Dequaire F, Heutink P, van Hilten JJ, Barker RA, Williams-Gray CH, Marinus J, Scherzer CR; HBS; CamPaIGN; PICNICS; PROPARK; PSG; DIGPD; PDBP.

BACKGROUND:

Cognitive decline is a debilitating manifestation of disease progression in Parkinson's disease. We aimed to develop a clinical-genetic score to predict global cognitive impairment in patients with the disease.

METHODS:

In this longitudinal analysis, we built a prediction algorithm for global cognitive impairment (defined as Mini Mental State Examination [MMSE] ≤25) using data from nine cohorts of patients with Parkinson's disease from North America and Europe assessed between 1986 and 2016. Candidate predictors of cognitive decline were selected through a backward eliminated Cox's proportional hazards analysis using the Akaike's information criterion. These were used to compute the multivariable predictor on the basis of data from six cohorts included in a discovery population. Independent replication was attained in patients from a further three independent longitudinal cohorts. The predictive score was rebuilt and retested in 10 000 training and test sets randomly generated from the entire study population.

FINDINGS:

3200 patients with Parkinson's disease who were longitudinally assessed with 27 022 study visits between 1986 and 2016 in nine cohorts from North America and Europe were assessed for eligibility. 235 patients with MMSE ≤25 at baseline and 135 whose first study visit occurred more than 12 years from disease onset were excluded. The discovery population comprised 1350 patients (after further exclusion of 334 with missing covariates) from six longitudinal cohorts with 5165 longitudinal visits over 12·8 years (median 2·8, IQR 1·6-4·6). Age at onset, baseline MMSE, years of education, motor exam score, sex, depression, and β-glucocerebrosidase (GBA) mutation status were included in the prediction model. The replication population comprised 1132 patients (further excluding 14 patients with missing covariates) from three longitudinal cohorts with 19 127 follow-up visits over 8·6 years (median 6·5, IQR 4·1-7·2). 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 (95% CI 0·82-0·90) and replication (95% CI 0·78-0·91) populations. Patients scoring in the highest quartile for cognitive risk score had an increased hazard for global cognitive impairment compared with those in the lowest quartile (hazard ratio 18·4 [95% CI 9·4-36·1]). Dementia or disabling cognitive impairment was predicted with an AUC of 0·88 (95% CI 0·79-0·94) and a negative predictive value of 0·92 (95% 0·88-0·95) at the predefined cutoff of 0·196. Performance was stable in 10 000 randomly resampled subsets.

INTERPRETATION:

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