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

Ganqiang Liu, Joseph J. Locascio, Jean Christophe Corvol, Brendon Boot, Zhixiang Liao, Kara Page, Daly Franco, Kyle Burke, Iris E. Jansen, Ana Trisini-Lipsanopoulos, Sophie Winder-Rhodes, Caroline M. Tanner, Anthony E. Lang, Shirley Eberly, Alexis Elbaz, Alexis Brice, Graziella Mangone, Bernard Ravina, Ira Shoulson, Florence Cormier-Dequaire & 6 others Peter Heutink, Jacobus J. van Hilten, Roger A. Barker, Caroline H. Williams-Gray, Johan Marinus, Clemens R. Scherzer

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

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. Funding National Institutes of Health, US Department of Defense.

Original languageEnglish
Pages (from-to)620-629
Number of pages10
JournalThe Lancet Neurology
Volume16
Issue number8
DOIs
Publication statusPublished - 1 Aug 2017

Cite this

Liu, Ganqiang ; Locascio, Joseph J. ; Corvol, Jean Christophe ; Boot, Brendon ; Liao, Zhixiang ; Page, Kara ; Franco, Daly ; Burke, Kyle ; Jansen, Iris E. ; Trisini-Lipsanopoulos, Ana ; Winder-Rhodes, Sophie ; Tanner, Caroline M. ; Lang, Anthony E. ; Eberly, Shirley ; Elbaz, Alexis ; Brice, Alexis ; Mangone, Graziella ; Ravina, Bernard ; Shoulson, Ira ; Cormier-Dequaire, Florence ; Heutink, Peter ; van Hilten, Jacobus J. ; Barker, Roger A. ; Williams-Gray, Caroline H. ; Marinus, Johan ; Scherzer, Clemens R. / Prediction of cognition in Parkinson's disease with a clinical–genetic score : a longitudinal analysis of nine cohorts. In: The Lancet Neurology. 2017 ; Vol. 16, No. 8. pp. 620-629.
@article{6b6b3533b14549798a44ac24734cd334,
title = "Prediction of cognition in Parkinson's disease with a clinical–genetic score: a longitudinal analysis of nine cohorts",
abstract = "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. Funding National Institutes of Health, US Department of Defense.",
author = "Ganqiang Liu and Locascio, {Joseph J.} and Corvol, {Jean Christophe} and Brendon Boot and Zhixiang Liao and Kara Page and Daly Franco and Kyle Burke and Jansen, {Iris E.} and Ana Trisini-Lipsanopoulos and Sophie Winder-Rhodes and Tanner, {Caroline M.} and Lang, {Anthony E.} and Shirley Eberly and Alexis Elbaz and Alexis Brice and Graziella Mangone and Bernard Ravina and Ira Shoulson and Florence Cormier-Dequaire and Peter Heutink and {van Hilten}, {Jacobus J.} and Barker, {Roger A.} and Williams-Gray, {Caroline H.} and Johan Marinus and Scherzer, {Clemens R.}",
year = "2017",
month = "8",
day = "1",
doi = "10.1016/S1474-4422(17)30122-9",
language = "English",
volume = "16",
pages = "620--629",
journal = "Lancet Neurology",
issn = "1474-4422",
publisher = "Lancet Publishing Group",
number = "8",

}

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 2017, 'Prediction of cognition in Parkinson's disease with a clinical–genetic score: a longitudinal analysis of nine cohorts' The Lancet Neurology, vol. 16, no. 8, pp. 620-629. https://doi.org/10.1016/S1474-4422(17)30122-9

Prediction of cognition in Parkinson's disease with a clinical–genetic score : a longitudinal analysis of nine cohorts. / Liu, Ganqiang; Locascio, Joseph J.; Corvol, Jean Christophe; Boot, Brendon; Liao, Zhixiang; Page, Kara; Franco, Daly; Burke, Kyle; Jansen, Iris E.; Trisini-Lipsanopoulos, Ana; Winder-Rhodes, Sophie; Tanner, Caroline M.; Lang, Anthony E.; Eberly, Shirley; Elbaz, Alexis; Brice, Alexis; Mangone, Graziella; Ravina, Bernard; Shoulson, Ira; Cormier-Dequaire, Florence; Heutink, Peter; van Hilten, Jacobus J.; Barker, Roger A.; Williams-Gray, Caroline H.; Marinus, Johan; Scherzer, Clemens R.

In: The Lancet Neurology, Vol. 16, No. 8, 01.08.2017, p. 620-629.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Prediction of cognition in Parkinson's disease with a clinical–genetic score

T2 - a longitudinal analysis of nine cohorts

AU - Liu, Ganqiang

AU - Locascio, Joseph J.

AU - Corvol, Jean Christophe

AU - Boot, Brendon

AU - Liao, Zhixiang

AU - Page, Kara

AU - Franco, Daly

AU - Burke, Kyle

AU - Jansen, Iris E.

AU - Trisini-Lipsanopoulos, Ana

AU - Winder-Rhodes, Sophie

AU - Tanner, Caroline M.

AU - Lang, Anthony E.

AU - Eberly, Shirley

AU - Elbaz, Alexis

AU - Brice, Alexis

AU - Mangone, Graziella

AU - Ravina, Bernard

AU - Shoulson, Ira

AU - Cormier-Dequaire, Florence

AU - Heutink, Peter

AU - van Hilten, Jacobus J.

AU - Barker, Roger A.

AU - Williams-Gray, Caroline H.

AU - Marinus, Johan

AU - Scherzer, Clemens R.

PY - 2017/8/1

Y1 - 2017/8/1

N2 - 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. Funding National Institutes of Health, US Department of Defense.

AB - 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. Funding National Institutes of Health, US Department of Defense.

UR - http://www.scopus.com/inward/record.url?scp=85020512138&partnerID=8YFLogxK

U2 - 10.1016/S1474-4422(17)30122-9

DO - 10.1016/S1474-4422(17)30122-9

M3 - Article

VL - 16

SP - 620

EP - 629

JO - Lancet Neurology

JF - Lancet Neurology

SN - 1474-4422

IS - 8

ER -