Multivariate prediction of motor diagnosis in Huntington's disease: 12 years of PREDICT-HD

PREDICT-HD Investigators and Coordinators of the Huntington Study Group, Kimberly Quaid

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Background: It is well known in Huntington's disease that cytosine-adenine-guanine expansion and age at study entry are predictive of the timing of motor diagnosis. The goal of this study was to assess whether additional motor, imaging, cognitive, functional, psychiatric, and demographic variables measured at study entry increased the ability to predict the risk of motor diagnosis over 12 years. Methods: One thousand seventy-eight Huntington's disease gene-expanded carriers (64% female) from the Neurobiological Predictors of Huntington's Disease study were followed up for up to 12 y (mean=5, standard deviation=3.3) covering 2002 to 2014. No one had a motor diagnosis at study entry, but 225 (21%) carriers prospectively received a motor diagnosis. Analysis was performed with random survival forests, which is a machine learning method for right-censored data. Results: Adding 34 variables along with cytosine-adenine-guanine and age substantially increased predictive accuracy relative to cytosine-adenine-guanine and age alone. Adding six of the common motor and cognitive variables (total motor score, diagnostic confidence level, Symbol Digit Modalities Test, three Stroop tests) resulted in lower predictive accuracy than the full set, but still had twice the 5-y predictive accuracy than when using cytosine-adenine-guanine and age alone. Additional analysis suggested interactions and nonlinear effects that were characterized in a post hoc Cox regression model. Conclusions: Measurement of clinical variables can substantially increase the accuracy of predicting motor diagnosis over and above cytosine-adenine-guanine and age (and their interaction). Estimated probabilities can be used to characterize progression level and aid in future studies' sample selection.

Original languageEnglish (US)
Pages (from-to)1664-1672
Number of pages9
JournalMovement Disorders
Volume30
Issue number12
DOIs
StatePublished - Oct 1 2015

Fingerprint

Cytosine
Huntington Disease
Guanine
Adenine
Stroop Test
Aptitude
Proportional Hazards Models
Psychiatry
Demography
Genes

Keywords

  • Assessment of cognitive disorders/dementia
  • Clinical trials methodology/study design
  • Huntington's disease
  • Prognosis

ASJC Scopus subject areas

  • Clinical Neurology
  • Neurology

Cite this

PREDICT-HD Investigators and Coordinators of the Huntington Study Group, & Quaid, K. (2015). Multivariate prediction of motor diagnosis in Huntington's disease: 12 years of PREDICT-HD. Movement Disorders, 30(12), 1664-1672. https://doi.org/10.1002/mds.26364

Multivariate prediction of motor diagnosis in Huntington's disease : 12 years of PREDICT-HD. / PREDICT-HD Investigators and Coordinators of the Huntington Study Group; Quaid, Kimberly.

In: Movement Disorders, Vol. 30, No. 12, 01.10.2015, p. 1664-1672.

Research output: Contribution to journalArticle

PREDICT-HD Investigators and Coordinators of the Huntington Study Group & Quaid, K 2015, 'Multivariate prediction of motor diagnosis in Huntington's disease: 12 years of PREDICT-HD', Movement Disorders, vol. 30, no. 12, pp. 1664-1672. https://doi.org/10.1002/mds.26364
PREDICT-HD Investigators and Coordinators of the Huntington Study Group, Quaid K. Multivariate prediction of motor diagnosis in Huntington's disease: 12 years of PREDICT-HD. Movement Disorders. 2015 Oct 1;30(12):1664-1672. https://doi.org/10.1002/mds.26364
PREDICT-HD Investigators and Coordinators of the Huntington Study Group ; Quaid, Kimberly. / Multivariate prediction of motor diagnosis in Huntington's disease : 12 years of PREDICT-HD. In: Movement Disorders. 2015 ; Vol. 30, No. 12. pp. 1664-1672.
@article{114c905a5bd0498589eb48220a813662,
title = "Multivariate prediction of motor diagnosis in Huntington's disease: 12 years of PREDICT-HD",
abstract = "Background: It is well known in Huntington's disease that cytosine-adenine-guanine expansion and age at study entry are predictive of the timing of motor diagnosis. The goal of this study was to assess whether additional motor, imaging, cognitive, functional, psychiatric, and demographic variables measured at study entry increased the ability to predict the risk of motor diagnosis over 12 years. Methods: One thousand seventy-eight Huntington's disease gene-expanded carriers (64{\%} female) from the Neurobiological Predictors of Huntington's Disease study were followed up for up to 12 y (mean=5, standard deviation=3.3) covering 2002 to 2014. No one had a motor diagnosis at study entry, but 225 (21{\%}) carriers prospectively received a motor diagnosis. Analysis was performed with random survival forests, which is a machine learning method for right-censored data. Results: Adding 34 variables along with cytosine-adenine-guanine and age substantially increased predictive accuracy relative to cytosine-adenine-guanine and age alone. Adding six of the common motor and cognitive variables (total motor score, diagnostic confidence level, Symbol Digit Modalities Test, three Stroop tests) resulted in lower predictive accuracy than the full set, but still had twice the 5-y predictive accuracy than when using cytosine-adenine-guanine and age alone. Additional analysis suggested interactions and nonlinear effects that were characterized in a post hoc Cox regression model. Conclusions: Measurement of clinical variables can substantially increase the accuracy of predicting motor diagnosis over and above cytosine-adenine-guanine and age (and their interaction). Estimated probabilities can be used to characterize progression level and aid in future studies' sample selection.",
keywords = "Assessment of cognitive disorders/dementia, Clinical trials methodology/study design, Huntington's disease, Prognosis",
author = "{PREDICT-HD Investigators and Coordinators of the Huntington Study Group} and Long, {Jeffrey D.} and Paulsen, {Jane S.} and Soriano, {Isabella De} and Courtney Shadrick and Amanda Miller and Edmond Chiu and Joy Preston and Anita Goh and Stephanie Antonopoulos and Samantha Loi and Phyllis Chua and Angela Komiti and Lynn Raymond and Joji Decolongon and Mannie Fan and Allison Coleman and Ross, {Christopher A.} and Mark Varvaris and Maryjane Ong and Nadine Yoritomo and Mallonee, {William M.} and Greg Suter and Ali Samii and Freney, {Emily P.} and Alma Macaraeg and Randi Jones and Cathy Wood-Siverio and Factor, {Stewart A.} and Barker, {Roger A.} and Sarah Mason and Guzman, {Natalie Valle} and Elizabeth McCusker and Jane Griffith and Clement Loy and Jillian McMillan and David Gunn and Michael Orth and Sigurd Submuth and Katrin Barth and Sonja Trautmann and Daniela Schwenk and Kimberly Quaid and Kimberly Quaid and Melissa Wesson and Joanne Wojcieszek and Mark Guttman and Alanna Sheinberg and Albie Law and Irita Karmalkar and Susan Perlman",
year = "2015",
month = "10",
day = "1",
doi = "10.1002/mds.26364",
language = "English (US)",
volume = "30",
pages = "1664--1672",
journal = "Movement Disorders",
issn = "0885-3185",
publisher = "John Wiley and Sons Inc.",
number = "12",

}

TY - JOUR

T1 - Multivariate prediction of motor diagnosis in Huntington's disease

T2 - 12 years of PREDICT-HD

AU - PREDICT-HD Investigators and Coordinators of the Huntington Study Group

AU - Long, Jeffrey D.

AU - Paulsen, Jane S.

AU - Soriano, Isabella De

AU - Shadrick, Courtney

AU - Miller, Amanda

AU - Chiu, Edmond

AU - Preston, Joy

AU - Goh, Anita

AU - Antonopoulos, Stephanie

AU - Loi, Samantha

AU - Chua, Phyllis

AU - Komiti, Angela

AU - Raymond, Lynn

AU - Decolongon, Joji

AU - Fan, Mannie

AU - Coleman, Allison

AU - Ross, Christopher A.

AU - Varvaris, Mark

AU - Ong, Maryjane

AU - Yoritomo, Nadine

AU - Mallonee, William M.

AU - Suter, Greg

AU - Samii, Ali

AU - Freney, Emily P.

AU - Macaraeg, Alma

AU - Jones, Randi

AU - Wood-Siverio, Cathy

AU - Factor, Stewart A.

AU - Barker, Roger A.

AU - Mason, Sarah

AU - Guzman, Natalie Valle

AU - McCusker, Elizabeth

AU - Griffith, Jane

AU - Loy, Clement

AU - McMillan, Jillian

AU - Gunn, David

AU - Orth, Michael

AU - Submuth, Sigurd

AU - Barth, Katrin

AU - Trautmann, Sonja

AU - Schwenk, Daniela

AU - Quaid, Kimberly

AU - Quaid, Kimberly

AU - Wesson, Melissa

AU - Wojcieszek, Joanne

AU - Guttman, Mark

AU - Sheinberg, Alanna

AU - Law, Albie

AU - Karmalkar, Irita

AU - Perlman, Susan

PY - 2015/10/1

Y1 - 2015/10/1

N2 - Background: It is well known in Huntington's disease that cytosine-adenine-guanine expansion and age at study entry are predictive of the timing of motor diagnosis. The goal of this study was to assess whether additional motor, imaging, cognitive, functional, psychiatric, and demographic variables measured at study entry increased the ability to predict the risk of motor diagnosis over 12 years. Methods: One thousand seventy-eight Huntington's disease gene-expanded carriers (64% female) from the Neurobiological Predictors of Huntington's Disease study were followed up for up to 12 y (mean=5, standard deviation=3.3) covering 2002 to 2014. No one had a motor diagnosis at study entry, but 225 (21%) carriers prospectively received a motor diagnosis. Analysis was performed with random survival forests, which is a machine learning method for right-censored data. Results: Adding 34 variables along with cytosine-adenine-guanine and age substantially increased predictive accuracy relative to cytosine-adenine-guanine and age alone. Adding six of the common motor and cognitive variables (total motor score, diagnostic confidence level, Symbol Digit Modalities Test, three Stroop tests) resulted in lower predictive accuracy than the full set, but still had twice the 5-y predictive accuracy than when using cytosine-adenine-guanine and age alone. Additional analysis suggested interactions and nonlinear effects that were characterized in a post hoc Cox regression model. Conclusions: Measurement of clinical variables can substantially increase the accuracy of predicting motor diagnosis over and above cytosine-adenine-guanine and age (and their interaction). Estimated probabilities can be used to characterize progression level and aid in future studies' sample selection.

AB - Background: It is well known in Huntington's disease that cytosine-adenine-guanine expansion and age at study entry are predictive of the timing of motor diagnosis. The goal of this study was to assess whether additional motor, imaging, cognitive, functional, psychiatric, and demographic variables measured at study entry increased the ability to predict the risk of motor diagnosis over 12 years. Methods: One thousand seventy-eight Huntington's disease gene-expanded carriers (64% female) from the Neurobiological Predictors of Huntington's Disease study were followed up for up to 12 y (mean=5, standard deviation=3.3) covering 2002 to 2014. No one had a motor diagnosis at study entry, but 225 (21%) carriers prospectively received a motor diagnosis. Analysis was performed with random survival forests, which is a machine learning method for right-censored data. Results: Adding 34 variables along with cytosine-adenine-guanine and age substantially increased predictive accuracy relative to cytosine-adenine-guanine and age alone. Adding six of the common motor and cognitive variables (total motor score, diagnostic confidence level, Symbol Digit Modalities Test, three Stroop tests) resulted in lower predictive accuracy than the full set, but still had twice the 5-y predictive accuracy than when using cytosine-adenine-guanine and age alone. Additional analysis suggested interactions and nonlinear effects that were characterized in a post hoc Cox regression model. Conclusions: Measurement of clinical variables can substantially increase the accuracy of predicting motor diagnosis over and above cytosine-adenine-guanine and age (and their interaction). Estimated probabilities can be used to characterize progression level and aid in future studies' sample selection.

KW - Assessment of cognitive disorders/dementia

KW - Clinical trials methodology/study design

KW - Huntington's disease

KW - Prognosis

UR - http://www.scopus.com/inward/record.url?scp=84944452142&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944452142&partnerID=8YFLogxK

U2 - 10.1002/mds.26364

DO - 10.1002/mds.26364

M3 - Article

C2 - 26340420

AN - SCOPUS:84944452142

VL - 30

SP - 1664

EP - 1672

JO - Movement Disorders

JF - Movement Disorders

SN - 0885-3185

IS - 12

ER -