Medical burden, cerebrovascular disease, and cognitive impairment in geriatric depression: Modeling the relationships with the CART analysis

Helen Lavretsky, Christina Kitchen, Jim Mintz, Moon Doo Kim, Laverne Estanol, Anand Kumar

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Herein, the background information reflecting roles of medical burden, cerebrovascular disease and risk factors, and cognitive impairment in geriatric depression are reviewed. The authors then propose a nonparametric statistical approach to the data analysis of multiple putative causal variables for late-life depression, the Classification and Regression Tree Analysis. This analysis presents a useful approach to modeling nonlinear relationships and interactions among variables measuring physical and mental health, as well as magnetic resonance imaging and cognitive measures in depressed elderly. This method uncovers the existing interactions among multiple predictor variables, and provide thresholds for each variable, at which its predictive power becomes statistically significant. It presents a "hierarchy" of the predictors in a form of a decision tree by finding the best combination of predictors of an outcome. The authors present two models based on demographic variables, measures of vascular and nonvascular medical burden, neuroimaging indices, the Mini-Mental State Examination score, and neuropsychological test scores of 81 elderly depressed subjects. Cognitive tests of verbal fluency and executive function are identified as the best predictors of depression, followed by the frontal lobe volume and Mini-Mental State Examination. The authors observed that an interaction between frontal lobe volume, total lesion volume, and medical burden was predictive of depression.

Original languageEnglish (US)
Pages (from-to)716-722
Number of pages7
JournalCNS Spectrums
Volume7
Issue number10
StatePublished - Oct 1 2002
Externally publishedYes

Fingerprint

Cerebrovascular Disorders
Geriatrics
Depression
Frontal Lobe
Decision Trees
Neuropsychological Tests
Executive Function
Neuroimaging
Blood Vessels
Mental Health
Regression Analysis
Magnetic Resonance Imaging
Demography
Cognitive Dysfunction

ASJC Scopus subject areas

  • Neuropsychology and Physiological Psychology

Cite this

Medical burden, cerebrovascular disease, and cognitive impairment in geriatric depression : Modeling the relationships with the CART analysis. / Lavretsky, Helen; Kitchen, Christina; Mintz, Jim; Kim, Moon Doo; Estanol, Laverne; Kumar, Anand.

In: CNS Spectrums, Vol. 7, No. 10, 01.10.2002, p. 716-722.

Research output: Contribution to journalArticle

Lavretsky, Helen ; Kitchen, Christina ; Mintz, Jim ; Kim, Moon Doo ; Estanol, Laverne ; Kumar, Anand. / Medical burden, cerebrovascular disease, and cognitive impairment in geriatric depression : Modeling the relationships with the CART analysis. In: CNS Spectrums. 2002 ; Vol. 7, No. 10. pp. 716-722.
@article{df3c8ed9f49046428cc5bcfc71cb34fb,
title = "Medical burden, cerebrovascular disease, and cognitive impairment in geriatric depression: Modeling the relationships with the CART analysis",
abstract = "Herein, the background information reflecting roles of medical burden, cerebrovascular disease and risk factors, and cognitive impairment in geriatric depression are reviewed. The authors then propose a nonparametric statistical approach to the data analysis of multiple putative causal variables for late-life depression, the Classification and Regression Tree Analysis. This analysis presents a useful approach to modeling nonlinear relationships and interactions among variables measuring physical and mental health, as well as magnetic resonance imaging and cognitive measures in depressed elderly. This method uncovers the existing interactions among multiple predictor variables, and provide thresholds for each variable, at which its predictive power becomes statistically significant. It presents a {"}hierarchy{"} of the predictors in a form of a decision tree by finding the best combination of predictors of an outcome. The authors present two models based on demographic variables, measures of vascular and nonvascular medical burden, neuroimaging indices, the Mini-Mental State Examination score, and neuropsychological test scores of 81 elderly depressed subjects. Cognitive tests of verbal fluency and executive function are identified as the best predictors of depression, followed by the frontal lobe volume and Mini-Mental State Examination. The authors observed that an interaction between frontal lobe volume, total lesion volume, and medical burden was predictive of depression.",
author = "Helen Lavretsky and Christina Kitchen and Jim Mintz and Kim, {Moon Doo} and Laverne Estanol and Anand Kumar",
year = "2002",
month = "10",
day = "1",
language = "English (US)",
volume = "7",
pages = "716--722",
journal = "CNS Spectrums",
issn = "1092-8529",
publisher = "MBL Communications",
number = "10",

}

TY - JOUR

T1 - Medical burden, cerebrovascular disease, and cognitive impairment in geriatric depression

T2 - Modeling the relationships with the CART analysis

AU - Lavretsky, Helen

AU - Kitchen, Christina

AU - Mintz, Jim

AU - Kim, Moon Doo

AU - Estanol, Laverne

AU - Kumar, Anand

PY - 2002/10/1

Y1 - 2002/10/1

N2 - Herein, the background information reflecting roles of medical burden, cerebrovascular disease and risk factors, and cognitive impairment in geriatric depression are reviewed. The authors then propose a nonparametric statistical approach to the data analysis of multiple putative causal variables for late-life depression, the Classification and Regression Tree Analysis. This analysis presents a useful approach to modeling nonlinear relationships and interactions among variables measuring physical and mental health, as well as magnetic resonance imaging and cognitive measures in depressed elderly. This method uncovers the existing interactions among multiple predictor variables, and provide thresholds for each variable, at which its predictive power becomes statistically significant. It presents a "hierarchy" of the predictors in a form of a decision tree by finding the best combination of predictors of an outcome. The authors present two models based on demographic variables, measures of vascular and nonvascular medical burden, neuroimaging indices, the Mini-Mental State Examination score, and neuropsychological test scores of 81 elderly depressed subjects. Cognitive tests of verbal fluency and executive function are identified as the best predictors of depression, followed by the frontal lobe volume and Mini-Mental State Examination. The authors observed that an interaction between frontal lobe volume, total lesion volume, and medical burden was predictive of depression.

AB - Herein, the background information reflecting roles of medical burden, cerebrovascular disease and risk factors, and cognitive impairment in geriatric depression are reviewed. The authors then propose a nonparametric statistical approach to the data analysis of multiple putative causal variables for late-life depression, the Classification and Regression Tree Analysis. This analysis presents a useful approach to modeling nonlinear relationships and interactions among variables measuring physical and mental health, as well as magnetic resonance imaging and cognitive measures in depressed elderly. This method uncovers the existing interactions among multiple predictor variables, and provide thresholds for each variable, at which its predictive power becomes statistically significant. It presents a "hierarchy" of the predictors in a form of a decision tree by finding the best combination of predictors of an outcome. The authors present two models based on demographic variables, measures of vascular and nonvascular medical burden, neuroimaging indices, the Mini-Mental State Examination score, and neuropsychological test scores of 81 elderly depressed subjects. Cognitive tests of verbal fluency and executive function are identified as the best predictors of depression, followed by the frontal lobe volume and Mini-Mental State Examination. The authors observed that an interaction between frontal lobe volume, total lesion volume, and medical burden was predictive of depression.

UR - http://www.scopus.com/inward/record.url?scp=0038799845&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038799845&partnerID=8YFLogxK

M3 - Article

C2 - 15034497

AN - SCOPUS:0038799845

VL - 7

SP - 716

EP - 722

JO - CNS Spectrums

JF - CNS Spectrums

SN - 1092-8529

IS - 10

ER -