Development of a late-life dementia prediction index with supervised machine learning in the population-based CAIDE study

Timo Pekkala, Anette Hall, Jyrki Lötjönen, Jussi Mattila, Hilkka Soininen, Tiia Ngandu, Tiina Laatikainen, Miia Kivipelto, Alina Solomon

Research output: Contribution to journalArticleScientificpeer-review

10 Citations (Scopus)

Abstract

Background and objective: This study aimed to develop a late-life dementia prediction model using a novel validated supervised machine learning method, the Disease State Index (DSI), in the Finnish population-based CAIDE study. Methods: The CAIDE study was based on previous population-based midlife surveys. CAIDE participants were re-examined twice in late-life, and the first late-life re-examination was used as baseline for the present study. The main study population included 709 cognitively normal subjects at first re-examination who returned to the second re-examination up to 10 years later (incident dementia n = 39). An extended population (n = 1009, incident dementia 151) included non-participants/non-survivors (national registers data). DSI was used to develop a dementia index based on first re-examination assessments. Performance in predicting dementia was assessed as area under the ROC curve (AUC). Results: AUCs for DSI were 0.79 and 0.75 for main and extended populations. Included predictors were cognition, vascular factors, age, subjective memory complaints, and APOE genotype. Conclusion: The supervised machine learning method performed well in identifying comprehensive profiles for predicting dementia development up to 10 years later. DSI could thus be useful for identifying individuals who are most at risk and may benefit from dementia prevention interventions.

Original languageEnglish
Pages (from-to)1055-1067
Number of pages13
JournalJournal of Alzheimer's Disease
Volume55
Issue number3
DOIs
Publication statusPublished - 1 Jan 2017
MoE publication typeA1 Journal article-refereed

Fingerprint

Dementia
Population
Area Under Curve
Supervised Machine Learning
ROC Curve
Cognition
Genotype

Keywords

  • Computer-assisted decision making
  • dementia
  • prediction
  • prevention
  • supervised machine learning

Cite this

Pekkala, T., Hall, A., Lötjönen, J., Mattila, J., Soininen, H., Ngandu, T., ... Solomon, A. (2017). Development of a late-life dementia prediction index with supervised machine learning in the population-based CAIDE study. Journal of Alzheimer's Disease, 55(3), 1055-1067. https://doi.org/10.3233/JAD-160560
Pekkala, Timo ; Hall, Anette ; Lötjönen, Jyrki ; Mattila, Jussi ; Soininen, Hilkka ; Ngandu, Tiia ; Laatikainen, Tiina ; Kivipelto, Miia ; Solomon, Alina. / Development of a late-life dementia prediction index with supervised machine learning in the population-based CAIDE study. In: Journal of Alzheimer's Disease. 2017 ; Vol. 55, No. 3. pp. 1055-1067.
@article{567476192ad94ec2af7fd80b5bf7c1d0,
title = "Development of a late-life dementia prediction index with supervised machine learning in the population-based CAIDE study",
abstract = "Background and objective: This study aimed to develop a late-life dementia prediction model using a novel validated supervised machine learning method, the Disease State Index (DSI), in the Finnish population-based CAIDE study. Methods: The CAIDE study was based on previous population-based midlife surveys. CAIDE participants were re-examined twice in late-life, and the first late-life re-examination was used as baseline for the present study. The main study population included 709 cognitively normal subjects at first re-examination who returned to the second re-examination up to 10 years later (incident dementia n = 39). An extended population (n = 1009, incident dementia 151) included non-participants/non-survivors (national registers data). DSI was used to develop a dementia index based on first re-examination assessments. Performance in predicting dementia was assessed as area under the ROC curve (AUC). Results: AUCs for DSI were 0.79 and 0.75 for main and extended populations. Included predictors were cognition, vascular factors, age, subjective memory complaints, and APOE genotype. Conclusion: The supervised machine learning method performed well in identifying comprehensive profiles for predicting dementia development up to 10 years later. DSI could thus be useful for identifying individuals who are most at risk and may benefit from dementia prevention interventions.",
keywords = "Computer-assisted decision making, dementia, prediction, prevention, supervised machine learning",
author = "Timo Pekkala and Anette Hall and Jyrki L{\"o}tj{\"o}nen and Jussi Mattila and Hilkka Soininen and Tiia Ngandu and Tiina Laatikainen and Miia Kivipelto and Alina Solomon",
year = "2017",
month = "1",
day = "1",
doi = "10.3233/JAD-160560",
language = "English",
volume = "55",
pages = "1055--1067",
journal = "Journal of Alzheimer's Disease",
issn = "1387-2877",
publisher = "IOS Press",
number = "3",

}

Pekkala, T, Hall, A, Lötjönen, J, Mattila, J, Soininen, H, Ngandu, T, Laatikainen, T, Kivipelto, M & Solomon, A 2017, 'Development of a late-life dementia prediction index with supervised machine learning in the population-based CAIDE study', Journal of Alzheimer's Disease, vol. 55, no. 3, pp. 1055-1067. https://doi.org/10.3233/JAD-160560

Development of a late-life dementia prediction index with supervised machine learning in the population-based CAIDE study. / Pekkala, Timo; Hall, Anette; Lötjönen, Jyrki; Mattila, Jussi; Soininen, Hilkka; Ngandu, Tiia; Laatikainen, Tiina; Kivipelto, Miia; Solomon, Alina.

In: Journal of Alzheimer's Disease, Vol. 55, No. 3, 01.01.2017, p. 1055-1067.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Development of a late-life dementia prediction index with supervised machine learning in the population-based CAIDE study

AU - Pekkala, Timo

AU - Hall, Anette

AU - Lötjönen, Jyrki

AU - Mattila, Jussi

AU - Soininen, Hilkka

AU - Ngandu, Tiia

AU - Laatikainen, Tiina

AU - Kivipelto, Miia

AU - Solomon, Alina

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Background and objective: This study aimed to develop a late-life dementia prediction model using a novel validated supervised machine learning method, the Disease State Index (DSI), in the Finnish population-based CAIDE study. Methods: The CAIDE study was based on previous population-based midlife surveys. CAIDE participants were re-examined twice in late-life, and the first late-life re-examination was used as baseline for the present study. The main study population included 709 cognitively normal subjects at first re-examination who returned to the second re-examination up to 10 years later (incident dementia n = 39). An extended population (n = 1009, incident dementia 151) included non-participants/non-survivors (national registers data). DSI was used to develop a dementia index based on first re-examination assessments. Performance in predicting dementia was assessed as area under the ROC curve (AUC). Results: AUCs for DSI were 0.79 and 0.75 for main and extended populations. Included predictors were cognition, vascular factors, age, subjective memory complaints, and APOE genotype. Conclusion: The supervised machine learning method performed well in identifying comprehensive profiles for predicting dementia development up to 10 years later. DSI could thus be useful for identifying individuals who are most at risk and may benefit from dementia prevention interventions.

AB - Background and objective: This study aimed to develop a late-life dementia prediction model using a novel validated supervised machine learning method, the Disease State Index (DSI), in the Finnish population-based CAIDE study. Methods: The CAIDE study was based on previous population-based midlife surveys. CAIDE participants were re-examined twice in late-life, and the first late-life re-examination was used as baseline for the present study. The main study population included 709 cognitively normal subjects at first re-examination who returned to the second re-examination up to 10 years later (incident dementia n = 39). An extended population (n = 1009, incident dementia 151) included non-participants/non-survivors (national registers data). DSI was used to develop a dementia index based on first re-examination assessments. Performance in predicting dementia was assessed as area under the ROC curve (AUC). Results: AUCs for DSI were 0.79 and 0.75 for main and extended populations. Included predictors were cognition, vascular factors, age, subjective memory complaints, and APOE genotype. Conclusion: The supervised machine learning method performed well in identifying comprehensive profiles for predicting dementia development up to 10 years later. DSI could thus be useful for identifying individuals who are most at risk and may benefit from dementia prevention interventions.

KW - Computer-assisted decision making

KW - dementia

KW - prediction

KW - prevention

KW - supervised machine learning

UR - http://www.scopus.com/inward/record.url?scp=85005977748&partnerID=8YFLogxK

U2 - 10.3233/JAD-160560

DO - 10.3233/JAD-160560

M3 - Article

AN - SCOPUS:85005977748

VL - 55

SP - 1055

EP - 1067

JO - Journal of Alzheimer's Disease

JF - Journal of Alzheimer's Disease

SN - 1387-2877

IS - 3

ER -