Generalizability of the disease state index prediction model for identifying patients progressin from mild cognitive impariment to Alzheimer's disease

Anette Hall (Corresponding Author), Miguel Muñoz-Ruiz, Jussi Mattila, Juha Koikkalainen, Magda Tsolaki, Patrizia Mecocci, Iwona Kloszewska, Bruno Vellas, Simon Lovestone, Pieter Jelle Visser, Jyrki Lötjönen, Hilkka Soininen

Research output: Contribution to journalArticleScientificpeer-review

20 Citations (Scopus)

Abstract

Background: The Disease State Index (DSI) prediction model measures the similarity of patient data to diagnosed stable and progressive mild cognitive impairment (MCI) cases to identify patients who are progressing to Alzheimer's disease. Objectives: We evaluated how well the DSI generalizes across four different cohorts: DESCRIPA, ADNI, AddNeuroMed, and the Kuopio MCI study. Methods: The accuracy of the DSI in predicting progression was examined for each cohort separately using 10 * 10-fold cross-validation and for inter-cohort validation using each cohort as a test set for the model built from the other independent cohorts using bootstrapping with 10 repetitions. Altogether 875 subjects were included in the analysis. The analyzed data included a comprehensive set of age and gender corrected magnetic resonance imaging (MRI) features from hippocampal volumetry, multi-template tensor-based morphometry, and voxel-based morphometry as well as Mini-Mental State Examination (MMSE), APOE genotype, and additional cohort specific data from neuropsychological tests and cerebrospinal fluid measurements (CSF). Results: The DSI model was used to classify the patients into stable and progressive MCI cases. AddNeuroMed had the highest classification results of the cohorts, while ADNI and Kuopio MCI exhibited the lowest values. The MRI features alone achieved a good classification performance for all cohorts. For ADNI and DESCRIPA, adding MMSE, APOE genotype, CSF, and neuropsychological data improved the results. Conclusions: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar.
Original languageEnglish
Pages (from-to)79-92
JournalJournal of Alzheimer's Disease
Volume44
Issue number1
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Alzheimer Disease
Cerebrospinal Fluid
Genotype
Magnetic Resonance Imaging
Neuropsychological Tests
progressin
Cognitive Dysfunction

Keywords

  • Alzheimer's disease
  • computer-assisted diagnosis
  • dementia
  • magnetic resonance imaging (MRI)
  • mild cognitive impairment

Cite this

Hall, Anette ; Muñoz-Ruiz, Miguel ; Mattila, Jussi ; Koikkalainen, Juha ; Tsolaki, Magda ; Mecocci, Patrizia ; Kloszewska, Iwona ; Vellas, Bruno ; Lovestone, Simon ; Visser, Pieter Jelle ; Lötjönen, Jyrki ; Soininen, Hilkka. / Generalizability of the disease state index prediction model for identifying patients progressin from mild cognitive impariment to Alzheimer's disease. In: Journal of Alzheimer's Disease. 2015 ; Vol. 44, No. 1. pp. 79-92.
@article{3211c347a18240388e5b05b51dd2182c,
title = "Generalizability of the disease state index prediction model for identifying patients progressin from mild cognitive impariment to Alzheimer's disease",
abstract = "Background: The Disease State Index (DSI) prediction model measures the similarity of patient data to diagnosed stable and progressive mild cognitive impairment (MCI) cases to identify patients who are progressing to Alzheimer's disease. Objectives: We evaluated how well the DSI generalizes across four different cohorts: DESCRIPA, ADNI, AddNeuroMed, and the Kuopio MCI study. Methods: The accuracy of the DSI in predicting progression was examined for each cohort separately using 10 * 10-fold cross-validation and for inter-cohort validation using each cohort as a test set for the model built from the other independent cohorts using bootstrapping with 10 repetitions. Altogether 875 subjects were included in the analysis. The analyzed data included a comprehensive set of age and gender corrected magnetic resonance imaging (MRI) features from hippocampal volumetry, multi-template tensor-based morphometry, and voxel-based morphometry as well as Mini-Mental State Examination (MMSE), APOE genotype, and additional cohort specific data from neuropsychological tests and cerebrospinal fluid measurements (CSF). Results: The DSI model was used to classify the patients into stable and progressive MCI cases. AddNeuroMed had the highest classification results of the cohorts, while ADNI and Kuopio MCI exhibited the lowest values. The MRI features alone achieved a good classification performance for all cohorts. For ADNI and DESCRIPA, adding MMSE, APOE genotype, CSF, and neuropsychological data improved the results. Conclusions: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar.",
keywords = "Alzheimer's disease, computer-assisted diagnosis, dementia, magnetic resonance imaging (MRI), mild cognitive impairment",
author = "Anette Hall and Miguel Mu{\~n}oz-Ruiz and Jussi Mattila and Juha Koikkalainen and Magda Tsolaki and Patrizia Mecocci and Iwona Kloszewska and Bruno Vellas and Simon Lovestone and Visser, {Pieter Jelle} and Jyrki L{\"o}tj{\"o}nen and Hilkka Soininen",
year = "2015",
doi = "10.3233/JAD-140942",
language = "English",
volume = "44",
pages = "79--92",
journal = "Journal of Alzheimer's Disease",
issn = "1387-2877",
publisher = "IOS Press",
number = "1",

}

Hall, A, Muñoz-Ruiz, M, Mattila, J, Koikkalainen, J, Tsolaki, M, Mecocci, P, Kloszewska, I, Vellas, B, Lovestone, S, Visser, PJ, Lötjönen, J & Soininen, H 2015, 'Generalizability of the disease state index prediction model for identifying patients progressin from mild cognitive impariment to Alzheimer's disease', Journal of Alzheimer's Disease, vol. 44, no. 1, pp. 79-92. https://doi.org/10.3233/JAD-140942

Generalizability of the disease state index prediction model for identifying patients progressin from mild cognitive impariment to Alzheimer's disease. / Hall, Anette (Corresponding Author); Muñoz-Ruiz, Miguel; Mattila, Jussi; Koikkalainen, Juha; Tsolaki, Magda; Mecocci, Patrizia; Kloszewska, Iwona; Vellas, Bruno; Lovestone, Simon; Visser, Pieter Jelle; Lötjönen, Jyrki; Soininen, Hilkka.

In: Journal of Alzheimer's Disease, Vol. 44, No. 1, 2015, p. 79-92.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Generalizability of the disease state index prediction model for identifying patients progressin from mild cognitive impariment to Alzheimer's disease

AU - Hall, Anette

AU - Muñoz-Ruiz, Miguel

AU - Mattila, Jussi

AU - Koikkalainen, Juha

AU - Tsolaki, Magda

AU - Mecocci, Patrizia

AU - Kloszewska, Iwona

AU - Vellas, Bruno

AU - Lovestone, Simon

AU - Visser, Pieter Jelle

AU - Lötjönen, Jyrki

AU - Soininen, Hilkka

PY - 2015

Y1 - 2015

N2 - Background: The Disease State Index (DSI) prediction model measures the similarity of patient data to diagnosed stable and progressive mild cognitive impairment (MCI) cases to identify patients who are progressing to Alzheimer's disease. Objectives: We evaluated how well the DSI generalizes across four different cohorts: DESCRIPA, ADNI, AddNeuroMed, and the Kuopio MCI study. Methods: The accuracy of the DSI in predicting progression was examined for each cohort separately using 10 * 10-fold cross-validation and for inter-cohort validation using each cohort as a test set for the model built from the other independent cohorts using bootstrapping with 10 repetitions. Altogether 875 subjects were included in the analysis. The analyzed data included a comprehensive set of age and gender corrected magnetic resonance imaging (MRI) features from hippocampal volumetry, multi-template tensor-based morphometry, and voxel-based morphometry as well as Mini-Mental State Examination (MMSE), APOE genotype, and additional cohort specific data from neuropsychological tests and cerebrospinal fluid measurements (CSF). Results: The DSI model was used to classify the patients into stable and progressive MCI cases. AddNeuroMed had the highest classification results of the cohorts, while ADNI and Kuopio MCI exhibited the lowest values. The MRI features alone achieved a good classification performance for all cohorts. For ADNI and DESCRIPA, adding MMSE, APOE genotype, CSF, and neuropsychological data improved the results. Conclusions: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar.

AB - Background: The Disease State Index (DSI) prediction model measures the similarity of patient data to diagnosed stable and progressive mild cognitive impairment (MCI) cases to identify patients who are progressing to Alzheimer's disease. Objectives: We evaluated how well the DSI generalizes across four different cohorts: DESCRIPA, ADNI, AddNeuroMed, and the Kuopio MCI study. Methods: The accuracy of the DSI in predicting progression was examined for each cohort separately using 10 * 10-fold cross-validation and for inter-cohort validation using each cohort as a test set for the model built from the other independent cohorts using bootstrapping with 10 repetitions. Altogether 875 subjects were included in the analysis. The analyzed data included a comprehensive set of age and gender corrected magnetic resonance imaging (MRI) features from hippocampal volumetry, multi-template tensor-based morphometry, and voxel-based morphometry as well as Mini-Mental State Examination (MMSE), APOE genotype, and additional cohort specific data from neuropsychological tests and cerebrospinal fluid measurements (CSF). Results: The DSI model was used to classify the patients into stable and progressive MCI cases. AddNeuroMed had the highest classification results of the cohorts, while ADNI and Kuopio MCI exhibited the lowest values. The MRI features alone achieved a good classification performance for all cohorts. For ADNI and DESCRIPA, adding MMSE, APOE genotype, CSF, and neuropsychological data improved the results. Conclusions: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar.

KW - Alzheimer's disease

KW - computer-assisted diagnosis

KW - dementia

KW - magnetic resonance imaging (MRI)

KW - mild cognitive impairment

U2 - 10.3233/JAD-140942

DO - 10.3233/JAD-140942

M3 - Article

VL - 44

SP - 79

EP - 92

JO - Journal of Alzheimer's Disease

JF - Journal of Alzheimer's Disease

SN - 1387-2877

IS - 1

ER -