Prediction progression from cognitive impairment to alzheimer's disease with the disease state index

Anette Hall, Jussi Mattila, Juha Koikkalainen, Jyrki Lötjonen, Robin Wolz, Philip Scheltens, Giovanni Frisoni, Magdalini Tsolaki, Flavio Nobili, Yvonne Freund-Levi, Lennart Minthon, Lutz Frölich, Harald Hampel, Pieter Jelle Visser, Hilkka Soininen

Research output: Contribution to journalArticleScientificpeer-review

14 Citations (Scopus)

Abstract

We evaluated the performance of the Disease State Index (DSI) method when predicting progression to Alzheimer's disease (AD) in patients with subjective cognitive impairment (SCI), amnestic or non-amnestic mild cognitive impairment (aMCI, naMCI). The DSI model measures patients' similarity to diagnosed cases based on available data, such as cognitive tests, the APOE genotype, CSF biomarkers and MRI. We applied the DSI model to data from the DESCRIPA cohort, where non-demented patients (N=775) with different subtypes of cognitive impairment were followed for 1 to 5 years. Classification accuracies for the subgroups were calculated with the DSI using leave-one-out crossvalidation. The DSI's classification accuracy in predicting progression to AD was 0.75 (AUC=0.83) in the total population, 0.70 (AUC=0.77) for aMCI and 0.71 (AUC=0.76) for naMCI. For a subset of approximately half of the patients with high or low DSI values, accuracy reached 0.86 (all), 0.78 (aMCI), and 0.85 (naMCI). For patients with MRI or CSF biomarker data available, theywere 0.78 (all), 0.76 (aMCI) and 0.76 (naMCI), while for clear cases the accuracies rose to 0.90 (all), 0.83 (aMCI) and 0.91 (naMCI). The results show that the DSI model can distinguish between clear and ambiguous cases, assess the severity of the disease and also provide information on the effectiveness of different biomarkers. While a specific test or biomarker may confound analysis for an individual patient, combining several different types of tests and biomarkers could be able to reveal the trajectory of the disease and improve the prediction of AD progression.
Original languageEnglish
Pages (from-to)69-79
JournalCurrent Alzheimer Research
Volume12
Issue number1
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Alzheimer Disease
Biomarkers
Area Under Curve
Cognitive Dysfunction
Disease Progression
Genotype
Population

Keywords

  • Alzheimer's disease
  • cerebrospinal fluid (CSF)
  • computer-assisted diagnosis
  • dementia
  • DESCRIPA
  • magnetic resonance imaging (MRI)
  • mild cognitive impairment (MCI)

Cite this

Hall, A., Mattila, J., Koikkalainen, J., Lötjonen, J., Wolz, R., Scheltens, P., ... Soininen, H. (2015). Prediction progression from cognitive impairment to alzheimer's disease with the disease state index. Current Alzheimer Research, 12(1), 69-79. https://doi.org/10.2174/1567205012666141218123829
Hall, Anette ; Mattila, Jussi ; Koikkalainen, Juha ; Lötjonen, Jyrki ; Wolz, Robin ; Scheltens, Philip ; Frisoni, Giovanni ; Tsolaki, Magdalini ; Nobili, Flavio ; Freund-Levi, Yvonne ; Minthon, Lennart ; Frölich, Lutz ; Hampel, Harald ; Visser, Pieter Jelle ; Soininen, Hilkka. / Prediction progression from cognitive impairment to alzheimer's disease with the disease state index. In: Current Alzheimer Research. 2015 ; Vol. 12, No. 1. pp. 69-79.
@article{982d9cdea8cd43e9b0e3c6d9ac1df74b,
title = "Prediction progression from cognitive impairment to alzheimer's disease with the disease state index",
abstract = "We evaluated the performance of the Disease State Index (DSI) method when predicting progression to Alzheimer's disease (AD) in patients with subjective cognitive impairment (SCI), amnestic or non-amnestic mild cognitive impairment (aMCI, naMCI). The DSI model measures patients' similarity to diagnosed cases based on available data, such as cognitive tests, the APOE genotype, CSF biomarkers and MRI. We applied the DSI model to data from the DESCRIPA cohort, where non-demented patients (N=775) with different subtypes of cognitive impairment were followed for 1 to 5 years. Classification accuracies for the subgroups were calculated with the DSI using leave-one-out crossvalidation. The DSI's classification accuracy in predicting progression to AD was 0.75 (AUC=0.83) in the total population, 0.70 (AUC=0.77) for aMCI and 0.71 (AUC=0.76) for naMCI. For a subset of approximately half of the patients with high or low DSI values, accuracy reached 0.86 (all), 0.78 (aMCI), and 0.85 (naMCI). For patients with MRI or CSF biomarker data available, theywere 0.78 (all), 0.76 (aMCI) and 0.76 (naMCI), while for clear cases the accuracies rose to 0.90 (all), 0.83 (aMCI) and 0.91 (naMCI). The results show that the DSI model can distinguish between clear and ambiguous cases, assess the severity of the disease and also provide information on the effectiveness of different biomarkers. While a specific test or biomarker may confound analysis for an individual patient, combining several different types of tests and biomarkers could be able to reveal the trajectory of the disease and improve the prediction of AD progression.",
keywords = "Alzheimer's disease, cerebrospinal fluid (CSF), computer-assisted diagnosis, dementia, DESCRIPA, magnetic resonance imaging (MRI), mild cognitive impairment (MCI)",
author = "Anette Hall and Jussi Mattila and Juha Koikkalainen and Jyrki L{\"o}tjonen and Robin Wolz and Philip Scheltens and Giovanni Frisoni and Magdalini Tsolaki and Flavio Nobili and Yvonne Freund-Levi and Lennart Minthon and Lutz Fr{\"o}lich and Harald Hampel and Visser, {Pieter Jelle} and Hilkka Soininen",
note = "LIS: Romeo yellow - but article is open Project code: 100765",
year = "2015",
doi = "10.2174/1567205012666141218123829",
language = "English",
volume = "12",
pages = "69--79",
journal = "Current Alzheimer Research",
issn = "1567-2050",
number = "1",

}

Hall, A, Mattila, J, Koikkalainen, J, Lötjonen, J, Wolz, R, Scheltens, P, Frisoni, G, Tsolaki, M, Nobili, F, Freund-Levi, Y, Minthon, L, Frölich, L, Hampel, H, Visser, PJ & Soininen, H 2015, 'Prediction progression from cognitive impairment to alzheimer's disease with the disease state index', Current Alzheimer Research, vol. 12, no. 1, pp. 69-79. https://doi.org/10.2174/1567205012666141218123829

Prediction progression from cognitive impairment to alzheimer's disease with the disease state index. / Hall, Anette; Mattila, Jussi; Koikkalainen, Juha; Lötjonen, Jyrki; Wolz, Robin; Scheltens, Philip; Frisoni, Giovanni; Tsolaki, Magdalini; Nobili, Flavio; Freund-Levi, Yvonne; Minthon, Lennart; Frölich, Lutz; Hampel, Harald; Visser, Pieter Jelle; Soininen, Hilkka.

In: Current Alzheimer Research, Vol. 12, No. 1, 2015, p. 69-79.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Prediction progression from cognitive impairment to alzheimer's disease with the disease state index

AU - Hall, Anette

AU - Mattila, Jussi

AU - Koikkalainen, Juha

AU - Lötjonen, Jyrki

AU - Wolz, Robin

AU - Scheltens, Philip

AU - Frisoni, Giovanni

AU - Tsolaki, Magdalini

AU - Nobili, Flavio

AU - Freund-Levi, Yvonne

AU - Minthon, Lennart

AU - Frölich, Lutz

AU - Hampel, Harald

AU - Visser, Pieter Jelle

AU - Soininen, Hilkka

N1 - LIS: Romeo yellow - but article is open Project code: 100765

PY - 2015

Y1 - 2015

N2 - We evaluated the performance of the Disease State Index (DSI) method when predicting progression to Alzheimer's disease (AD) in patients with subjective cognitive impairment (SCI), amnestic or non-amnestic mild cognitive impairment (aMCI, naMCI). The DSI model measures patients' similarity to diagnosed cases based on available data, such as cognitive tests, the APOE genotype, CSF biomarkers and MRI. We applied the DSI model to data from the DESCRIPA cohort, where non-demented patients (N=775) with different subtypes of cognitive impairment were followed for 1 to 5 years. Classification accuracies for the subgroups were calculated with the DSI using leave-one-out crossvalidation. The DSI's classification accuracy in predicting progression to AD was 0.75 (AUC=0.83) in the total population, 0.70 (AUC=0.77) for aMCI and 0.71 (AUC=0.76) for naMCI. For a subset of approximately half of the patients with high or low DSI values, accuracy reached 0.86 (all), 0.78 (aMCI), and 0.85 (naMCI). For patients with MRI or CSF biomarker data available, theywere 0.78 (all), 0.76 (aMCI) and 0.76 (naMCI), while for clear cases the accuracies rose to 0.90 (all), 0.83 (aMCI) and 0.91 (naMCI). The results show that the DSI model can distinguish between clear and ambiguous cases, assess the severity of the disease and also provide information on the effectiveness of different biomarkers. While a specific test or biomarker may confound analysis for an individual patient, combining several different types of tests and biomarkers could be able to reveal the trajectory of the disease and improve the prediction of AD progression.

AB - We evaluated the performance of the Disease State Index (DSI) method when predicting progression to Alzheimer's disease (AD) in patients with subjective cognitive impairment (SCI), amnestic or non-amnestic mild cognitive impairment (aMCI, naMCI). The DSI model measures patients' similarity to diagnosed cases based on available data, such as cognitive tests, the APOE genotype, CSF biomarkers and MRI. We applied the DSI model to data from the DESCRIPA cohort, where non-demented patients (N=775) with different subtypes of cognitive impairment were followed for 1 to 5 years. Classification accuracies for the subgroups were calculated with the DSI using leave-one-out crossvalidation. The DSI's classification accuracy in predicting progression to AD was 0.75 (AUC=0.83) in the total population, 0.70 (AUC=0.77) for aMCI and 0.71 (AUC=0.76) for naMCI. For a subset of approximately half of the patients with high or low DSI values, accuracy reached 0.86 (all), 0.78 (aMCI), and 0.85 (naMCI). For patients with MRI or CSF biomarker data available, theywere 0.78 (all), 0.76 (aMCI) and 0.76 (naMCI), while for clear cases the accuracies rose to 0.90 (all), 0.83 (aMCI) and 0.91 (naMCI). The results show that the DSI model can distinguish between clear and ambiguous cases, assess the severity of the disease and also provide information on the effectiveness of different biomarkers. While a specific test or biomarker may confound analysis for an individual patient, combining several different types of tests and biomarkers could be able to reveal the trajectory of the disease and improve the prediction of AD progression.

KW - Alzheimer's disease

KW - cerebrospinal fluid (CSF)

KW - computer-assisted diagnosis

KW - dementia

KW - DESCRIPA

KW - magnetic resonance imaging (MRI)

KW - mild cognitive impairment (MCI)

U2 - 10.2174/1567205012666141218123829

DO - 10.2174/1567205012666141218123829

M3 - Article

VL - 12

SP - 69

EP - 79

JO - Current Alzheimer Research

JF - Current Alzheimer Research

SN - 1567-2050

IS - 1

ER -