Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference

The Genetic FTD Initiative (GENFI), The Alzheimer’s Disease Neuroimaging Initiative (ADNI)

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The heterogeneity of neurodegenerative diseases is a key confound to disease understanding and treatment development, as study cohorts typically include multiple phenotypes on distinct disease trajectories. Here we introduce a machine-learning technique—Subtype and Stage Inference (SuStaIn)—able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available cross-sectional patient studies. Results from imaging studies in two neurodegenerative diseases reveal subgroups and their distinct trajectories of regional neurodegeneration. In genetic frontotemporal dementia, SuStaIn identifies genotypes from imaging alone, validating its ability to identify subtypes; further the technique reveals within-genotype heterogeneity. In Alzheimer’s disease, SuStaIn uncovers three subtypes, uniquely characterising their temporal complexity. SuStaIn provides fine-grained patient stratification, which substantially enhances the ability to predict conversion between diagnostic categories over standard models that ignore subtype (p = 7.18 × 10−4) or temporal stage (p = 3.96 × 10−5). SuStaIn offers new promise for enabling disease subtype discovery and precision medicine.

Original languageEnglish (US)
Article number4273
JournalNature communications
Volume9
Issue number1
DOIs
StatePublished - Dec 1 2018

Fingerprint

Neurodegenerative diseases
inference
Neurodegenerative Diseases
Aptitude
Genotype
phenotype
Phenotype
Frontotemporal Dementia
Precision Medicine
Trajectories
Imaging techniques
trajectories
Alzheimer Disease
Cohort Studies
Cross-Sectional Studies
Medicine
Learning systems
machine learning
subgroups
stratification

ASJC Scopus subject areas

  • Chemistry(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Physics and Astronomy(all)

Cite this

The Genetic FTD Initiative (GENFI), & The Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2018). Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference. Nature communications, 9(1), [4273]. https://doi.org/10.1038/s41467-018-05892-0
The Genetic FTD Initiative (GENFI) ; The Alzheimer’s Disease Neuroimaging Initiative (ADNI). / Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference. In: Nature communications. 2018 ; Vol. 9, No. 1.
@article{a613d22f9f324816a6cfade3b1ed7c92,
title = "Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference",
abstract = "The heterogeneity of neurodegenerative diseases is a key confound to disease understanding and treatment development, as study cohorts typically include multiple phenotypes on distinct disease trajectories. Here we introduce a machine-learning technique—Subtype and Stage Inference (SuStaIn)—able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available cross-sectional patient studies. Results from imaging studies in two neurodegenerative diseases reveal subgroups and their distinct trajectories of regional neurodegeneration. In genetic frontotemporal dementia, SuStaIn identifies genotypes from imaging alone, validating its ability to identify subtypes; further the technique reveals within-genotype heterogeneity. In Alzheimer’s disease, SuStaIn uncovers three subtypes, uniquely characterising their temporal complexity. SuStaIn provides fine-grained patient stratification, which substantially enhances the ability to predict conversion between diagnostic categories over standard models that ignore subtype (p = 7.18 × 10−4) or temporal stage (p = 3.96 × 10−5). SuStaIn offers new promise for enabling disease subtype discovery and precision medicine.",
author = "{The Genetic FTD Initiative (GENFI)} and {The Alzheimer’s Disease Neuroimaging Initiative (ADNI)} and Young, {Alexandra L.} and Marinescu, {Razvan V.} and Oxtoby, {Neil P.} and Martina Bocchetta and Keir Yong and Firth, {Nicholas C.} and Cash, {David M.} and Thomas, {David L.} and Dick, {Katrina M.} and Jorge Cardoso and {van Swieten}, John and Barbara Borroni and Daniela Galimberti and Mario Masellis and Tartaglia, {Maria Carmela} and Rowe, {James B.} and Caroline Graff and Fabrizio Tagliavini and Frisoni, {Giovanni B.} and Robert Laforce and Elizabeth Finger and {de Mendon{\cc}a}, Alexandre and Sandro Sorbi and Warren, {Jason D.} and Sebastian Crutch and Fox, {Nick C.} and Sebastien Ourselin and Schott, {Jonathan M.} and Rohrer, {Jonathan D.} and Alexander, {Daniel C.} and Christin Andersson and Silvana Archetti and Andrea Arighi and Luisa Benussi and Giuliano Binetti and Sandra Black and Maura Cosseddu and Marie Fallstr{\"o}m and Carlos Ferreira and Chiara Fenoglio and Morris Freedman and Fumagalli, {Giorgio G.} and Stefano Gazzina and Roberta Ghidoni and Marina Grisoli and Vesna Jelic and Lize Jiskoot and Ron Keren and Marek-Marsel Mesulam and Grafman, {Jordan Henry}",
year = "2018",
month = "12",
day = "1",
doi = "10.1038/s41467-018-05892-0",
language = "English (US)",
volume = "9",
journal = "Nature Communications",
issn = "2041-1723",
publisher = "Nature Publishing Group",
number = "1",

}

The Genetic FTD Initiative (GENFI) & The Alzheimer’s Disease Neuroimaging Initiative (ADNI) 2018, 'Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference', Nature communications, vol. 9, no. 1, 4273. https://doi.org/10.1038/s41467-018-05892-0

Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference. / The Genetic FTD Initiative (GENFI); The Alzheimer’s Disease Neuroimaging Initiative (ADNI).

In: Nature communications, Vol. 9, No. 1, 4273, 01.12.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference

AU - The Genetic FTD Initiative (GENFI)

AU - The Alzheimer’s Disease Neuroimaging Initiative (ADNI)

AU - Young, Alexandra L.

AU - Marinescu, Razvan V.

AU - Oxtoby, Neil P.

AU - Bocchetta, Martina

AU - Yong, Keir

AU - Firth, Nicholas C.

AU - Cash, David M.

AU - Thomas, David L.

AU - Dick, Katrina M.

AU - Cardoso, Jorge

AU - van Swieten, John

AU - Borroni, Barbara

AU - Galimberti, Daniela

AU - Masellis, Mario

AU - Tartaglia, Maria Carmela

AU - Rowe, James B.

AU - Graff, Caroline

AU - Tagliavini, Fabrizio

AU - Frisoni, Giovanni B.

AU - Laforce, Robert

AU - Finger, Elizabeth

AU - de Mendonça, Alexandre

AU - Sorbi, Sandro

AU - Warren, Jason D.

AU - Crutch, Sebastian

AU - Fox, Nick C.

AU - Ourselin, Sebastien

AU - Schott, Jonathan M.

AU - Rohrer, Jonathan D.

AU - Alexander, Daniel C.

AU - Andersson, Christin

AU - Archetti, Silvana

AU - Arighi, Andrea

AU - Benussi, Luisa

AU - Binetti, Giuliano

AU - Black, Sandra

AU - Cosseddu, Maura

AU - Fallström, Marie

AU - Ferreira, Carlos

AU - Fenoglio, Chiara

AU - Freedman, Morris

AU - Fumagalli, Giorgio G.

AU - Gazzina, Stefano

AU - Ghidoni, Roberta

AU - Grisoli, Marina

AU - Jelic, Vesna

AU - Jiskoot, Lize

AU - Keren, Ron

AU - Mesulam, Marek-Marsel

AU - Grafman, Jordan Henry

PY - 2018/12/1

Y1 - 2018/12/1

N2 - The heterogeneity of neurodegenerative diseases is a key confound to disease understanding and treatment development, as study cohorts typically include multiple phenotypes on distinct disease trajectories. Here we introduce a machine-learning technique—Subtype and Stage Inference (SuStaIn)—able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available cross-sectional patient studies. Results from imaging studies in two neurodegenerative diseases reveal subgroups and their distinct trajectories of regional neurodegeneration. In genetic frontotemporal dementia, SuStaIn identifies genotypes from imaging alone, validating its ability to identify subtypes; further the technique reveals within-genotype heterogeneity. In Alzheimer’s disease, SuStaIn uncovers three subtypes, uniquely characterising their temporal complexity. SuStaIn provides fine-grained patient stratification, which substantially enhances the ability to predict conversion between diagnostic categories over standard models that ignore subtype (p = 7.18 × 10−4) or temporal stage (p = 3.96 × 10−5). SuStaIn offers new promise for enabling disease subtype discovery and precision medicine.

AB - The heterogeneity of neurodegenerative diseases is a key confound to disease understanding and treatment development, as study cohorts typically include multiple phenotypes on distinct disease trajectories. Here we introduce a machine-learning technique—Subtype and Stage Inference (SuStaIn)—able to uncover data-driven disease phenotypes with distinct temporal progression patterns, from widely available cross-sectional patient studies. Results from imaging studies in two neurodegenerative diseases reveal subgroups and their distinct trajectories of regional neurodegeneration. In genetic frontotemporal dementia, SuStaIn identifies genotypes from imaging alone, validating its ability to identify subtypes; further the technique reveals within-genotype heterogeneity. In Alzheimer’s disease, SuStaIn uncovers three subtypes, uniquely characterising their temporal complexity. SuStaIn provides fine-grained patient stratification, which substantially enhances the ability to predict conversion between diagnostic categories over standard models that ignore subtype (p = 7.18 × 10−4) or temporal stage (p = 3.96 × 10−5). SuStaIn offers new promise for enabling disease subtype discovery and precision medicine.

UR - http://www.scopus.com/inward/record.url?scp=85054898182&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054898182&partnerID=8YFLogxK

U2 - 10.1038/s41467-018-05892-0

DO - 10.1038/s41467-018-05892-0

M3 - Article

VL - 9

JO - Nature Communications

JF - Nature Communications

SN - 2041-1723

IS - 1

M1 - 4273

ER -

The Genetic FTD Initiative (GENFI), The Alzheimer’s Disease Neuroimaging Initiative (ADNI). Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference. Nature communications. 2018 Dec 1;9(1). 4273. https://doi.org/10.1038/s41467-018-05892-0