Predicting sporadic Alzheimer's disease progression via inherited Alzheimer's disease-informed machine-learning

Nicolai Franzmeier; Nikolaos Koutsouleris; Tammie Benzinger; Alison Goate; Celeste M Karch; Anne M Fagan; Eric McDade; Marco Duering; Martin Dichgans; Johannes Levin; Brian A Gordon; Yen Ying Lim; Colin L Masters; Martin Rossor; Nick C Fox; Antoinette O'Connor; Jasmeer Chhatwal; Stephen Salloway; Adrian Danek; Jason Hassenstab; Peter R Schofield; John C Morris; Randall J Bateman; Alzheimer's disease neuroimaging initiative (ADNI); Dominantly Inherited Alzheimer Network (DIAN); Michael Ewers

doi:10.1002/alz.12032

Predicting sporadic Alzheimer's disease progression via inherited Alzheimer's disease-informed machine-learning

Alzheimers Dement. 2020 Mar;16(3):501-511. doi: 10.1002/alz.12032. Epub 2020 Feb 11.

Authors

Nicolai Franzmeier¹, Nikolaos Koutsouleris², Tammie Benzinger^{3

4}, Alison Goate^{5

6}, Celeste M Karch^{4

7

8}, Anne M Fagan^{4

7

9}, Eric McDade^{4

9}, Marco Duering¹, Martin Dichgans^{1

10

11}, Johannes Levin^{10

11

12}, Brian A Gordon^{4

13

14}, Yen Ying Lim¹⁵, Colin L Masters¹⁵, Martin Rossor¹⁶, Nick C Fox¹⁶, Antoinette O'Connor¹⁶, Jasmeer Chhatwal¹⁷, Stephen Salloway¹⁸, Adrian Danek¹², Jason Hassenstab^{4

9

14}, Peter R Schofield^{19

20}, John C Morris^{4

8

9}, Randall J Bateman^{4

9}; Alzheimer's disease neuroimaging initiative (ADNI)²¹; Dominantly Inherited Alzheimer Network (DIAN)²²; Michael Ewers¹

Affiliations

¹ Institute for Stroke and Dementia Research, Klinikum der Universität München, Ludwig-Maximilians-Universität LMU, Munich, Germany.
² Department of Psychiatry and Psychotherapy, Ludwig-Maximilians-Universität LMU, Munich, Germany.
³ Department of Radiology, Washington University in St. Louis, St. Louis, Missouri, USA.
⁴ Knight Alzheimer's Disease Research Center, Washington University in St. Louis, St. Louis, Missouri, USA.
⁵ Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
⁶ Ronald M. Loeb Center for Alzheimer's Disease, Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
⁷ Hope Center for Neurological Disorders, Washington University in St. Louis, St. Louis, Missouri, USA.
⁸ Department of Psychiatry, Washington University in St. Louis, St. Louis, Missouri, USA.
⁹ Department of Neurology, Washington University in St. Louis, St. Louis, Missouri, USA.
¹⁰ Munich Cluster for Systems Neurology, Munich, Germany.
¹¹ German Center for Neurodegenerative Diseases (DZNE), Munich, Germany.
¹² Department of Neurology, Ludwig-Maximilians-Universität München, Munich, Germany.
¹³ Mallinckrodt Institute of Radiology, Washington University, St. Louis, Missouri, USA.
¹⁴ Department of Psychological and Brain Sciences, Washington University, St. Louis, Missouri, USA.
¹⁵ The Florey Institute, The University of Melbourne, Parkville, Victoria, Australia.
¹⁶ Dementia Research Centre, University College London, Queen Square, London, UK.
¹⁷ Massachusetts General Hospital, Department of Neurology, Harvard Medical School, Boston, Massachusetts, USA.
¹⁸ Department of Neurology, Warren Alpert Medical School of Brown University, Providence, Rhode Island, USA.
¹⁹ Neuroscience Research Australia, Randwick, New South Wales, Australia.
²⁰ School of Medical Sciences, University of New South Wales, Sydney, New South Wales, Australia.
²¹ ADNI Consortium members are listed in the appendix.
²² DIAN Consortium members are listed in the appendix.

Abstract

Introduction: Developing cross-validated multi-biomarker models for the prediction of the rate of cognitive decline in Alzheimer's disease (AD) is a critical yet unmet clinical challenge.

Methods: We applied support vector regression to AD biomarkers derived from cerebrospinal fluid, structural magnetic resonance imaging (MRI), amyloid-PET and fluorodeoxyglucose positron-emission tomography (FDG-PET) to predict rates of cognitive decline. Prediction models were trained in autosomal-dominant Alzheimer's disease (ADAD, n = 121) and subsequently cross-validated in sporadic prodromal AD (n = 216). The sample size needed to detect treatment effects when using model-based risk enrichment was estimated.

Results: A model combining all biomarker modalities and established in ADAD predicted the 4-year rate of decline in global cognition (R² = 24%) and memory (R² = 25%) in sporadic AD. Model-based risk-enrichment reduced the sample size required for detecting simulated intervention effects by 50%-75%.

Discussion: Our independently validated machine-learning model predicted cognitive decline in sporadic prodromal AD and may substantially reduce sample size needed in clinical trials in AD.

Keywords: Alzheimer's disease; MRI; PET; autosomal-dominant Alzheimer's disease; biomarkers; machine learning; progression prediction; risk enrichment.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Adult
Alzheimer Disease* / genetics
Alzheimer Disease* / pathology
Biomarkers / cerebrospinal fluid
Cognitive Dysfunction* / genetics
Cognitive Dysfunction* / pathology
Disease Progression*
Female
Humans
Machine Learning*
Magnetic Resonance Imaging
Male
Positron-Emission Tomography

Substances

Biomarkers

Abstract

Publication types

MeSH terms

Substances

Grants and funding