Machine learning of neuroimaging for assisted diagnosis of cognitive impairment and dementia: A systematic review

Enrico Pellegrini, Lucia Ballerini, Maria Del C. Valdes Hernandez, Francesca M. Chappell, Victor González-castro, Devasuda Anblagan, Samuel Danso, Susana Muñoz Maniega, Dominic Job, Cyril Pernet, Grant Mair, Tom Macgillivray, Emanuele Trucco, Joanna Wardlaw

Research output: Contribution to journalReview articlepeer-review

Abstract

Introduction
Advanced machine learning methods might help to identify dementia risk from neuroimaging, but their accuracy to date is unclear.

Methods
We systematically reviewed the literature, 2006 to late 2016, for machine learning studies differentiating healthy aging from aging with dementia of various types, assessing study quality, and comparing accuracy at different disease boundaries.

Results
Of 111 relevant studies, most assessed Alzheimer's disease versus healthy controls, using AD Neuroimaging Initiative data, support vector machines, and only T1-weighted sequences. Accuracy was highest for differentiating Alzheimer's disease from healthy controls and poor for differentiating healthy controls versus mild cognitive impairment versus Alzheimer's disease or mild cognitive impairment converters versus nonconverters. Accuracy increased using combined data types, but not by data source, sample size, or machine learning method.

Discussion
Machine learning does not differentiate clinically relevant disease categories yet. More diverse data sets, combinations of different types of data, and close clinical integration of machine learning would help to advance the field.
Original languageEnglish
JournalAlzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
Early online date11 Aug 2018
DOIs
Publication statusE-pub ahead of print - 11 Aug 2018

Fingerprint

Dive into the research topics of 'Machine learning of neuroimaging for assisted diagnosis of cognitive impairment and dementia: A systematic review'. Together they form a unique fingerprint.

Cite this