O2‐09‐04: Single‐subject Grey Matter Networks Deteriorate 12 Years Before Dementia

Vermunt, Lisa; Tijms, Betty M.; Visser, Pieter Jelle; Scheltens, Philip; Bateman, Randall J.; Benzinger, Tammie L.S.; Gordon, Brian A.; Dian,

doi:10.1016/j.jalz.2019.06.4502

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alzheimer’s disease (AD) is a neurodegenerative condition, and one of the most prevalent forms of dementia 1 . Clinical and epidemiological evidence suggests that the initial disease-related changes occur decades before the onset of clinical symptom 2 . In that respect, Mild Cognitive Impairment (MCI) is a transitional state between healthy aging and dementia and a prodromal phase of AD 3 .…”

Section: Introductionmentioning

confidence: 99%

A machine learning-based holistic approach for diagnoses within the Alzheimer’s disease spectrum

Massetti

Granzotto

Bomba

et al. 2020

Preprint

View full text Add to dashboard Cite

Alzheimer's disease (AD) and related dementias are neurodegenerative conditions driven by a multifactorial etiology. Growing clinical and epidemiological evidence indicates that the convergence of many polygenic, epigenetic, environmental, vascular, and metabolic factors shapes the risk, onset, and progression of the disease. Capturing and framing the complexity of these factors represent an unmet clinical and etiological challenge. Machine learning (ML) is a powerful approach to infer the processes behind the complex interaction of converging pathogenic factors that work with different weights and mechanisms at different stages of the disease. We employed an ML-based Random Forest (RF) algorithm and the wealth of information offered by the ADNI database to investigate the relative contribution of clinically relevant factors for identifying subjects affected by Mild Cognitive Impairment (MCI), a transitional state between healthy aging and dementia. The results of our ML-based approach indicate that the tool cannot help to predict the clinical outcome and conversion to AD of MCI subjects. On the other hand, non converting (ncMCI) subjects were correctly classified and predicted. In particular, our findings indicate that two neuropsychological tests, the FAQ and ADAS13, are the most relevant features used by our ML for the classification and prediction of younger (under 70 y.o.) ncMCI subjects. In addition, structural MRI data combined with indices representing the status of energy and lipid metabolism, measurements of the patient cardiovascular status, and systemic indices are the most critical factors for the classification and prediction of older (over 70 y.o) ncMCI.

show abstract

Section: Introductionmentioning

confidence: 99%