A similarity-based approach to leverage multi-cohort medical data on the diagnosis and prognosis of Alzheimer's disease

• Published in: Gigascience Vol. 7; no. 7
• Main Authors: Zhang, Hongjiu, Zhu, Fan, Dodge, Hiroko H, Higgins, Gerald A, Omenn, Gilbert S, Guan, Yuanfang
• Format: Journal Article
• Language: English
• Published: United States Oxford University Press 01.07.2018
• Subjects: Algorithms; Alzheimer Disease - diagnosis; Alzheimer Disease - genetics; Alzheimer's disease; Big Data; Biomarkers; Cognition Disorders - diagnosis; Cognitive ability; Cognitive Dysfunction - diagnosis; Cohort Studies; Diagnosis; Diagnosis, Computer-Assisted; Diagnostic systems; Disease Progression; Gaussian process; Heterogeneity; Humans; Impairment; Machine Learning; Magnetic Resonance Imaging; Medical Informatics - methods; Movement disorders; Neurodegenerative diseases; Normal Distribution; Parkinson Disease - diagnosis; Parkinson's disease; Patients; Phenotype; Phenotypes; Principal Component Analysis; Prognosis; ROC Curve; Sensitivity and Specificity; Similarity
• ISSN: 2047-217X; 2047-217X
• DOI: 10.1093/gigascience/giy085

Heterogeneous diseases such as Alzheimer's disease (AD) manifest a variety of phenotypes among populations. Early diagnosis and effective treatment offer cost benefits. Many studies on biochemical and imaging markers have shown potential promise in improving diagnosis, yet establishing quantitative diagnostic criteria for ancillary tests remains challenging. We have developed a similarity-based approach that matches individuals to subjects with similar conditions. We modeled the disease with a Gaussian process, and tested the method in the Alzheimer's Disease Big Data DREAM Challenge. Ranked the highest among submitted methods, our diagnostic model predicted cognitive impairment scores in an independent dataset test with a correlation score of 0.573. It differentiated AD patients from control subjects with an area under the receiver operating curve of 0.920. Without knowing longitudinal information about subjects, the model predicted patients who are vulnerable to conversion from mild-cognitive impairment to AD through the similarity network. This diagnostic framework can be applied to other diseases with clinical heterogeneity, such as Parkinson's disease.