Machine learning as a means toward precision diagnostics and prognostics

A. Sotiras, B. Gaonkar, H. Eavani, N. Honnorat, E. Varol, A. Dong, C. Davatzikos

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

5 Scopus citations


Machine learning plays an essential role in medical imaging. Pattern analysis techniques can identify, and quantify, subtle and spatially complex patterns of disease-induced changes in the brain despite confounding statistical noise and inter-individual variability. This allows the construction of sensitive biomarkers that can identify disease, or risk of developing it, and characterize future clinical progression on an individual patient basis. Thus pattern analysis techniques have become an indispensable part of the growing need for personalized, predictive medicine. However, despite important advances, several challenges remain before they can gain widespread acceptance as tools for precision diagnostics and prognostics in clinical practice. These include: (i) feature extraction and dimensionality reduction; (ii) readily interpreting complex multivariate models; and (iii) elucidating disease heterogeneity. In this chapter, we describe these challenges, putting emphasis on possible solutions, and present evidence of the usefulness of machine learning techniques at the clinical and research levels.

Original languageEnglish
Title of host publicationMachine Learning and Medical Imaging
PublisherElsevier Inc.
Number of pages36
ISBN (Electronic)9780128041147
ISBN (Print)9780128040768
StatePublished - Aug 9 2016


  • Alzheimer's disease
  • Clustering
  • FMRI
  • Genetics
  • Heterogeneity
  • Markov random fields
  • Matrix factorization
  • Multivariate pattern analysis
  • Structural MRI
  • Support vector machines


Dive into the research topics of 'Machine learning as a means toward precision diagnostics and prognostics'. Together they form a unique fingerprint.

Cite this