FeaFiner: Biomarker identification from medical data through feature generalization and selection

Jiayu Zhou, Zhaosong Lu, Jimeng Sun, Lei Yuan, Fei Wang, Jieping Ye

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Traditionally, feature construction and feature selection are two important but separate processes in data mining. However, many real world applications require an integrated approach for creating, refining and selecting features. To address this problem, we propose FeaFiner (short for Feature Refiner), an efficient formulation that simultaneously generalizes low-level features into higher level concepts and then selects relevant concepts based on the target variable. Specifically, we formulate a double sparsity optimization problem that identifies groups in the low-level features, generalizes higher level features using the groups and performs feature selection. Since in many clinical researches nonoverlapping groups are preferred for better interpretability, we further improve the formulation to generalize features using mutually exclusive feature groups. The proposed formulation is challenging to solve due to the orthogonality constraints, non-convexity objective and non-smoothness penalties. We apply a recently developed augmented Lagrangian method to solve this formulation in which each subproblem is solved by a non-monotone spectral projected gradient method. Our numerical experiments show that this approach is computationally efficient and also capable of producing solutions of high quality. We also present a generalization bound showing the consistency and the asymptotic behavior of the learning process of our proposed formulation. Finally, the proposed FeaFiner method is validated on Alzheimer's Disease Neuroimaging Initiative dataset, where low-level biomarkers are automatically generalized into robust higher level concepts which are then selected for predicting the disease status measured by Mini Mental State Examination and Alzheimer's Disease Assessment Scale cognitive subscore. Compared to existing predictive modeling methods, FeaFiner provides intuitive and robust feature concepts and competitive predictive accuracy.

Original languageEnglish (US)
Title of host publicationKDD 2013 - 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
EditorsRajesh Parekh, Jingrui He, Dhillon S. Inderjit, Paul Bradley, Yehuda Koren, Rayid Ghani, Ted E. Senator, Robert L. Grossman, Ramasamy Uthurusamy
PublisherAssociation for Computing Machinery
Pages1034-1042
Number of pages9
ISBN (Electronic)9781450321747
DOIs
StatePublished - Aug 11 2013
Event19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2013 - Chicago, United States
Duration: Aug 11 2013Aug 14 2013

Publication series

NameProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
VolumePart F128815

Other

Other19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2013
Country/TerritoryUnited States
CityChicago
Period8/11/138/14/13

Keywords

  • Augmented lagrangian
  • Biomarkers
  • Feature generalization
  • Feature selection
  • Sparse learning
  • Spectral gradient descent

ASJC Scopus subject areas

  • Software
  • Information Systems

Fingerprint

Dive into the research topics of 'FeaFiner: Biomarker identification from medical data through feature generalization and selection'. Together they form a unique fingerprint.

Cite this