Stable clinical prediction using graph support vector machines

Iman Kamkar, Sunil Gupta, Cheng Li, Dinh Phung, Svetha Venkatesh

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


The stability matters in clinical prediction models because it makes the model to be interpretable and generalizable. It is paramount for high dimensional data, which employ sparse models with feature selection ability. We propose a new method to stabilize sparse support vector machines using intrinsic graph structure of the electronic medical records. The graph structure is exploited using the Jaccard similarity among features. Our method employs a convex function to penalize the pairwise l-norm of connected feature coefficients in the graph. We apply the alternating direction method of multipliers to solve the proposed formulation. Our experiments are conducted on a synthetic and three real-world hospital datasets. We show that our proposed method is more stable than the state-of-the-art feature selection and classification techniques in terms of three stability measures namely, Jaccard similarity measure, Spearman's rank correlation coefficient and Kuncheva index. We further show that our method has resulted in better classification performance compared to the baselines.

Original languageEnglish
Title of host publication2016 23rd International Conference on Pattern Recognition (ICPR 2016)
EditorsLarry Davis, Alberto Del Bimbo, Brian C. Lovell
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages6
ISBN (Electronic)9781509048472
ISBN (Print)9781509048489
Publication statusPublished - 2016
Externally publishedYes
EventInternational Conference on Pattern Recognition 2016 - Cancun, Mexico
Duration: 4 Dec 20168 Dec 2016
Conference number: 23rd


ConferenceInternational Conference on Pattern Recognition 2016
Abbreviated titleICPR 2016
Internet address

Cite this