Clustering Patients with Tensor Decomposition

descriptionPublicationkeyboard_double_arrow_right Article , Preprint , Conference object 01 Jan 2017Embargo end date: 01 Jan 2017 Spain Publisher:arXivJournal:CoRR, volume abs/1708.08994

Authors: Ruffini, Matteo; Gavaldà Mestre, Ricard; Limón, Esther;

doi: 10.48550/arxiv.1708.08994

arXiv: 1708.08994

handle: 2117/114857

Clustering Patients with Tensor Decomposition

- Summary
- Subjects
- Metrics

Abstract

In this paper we present a method for the unsupervised clustering of high-dimensional binary data, with a special focus on electronic healthcare records. We present a robust and efficient heuristic to face this problem using tensor decomposition. We present the reasons why this approach is preferable for tasks such as clustering patient records, to more commonly used distance-based methods. We run the algorithm on two datasets of healthcare records, obtaining clinically meaningful results.

Presented at 2017 Machine Learning for Healthcare Conference (MLHC 2017). Boston, MA

Country

Spain

Related Organizations

Universitat Polite`cnica de Catalunya
Spain

Keywords

FOS: Computer and information sciences, Computer Science - Machine Learning, :Informàtica::Sistemes d'informació [Àrees temàtiques de la UPC], Machine Learning (stat.ML), Electronic healthcare records, Machine Learning (cs.LG), Information storage and retrieval systems -- Medicine, Statistics - Machine Learning, Medical records -- Data processing, Tensor decomposition, Informació -- Sistemes d'emmagatzematge i recuperació -- Medicina, Àrees temàtiques de la UPC::Informàtica::Sistemes d'informació, Mineria de dades, Unsupervised clustering, Històries clíniques -- Informàtica, Data mining

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average