Sparse Learning of the Disease Severity Score for High-Dimensional Data

Learning disease severity scores automatically from collected measurements may aid in the quality of both healthcare and scientific understanding. Some steps in that direction have been taken and machine learning algorithms for extracting scoring functions from data have been proposed. Given the rap...

Full description

Saved in:
Bibliographic Details
Main Authors: Ivan Stojkovic, Zoran Obradovic
Format: Article
Language:English
Published: Wiley 2017-01-01
Series:Complexity
Online Access:http://dx.doi.org/10.1155/2017/7120691
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849434725124407296
author Ivan Stojkovic
Zoran Obradovic
author_facet Ivan Stojkovic
Zoran Obradovic
author_sort Ivan Stojkovic
collection DOAJ
description Learning disease severity scores automatically from collected measurements may aid in the quality of both healthcare and scientific understanding. Some steps in that direction have been taken and machine learning algorithms for extracting scoring functions from data have been proposed. Given the rapid increase in both quantity and diversity of data measured and stored, the large amount of information is becoming one of the challenges for learning algorithms. In this work, we investigated the direction of the problem where the dimensionality of measured variables is large. Learning the severity score in such cases brings the issue of which of measured features are relevant. We have proposed a novel approach by combining desirable properties of existing formulations, which compares favorably to alternatives in accuracy and especially in the robustness of the learned scoring function. The proposed formulation has a nonsmooth penalty that induces sparsity. This problem is solved by addressing a dual formulation which is smooth and allows an efficient optimization. The proposed approach might be used as an effective and reliable tool for both scoring function learning and biomarker discovery, as demonstrated by identifying a stable set of genes related to influenza symptoms’ severity, which are enriched in immune-related processes.
format Article
id doaj-art-e3fa7731454d494c83f6ab5572ee0abf
institution Kabale University
issn 1076-2787
1099-0526
language English
publishDate 2017-01-01
publisher Wiley
record_format Article
series Complexity
spelling doaj-art-e3fa7731454d494c83f6ab5572ee0abf2025-08-20T03:26:33ZengWileyComplexity1076-27871099-05262017-01-01201710.1155/2017/71206917120691Sparse Learning of the Disease Severity Score for High-Dimensional DataIvan Stojkovic0Zoran Obradovic1Signals and Systems Department, School of Electrical Engineering, University of Belgrade, Bulevar Kralja Aleksandra 73, 11120 Belgrade, SerbiaCenter for Data Analytics and Biomedical Informatics, College of Science and Technology, Temple University, 1925 North 12th Street, Philadelphia, PA 19122, USALearning disease severity scores automatically from collected measurements may aid in the quality of both healthcare and scientific understanding. Some steps in that direction have been taken and machine learning algorithms for extracting scoring functions from data have been proposed. Given the rapid increase in both quantity and diversity of data measured and stored, the large amount of information is becoming one of the challenges for learning algorithms. In this work, we investigated the direction of the problem where the dimensionality of measured variables is large. Learning the severity score in such cases brings the issue of which of measured features are relevant. We have proposed a novel approach by combining desirable properties of existing formulations, which compares favorably to alternatives in accuracy and especially in the robustness of the learned scoring function. The proposed formulation has a nonsmooth penalty that induces sparsity. This problem is solved by addressing a dual formulation which is smooth and allows an efficient optimization. The proposed approach might be used as an effective and reliable tool for both scoring function learning and biomarker discovery, as demonstrated by identifying a stable set of genes related to influenza symptoms’ severity, which are enriched in immune-related processes.http://dx.doi.org/10.1155/2017/7120691
spellingShingle Ivan Stojkovic
Zoran Obradovic
Sparse Learning of the Disease Severity Score for High-Dimensional Data
Complexity
title Sparse Learning of the Disease Severity Score for High-Dimensional Data
title_full Sparse Learning of the Disease Severity Score for High-Dimensional Data
title_fullStr Sparse Learning of the Disease Severity Score for High-Dimensional Data
title_full_unstemmed Sparse Learning of the Disease Severity Score for High-Dimensional Data
title_short Sparse Learning of the Disease Severity Score for High-Dimensional Data
title_sort sparse learning of the disease severity score for high dimensional data
url http://dx.doi.org/10.1155/2017/7120691
work_keys_str_mv AT ivanstojkovic sparselearningofthediseaseseverityscoreforhighdimensionaldata
AT zoranobradovic sparselearningofthediseaseseverityscoreforhighdimensionaldata