Combining unsupervised and supervised learning for discovering disease subclasses

Pietro Bosoni; Allan Tucker; Riccardo Bellazzi; Svetlana I. Nihtyanova; Christopher P. Denton

doi:10.1109/CBMS.2016.37

Combining unsupervised and supervised learning for discovering disease subclasses

Pietro Bosoni, Allan Tucker, Riccardo Bellazzi, Svetlana I. Nihtyanova, Christopher P. Denton

Istituti Clinici Scientifici Maugeri Spa – Società Benefit

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Diseases are often umbrella terms for many subcategories of disease. The identification of these subcategories is vital if we are to develop personalised treatments that are better focussed on individual patients. In this short paper, we explore the use of a combination of unsupervised learning to identify potential subclasses, and supervised learning to build models for better predicting a number of different health outcomes for patients that suffer from systemic sclerosis, a rare chronic connective tissue disorder - but one that shares many characteristics with other diseases. We explore a number of different algorithms for constructing models that simultaneously predict health outcomes and identify subcategories.

Original language	English
Title of host publication	Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	225-226
Number of pages	2
Volume	2016-August
ISBN (Electronic)	9781467390361
DOIs	https://doi.org/10.1109/CBMS.2016.37
Publication status	Published - Aug 16 2016
Event	29th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2016 - Belfast, Ireland Duration: Jun 20 2016 → Jun 23 2016

Other

Other	29th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2016
Country/Territory	Ireland
City	Belfast
Period	6/20/16 → 6/23/16

Keywords

Classification
Disease subclass
Systemic sclerosis

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging
Computer Science Applications

Access to Document

10.1109/CBMS.2016.37

Cite this

Bosoni, P., Tucker, A., Bellazzi, R., Nihtyanova, S. I., & Denton, C. P. (2016). Combining unsupervised and supervised learning for discovering disease subclasses. In Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016 (Vol. 2016-August, pp. 225-226). [7545990] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CBMS.2016.37

Combining unsupervised and supervised learning for discovering disease subclasses. / Bosoni, Pietro; Tucker, Allan; Bellazzi, Riccardo; Nihtyanova, Svetlana I.; Denton, Christopher P.

Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016. Vol. 2016-August Institute of Electrical and Electronics Engineers Inc., 2016. p. 225-226 7545990.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Bosoni, P, Tucker, A, Bellazzi, R, Nihtyanova, SI & Denton, CP 2016, Combining unsupervised and supervised learning for discovering disease subclasses. in Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016. vol. 2016-August, 7545990, Institute of Electrical and Electronics Engineers Inc., pp. 225-226, 29th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2016, Belfast, Ireland, 6/20/16. https://doi.org/10.1109/CBMS.2016.37

Bosoni P, Tucker A, Bellazzi R, Nihtyanova SI, Denton CP. Combining unsupervised and supervised learning for discovering disease subclasses. In Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016. Vol. 2016-August. Institute of Electrical and Electronics Engineers Inc. 2016. p. 225-226. 7545990 https://doi.org/10.1109/CBMS.2016.37

Bosoni, Pietro ; Tucker, Allan ; Bellazzi, Riccardo ; Nihtyanova, Svetlana I. ; Denton, Christopher P. / Combining unsupervised and supervised learning for discovering disease subclasses. Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016. Vol. 2016-August Institute of Electrical and Electronics Engineers Inc., 2016. pp. 225-226

@inproceedings{36765de61e0b49a08286d8c5f2d140e1,

title = "Combining unsupervised and supervised learning for discovering disease subclasses",

abstract = "Diseases are often umbrella terms for many subcategories of disease. The identification of these subcategories is vital if we are to develop personalised treatments that are better focussed on individual patients. In this short paper, we explore the use of a combination of unsupervised learning to identify potential subclasses, and supervised learning to build models for better predicting a number of different health outcomes for patients that suffer from systemic sclerosis, a rare chronic connective tissue disorder - but one that shares many characteristics with other diseases. We explore a number of different algorithms for constructing models that simultaneously predict health outcomes and identify subcategories.",

keywords = "Classification, Disease subclass, Systemic sclerosis",

author = "Pietro Bosoni and Allan Tucker and Riccardo Bellazzi and Nihtyanova, {Svetlana I.} and Denton, {Christopher P.}",

year = "2016",

month = aug,

day = "16",

doi = "10.1109/CBMS.2016.37",

language = "English",

volume = "2016-August",

pages = "225--226",

booktitle = "Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "29th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2016 ; Conference date: 20-06-2016 Through 23-06-2016",

}

TY - GEN

T1 - Combining unsupervised and supervised learning for discovering disease subclasses

AU - Bosoni, Pietro

AU - Tucker, Allan

AU - Bellazzi, Riccardo

AU - Nihtyanova, Svetlana I.

AU - Denton, Christopher P.

PY - 2016/8/16

Y1 - 2016/8/16

N2 - Diseases are often umbrella terms for many subcategories of disease. The identification of these subcategories is vital if we are to develop personalised treatments that are better focussed on individual patients. In this short paper, we explore the use of a combination of unsupervised learning to identify potential subclasses, and supervised learning to build models for better predicting a number of different health outcomes for patients that suffer from systemic sclerosis, a rare chronic connective tissue disorder - but one that shares many characteristics with other diseases. We explore a number of different algorithms for constructing models that simultaneously predict health outcomes and identify subcategories.

AB - Diseases are often umbrella terms for many subcategories of disease. The identification of these subcategories is vital if we are to develop personalised treatments that are better focussed on individual patients. In this short paper, we explore the use of a combination of unsupervised learning to identify potential subclasses, and supervised learning to build models for better predicting a number of different health outcomes for patients that suffer from systemic sclerosis, a rare chronic connective tissue disorder - but one that shares many characteristics with other diseases. We explore a number of different algorithms for constructing models that simultaneously predict health outcomes and identify subcategories.

KW - Classification

KW - Disease subclass

KW - Systemic sclerosis

UR - http://www.scopus.com/inward/record.url?scp=84987673585&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84987673585&partnerID=8YFLogxK

U2 - 10.1109/CBMS.2016.37

DO - 10.1109/CBMS.2016.37

M3 - Conference contribution

AN - SCOPUS:84987673585

VL - 2016-August

SP - 225

EP - 226

BT - Proceedings - IEEE 29th International Symposium on Computer-Based Medical Systems, CBMS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 29th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2016

Y2 - 20 June 2016 through 23 June 2016

ER -

Combining unsupervised and supervised learning for discovering disease subclasses

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this