Cross-network clustering and cluster ranking for medical diagnosis

Jingchao Ni, Hongliang Fei, Wei Fan, Xiang Zhang

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

5 Citations (Scopus)

Abstract

Automating medical diagnosis is an important data mining problem, which is to infer likely disease(s) for some observed symptoms. Algorithms to the problem are very beneficial as a supplement to a real diagnosis. Existing diagnosis methods typically perform the inference on a sparse bipartite graph with two sets of nodes representing diseases and symptoms, respectively. By using this graph, existing methods basically assume no direct dependency exists between diseases (or symptoms), which may not be true in reality. To address this limitation, in this paper, we introduce two domain networks encoding similarities between diseases and those between symptoms to avoid information loss as well as to alleviate the sparsity problem of the bipartite graph. Based on the domain networks and the bipartite graph bridging them, we develop a novel algorithm, CCCR, to perform diagnosis by ranking symptom-disease clusters. Comparing with existing approaches, CCCR is more accurate, and more interpretable since its results deliver rich information about how the inferred diseases are categorized. Experimental results on real-life datasets demonstrate the effectiveness of the proposed method.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017
PublisherIEEE Computer Society
Pages163-166
Number of pages4
ISBN (Electronic)9781509065431
DOIs
StatePublished - May 16 2017
Event33rd IEEE International Conference on Data Engineering, ICDE 2017 - San Diego, United States
Duration: Apr 19 2017Apr 22 2017

Publication series

NameProceedings - International Conference on Data Engineering
ISSN (Print)1084-4627

Other

Other33rd IEEE International Conference on Data Engineering, ICDE 2017
CountryUnited States
CitySan Diego
Period4/19/174/22/17

Fingerprint

Data mining

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Information Systems

Cite this

Ni, J., Fei, H., Fan, W., & Zhang, X. (2017). Cross-network clustering and cluster ranking for medical diagnosis. In Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017 (pp. 163-166). [7929961] (Proceedings - International Conference on Data Engineering). IEEE Computer Society. https://doi.org/10.1109/ICDE.2017.65
Ni, Jingchao ; Fei, Hongliang ; Fan, Wei ; Zhang, Xiang. / Cross-network clustering and cluster ranking for medical diagnosis. Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017. IEEE Computer Society, 2017. pp. 163-166 (Proceedings - International Conference on Data Engineering).
@inproceedings{5e1dcf34cbb341119d80440b5e5df614,
title = "Cross-network clustering and cluster ranking for medical diagnosis",
abstract = "Automating medical diagnosis is an important data mining problem, which is to infer likely disease(s) for some observed symptoms. Algorithms to the problem are very beneficial as a supplement to a real diagnosis. Existing diagnosis methods typically perform the inference on a sparse bipartite graph with two sets of nodes representing diseases and symptoms, respectively. By using this graph, existing methods basically assume no direct dependency exists between diseases (or symptoms), which may not be true in reality. To address this limitation, in this paper, we introduce two domain networks encoding similarities between diseases and those between symptoms to avoid information loss as well as to alleviate the sparsity problem of the bipartite graph. Based on the domain networks and the bipartite graph bridging them, we develop a novel algorithm, CCCR, to perform diagnosis by ranking symptom-disease clusters. Comparing with existing approaches, CCCR is more accurate, and more interpretable since its results deliver rich information about how the inferred diseases are categorized. Experimental results on real-life datasets demonstrate the effectiveness of the proposed method.",
author = "Jingchao Ni and Hongliang Fei and Wei Fan and Xiang Zhang",
year = "2017",
month = "5",
day = "16",
doi = "10.1109/ICDE.2017.65",
language = "English (US)",
series = "Proceedings - International Conference on Data Engineering",
publisher = "IEEE Computer Society",
pages = "163--166",
booktitle = "Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017",
address = "United States",

}

Ni, J, Fei, H, Fan, W & Zhang, X 2017, Cross-network clustering and cluster ranking for medical diagnosis. in Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017., 7929961, Proceedings - International Conference on Data Engineering, IEEE Computer Society, pp. 163-166, 33rd IEEE International Conference on Data Engineering, ICDE 2017, San Diego, United States, 4/19/17. https://doi.org/10.1109/ICDE.2017.65

Cross-network clustering and cluster ranking for medical diagnosis. / Ni, Jingchao; Fei, Hongliang; Fan, Wei; Zhang, Xiang.

Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017. IEEE Computer Society, 2017. p. 163-166 7929961 (Proceedings - International Conference on Data Engineering).

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

TY - GEN

T1 - Cross-network clustering and cluster ranking for medical diagnosis

AU - Ni, Jingchao

AU - Fei, Hongliang

AU - Fan, Wei

AU - Zhang, Xiang

PY - 2017/5/16

Y1 - 2017/5/16

N2 - Automating medical diagnosis is an important data mining problem, which is to infer likely disease(s) for some observed symptoms. Algorithms to the problem are very beneficial as a supplement to a real diagnosis. Existing diagnosis methods typically perform the inference on a sparse bipartite graph with two sets of nodes representing diseases and symptoms, respectively. By using this graph, existing methods basically assume no direct dependency exists between diseases (or symptoms), which may not be true in reality. To address this limitation, in this paper, we introduce two domain networks encoding similarities between diseases and those between symptoms to avoid information loss as well as to alleviate the sparsity problem of the bipartite graph. Based on the domain networks and the bipartite graph bridging them, we develop a novel algorithm, CCCR, to perform diagnosis by ranking symptom-disease clusters. Comparing with existing approaches, CCCR is more accurate, and more interpretable since its results deliver rich information about how the inferred diseases are categorized. Experimental results on real-life datasets demonstrate the effectiveness of the proposed method.

AB - Automating medical diagnosis is an important data mining problem, which is to infer likely disease(s) for some observed symptoms. Algorithms to the problem are very beneficial as a supplement to a real diagnosis. Existing diagnosis methods typically perform the inference on a sparse bipartite graph with two sets of nodes representing diseases and symptoms, respectively. By using this graph, existing methods basically assume no direct dependency exists between diseases (or symptoms), which may not be true in reality. To address this limitation, in this paper, we introduce two domain networks encoding similarities between diseases and those between symptoms to avoid information loss as well as to alleviate the sparsity problem of the bipartite graph. Based on the domain networks and the bipartite graph bridging them, we develop a novel algorithm, CCCR, to perform diagnosis by ranking symptom-disease clusters. Comparing with existing approaches, CCCR is more accurate, and more interpretable since its results deliver rich information about how the inferred diseases are categorized. Experimental results on real-life datasets demonstrate the effectiveness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=85021251872&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021251872&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2017.65

DO - 10.1109/ICDE.2017.65

M3 - Conference contribution

AN - SCOPUS:85021251872

T3 - Proceedings - International Conference on Data Engineering

SP - 163

EP - 166

BT - Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017

PB - IEEE Computer Society

ER -

Ni J, Fei H, Fan W, Zhang X. Cross-network clustering and cluster ranking for medical diagnosis. In Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017. IEEE Computer Society. 2017. p. 163-166. 7929961. (Proceedings - International Conference on Data Engineering). https://doi.org/10.1109/ICDE.2017.65