Disease risk prediction by mining personalized health trend patterns

A case study on diabetes

Guo Cheng Lan, Chao Hui Lee, Yu Yen Lee, Vincent S. Tseng, Chu Yu Chin, Miin Luen Day, Shyh Chyi Wang, Ching Nain Chang, Shyr Yuan Cheng, Jin-Shang Wu

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

6 Citations (Scopus)

Abstract

Health examination has played an important role for maintaining people's health since it can not only help people understand their own health conditions clearly but also avoid missing the best timing of disease treatment. However, in current health examination systems, people get only a basic report from single health examination and no advanced health risk analysis is provided. In this paper, we proposed an effective mechanism for chronic disease risk prediction by mining the data containing historical health records and personal life style information. Value change trends of the data are important for disease status prediction, and we defined significant ones as health risk patterns in our mechanism. Risks of a chronic disease can be predicted early with a mechanism built with our health risk patterns and it also proven work well through experimental evaluations on real datasets. Our method outperformed traditional mechanism in terms of accuracy, precision and sensitivity for predicting the risk of diabetes. In particular, insightful observations show that the consideration of life-style information can effectively enhance whole performance for risk prediction. Moreover, classification rules produced by our mechanism which integrates C4.5 and CBA provide physicians disease related health risk patterns such that appropriate treatments could be given to people for disease prevention.

Original languageEnglish
Title of host publicationProceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012
Pages27-32
Number of pages6
DOIs
Publication statusPublished - 2012
Event2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012 - Tainan, Taiwan
Duration: 2012 Nov 162012 Nov 18

Other

Other2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012
CountryTaiwan
CityTainan
Period12-11-1612-11-18

Fingerprint

Medical problems
Health risks
Health
Risk analysis

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Lan, G. C., Lee, C. H., Lee, Y. Y., Tseng, V. S., Chin, C. Y., Day, M. L., ... Wu, J-S. (2012). Disease risk prediction by mining personalized health trend patterns: A case study on diabetes. In Proceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012 (pp. 27-32). [6395001] https://doi.org/10.1109/TAAI.2012.53
Lan, Guo Cheng ; Lee, Chao Hui ; Lee, Yu Yen ; Tseng, Vincent S. ; Chin, Chu Yu ; Day, Miin Luen ; Wang, Shyh Chyi ; Chang, Ching Nain ; Cheng, Shyr Yuan ; Wu, Jin-Shang. / Disease risk prediction by mining personalized health trend patterns : A case study on diabetes. Proceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012. 2012. pp. 27-32
@inproceedings{97d0374848224ab2bd24e5be47647d56,
title = "Disease risk prediction by mining personalized health trend patterns: A case study on diabetes",
abstract = "Health examination has played an important role for maintaining people's health since it can not only help people understand their own health conditions clearly but also avoid missing the best timing of disease treatment. However, in current health examination systems, people get only a basic report from single health examination and no advanced health risk analysis is provided. In this paper, we proposed an effective mechanism for chronic disease risk prediction by mining the data containing historical health records and personal life style information. Value change trends of the data are important for disease status prediction, and we defined significant ones as health risk patterns in our mechanism. Risks of a chronic disease can be predicted early with a mechanism built with our health risk patterns and it also proven work well through experimental evaluations on real datasets. Our method outperformed traditional mechanism in terms of accuracy, precision and sensitivity for predicting the risk of diabetes. In particular, insightful observations show that the consideration of life-style information can effectively enhance whole performance for risk prediction. Moreover, classification rules produced by our mechanism which integrates C4.5 and CBA provide physicians disease related health risk patterns such that appropriate treatments could be given to people for disease prevention.",
author = "Lan, {Guo Cheng} and Lee, {Chao Hui} and Lee, {Yu Yen} and Tseng, {Vincent S.} and Chin, {Chu Yu} and Day, {Miin Luen} and Wang, {Shyh Chyi} and Chang, {Ching Nain} and Cheng, {Shyr Yuan} and Jin-Shang Wu",
year = "2012",
doi = "10.1109/TAAI.2012.53",
language = "English",
isbn = "9780769549194",
pages = "27--32",
booktitle = "Proceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012",

}

Lan, GC, Lee, CH, Lee, YY, Tseng, VS, Chin, CY, Day, ML, Wang, SC, Chang, CN, Cheng, SY & Wu, J-S 2012, Disease risk prediction by mining personalized health trend patterns: A case study on diabetes. in Proceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012., 6395001, pp. 27-32, 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012, Tainan, Taiwan, 12-11-16. https://doi.org/10.1109/TAAI.2012.53

Disease risk prediction by mining personalized health trend patterns : A case study on diabetes. / Lan, Guo Cheng; Lee, Chao Hui; Lee, Yu Yen; Tseng, Vincent S.; Chin, Chu Yu; Day, Miin Luen; Wang, Shyh Chyi; Chang, Ching Nain; Cheng, Shyr Yuan; Wu, Jin-Shang.

Proceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012. 2012. p. 27-32 6395001.

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

TY - GEN

T1 - Disease risk prediction by mining personalized health trend patterns

T2 - A case study on diabetes

AU - Lan, Guo Cheng

AU - Lee, Chao Hui

AU - Lee, Yu Yen

AU - Tseng, Vincent S.

AU - Chin, Chu Yu

AU - Day, Miin Luen

AU - Wang, Shyh Chyi

AU - Chang, Ching Nain

AU - Cheng, Shyr Yuan

AU - Wu, Jin-Shang

PY - 2012

Y1 - 2012

N2 - Health examination has played an important role for maintaining people's health since it can not only help people understand their own health conditions clearly but also avoid missing the best timing of disease treatment. However, in current health examination systems, people get only a basic report from single health examination and no advanced health risk analysis is provided. In this paper, we proposed an effective mechanism for chronic disease risk prediction by mining the data containing historical health records and personal life style information. Value change trends of the data are important for disease status prediction, and we defined significant ones as health risk patterns in our mechanism. Risks of a chronic disease can be predicted early with a mechanism built with our health risk patterns and it also proven work well through experimental evaluations on real datasets. Our method outperformed traditional mechanism in terms of accuracy, precision and sensitivity for predicting the risk of diabetes. In particular, insightful observations show that the consideration of life-style information can effectively enhance whole performance for risk prediction. Moreover, classification rules produced by our mechanism which integrates C4.5 and CBA provide physicians disease related health risk patterns such that appropriate treatments could be given to people for disease prevention.

AB - Health examination has played an important role for maintaining people's health since it can not only help people understand their own health conditions clearly but also avoid missing the best timing of disease treatment. However, in current health examination systems, people get only a basic report from single health examination and no advanced health risk analysis is provided. In this paper, we proposed an effective mechanism for chronic disease risk prediction by mining the data containing historical health records and personal life style information. Value change trends of the data are important for disease status prediction, and we defined significant ones as health risk patterns in our mechanism. Risks of a chronic disease can be predicted early with a mechanism built with our health risk patterns and it also proven work well through experimental evaluations on real datasets. Our method outperformed traditional mechanism in terms of accuracy, precision and sensitivity for predicting the risk of diabetes. In particular, insightful observations show that the consideration of life-style information can effectively enhance whole performance for risk prediction. Moreover, classification rules produced by our mechanism which integrates C4.5 and CBA provide physicians disease related health risk patterns such that appropriate treatments could be given to people for disease prevention.

UR - http://www.scopus.com/inward/record.url?scp=84873398640&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873398640&partnerID=8YFLogxK

U2 - 10.1109/TAAI.2012.53

DO - 10.1109/TAAI.2012.53

M3 - Conference contribution

SN - 9780769549194

SP - 27

EP - 32

BT - Proceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012

ER -

Lan GC, Lee CH, Lee YY, Tseng VS, Chin CY, Day ML et al. Disease risk prediction by mining personalized health trend patterns: A case study on diabetes. In Proceedings - 2012 Conference on Technologies and Applications of Artificial Intelligence, TAAI 2012. 2012. p. 27-32. 6395001 https://doi.org/10.1109/TAAI.2012.53