Method of Screening the Health of Persons with High Risk for Potential Lifestyle-related Diseases using LDA - Toward a Better Screening Method for Persons with High Health Risks

Keisuke Ogawa, Kazunori Matsumoto, Masayuki Hashimoto, Ryoichi Nagatomi

2015

Abstract

Recently, the number of patients with lifestyle-related diseases, such as diabetes mellitus, has increased dramatically. Lifestyle-related diseases are responsible for 60% of deaths in Japan. In order to screen persons at potentially high risk for these diseases, medical checkups for metabolic syndrome are used throughout Japan. Prediction and prevention of lifestyle-related diseases would yield a direct reduction in medical costs. However, many cases cannot be screened with a metabolic syndrome checkup. In this paper, we propose a new machine-learning-based screening method using medical checkup data and medical billings. By processing the medical data into a bag-of-words representation and classifying the health factors using latent Dirichlet allocation (LDA), the screening method achieves high accuracy. We evaluate the method by comparing the accuracy of predictions of the future incidence of the diseases. The results show that F-measure increases 0.17 compared with the conventional method. In addition, we confirmed that the proposed method classified persons with different health risk factors, such as a combination of metabolic disorders, hypertensive disorders, and mental disorders (stress).

References

  1. Labour and Welfare, Report of Lifestyle-Related Disease Administration Using Medical Checkup and Billing Data 2007.
  2. Health, Labour and Welfare Statistics Association, Trend of National Health, Journal of Health and Welfare Statistics: 449-453, 2002.
  3. Ministry of Health, Labour and Welfare, Overview of national medical cost in 2010, http://www.mhlw. go.jp/toukei/saikin/hw/k-iryohi/10/, 2010.
  4. K. G. M. M. Alberti, P. Zimmet and J. Shaw, Metabolic syndrome-a new world-wide definition. A Consensus Statement from the International Diabetes Federation, Diabetic Medicine, 23:469-480, 2006.
  5. Maria D. Llorente and Victoria Urrutia, Diabetes, Psychiatric Disorders, and the Metabolic Effects of Antipsychotic Medications, Journal of Clinical Diabetes, Vol.24 No.1:18-24, 2006.
  6. H. Klar Yaggi, Andre B. Araujo and John B. McKinlay, Sleep Duration as a Risk Factor for the Development of Type 2 Diabetes, Journal of Diabetes Care, Vol.29 No.3:657-661,2006.
  7. World Health Organization (WHO), Definition, Diagnosis and Classification of Diabetes Mellitus and its Complications, Report of a WHO consultation, 1999.
  8. Ogushi, Metabo no wana, Kadokawa shinsho, 2007.
  9. Wataru Sakamoto, Naoki Isogawa, and Masashi Goto, Statistical problem of Japanese metabolic syndrome criteria, The Behaviometric Society of Japan, 69:177- 192, 2008.
  10. David M. Blei. Ng, A. Y. and Jordan, M. I., Latent Dirichlet Allocation. Journal of Machine Learning Research 3:993-1022, 2003.
  11. Fei-Fei.L. and Perona P., A Bayesian Hierarchical Model for Learning Natural Scene Categories, CVPR 2005. IEEE Computer Society Conference, 2005.
  12. Chong Wang, David M. Blei, and Li Fei-Fei, Simultaneous image classification and annotation, CVPR 2009, IEEE Conference, 2009.
  13. Yang Wang, and Greg Mori, Human Action Recognition by Semi-latent Topic Models, Pattern Analysis and Machine Intelligence, IEEE Transactions, 2009.
  14. Niebles et al., Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words, International Journal of Computer Vision, Vol. 79:299-318,2008.
  15. Griffiths T.L. and Steyvers M., Finding scientific topics, proceedings of the National Academy of Science, 101:5228-5235, 2004.
  16. Yee Whye Teh et al., A Collapsed Variational Bayesian Inference Algorithm for Latent Dirichlet Allocation, NIPS, Vol. 19, 2006.
  17. Ishiguro et al., Probabilistic Speaker Diarization with Bagof-Words Representations of Speaker Angle Information, IEEE Transcription, Vol. 20(2):447-460, 2012.
  18. Otsuka et al., Bayesian Unification of Sound Source Localization and Separation with Permutation Resolution, Proc. AAAI, 2012.
Download


Paper Citation


in Harvard Style

Ogawa K., Matsumoto K., Hashimoto M. and Nagatomi R. (2015). Method of Screening the Health of Persons with High Risk for Potential Lifestyle-related Diseases using LDA - Toward a Better Screening Method for Persons with High Health Risks . In Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2015) ISBN 978-989-758-068-0, pages 502-507. DOI: 10.5220/0005250905020507


in Bibtex Style

@conference{healthinf15,
author={Keisuke Ogawa and Kazunori Matsumoto and Masayuki Hashimoto and Ryoichi Nagatomi},
title={Method of Screening the Health of Persons with High Risk for Potential Lifestyle-related Diseases using LDA - Toward a Better Screening Method for Persons with High Health Risks},
booktitle={Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2015)},
year={2015},
pages={502-507},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005250905020507},
isbn={978-989-758-068-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2015)
TI - Method of Screening the Health of Persons with High Risk for Potential Lifestyle-related Diseases using LDA - Toward a Better Screening Method for Persons with High Health Risks
SN - 978-989-758-068-0
AU - Ogawa K.
AU - Matsumoto K.
AU - Hashimoto M.
AU - Nagatomi R.
PY - 2015
SP - 502
EP - 507
DO - 10.5220/0005250905020507