Mining discriminative patterns to predict health status for cardiopulmonary patients

Qian Cheng, Jingbo Shang, Joshua Juen, Jiawei Han, Bruce R Schatz

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

Abstract

Smartphones are ubiquitous now, but it is still unclear what physiological functions they can monitor at clinical quality. Pulmonary function is a standard measure of health status for cardiopulmonary patients. We have shown that predictive models can accurately classify cardiopulmonary conditions from healthy status, as well as different severity levels within cardiopulmonary disease, the GOLD stages. Here we propose several universal models to monitor cardiopulmonary conditions, including DPClass, a novel learning approach we designed. We carefully prepare motion dataset covering status from GOLD 0 (healthy), GOLD 1(mild), GOLD 2(moderate), all the way to GOLD 3 (severe). Sixty-six subjects participate in this study. After de-identification, their walking data are applied to train the predictive models. The RBF-SVM model yields the highest accuracy while the DPClass model provides better interpretation of the model mechanisms. We not only provide promising solutions to monitor health status by simply carrying a smartphone, but also demonstrate how demographics influences predictive models of cardiopulmonary disease.

Original languageEnglish (US)
Title of host publicationACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics
PublisherAssociation for Computing Machinery, Inc
Pages41-49
Number of pages9
ISBN (Electronic)9781450342254
DOIs
StatePublished - Oct 2 2016
Event7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2016 - Seattle, United States
Duration: Oct 2 2016Oct 5 2016

Publication series

NameACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

Other

Other7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2016
CountryUnited States
CitySeattle
Period10/2/1610/5/16

Fingerprint

Health Status
Health
Walking
Demography
Learning
Smartphones
Lung
Smartphone
Datasets

Keywords

  • Chronic disease assessment
  • Discriminative pattern mining
  • Free-living health monitoring

ASJC Scopus subject areas

  • Software
  • Health Informatics
  • Biomedical Engineering
  • Computer Science Applications

Cite this

Cheng, Q., Shang, J., Juen, J., Han, J., & Schatz, B. R. (2016). Mining discriminative patterns to predict health status for cardiopulmonary patients. In ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 41-49). (ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics). Association for Computing Machinery, Inc. https://doi.org/10.1145/2975167.2975171

Mining discriminative patterns to predict health status for cardiopulmonary patients. / Cheng, Qian; Shang, Jingbo; Juen, Joshua; Han, Jiawei; Schatz, Bruce R.

ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2016. p. 41-49 (ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics).

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

Cheng, Q, Shang, J, Juen, J, Han, J & Schatz, BR 2016, Mining discriminative patterns to predict health status for cardiopulmonary patients. in ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, Association for Computing Machinery, Inc, pp. 41-49, 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2016, Seattle, United States, 10/2/16. https://doi.org/10.1145/2975167.2975171
Cheng Q, Shang J, Juen J, Han J, Schatz BR. Mining discriminative patterns to predict health status for cardiopulmonary patients. In ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc. 2016. p. 41-49. (ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics). https://doi.org/10.1145/2975167.2975171
Cheng, Qian ; Shang, Jingbo ; Juen, Joshua ; Han, Jiawei ; Schatz, Bruce R. / Mining discriminative patterns to predict health status for cardiopulmonary patients. ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics. Association for Computing Machinery, Inc, 2016. pp. 41-49 (ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics).
@inproceedings{56c2e1c8a8bb43469ec95876aaabb154,
title = "Mining discriminative patterns to predict health status for cardiopulmonary patients",
abstract = "Smartphones are ubiquitous now, but it is still unclear what physiological functions they can monitor at clinical quality. Pulmonary function is a standard measure of health status for cardiopulmonary patients. We have shown that predictive models can accurately classify cardiopulmonary conditions from healthy status, as well as different severity levels within cardiopulmonary disease, the GOLD stages. Here we propose several universal models to monitor cardiopulmonary conditions, including DPClass, a novel learning approach we designed. We carefully prepare motion dataset covering status from GOLD 0 (healthy), GOLD 1(mild), GOLD 2(moderate), all the way to GOLD 3 (severe). Sixty-six subjects participate in this study. After de-identification, their walking data are applied to train the predictive models. The RBF-SVM model yields the highest accuracy while the DPClass model provides better interpretation of the model mechanisms. We not only provide promising solutions to monitor health status by simply carrying a smartphone, but also demonstrate how demographics influences predictive models of cardiopulmonary disease.",
keywords = "Chronic disease assessment, Discriminative pattern mining, Free-living health monitoring",
author = "Qian Cheng and Jingbo Shang and Joshua Juen and Jiawei Han and Schatz, {Bruce R}",
year = "2016",
month = "10",
day = "2",
doi = "10.1145/2975167.2975171",
language = "English (US)",
series = "ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics",
publisher = "Association for Computing Machinery, Inc",
pages = "41--49",
booktitle = "ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics",

}

TY - GEN

T1 - Mining discriminative patterns to predict health status for cardiopulmonary patients

AU - Cheng, Qian

AU - Shang, Jingbo

AU - Juen, Joshua

AU - Han, Jiawei

AU - Schatz, Bruce R

PY - 2016/10/2

Y1 - 2016/10/2

N2 - Smartphones are ubiquitous now, but it is still unclear what physiological functions they can monitor at clinical quality. Pulmonary function is a standard measure of health status for cardiopulmonary patients. We have shown that predictive models can accurately classify cardiopulmonary conditions from healthy status, as well as different severity levels within cardiopulmonary disease, the GOLD stages. Here we propose several universal models to monitor cardiopulmonary conditions, including DPClass, a novel learning approach we designed. We carefully prepare motion dataset covering status from GOLD 0 (healthy), GOLD 1(mild), GOLD 2(moderate), all the way to GOLD 3 (severe). Sixty-six subjects participate in this study. After de-identification, their walking data are applied to train the predictive models. The RBF-SVM model yields the highest accuracy while the DPClass model provides better interpretation of the model mechanisms. We not only provide promising solutions to monitor health status by simply carrying a smartphone, but also demonstrate how demographics influences predictive models of cardiopulmonary disease.

AB - Smartphones are ubiquitous now, but it is still unclear what physiological functions they can monitor at clinical quality. Pulmonary function is a standard measure of health status for cardiopulmonary patients. We have shown that predictive models can accurately classify cardiopulmonary conditions from healthy status, as well as different severity levels within cardiopulmonary disease, the GOLD stages. Here we propose several universal models to monitor cardiopulmonary conditions, including DPClass, a novel learning approach we designed. We carefully prepare motion dataset covering status from GOLD 0 (healthy), GOLD 1(mild), GOLD 2(moderate), all the way to GOLD 3 (severe). Sixty-six subjects participate in this study. After de-identification, their walking data are applied to train the predictive models. The RBF-SVM model yields the highest accuracy while the DPClass model provides better interpretation of the model mechanisms. We not only provide promising solutions to monitor health status by simply carrying a smartphone, but also demonstrate how demographics influences predictive models of cardiopulmonary disease.

KW - Chronic disease assessment

KW - Discriminative pattern mining

KW - Free-living health monitoring

UR - http://www.scopus.com/inward/record.url?scp=85009826594&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009826594&partnerID=8YFLogxK

U2 - 10.1145/2975167.2975171

DO - 10.1145/2975167.2975171

M3 - Conference contribution

AN - SCOPUS:85009826594

T3 - ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

SP - 41

EP - 49

BT - ACM-BCB 2016 - 7th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

PB - Association for Computing Machinery, Inc

ER -