Personal health indexing based on medical examinations: A data mining approach

Ling Chen; Xue Li; Yi Yang; Hanna Kurniawati; Quan Z. Sheng; Hsiao Yun Hu; Nicole Huang

doi:10.1016/j.dss.2015.10.008

Personal health indexing based on medical examinations: A data mining approach

Ling Chen^*, Xue Li, Yi Yang, Hanna Kurniawati, Quan Z. Sheng, Hsiao Yun Hu, Nicole Huang

^*Corresponding author for this work

Institute of Hospital and Health Care Administration

Research output: Contribution to journal › Article › peer-review

32 Scopus citations

Abstract

We design a method called MyPHI that predicts personal health index (PHI), a new evidence-based health indicator to explore the underlying patterns of a large collection of geriatric medical examination (GME) records using data mining techniques. We define PHI as a vector of scores, each reflecting the health risk in a particular disease category. The PHI prediction is formulated as an optimization problem that finds the optimal soft labels as health scores based on medical records that are infrequent, incomplete, and sparse. Our method is compared with classification models commonly used in medical applications. The experimental evaluation has demonstrated the effectiveness of our method based on a real-world GME data set collected from 102,258 participants.

Original language	English
Pages (from-to)	54-65
Number of pages	12
Journal	Decision Support Systems
Volume	81
DOIs	https://doi.org/10.1016/j.dss.2015.10.008
State	Published - Jan 2016

Keywords

Data mining
Feature extraction
Geriatric medical examination
Label uncertainty
Personal health index

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.dss.2015.10.008

Cite this

@article{e2b21ff476f740958b032629a4159865,

title = "Personal health indexing based on medical examinations: A data mining approach",

abstract = "We design a method called MyPHI that predicts personal health index (PHI), a new evidence-based health indicator to explore the underlying patterns of a large collection of geriatric medical examination (GME) records using data mining techniques. We define PHI as a vector of scores, each reflecting the health risk in a particular disease category. The PHI prediction is formulated as an optimization problem that finds the optimal soft labels as health scores based on medical records that are infrequent, incomplete, and sparse. Our method is compared with classification models commonly used in medical applications. The experimental evaluation has demonstrated the effectiveness of our method based on a real-world GME data set collected from 102,258 participants.",

keywords = "Data mining, Feature extraction, Geriatric medical examination, Label uncertainty, Personal health index",

author = "Ling Chen and Xue Li and Yi Yang and Hanna Kurniawati and Sheng, {Quan Z.} and Hu, {Hsiao Yun} and Nicole Huang",

year = "2016",

month = jan,

doi = "10.1016/j.dss.2015.10.008",

language = "English",

volume = "81",

pages = "54--65",

journal = "Decision Support Systems",

issn = "0167-9236",

publisher = "Elsevier",

}

TY - JOUR

T1 - Personal health indexing based on medical examinations

T2 - A data mining approach

AU - Chen, Ling

AU - Li, Xue

AU - Yang, Yi

AU - Kurniawati, Hanna

AU - Sheng, Quan Z.

AU - Hu, Hsiao Yun

AU - Huang, Nicole

PY - 2016/1

Y1 - 2016/1

N2 - We design a method called MyPHI that predicts personal health index (PHI), a new evidence-based health indicator to explore the underlying patterns of a large collection of geriatric medical examination (GME) records using data mining techniques. We define PHI as a vector of scores, each reflecting the health risk in a particular disease category. The PHI prediction is formulated as an optimization problem that finds the optimal soft labels as health scores based on medical records that are infrequent, incomplete, and sparse. Our method is compared with classification models commonly used in medical applications. The experimental evaluation has demonstrated the effectiveness of our method based on a real-world GME data set collected from 102,258 participants.

AB - We design a method called MyPHI that predicts personal health index (PHI), a new evidence-based health indicator to explore the underlying patterns of a large collection of geriatric medical examination (GME) records using data mining techniques. We define PHI as a vector of scores, each reflecting the health risk in a particular disease category. The PHI prediction is formulated as an optimization problem that finds the optimal soft labels as health scores based on medical records that are infrequent, incomplete, and sparse. Our method is compared with classification models commonly used in medical applications. The experimental evaluation has demonstrated the effectiveness of our method based on a real-world GME data set collected from 102,258 participants.

KW - Data mining

KW - Feature extraction

KW - Geriatric medical examination

KW - Label uncertainty

KW - Personal health index

UR - http://www.scopus.com/inward/record.url?scp=84952863423&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2015.10.008

DO - 10.1016/j.dss.2015.10.008

M3 - Article

AN - SCOPUS:84952863423

SN - 0167-9236

VL - 81

SP - 54

EP - 65

JO - Decision Support Systems

JF - Decision Support Systems

ER -

Personal health indexing based on medical examinations: A data mining approach

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this