Early Cancer Detection from Multianalyte Blood Test Results

Ka-Chun WONG; Junyi CHEN; Jiao ZHANG; Jiecong LIN; Shankai YAN; Shxiong ZHANG; Xiangtao LI; Cheng LIANG; Chengbin PENG; Qiuzhen LIN; Sam KWONG; Jun YU

doi:10.1016/j.isci.2019.04.035

Early Cancer Detection from Multianalyte Blood Test Results

Ka-Chun WONG^*, Junyi CHEN, Jiao ZHANG, Jiecong LIN, Shankai YAN, Shxiong ZHANG, Xiangtao LI, Cheng LIANG, Chengbin PENG, Qiuzhen LIN, Sam KWONG, Jun YU

^*Corresponding author for this work

Research output: Journal Publications › Journal Article (refereed) › peer-review

22 Citations (Scopus)

Abstract

The early detection of cancers has the potential to save many lives. A recent attempt has been demonstrated successful. However, we note several critical limitations. Given the central importance and broad impact of early cancer detection, we aspire to address those limitations. We explore different supervised learning approaches for multiple cancer type detection and observe significant improvements; for instance, one of our approaches (i.e., CancerA1DE) can double the existing sensitivity from 38% to 77% for the earliest cancer detection (i.e., Stage I) at the 99% specificity level. For Stage II, it can even reach up to about 90% across multiple cancer types. In addition, CancerA1DE can also double the existing sensitivity from 30% to 70% for detecting breast cancers at the 99% specificity level. Data and model analysis are conducted to reveal the underlying reasons. A website is built at http://cancer.cs.cityu.edu.hk/.

Original language	English
Pages (from-to)	332-341
Number of pages	10
Journal	iScience
Volume	15
Early online date	4 May 2019
DOIs	https://doi.org/10.1016/j.isci.2019.04.035
Publication status	Published - 31 May 2019
Externally published	Yes

Bibliographical note

Publisher Copyright:
© 2019

Funding

The authors would like to thank the reviewers for their constructive comments. They would also like to thank Prashant Sridhar and Ajay Rajnikanth for their English proofreading. The work described in this paper was substantially supported by three grants from the Research Grants Council of the Hong Kong Special Administrative Region [CityU 21200816 ], [CityU 11203217 ], and [CityU 11200218 ]. We acknowledge the donation support of the Titan Xp GPU from the Nvidia Corporation.

Keywords

Algorithms
Bioinformatics
Biological Sciences
Cancer
Cancer Systems Biology

UN SDGs

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

Access to Document

10.1016/j.isci.2019.04.035Licence: CC BY-NC-ND

Cite this

@article{63c2850dc0464c3d8b7c41b65ac30be6,

title = "Early Cancer Detection from Multianalyte Blood Test Results",

abstract = "The early detection of cancers has the potential to save many lives. A recent attempt has been demonstrated successful. However, we note several critical limitations. Given the central importance and broad impact of early cancer detection, we aspire to address those limitations. We explore different supervised learning approaches for multiple cancer type detection and observe significant improvements; for instance, one of our approaches (i.e., CancerA1DE) can double the existing sensitivity from 38% to 77% for the earliest cancer detection (i.e., Stage I) at the 99% specificity level. For Stage II, it can even reach up to about 90% across multiple cancer types. In addition, CancerA1DE can also double the existing sensitivity from 30% to 70% for detecting breast cancers at the 99% specificity level. Data and model analysis are conducted to reveal the underlying reasons. A website is built at http://cancer.cs.cityu.edu.hk/.",

keywords = "Algorithms, Bioinformatics, Biological Sciences, Cancer, Cancer Systems Biology",

author = "Ka-Chun WONG and Junyi CHEN and Jiao ZHANG and Jiecong LIN and Shankai YAN and Shxiong ZHANG and Xiangtao LI and Cheng LIANG and Chengbin PENG and Qiuzhen LIN and Sam KWONG and Jun YU",

note = "Publisher Copyright: {\textcopyright} 2019",

year = "2019",

month = may,

day = "31",

doi = "10.1016/j.isci.2019.04.035",

language = "English",

volume = "15",

pages = "332--341",

journal = "iScience",

issn = "2589-0042",

publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Early Cancer Detection from Multianalyte Blood Test Results

AU - WONG, Ka-Chun

AU - CHEN, Junyi

AU - ZHANG, Jiao

AU - LIN, Jiecong

AU - YAN, Shankai

AU - ZHANG, Shxiong

AU - LI, Xiangtao

AU - LIANG, Cheng

AU - PENG, Chengbin

AU - LIN, Qiuzhen

AU - KWONG, Sam

AU - YU, Jun

PY - 2019/5/31

Y1 - 2019/5/31

N2 - The early detection of cancers has the potential to save many lives. A recent attempt has been demonstrated successful. However, we note several critical limitations. Given the central importance and broad impact of early cancer detection, we aspire to address those limitations. We explore different supervised learning approaches for multiple cancer type detection and observe significant improvements; for instance, one of our approaches (i.e., CancerA1DE) can double the existing sensitivity from 38% to 77% for the earliest cancer detection (i.e., Stage I) at the 99% specificity level. For Stage II, it can even reach up to about 90% across multiple cancer types. In addition, CancerA1DE can also double the existing sensitivity from 30% to 70% for detecting breast cancers at the 99% specificity level. Data and model analysis are conducted to reveal the underlying reasons. A website is built at http://cancer.cs.cityu.edu.hk/.

AB - The early detection of cancers has the potential to save many lives. A recent attempt has been demonstrated successful. However, we note several critical limitations. Given the central importance and broad impact of early cancer detection, we aspire to address those limitations. We explore different supervised learning approaches for multiple cancer type detection and observe significant improvements; for instance, one of our approaches (i.e., CancerA1DE) can double the existing sensitivity from 38% to 77% for the earliest cancer detection (i.e., Stage I) at the 99% specificity level. For Stage II, it can even reach up to about 90% across multiple cancer types. In addition, CancerA1DE can also double the existing sensitivity from 30% to 70% for detecting breast cancers at the 99% specificity level. Data and model analysis are conducted to reveal the underlying reasons. A website is built at http://cancer.cs.cityu.edu.hk/.

KW - Algorithms

KW - Bioinformatics

KW - Biological Sciences

KW - Cancer

KW - Cancer Systems Biology

UR - http://www.scopus.com/inward/record.url?scp=85066313563&partnerID=8YFLogxK

U2 - 10.1016/j.isci.2019.04.035

DO - 10.1016/j.isci.2019.04.035

M3 - Journal Article (refereed)

AN - SCOPUS:85066313563

SN - 2589-0042

VL - 15

SP - 332

EP - 341

JO - iScience

JF - iScience

ER -

Early Cancer Detection from Multianalyte Blood Test Results

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this