Cardiovascular Risk Prediction Based on XGBoost

Nitten S. Rajliwall, Rachel Davey, Girija Chetty

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

Detection of early signs of the diseases at geospatial level can help in promoting evidence-based health policies and proper disease management strategies to be formulated beforehand. In this paper, we report the performance of XGboosting algorithm as a part of a novel unified predictive modelling framework. The proposed scalable end to end tree boosting system called XGBoost, results in significantly improved performance. The experimental validation of the proposed algorithm, when compared with traditional shallow machine learning techniques, for two publicly available cardiovascular disease datasets (the NHANES dataset, and the Framingham Heart Study CHS dataset), resulted in promising outcomes, in terms of performance of different performance metrics including prediction accuracy and model building time.

Original languageEnglish
Title of host publicationProceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering
Subtitle of host publicationAPWConCSE 2018
EditorsA B M Shawkat Ali, Shah Miah, Maheswara Rao Valluri
Place of PublicationDanvers, USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages246-252
Number of pages7
ISBN (Print)9781728113906
DOIs
Publication statusPublished - 10 Dec 2018
Event2018 5th Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE)
- Momi Bay, Fiji, Nadi, Fiji
Duration: 10 Dec 201812 Dec 2018
http://ilab-australia.org/apwconcse2018/

Publication series

NameProceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018

Conference

Conference2018 5th Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE)
Abbreviated title(APWC on CSE
CountryFiji
CityNadi
Period10/12/1812/12/18
Internet address

Fingerprint

Nutrition Surveys
Disease Management
Health Policy
Learning systems
Early Diagnosis
Cardiovascular Diseases
Health
Datasets
Machine Learning

Cite this

Rajliwall, N. S., Davey, R., & Chetty, G. (2018). Cardiovascular Risk Prediction Based on XGBoost. In A. B. M. S. Ali, S. Miah, & M. R. Valluri (Eds.), Proceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering : APWConCSE 2018 (pp. 246-252). [8853798] (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018). Danvers, USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/apwconcse.2018.00047
Rajliwall, Nitten S. ; Davey, Rachel ; Chetty, Girija. / Cardiovascular Risk Prediction Based on XGBoost. Proceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering : APWConCSE 2018 . editor / A B M Shawkat Ali ; Shah Miah ; Maheswara Rao Valluri. Danvers, USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 246-252 (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018).
@inproceedings{4cd3e832c8e6460985d1cc01bf34e6fb,
title = "Cardiovascular Risk Prediction Based on XGBoost",
abstract = "Detection of early signs of the diseases at geospatial level can help in promoting evidence-based health policies and proper disease management strategies to be formulated beforehand. In this paper, we report the performance of XGboosting algorithm as a part of a novel unified predictive modelling framework. The proposed scalable end to end tree boosting system called XGBoost, results in significantly improved performance. The experimental validation of the proposed algorithm, when compared with traditional shallow machine learning techniques, for two publicly available cardiovascular disease datasets (the NHANES dataset, and the Framingham Heart Study CHS dataset), resulted in promising outcomes, in terms of performance of different performance metrics including prediction accuracy and model building time.",
keywords = "cardiovascular diseases, Data Analytics, Machine Learning, Obesity, Predictive modelling, Public health management",
author = "Rajliwall, {Nitten S.} and Rachel Davey and Girija Chetty",
year = "2018",
month = "12",
day = "10",
doi = "10.1109/apwconcse.2018.00047",
language = "English",
isbn = "9781728113906",
series = "Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "246--252",
editor = "Ali, {A B M Shawkat} and Shah Miah and Valluri, {Maheswara Rao}",
booktitle = "Proceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering",
address = "United States",

}

Rajliwall, NS, Davey, R & Chetty, G 2018, Cardiovascular Risk Prediction Based on XGBoost. in ABMS Ali, S Miah & MR Valluri (eds), Proceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering : APWConCSE 2018 ., 8853798, Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018, IEEE, Institute of Electrical and Electronics Engineers, Danvers, USA, pp. 246-252, 2018 5th Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE)
, Nadi, Fiji, 10/12/18. https://doi.org/10.1109/apwconcse.2018.00047

Cardiovascular Risk Prediction Based on XGBoost. / Rajliwall, Nitten S.; Davey, Rachel; Chetty, Girija.

Proceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering : APWConCSE 2018 . ed. / A B M Shawkat Ali; Shah Miah; Maheswara Rao Valluri. Danvers, USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 246-252 8853798 (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Cardiovascular Risk Prediction Based on XGBoost

AU - Rajliwall, Nitten S.

AU - Davey, Rachel

AU - Chetty, Girija

PY - 2018/12/10

Y1 - 2018/12/10

N2 - Detection of early signs of the diseases at geospatial level can help in promoting evidence-based health policies and proper disease management strategies to be formulated beforehand. In this paper, we report the performance of XGboosting algorithm as a part of a novel unified predictive modelling framework. The proposed scalable end to end tree boosting system called XGBoost, results in significantly improved performance. The experimental validation of the proposed algorithm, when compared with traditional shallow machine learning techniques, for two publicly available cardiovascular disease datasets (the NHANES dataset, and the Framingham Heart Study CHS dataset), resulted in promising outcomes, in terms of performance of different performance metrics including prediction accuracy and model building time.

AB - Detection of early signs of the diseases at geospatial level can help in promoting evidence-based health policies and proper disease management strategies to be formulated beforehand. In this paper, we report the performance of XGboosting algorithm as a part of a novel unified predictive modelling framework. The proposed scalable end to end tree boosting system called XGBoost, results in significantly improved performance. The experimental validation of the proposed algorithm, when compared with traditional shallow machine learning techniques, for two publicly available cardiovascular disease datasets (the NHANES dataset, and the Framingham Heart Study CHS dataset), resulted in promising outcomes, in terms of performance of different performance metrics including prediction accuracy and model building time.

KW - cardiovascular diseases

KW - Data Analytics

KW - Machine Learning

KW - Obesity

KW - Predictive modelling

KW - Public health management

UR - http://www.scopus.com/inward/record.url?scp=85074296606&partnerID=8YFLogxK

U2 - 10.1109/apwconcse.2018.00047

DO - 10.1109/apwconcse.2018.00047

M3 - Conference contribution

SN - 9781728113906

T3 - Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018

SP - 246

EP - 252

BT - Proceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering

A2 - Ali, A B M Shawkat

A2 - Miah, Shah

A2 - Valluri, Maheswara Rao

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Danvers, USA

ER -

Rajliwall NS, Davey R, Chetty G. Cardiovascular Risk Prediction Based on XGBoost. In Ali ABMS, Miah S, Valluri MR, editors, Proceedings: 2018 5th Asia-Pacific World Congress on Computer Science and Engineering : APWConCSE 2018 . Danvers, USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 246-252. 8853798. (Proceedings - 2018 5th Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2018). https://doi.org/10.1109/apwconcse.2018.00047