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
Event5th Asia-Pacific World Congress on Computer Science and Engineering 2018 (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

Conference5th Asia-Pacific World Congress on Computer Science and Engineering 2018 (APWC on CSE)
Abbreviated title(APWC on CSE
CountryFiji
CityNadi
Period10/12/1812/12/18
Internet address

Fingerprint Dive into the research topics of 'Cardiovascular Risk Prediction Based on XGBoost'. Together they form a unique fingerprint.

  • 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). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/apwconcse.2018.00047