skip to main content
10.1145/3310986.3311024acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicmlscConference Proceedingsconference-collections
research-article

An improved prediction method for diabetes based on a feature-based least angle regression algorithm

Published: 25 January 2019 Publication History

Abstract

Existing diabetes prediction algorithms have a number of shortcomings, most notably low accuracy and poor generalizability. In this paper, we propose a method based on feature weights to improve diabetes prediction that combines the advantages of traditional least angle regression (LARS) algorithms and principal component analysis (PCA) algorithms.First of all, a principal component analysis algorithm is used to obtain the characteristic independent variables found in typical diabetes prediction regression models. Each of these variables is assigned its own characteristics. After this, the original variable correlation is multiplied by the weight of the variable obtained using principal component analysis to obtain a new degree of correlation. This new correlation is used to optimize the forward direction and variable selection of a least angle regression solution before calculating the regression coefficients for the new model. An experiment using the Pima Indians Diabetes dataset provided by the University of California was performed to validate the proposed algorithm. The experimental results show that the algorithm improved the approximation speed for the dependent variables and the accuracy of the regression coefficients. It was also able to select the key characteristic variables for diabetes prediction whilst simplifying the standard diabetes prediction model. Thus, it may help with the provision of more accurate diabetes prevention and treatment measures in the future.

References

[1]
Ma, R. C. W. Lin, X. and Jia, W. P. 1993. Causes of type 2 diabetes in China. J. Lancet Diabetes Endocrinol. 2, 12 (Sep. 2014), 980--991.
[2]
Anand, S. S. Gupta, M. Teo, K.K. et al. Causes and consequences of gestational diabetes in South Asians living in Canada: results from a prospective cohort study. J. Cmaj Open. 5, 3 (Aug. 2017), E604-E611.
[3]
Wang, X. and Hu, X.G. Overview on Feature Selection in High-dimensional and Small-sample Size Classification. J. Journal of Computer Applications. 37, 9 (Sep. 2017), 2433--2438.
[4]
Vijayanv, V. and Ravikumar, A. Study of Data Mining Algorithms for Prediction and Diagnosis of Diabetes Mellitus. J. International Journal of Computer Applications. 95, 17 (Jun. 2014), 12--16.
[5]
Rau, H.H. Hsu, C.Y. Lin, Y.A. et al. Development of a web-based liver cancer prediction model for type II diabetes patients by using an artificial neural network. J. Computer Methods & Programs in Biomedicine. vol. 125, C (Mar. 2016) 58--65.
[6]
Richards, G. and Wang, W. What influences the accuracy of decision tree ensembles?. J. Journal of Intelligent Information Systems. 39, 3 (Dec. 2012) 627--650.
[7]
Musa, A. B. A comparison of l1-regularizion, PCA, KPCA and ICA for dimensionality reduction in logistic regression. J. International Journal of Machine Learning & Cybernetics. 5, 6 (Dec. 2014) 861--873.
[8]
Kun, D. Hong-Yi, Y. U. and Qing, L. I. A Multi-class Feature Selection Algorithm Based on Support Vector Machine. J. Pattern Recognition and Artificial Intelligence. 27, 5 (May. 2014) 463--471.
[9]
Tibshirani, R. Regression Shrinkage and Selection via the Lasso. J. Journal of the Royal Statistical Society: Series B Statistical Methodology. 73, 3 (Jun. 2011) 273--282.
[10]
Kennelly, M. A. and Mcauliffe, F. M. Prediction and prevention of Gestational Diabetes: an update of recent literature. J. Eur J Obstet Gynecol Reprod Biol. 202 (Jul. 2016) 92--98.
[11]
Hastie, B. T. Johnstone, I. and Tibshirani. R. Least angle regression. J. Ann. Statist. 32 (Num. 2004) 407--499.
[12]
Zhao, W. Beach, T. H. and Rezgui, Y. Efficient least angle regression for identification of linear-in-the-parameters models. J. Proceedings Mathematical Physical & Engineering Sciences. 473, 2198 (Feb. 2017) 20160775.
[13]
Sayama, Y. Bandou, Y. Takamura, S. et al. 2016. Adaptive intra prediction algorithm based on extended LARS. In 2016 Picture Coding Symposium(The Nuremberg, The Germany April 01--05, 2016).
[14]
Uraibi, H. S. Midi, H. and Rana, S. Robust multivariate least angle regression. J. Scienceasia. 43, 1(2017) 56--60.
[15]
Olive, D. and Hawkins, D. Robust multivariate location and dispersion. http://www.math.siu.edu/olive/preprints.htm.
[16]
Abdi, H. and Williams, L. J. Principal component analysis. J. Wiley Interdisciplinary Reviews Computational Statistics. 2, 4 (Jul. 2010) 433--459.
[17]
Subramanian, J. and Simon, R. Overfitting in prediction models - is it a problem only in high dimensions?. J. Contemporary Clinical Trials. 36, 2 (Jun. 2013) 636--641.
[18]
Kong, K. Wang, Q. S. and Liang, W. L. Solution Analysis of L1 Regularized Machine Learning Problem. J. Computer Engineering. 37, 17 (Sep. 2011) 175--177.
[19]
Bache, K. and Lichman, M. UCI machine learning repository{DB/OL}. Irvine, CA: University of California. http://archive.ics.uci.edu/ml

Cited By

View all
  • (2024)Machine and deep learning techniques for the prediction of diabetics: a reviewMultimedia Tools and Applications10.1007/s11042-024-19766-9Online publication date: 16-Jul-2024
  • (2021)Diabetes Prediction Using Machine LearningProceedings of Second International Conference on Computing, Communications, and Cyber-Security10.1007/978-981-16-0733-2_50(703-715)Online publication date: 25-May-2021

Index Terms

  1. An improved prediction method for diabetes based on a feature-based least angle regression algorithm

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICMLSC '19: Proceedings of the 3rd International Conference on Machine Learning and Soft Computing
    January 2019
    268 pages
    ISBN:9781450366120
    DOI:10.1145/3310986
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 25 January 2019

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Diabetes prediction method
    2. Feature weight
    3. LARS

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICMLSC 2019

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)3
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 17 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Machine and deep learning techniques for the prediction of diabetics: a reviewMultimedia Tools and Applications10.1007/s11042-024-19766-9Online publication date: 16-Jul-2024
    • (2021)Diabetes Prediction Using Machine LearningProceedings of Second International Conference on Computing, Communications, and Cyber-Security10.1007/978-981-16-0733-2_50(703-715)Online publication date: 25-May-2021

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media