Download PDF
Methods Inf Med 2016; 55(05): 450-454
DOI: 10.3414/ME15-01-0137
Original Articles
Schattauer GmbH

To Explore Intracerebral Hematoma with a Hybrid Approach and Combination of Discriminative Factors

Hui-Chu Chiu
1   PhD Program of Technology Management, Chung-Hua University, Hsinchu, Taiwan
,
Deng-Yiv Chiu
2   Department of Information Management, Chung-Hua University, Hsinchu, Taiwan
,
Yao-Hsien Lee
3   Department of Finance, Chung-Hua University, Hsinchu, Taiwan
,
Chih-Cheng Wang
2   Department of Information Management, Chung-Hua University, Hsinchu, Taiwan
,
Chen-Shu Wang
4   Department of Information and Finance Management, National Taipei University of Technology, Taipei, Taiwan
,
Chi-Chung Lee
2   Department of Information Management, Chung-Hua University, Hsinchu, Taiwan
,
Ming-Hsiung Ying
2   Department of Information Management, Chung-Hua University, Hsinchu, Taiwan
,
Mei-Yu Wu
2   Department of Information Management, Chung-Hua University, Hsinchu, Taiwan
,
Wen-Chih Chang
2   Department of Information Management, Chung-Hua University, Hsinchu, Taiwan
› Author Affiliations
Further Information

Publication History

Received 19 October 2015

Accepted in revised form: 04 April 2016

Publication Date:
08 January 2018 (online)

    Permissions and Reprints

Summary

Objectives: To find discriminative combination of influential factors of Intracerebral hematoma (ICH) to cluster ICH patients with similar features to explore relationship among influential factors and 30-day mortality of ICH. Methods: The data of ICH patients are collected. We use a decision tree to find discriminative combination of the influential factors. We cluster ICH patients with similar features using Fuzzy C-means algorithm (FCM) to construct a support vector machine (SVM) for each cluster to build a multi-SVM classifier. Finally, we designate each testing data into its appropriate cluster and apply the corresponding SVM classifier of the cluster to explore the relationship among impact factors and 30-day mortality. Results: The two influential factors chosen to split the decision tree are Glasgow coma scale (GCS) score and Hematoma size. FCM algorithm finds three centroids, one for high danger group, one for middle danger group, and the other for low danger group. The proposed approach outperforms benchmark experiments without FCM algorithm to cluster training data. Conclusions: It is appropriate to construct a classifier for each cluster with similar features. The combination of factors with significant discrimination as input variables should outperform that with only single discriminative factor as input variable.

Keywords

Intracerebral hematoma - Glasgow coma scale score - Fuzzy C-means algorithm - support vector machine - decision tree

* Supplementary material published on our web-site http://dx.doi.org/10.3414/ME15-01-0137


 

  • References

  • 1 Hemphill 3rd JC, Bonovich DC, Besmertis L, Manley GT, Johnston SC. The ICH score: a simple, reliable grading scale for intracerebral hemorrhage. Stroke 2001; 32: 891-897.
    CrossrefPubMedGoogle Scholar
  • 2 Wang W, Lu J, Wang C. et al. Prognostic value of ICH score and ICH-GS score in Chinese intracerebral hemorrhage patients: analysis from the China National Stroke Registry (CNSR). PLoS One 2003; 8: e77421.
    PubMedGoogle Scholar
  • 3 Chuang YC, Chen YM, Peng SK, Peng SY. Risk stratification for predicting 30-day mortality of intracerebral hemorrhage. Int J Qual Health Care 2009; 21: 441-447.
    CrossrefPubMedGoogle Scholar
  • 4 Salihovic D, Smajlovic D, Ibrahimagic OC. Does the volume and localization of intracerebral hematoma affect short-term prognosis of patients with intracerebral hemorrhage?. ISRN Neurosci 2013; 2013: 327968.
    PubMedGoogle Scholar
  • 5 Peng SY, Chuang YC, Kang TW, Tseng KH. Random forest can predict 30-day mortality of spontaneous intracerebral hemorrhage with remarkable discrimination. Eur J Neurol 2010; 17: 945-950.
    CrossrefPubMedGoogle Scholar
  • 6 Ibrikci T, Ustun D, Kaya IE. Diagnosis of several diseases by using combined kernels with Support Vector Machine. J Med Syst 2012; 36: 1831-1840.
    CrossrefPubMedGoogle Scholar
  • 7 Wang CW, Liu YJ, Lee YH. et al. Hematoma shape, hematoma size, Glasgow coma scale score and ICH score: which predicts the 30-day mortality better for intracerebral hematoma?. PLoS One 2014; 9: e102326.
    CrossrefPubMedGoogle Scholar
  • 8 Schwarzer G, Nagata T, Mattern D, Schmelzeisen R, Schumacher M. Comparison of fuzzy inference, logistic regression, and classification trees (CART) prediction of cervical lymph node metastasis in carcinoma of the tongue. Methods Inf Med 2003; 42 (Suppl. 05) 572-577.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 9 Silipo R, Vergassola R, Zong W, Berthold MR. Knowledge-based and data-driven models in arrhythmia fuzzy classification. Methods Inf Med 2001; 40 (Suppl. 05) 397-403.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 10 Martin-González F, González-Robledo J, SánchezHernández F, Moreno-García MN. Success/Failure Prediction of Noninvasive Mechanical Ventilation in Intensive Care Units. Using Multiclassifiers and Feature Selection Methods. Methods Inf Med 2016; 55 (Suppl. 03) 234-241.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 11 Vapnik VN GS, Smol A. Support vector method for function approximation, regression estimation and signal processing. In: Mozer M, Jordan M, Petsche T. editors. Advances in Neural Information Processing Systems 9. Cambridge (MA): MIT Press; 1997. p. 281-287.
    Google Scholar
  • 12 Dunham MH. Data Mining: Introductory and Advanced Topics. Englewood Cliffs: Prentice-Hall; 2003
    Google Scholar
  • 13 Bezdek JC. Cluster validity with fuzzy sets. J Cybernet 1974; 3: 58-73.
    PubMedGoogle Scholar