A support vector machine model for predicting non-sentinel lymph node status in patients with sentinel lymph node positive breast cancer.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Author(s): Ding X;Ding X; Xie S; Chen J; Mo W; Yang H
  • Source:
    Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine [Tumour Biol] 2013 Jun; Vol. 34 (3), pp. 1547-52. Date of Electronic Publication: 2013 Feb 10.
  • Publication Type:
    Journal Article
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: IOS Press Country of Publication: Netherlands NLM ID: 8409922 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1423-0380 (Electronic) Linking ISSN: 10104283 NLM ISO Abbreviation: Tumour Biol Subsets: MEDLINE
    • Publication Information:
      Publication: 2021- : Amsterdam, The Netherlands : IOS Press
      Original Publication: Tokyo, Japan : Saikon Pub. Co., c1984-
    • Subject Terms:
    • Abstract:
      This study aimed to investigate the accuracy and feasibility of support vector machine (SVM) modeling in predicting non-sentinel lymph node (NSLN) status in patients with SLN-positive breast cancer. Clinicopathological data were collected from 201 cases with sentinel lymph node biopsy breast cancer and included patient age, tumor size, histological type and grade, vascular invasion, estrogen receptor status, progesterone receptor status, CerbB2 status, size and number of positive SLNs, number of negative SLNs, and positive SLN membrane invasion. Feature vector selection was based on a combination of statistical filtration and model-dependent screening. The arbitrary combination with the smallest p value for SVM input was selected, the predicative results of the model were evaluated by a 10-fold cross validation, and a training model was established. Using SLN-positive patients as a double-blind test set, 85 patients were input into the model to analyze its sensitivity and specificity. The combination with the highest cross-validation accuracy was selected for the SVM model and consisted of the following: the number and size of positive SLNs, the number of negative SLNs, and the membrane invasion of positive SLNs. The training accuracy of the model established with the four variables was 92 %, and its cross-validation veracity was 87.6 %. The accuracy of an 85-patient double-blind test of the SVM model was 91.8 %. In conclusion, this SVM model is an accurate and feasible method for the prediction of NSLN status in SLN-positive breast cancer and is conducive to guide clinical treatment.
    • References:
      J Natl Cancer Inst. 2006 May 3;98(9):599-609. (PMID: 16670385)
      Ann Surg. 1997 Sep;226(3):271-6; discussion 276-8. (PMID: 9339933)
      BMC Cancer. 2008 Mar 04;8:66. (PMID: 18315887)
      N Engl J Med. 2003 Aug 7;349(6):546-53. (PMID: 12904519)
      Chin J Cancer Res. 2013 Feb;25(1):10-21. (PMID: 23372337)
      Gland Surg. 2012 May;1(1):5-6. (PMID: 25083419)
      Arch Surg. 2001 Jun;136(6):688-92. (PMID: 11387010)
      J Clin Oncol. 2000 Jul;18(13):2553-9. (PMID: 10893286)
      J Thorac Dis. 2012 Aug;4(4):420-4. (PMID: 22934145)
      Analyst. 2010 May;135(5):895-901. (PMID: 20419237)
      Gland Surg. 2012 May;1(1):7-8. (PMID: 25083420)
      Breast Cancer Res Treat. 2005 May;91(2):113-9. (PMID: 15868438)
      Gland Surg. 2012 May;1(1):39-61. (PMID: 25083426)
      J Surg Oncol. 2010 Aug 1;102(2):111-8. (PMID: 20648579)
      J Clin Oncol. 2005 Jul 1;23(19):4312-21. (PMID: 15994144)
      Br J Surg. 2008 Mar;95(3):302-9. (PMID: 17876750)
      Ann Surg Oncol. 2003 Dec;10(10):1140-51. (PMID: 14654469)
      Cancer Control. 2012 Oct;19(4):267-76. (PMID: 23037494)
      Chin Clin Oncol. 2013 Mar;2(1):10. (PMID: 25841451)
      J Clin Oncol. 2008 Nov 10;26(32):5213-9. (PMID: 18838709)
    • Publication Date:
      Date Created: 20130212 Date Completed: 20130718 Latest Revision: 20211021
    • Publication Date:
      20221213
    • Accession Number:
      10.1007/s13277-013-0683-5
    • Accession Number:
      23397544