An immunohistochemical analysis-based decision tree model for estimating the risk of lymphatic metastasis in pN0 squamous cell carcinomas of the lung

Yu Liu, Dongmei Lin, Ting Xiao, Ying Ma, Zhi Hu, Hongwei Zheng, Shan Zheng, Yan Liu, Min Li, Lin Li, Yan Cao, Suping Guo, Naijun Han, Xuebing Di, Kaitai Zhang, Shujun Cheng, Yanning Gao

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Aims: Lung cancer patients within the pN0 category have a significantly different outcome. The aim of this study was to develop a mathematical model to assist in predicting the prognosis of pN0 lung squamous cell carcinoma (SCC). Methods and results: Twenty-three proteins were examined by immunohistochemical (IHC) analysis on primary tumour tissues from 319 lung SCC patients. In a training group, using IHC data, a recursive partitioning decision tree (RP-DT) was used to build a model for estimating the risk for lymphatic metastasis. This model was then validated in a test cohort. Of 23 proteins, 8 (matrix metallopeptidase 1, metalloproteinase inhibitor 1, Ras GTPase-activating-like protein IQGAP1, targeting protein for Xklp2, urokinase-type plasminogen activator, cathepsin D, fascin, polymeric immunoglobulin receptor/secretory component) were selected, and generated a tree model in a training group of 255 patients to classify them as at high or low risk of lymphatic invasion, with accuracy of 78.0% (compared to histopathological diagnosis), sensitivity of 83.0% and specificity of 70.3%. When the tree model was applied to the test group, the accuracy, sensitivity and specificity were 76.6%, 76.0% and 76.9%, respectively. The performance of this mathematical model was substantiated further in 34 'problematic' stage I/pN0 patients by survival analysis. Conclusions: The RP-DT model, constructed with eight protein markers for estimating lymphatic metastasis risk in pN0 lung SCC, is clinically feasible and practical, using IHC data from the primary tumour.

Original languageEnglish (US)
Pages (from-to)882-891
Number of pages10
JournalHistopathology
Volume59
Issue number5
DOIs
StatePublished - Nov 2011
Externally publishedYes

Fingerprint

Lymphatic Metastasis
Decision Trees
Squamous Cell Carcinoma
Lung
Theoretical Models
Polymeric Immunoglobulin Receptors
ras GTPase-Activating Proteins
Secretory Component
Sensitivity and Specificity
Cathepsin D
Matrix Metalloproteinase 1
Proteins
Urokinase-Type Plasminogen Activator
Protein Transport
Survival Analysis
Lung Neoplasms
Neoplasms

Keywords

  • Decision tree
  • Immunohistochemical analysis
  • Lymphatic metastasis
  • Prognosis
  • Squamous cell carcinomas of the lung

ASJC Scopus subject areas

  • Histology
  • Pathology and Forensic Medicine

Cite this

An immunohistochemical analysis-based decision tree model for estimating the risk of lymphatic metastasis in pN0 squamous cell carcinomas of the lung. / Liu, Yu; Lin, Dongmei; Xiao, Ting; Ma, Ying; Hu, Zhi; Zheng, Hongwei; Zheng, Shan; Liu, Yan; Li, Min; Li, Lin; Cao, Yan; Guo, Suping; Han, Naijun; Di, Xuebing; Zhang, Kaitai; Cheng, Shujun; Gao, Yanning.

In: Histopathology, Vol. 59, No. 5, 11.2011, p. 882-891.

Research output: Contribution to journalArticle

Liu, Y, Lin, D, Xiao, T, Ma, Y, Hu, Z, Zheng, H, Zheng, S, Liu, Y, Li, M, Li, L, Cao, Y, Guo, S, Han, N, Di, X, Zhang, K, Cheng, S & Gao, Y 2011, 'An immunohistochemical analysis-based decision tree model for estimating the risk of lymphatic metastasis in pN0 squamous cell carcinomas of the lung', Histopathology, vol. 59, no. 5, pp. 882-891. https://doi.org/10.1111/j.1365-2559.2011.04013.x
Liu, Yu ; Lin, Dongmei ; Xiao, Ting ; Ma, Ying ; Hu, Zhi ; Zheng, Hongwei ; Zheng, Shan ; Liu, Yan ; Li, Min ; Li, Lin ; Cao, Yan ; Guo, Suping ; Han, Naijun ; Di, Xuebing ; Zhang, Kaitai ; Cheng, Shujun ; Gao, Yanning. / An immunohistochemical analysis-based decision tree model for estimating the risk of lymphatic metastasis in pN0 squamous cell carcinomas of the lung. In: Histopathology. 2011 ; Vol. 59, No. 5. pp. 882-891.
@article{46bf8f4f89134c85bb2e953c70748efb,
title = "An immunohistochemical analysis-based decision tree model for estimating the risk of lymphatic metastasis in pN0 squamous cell carcinomas of the lung",
abstract = "Aims: Lung cancer patients within the pN0 category have a significantly different outcome. The aim of this study was to develop a mathematical model to assist in predicting the prognosis of pN0 lung squamous cell carcinoma (SCC). Methods and results: Twenty-three proteins were examined by immunohistochemical (IHC) analysis on primary tumour tissues from 319 lung SCC patients. In a training group, using IHC data, a recursive partitioning decision tree (RP-DT) was used to build a model for estimating the risk for lymphatic metastasis. This model was then validated in a test cohort. Of 23 proteins, 8 (matrix metallopeptidase 1, metalloproteinase inhibitor 1, Ras GTPase-activating-like protein IQGAP1, targeting protein for Xklp2, urokinase-type plasminogen activator, cathepsin D, fascin, polymeric immunoglobulin receptor/secretory component) were selected, and generated a tree model in a training group of 255 patients to classify them as at high or low risk of lymphatic invasion, with accuracy of 78.0{\%} (compared to histopathological diagnosis), sensitivity of 83.0{\%} and specificity of 70.3{\%}. When the tree model was applied to the test group, the accuracy, sensitivity and specificity were 76.6{\%}, 76.0{\%} and 76.9{\%}, respectively. The performance of this mathematical model was substantiated further in 34 'problematic' stage I/pN0 patients by survival analysis. Conclusions: The RP-DT model, constructed with eight protein markers for estimating lymphatic metastasis risk in pN0 lung SCC, is clinically feasible and practical, using IHC data from the primary tumour.",
keywords = "Decision tree, Immunohistochemical analysis, Lymphatic metastasis, Prognosis, Squamous cell carcinomas of the lung",
author = "Yu Liu and Dongmei Lin and Ting Xiao and Ying Ma and Zhi Hu and Hongwei Zheng and Shan Zheng and Yan Liu and Min Li and Lin Li and Yan Cao and Suping Guo and Naijun Han and Xuebing Di and Kaitai Zhang and Shujun Cheng and Yanning Gao",
year = "2011",
month = "11",
doi = "10.1111/j.1365-2559.2011.04013.x",
language = "English (US)",
volume = "59",
pages = "882--891",
journal = "Histopathology",
issn = "0309-0167",
publisher = "Wiley-Blackwell",
number = "5",

}

TY - JOUR

T1 - An immunohistochemical analysis-based decision tree model for estimating the risk of lymphatic metastasis in pN0 squamous cell carcinomas of the lung

AU - Liu, Yu

AU - Lin, Dongmei

AU - Xiao, Ting

AU - Ma, Ying

AU - Hu, Zhi

AU - Zheng, Hongwei

AU - Zheng, Shan

AU - Liu, Yan

AU - Li, Min

AU - Li, Lin

AU - Cao, Yan

AU - Guo, Suping

AU - Han, Naijun

AU - Di, Xuebing

AU - Zhang, Kaitai

AU - Cheng, Shujun

AU - Gao, Yanning

PY - 2011/11

Y1 - 2011/11

N2 - Aims: Lung cancer patients within the pN0 category have a significantly different outcome. The aim of this study was to develop a mathematical model to assist in predicting the prognosis of pN0 lung squamous cell carcinoma (SCC). Methods and results: Twenty-three proteins were examined by immunohistochemical (IHC) analysis on primary tumour tissues from 319 lung SCC patients. In a training group, using IHC data, a recursive partitioning decision tree (RP-DT) was used to build a model for estimating the risk for lymphatic metastasis. This model was then validated in a test cohort. Of 23 proteins, 8 (matrix metallopeptidase 1, metalloproteinase inhibitor 1, Ras GTPase-activating-like protein IQGAP1, targeting protein for Xklp2, urokinase-type plasminogen activator, cathepsin D, fascin, polymeric immunoglobulin receptor/secretory component) were selected, and generated a tree model in a training group of 255 patients to classify them as at high or low risk of lymphatic invasion, with accuracy of 78.0% (compared to histopathological diagnosis), sensitivity of 83.0% and specificity of 70.3%. When the tree model was applied to the test group, the accuracy, sensitivity and specificity were 76.6%, 76.0% and 76.9%, respectively. The performance of this mathematical model was substantiated further in 34 'problematic' stage I/pN0 patients by survival analysis. Conclusions: The RP-DT model, constructed with eight protein markers for estimating lymphatic metastasis risk in pN0 lung SCC, is clinically feasible and practical, using IHC data from the primary tumour.

AB - Aims: Lung cancer patients within the pN0 category have a significantly different outcome. The aim of this study was to develop a mathematical model to assist in predicting the prognosis of pN0 lung squamous cell carcinoma (SCC). Methods and results: Twenty-three proteins were examined by immunohistochemical (IHC) analysis on primary tumour tissues from 319 lung SCC patients. In a training group, using IHC data, a recursive partitioning decision tree (RP-DT) was used to build a model for estimating the risk for lymphatic metastasis. This model was then validated in a test cohort. Of 23 proteins, 8 (matrix metallopeptidase 1, metalloproteinase inhibitor 1, Ras GTPase-activating-like protein IQGAP1, targeting protein for Xklp2, urokinase-type plasminogen activator, cathepsin D, fascin, polymeric immunoglobulin receptor/secretory component) were selected, and generated a tree model in a training group of 255 patients to classify them as at high or low risk of lymphatic invasion, with accuracy of 78.0% (compared to histopathological diagnosis), sensitivity of 83.0% and specificity of 70.3%. When the tree model was applied to the test group, the accuracy, sensitivity and specificity were 76.6%, 76.0% and 76.9%, respectively. The performance of this mathematical model was substantiated further in 34 'problematic' stage I/pN0 patients by survival analysis. Conclusions: The RP-DT model, constructed with eight protein markers for estimating lymphatic metastasis risk in pN0 lung SCC, is clinically feasible and practical, using IHC data from the primary tumour.

KW - Decision tree

KW - Immunohistochemical analysis

KW - Lymphatic metastasis

KW - Prognosis

KW - Squamous cell carcinomas of the lung

UR - http://www.scopus.com/inward/record.url?scp=81555200677&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81555200677&partnerID=8YFLogxK

U2 - 10.1111/j.1365-2559.2011.04013.x

DO - 10.1111/j.1365-2559.2011.04013.x

M3 - Article

C2 - 22092400

AN - SCOPUS:81555200677

VL - 59

SP - 882

EP - 891

JO - Histopathology

JF - Histopathology

SN - 0309-0167

IS - 5

ER -