Classification of localized melanoma by the exponential survival trees method

Xin Huang, Seng Jaw Soong, William H. McCarthy, Marshall M. Urist, Charles M. Balch

Research output: Contribution to journalArticle

Abstract

BACKGROUND. Over the past 2 decades, remarkable progress has been made in the identification of clinical and pathologic factors that affect the survival of patients with melanoma. Through the use of multivariate regression methods, key prognostic factors, such as tumor thickness, tumor ulceration, invasion level, and lesion location, have been identified. Clinical investigators are often interested in developing criteria to classify melanoma patients into different risk groups based on the key prognostic factors identified. However, classical multivariate regression models are generally less efficient in accomplishing this task than newly developed tree-based methods. METHODS. In this study, the authors applied the exponential survival trees method to analyze a combined data set (n = 4568) from the University of Alabama at Birmingham and the Sydney Melanoma Unit in Camperdown, Australia. A survival tree was created according to prognostic factors that classified patients into homogeneous subgroups by survival. Six clinical and pathologic factors were included in the analysis. This three- based method provided a superior means of prognostic classification and was shown to have greater ability to detect interactions among the variables than regression models. RESULTS. Tumor thickness was found to be the most important prognostic factor, followed by tumor ulceration and primary lesion site. Some important interactions among these prognostic factors were identified. Five distinct risk groups, defined by tumor thickness, ulceration, and primary lesion site, were created. Patients who had tumor thickness less than or equal to 0.75 mm and lesions on their arms or legs had the best prognosis. Patients who had ulcerated tumors with thickness greater than 4.50 mm had the poorest prognosis. CONCLUSIONS. The authors' analysis, based on exponential survival trees, provides a comprehensive, easy-to-use risk grouping system for classifying patients with localized melanoma. This grouping system would be useful in the clinical management of melanoma patients and in designing and analyzing clinical trials.

Original languageEnglish (US)
Pages (from-to)1122-1128
Number of pages7
JournalCancer
Volume79
Issue number6
DOIs
StatePublished - Mar 15 1997
Externally publishedYes

Fingerprint

Melanoma
Neoplasms
Survival
Leg
Arm
Research Personnel
Clinical Trials

Keywords

  • Breslow's thickness
  • classification
  • exponential survival trees method
  • interaction
  • level of invasion
  • localized melanoma
  • primary lesion site
  • prognostic factors
  • ulceration

ASJC Scopus subject areas

  • Cancer Research
  • Oncology

Cite this

Classification of localized melanoma by the exponential survival trees method. / Huang, Xin; Soong, Seng Jaw; McCarthy, William H.; Urist, Marshall M.; Balch, Charles M.

In: Cancer, Vol. 79, No. 6, 15.03.1997, p. 1122-1128.

Research output: Contribution to journalArticle

Huang, Xin ; Soong, Seng Jaw ; McCarthy, William H. ; Urist, Marshall M. ; Balch, Charles M. / Classification of localized melanoma by the exponential survival trees method. In: Cancer. 1997 ; Vol. 79, No. 6. pp. 1122-1128.
@article{aadc2dc1ab7a419c9407812904eed667,
title = "Classification of localized melanoma by the exponential survival trees method",
abstract = "BACKGROUND. Over the past 2 decades, remarkable progress has been made in the identification of clinical and pathologic factors that affect the survival of patients with melanoma. Through the use of multivariate regression methods, key prognostic factors, such as tumor thickness, tumor ulceration, invasion level, and lesion location, have been identified. Clinical investigators are often interested in developing criteria to classify melanoma patients into different risk groups based on the key prognostic factors identified. However, classical multivariate regression models are generally less efficient in accomplishing this task than newly developed tree-based methods. METHODS. In this study, the authors applied the exponential survival trees method to analyze a combined data set (n = 4568) from the University of Alabama at Birmingham and the Sydney Melanoma Unit in Camperdown, Australia. A survival tree was created according to prognostic factors that classified patients into homogeneous subgroups by survival. Six clinical and pathologic factors were included in the analysis. This three- based method provided a superior means of prognostic classification and was shown to have greater ability to detect interactions among the variables than regression models. RESULTS. Tumor thickness was found to be the most important prognostic factor, followed by tumor ulceration and primary lesion site. Some important interactions among these prognostic factors were identified. Five distinct risk groups, defined by tumor thickness, ulceration, and primary lesion site, were created. Patients who had tumor thickness less than or equal to 0.75 mm and lesions on their arms or legs had the best prognosis. Patients who had ulcerated tumors with thickness greater than 4.50 mm had the poorest prognosis. CONCLUSIONS. The authors' analysis, based on exponential survival trees, provides a comprehensive, easy-to-use risk grouping system for classifying patients with localized melanoma. This grouping system would be useful in the clinical management of melanoma patients and in designing and analyzing clinical trials.",
keywords = "Breslow's thickness, classification, exponential survival trees method, interaction, level of invasion, localized melanoma, primary lesion site, prognostic factors, ulceration",
author = "Xin Huang and Soong, {Seng Jaw} and McCarthy, {William H.} and Urist, {Marshall M.} and Balch, {Charles M.}",
year = "1997",
month = "3",
day = "15",
doi = "10.1002/(SICI)1097-0142(19970315)79:6<1122::AID-CNCR10>3.0.CO;2-1",
language = "English (US)",
volume = "79",
pages = "1122--1128",
journal = "Cancer",
issn = "0008-543X",
publisher = "John Wiley and Sons Inc.",
number = "6",

}

TY - JOUR

T1 - Classification of localized melanoma by the exponential survival trees method

AU - Huang, Xin

AU - Soong, Seng Jaw

AU - McCarthy, William H.

AU - Urist, Marshall M.

AU - Balch, Charles M.

PY - 1997/3/15

Y1 - 1997/3/15

N2 - BACKGROUND. Over the past 2 decades, remarkable progress has been made in the identification of clinical and pathologic factors that affect the survival of patients with melanoma. Through the use of multivariate regression methods, key prognostic factors, such as tumor thickness, tumor ulceration, invasion level, and lesion location, have been identified. Clinical investigators are often interested in developing criteria to classify melanoma patients into different risk groups based on the key prognostic factors identified. However, classical multivariate regression models are generally less efficient in accomplishing this task than newly developed tree-based methods. METHODS. In this study, the authors applied the exponential survival trees method to analyze a combined data set (n = 4568) from the University of Alabama at Birmingham and the Sydney Melanoma Unit in Camperdown, Australia. A survival tree was created according to prognostic factors that classified patients into homogeneous subgroups by survival. Six clinical and pathologic factors were included in the analysis. This three- based method provided a superior means of prognostic classification and was shown to have greater ability to detect interactions among the variables than regression models. RESULTS. Tumor thickness was found to be the most important prognostic factor, followed by tumor ulceration and primary lesion site. Some important interactions among these prognostic factors were identified. Five distinct risk groups, defined by tumor thickness, ulceration, and primary lesion site, were created. Patients who had tumor thickness less than or equal to 0.75 mm and lesions on their arms or legs had the best prognosis. Patients who had ulcerated tumors with thickness greater than 4.50 mm had the poorest prognosis. CONCLUSIONS. The authors' analysis, based on exponential survival trees, provides a comprehensive, easy-to-use risk grouping system for classifying patients with localized melanoma. This grouping system would be useful in the clinical management of melanoma patients and in designing and analyzing clinical trials.

AB - BACKGROUND. Over the past 2 decades, remarkable progress has been made in the identification of clinical and pathologic factors that affect the survival of patients with melanoma. Through the use of multivariate regression methods, key prognostic factors, such as tumor thickness, tumor ulceration, invasion level, and lesion location, have been identified. Clinical investigators are often interested in developing criteria to classify melanoma patients into different risk groups based on the key prognostic factors identified. However, classical multivariate regression models are generally less efficient in accomplishing this task than newly developed tree-based methods. METHODS. In this study, the authors applied the exponential survival trees method to analyze a combined data set (n = 4568) from the University of Alabama at Birmingham and the Sydney Melanoma Unit in Camperdown, Australia. A survival tree was created according to prognostic factors that classified patients into homogeneous subgroups by survival. Six clinical and pathologic factors were included in the analysis. This three- based method provided a superior means of prognostic classification and was shown to have greater ability to detect interactions among the variables than regression models. RESULTS. Tumor thickness was found to be the most important prognostic factor, followed by tumor ulceration and primary lesion site. Some important interactions among these prognostic factors were identified. Five distinct risk groups, defined by tumor thickness, ulceration, and primary lesion site, were created. Patients who had tumor thickness less than or equal to 0.75 mm and lesions on their arms or legs had the best prognosis. Patients who had ulcerated tumors with thickness greater than 4.50 mm had the poorest prognosis. CONCLUSIONS. The authors' analysis, based on exponential survival trees, provides a comprehensive, easy-to-use risk grouping system for classifying patients with localized melanoma. This grouping system would be useful in the clinical management of melanoma patients and in designing and analyzing clinical trials.

KW - Breslow's thickness

KW - classification

KW - exponential survival trees method

KW - interaction

KW - level of invasion

KW - localized melanoma

KW - primary lesion site

KW - prognostic factors

KW - ulceration

UR - http://www.scopus.com/inward/record.url?scp=0030941978&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030941978&partnerID=8YFLogxK

U2 - 10.1002/(SICI)1097-0142(19970315)79:6<1122::AID-CNCR10>3.0.CO;2-1

DO - 10.1002/(SICI)1097-0142(19970315)79:6<1122::AID-CNCR10>3.0.CO;2-1

M3 - Article

C2 - 9070489

AN - SCOPUS:0030941978

VL - 79

SP - 1122

EP - 1128

JO - Cancer

JF - Cancer

SN - 0008-543X

IS - 6

ER -