Trees for correlated survival data by goodness of split, with applications to tooth prognosis

Juanjuan Fan, Xiao Gang Su, Richard A. Levine, Martha E. Nunn, Michael Leblanc

Research output: Contribution to journalReview article

17 Citations (Scopus)

Abstract

In this article the regression tree method is extended to correlated survival data and applied to the problem of developing objective prognostic classification rules in periodontal research. The robust logrank statistic is used as the splitting statistic to measure the between-node difference in survival, while adjusting for correlation among failure times from the same patient. The partition-based survival function estimator is shown to converge to the true conditional survival function. Tooth loss data from 100 periodontal patients (2,509 teeth) was analyzed using the proposed method. The goal is to assign each tooth to one of the five prognosis categories (good, fair, poor, questionable, or hopeless). After the best-sized tree was identified, an amalgamation procedure was used to form five prognostic groups. The prognostic rules established here may be used by periodontists, general dentists, and insurance companies in devising appropriate treatment plans for periodontal oatients.

Original languageEnglish
Pages (from-to)959-967
Number of pages9
JournalJournal of the American Statistical Association
Volume101
Issue number475
DOIs
StatePublished - Sep 2006
Externally publishedYes

Fingerprint

Correlated Data
Survival Function
Survival Data
Prognosis
Log-rank Statistic
Regression Tree
Amalgamation
Classification Rules
Failure Time
Insurance
Statistic
Assign
Partition
Converge
Estimator
Vertex of a graph

All Science Journal Classification (ASJC) codes

  • Mathematics(all)
  • Statistics and Probability

Cite this

Trees for correlated survival data by goodness of split, with applications to tooth prognosis. / Fan, Juanjuan; Su, Xiao Gang; Levine, Richard A.; Nunn, Martha E.; Leblanc, Michael.

In: Journal of the American Statistical Association, Vol. 101, No. 475, 09.2006, p. 959-967.

Research output: Contribution to journalReview article

Fan, Juanjuan ; Su, Xiao Gang ; Levine, Richard A. ; Nunn, Martha E. ; Leblanc, Michael. / Trees for correlated survival data by goodness of split, with applications to tooth prognosis. In: Journal of the American Statistical Association. 2006 ; Vol. 101, No. 475. pp. 959-967.
@article{eedb3d1a5a4c4fe68f0c789f9edc6cb7,
title = "Trees for correlated survival data by goodness of split, with applications to tooth prognosis",
abstract = "In this article the regression tree method is extended to correlated survival data and applied to the problem of developing objective prognostic classification rules in periodontal research. The robust logrank statistic is used as the splitting statistic to measure the between-node difference in survival, while adjusting for correlation among failure times from the same patient. The partition-based survival function estimator is shown to converge to the true conditional survival function. Tooth loss data from 100 periodontal patients (2,509 teeth) was analyzed using the proposed method. The goal is to assign each tooth to one of the five prognosis categories (good, fair, poor, questionable, or hopeless). After the best-sized tree was identified, an amalgamation procedure was used to form five prognostic groups. The prognostic rules established here may be used by periodontists, general dentists, and insurance companies in devising appropriate treatment plans for periodontal oatients.",
author = "Juanjuan Fan and Su, {Xiao Gang} and Levine, {Richard A.} and Nunn, {Martha E.} and Michael Leblanc",
year = "2006",
month = "9",
doi = "10.1198/016214506000000438",
language = "English",
volume = "101",
pages = "959--967",
journal = "Journal of the American Statistical Association",
issn = "0162-1459",
publisher = "Taylor and Francis Ltd.",
number = "475",

}

TY - JOUR

T1 - Trees for correlated survival data by goodness of split, with applications to tooth prognosis

AU - Fan, Juanjuan

AU - Su, Xiao Gang

AU - Levine, Richard A.

AU - Nunn, Martha E.

AU - Leblanc, Michael

PY - 2006/9

Y1 - 2006/9

N2 - In this article the regression tree method is extended to correlated survival data and applied to the problem of developing objective prognostic classification rules in periodontal research. The robust logrank statistic is used as the splitting statistic to measure the between-node difference in survival, while adjusting for correlation among failure times from the same patient. The partition-based survival function estimator is shown to converge to the true conditional survival function. Tooth loss data from 100 periodontal patients (2,509 teeth) was analyzed using the proposed method. The goal is to assign each tooth to one of the five prognosis categories (good, fair, poor, questionable, or hopeless). After the best-sized tree was identified, an amalgamation procedure was used to form five prognostic groups. The prognostic rules established here may be used by periodontists, general dentists, and insurance companies in devising appropriate treatment plans for periodontal oatients.

AB - In this article the regression tree method is extended to correlated survival data and applied to the problem of developing objective prognostic classification rules in periodontal research. The robust logrank statistic is used as the splitting statistic to measure the between-node difference in survival, while adjusting for correlation among failure times from the same patient. The partition-based survival function estimator is shown to converge to the true conditional survival function. Tooth loss data from 100 periodontal patients (2,509 teeth) was analyzed using the proposed method. The goal is to assign each tooth to one of the five prognosis categories (good, fair, poor, questionable, or hopeless). After the best-sized tree was identified, an amalgamation procedure was used to form five prognostic groups. The prognostic rules established here may be used by periodontists, general dentists, and insurance companies in devising appropriate treatment plans for periodontal oatients.

UR - http://www.scopus.com/inward/record.url?scp=33748861409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748861409&partnerID=8YFLogxK

U2 - 10.1198/016214506000000438

DO - 10.1198/016214506000000438

M3 - Review article

VL - 101

SP - 959

EP - 967

JO - Journal of the American Statistical Association

JF - Journal of the American Statistical Association

SN - 0162-1459

IS - 475

ER -