An Exploratory Analysis of Survival with AIDS Using a Nonparametric Tree-Structured Approach

We illustrate an analysis with classification and regression trees applied to survival data. Through this application, we provide a description of the opportunistic diseases and sociodemographic factors that contribute to survival among people with human immunodeficiency virus disease. The analyses are based on 43,795 cases reported to the Centers for Disease Control between January 1, 1984, and December 31, 1987. We used vital status as of December 31, 1989, to estimate mortality rates. We identified Kaposi's sarcoma and opportunistic diseases causing central nervous system damage (cryptococcosis, primary lymphoma of the brain, cytomegalovirus disease, and progressive multifocal leukoencephalopathy) as important predictors of death. In addition, advanced age at diagnosis (50+), race (white/other), and history of illicit drug use were found to be important determinants. Estimates of the cumulative probability of survival for subgroups of individuals defined by the tree structure illustrate the effect of these determinants on mortality. For the purpose of comparison, two proportional hazards models were also fit to the data using factors identified in the tree structure as the determinants of interest. This application illustrates the utility and limitations of both this new technique and proportional hazards models for epidemiologic research. (Epidemiology 1992;3:310–318)

[1]  J. Edelson,et al.  CORTICOSTEROIDS AS ADJUNCTIVE THERAPY IN TREATMENT OF PNEUMOCYSTIS CARINII PNEUMONIA IN PATIENTS WITH ACQUIRED IMMUNODEFICIENCY SYNDROME , 1987, The Lancet.

[2]  R. Davis,et al.  Primary central nervous system lymphoma in acquired immune deficiency syndrome: A clinical and pathological study , 1986, Annals of neurology.

[3]  R A Olshen,et al.  Prognostic significance of actual dose intensity in diffuse large-cell lymphoma: results of a tree-structured survival analysis. , 1990, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[4]  P. Pizzo,et al.  Acquired immune deficiency syndrome in children. Current problems and therapeutic considerations. , 1988, American Journal of Medicine.

[5]  J. Phair,et al.  Infection with the human immunodeficiency virus: clinical manifestations and their relationship to immune deficiency. A report from the Multicenter AIDS Cohort Study. , 1987, Annals of internal medicine.

[6]  R. Chaisson,et al.  Survival patterns of the first 500 patients with AIDS in San Francisco. , 1988, The Journal of infectious diseases.

[7]  A. Glatt,et al.  Treatment of Infections Associated with Human Immunodeficiency Virus , 1988 .

[8]  J. Fleishman,et al.  Patterns of survival with AIDS in the United States. , 1991, Health services research.

[9]  Paul D. Allison,et al.  Event History Analysis : Regression for Longitudinal Event Data , 1984 .

[10]  P. Gøtzsche,et al.  Opportunistic infections and malignancies in 231 Danish AIDS patients , 1990, AIDS.

[11]  S Greenland,et al.  Modeling and variable selection in epidemiologic analysis. , 1989, American journal of public health.

[12]  M. Blaser,et al.  Opportunistic infections in patients with AIDS: clues to the epidemiology of AIDS and the relative virulence of pathogens. , 1986, Reviews of infectious diseases.

[13]  B. Truman,et al.  Survival with the acquired immunodeficiency syndrome. Experience with 5833 cases in New York City. , 1987, The New England journal of medicine.

[14]  E F Cook,et al.  Asymmetric stratification. An outline for an efficient method for controlling confounding in cohort studies. , 1988, American journal of epidemiology.

[15]  D. Cox Regression Models and Life-Tables , 1972 .

[16]  J. Phair,et al.  The risk of Pneumocystis carinii pneumonia among men infected with human immunodeficiency virus type 1. Multicenter AIDS Cohort Study Group. , 1990, The New England journal of medicine.

[17]  R. Tibshirani,et al.  Generalized Additive Models , 1991 .

[18]  L. Aiken,et al.  Access to medical care for black and white Americans. A matter of continuing concern. , 1989, JAMA.

[19]  J. Godbold,et al.  Progression to AIDS in patients with lymphadenopathy or AIDS-related complex: reappraisal of risk and predictive factors. , 1989, The American journal of medicine.

[20]  H Checkoway,et al.  Bias due to misclassification in the estimation of relative risk. , 1977, American journal of epidemiology.

[21]  R. Whitley,et al.  Ganciclovir--have we established clinical value in the treatment of cytomegalovirus infections? , 1988, Annals of internal medicine.