Causal modeling to estimate sensitivity and specificity of a test when prevalence changes

被引:20
作者
Choi, BCK
机构
[1] Comm. Dent. Hlth. Serv. Res. Unit, Faculty of Dentistry, University of Toronto, Toronto, Ont.
[2] Comm. Dent. Hlth. Serv. Res. Unit, Faculty of Dentistry, University of Toronto, Toronto, Ont. M5G 1G6
关键词
sensitivity; specificity; screening test; diagnostic test; prevalence;
D O I
10.1097/00001648-199701000-00013
中图分类号
R1 [预防医学、卫生学];
学科分类号
1004 ; 120402 ;
摘要
The objective of this paper is to demonstrate, by causal modeling, whether the sensitivity and specificity of a test are constant, or whether they change with prevalence. I use three assumptions, diagnostic, predictive, and correlational, in three sets of mathematical models. A diagnostic test measures an outcome of a disease and is based on the assumption that the ''gold standard'' result indicates a disease state that causes a test result. A predictive test measures a risk factor for a disease and is based on the assumption that the test result indicates a risk factor that causes a disease state. A correlational test measures a condition which is an outcome of an underlying causal risk factor for a disease and is based on the assumption that the disease and the test result are noncausally related. I find that sensitivity and specificity are constant for diagnostic tests but change with prevalence for predictive and correlational tests. I present equations to show the effects on various test performance indices when prevalence changes. Different equations must be used to estimate the sensitivity, specificity, and other test performance indicators for various types of tests that are under different causal assumptions.
引用
收藏
页码:80 / 86
页数:7
相关论文
共 42 条
  • [31] SERUM CERULOPLASMIN LEVEL AND THE RISK OF MYOCARDIAL-INFARCTION AND STROKE
    REUNANEN, A
    KNEKT, P
    AARAN, RK
    [J]. AMERICAN JOURNAL OF EPIDEMIOLOGY, 1992, 136 (09) : 1082 - 1090
  • [32] Rothstein, 1984, MED SCREENING WORKER
  • [33] Sackett D.L., 1985, CLIN EPIDEMIOLOGY BA
  • [34] SIMON JA, 1992, J AM COLL NUTR, V11, P107
  • [35] PROGNOSTIC VALUE OF EXERCISE TESTING SOON AFTER MYOCARDIAL-INFARCTION
    THEROUX, P
    WATERS, DD
    HALPHEN, C
    DEBAISIEUX, JC
    MIZGALA, HF
    [J]. NEW ENGLAND JOURNAL OF MEDICINE, 1979, 301 (07) : 341 - 345
  • [36] PREDICTIVE VALUE OF A SINGLE DIAGNOSTIC TEST IN UNSELECTED POPULATIONS
    VECCHIO, TJ
    [J]. NEW ENGLAND JOURNAL OF MEDICINE, 1966, 274 (21) : 1171 - &
  • [37] WEGMAN DH, 1992, PUBLIC HLTH SURVEILL, P67
  • [38] EXERCISE STRESS-TESTING - CORRELATIONS AMONG HISTORY OF ANGINA, ST-SEGMENT RESPONSE AND PREVALENCE OF CORONARY-ARTERY DISEASE IN THE CORONARY-ARTERY SURGERY STUDY (CASS)
    WEINER, DA
    RYAN, TJ
    MCCABE, CH
    KENNEDY, JW
    SCHLOSS, M
    TRISTANI, F
    CHAITMAN, BR
    FISHER, LD
    [J]. NEW ENGLAND JOURNAL OF MEDICINE, 1979, 301 (05) : 230 - 235
  • [39] UNIVERSAL COMMUNITY CARRIER SCREENING FOR CYSTIC-FIBROSIS
    WILLIAMSON, R
    [J]. NATURE GENETICS, 1993, 3 (03) : 195 - 201
  • [40] PREOPERATIVE CARDIAC RISK ASSESSMENT FOR PATIENTS HAVING PERIPHERAL VASCULAR-SURGERY
    WONG, T
    DETSKY, AS
    [J]. ANNALS OF INTERNAL MEDICINE, 1992, 116 (09) : 743 - 753