诊断试验(英文).pptxVIP

Analysis and evaluation of the evidence of diagnostic test ;Diagnostic test are not just about diagnosis;Example;Basic principles of conducting diagnostic studies;What if your test is more gold than the standard;To Whom Should the Gold Standard Be Applied?;Recruit your participants;Measurement procedures;Select statistical procedure; Example: Assuming a sensitivity of 80%, specificity of 60% of ultrasonography for diagnosis of cholecystolithiasis. How many samples are needed ? ;Result evaluation index;sensitivity：a/(a+c)=35/40=0.88, or 88% specificity：d/(b+d)=29/86=0.34, or 34% positive predictive value (PPV)：a/(a+b)=35/92=0.38, or 38% negative predictive value (NPV)：d/(c+d)=29/34=0.85, or 85% prevalence: (a+c) / (a+b+c+d)=40/126=0.32, or 32% Pre-test odds: pre-test probability/(1- pre-test probability) =32% / 68%=0.47 positive likelihood ratio ( LR+ ): Sen/1-Spe=88% /(100%-34%)=1.3 ;Multilevel likelihood ratios;Stability of the index;Receiver operating characteristic curves(ROC); Fig A ROC for BNP as a diagnostic test for LVD ;Parallel test ;Reduction miss diagnosis Exclude some disease When prevalence is low, as the primary screening method;Serial test;Sen = Sen A ×SenBSpe = Spe A + (1-Spe A) Spe B;Serial test with enzyme labeled compound assay for diagnosis of myocardial infarction;Multivariate analysis; single variable analysis;multivariate analysis using logistic regression ;Prediction the probability of a disease;Avoiding overfitting;The EBM steps for diagnostic tests;Evaluation of the scientificity of the papers;If detected with the control test for every quizzee;Verification bias;If the patient samples included a broad spectrum of the disease;The precision of the diagnostic tests ;Estimate the significance of clinical application;The predictive value depend on the pre-test probability of illness;Explain and use of sensitivity and specificity;Use likelihood ratio, LR;post-test probability ;The LR with serum ferritin for diagnosis