LIKELIHOOD RATIOS - A REAL IMPROVEMENT FOR CLINICAL DECISION-MAKING

The concept of likelihood ratio has been advocated for several years a s one of the better means to evaluate diagnostic tests and as a practi cal and valuable tool in clinical decision making. In this paper we re view the basic concepts underlying the evaluation of diagnostic tests and we explore the properties and usefulness of both positive and nega tive likelihood ratios compared with sensitivity and specificity. Part icular attention is given to the use of likelihood ratios in the clini cal setting. Likelihood ratios have three main advantages: they are in tuitive, they simplify the predictive value calculation and the overal l evaluation of sequential testing. Disadvantages are the non-linearit y and the necessity to recalculate probabilities in odds. Although the y summarize the information contained in sensitivity and specificity, these characteristics are still necessary for certain clinical decisio ns. Since likelihood ratios have been promoted among physicians and me dical students, we discuss examples of inappropriate use and misunders tandings in the medical literature: the frequent omission of confidenc e intervals, the choice of cut-off points based on likelihood ratios f or positive test results only and the confusion between likelihood rat ios for ranges and those for cut-off points.