Related Experiment Video
Updated: Aug 19, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Diagnostic entropy as a function of therapeutic benefit/risk ratio
B Djulbegovic1, I Hozo, I Abdomerovic
1University of Louisville, Department of Medicine, James Graham Brown Cancer Center, KY 40292, USA. bmdjul01@ulkyvx.louisville.edu
Abstract:
Current clinical practice is based upon 'out stubborn quest for diagnostic certainty' which in turn is considered as one of the major reasons for ever-increasing health costs. We linked a treatment-threshold concept with classic information theory to show that measurable clinical variables, such as benefit and risk of available treatments, can be used to calculate the acceptable levels of diagnostic uncertainties associated with a particular clinical situation. Our analysis shows that practising physicians should aim for diagnostic certainty only when the benefit of treatment is equal to its associated risk. In all other cases, decisions about treatment do not have to rely on maximum diagnostic certainty. Determination of acceptable levels of diagnostic uncertainty according to the concepts outlined here should lead to improvement of clinical practice and decrease healthcare costs.
Related Concept Videos
Therapeutic Index
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast, controlled...
Sensitivity, Specificity, and Predicted Value
Sensitivity is the...
Receiver Operating Characteristic Plot
Relative Risk
Hazard Ratio
For example, in a clinical trial evaluating a...

