Optimal diagnosis cut-off value determination method based on arbitrarily weighted sensitivity and specificity
A technology for determining the method and sensitivity, applied in the computer field, can solve the problem that the optimal diagnostic threshold cannot meet the practical needs of the evaluation of the diagnostic method, and achieves the effect of strong practicability, easy to use, and concise model program.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0023] When the importance of sensitivity and specificity is different, the existing methods for determining the optimal diagnostic cut-off value cannot meet the practical needs of evaluating diagnostic methods in clinical medicine. This study established three methods for determining the optimal diagnostic cut-off value under the ROC curve that can be arbitrarily weighted based on sensitivity and specificity. Starting from practical applications, it has strong practicability, and this is a groundbreaking research.
[0024] Perkins and Schisterman (2006) compared two different principles for determining the optimal diagnostic cut-off value in the ROC curve: the principle of the largest "Youden index" and the principle of "minimum (0,1) distance", where (0,1) means figure 1 The (0, 1) point of the upper left corner in the coordinate system. Liu (2012) proposed the principle of "maximum product of sensitivity and specificity" and compared it with the principle of maximum "Youden...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


