ROC Curve Documentation

Price List & Order Information System Requirements Key Features by Version User Testimonials

ROC (Receiver Operating Characteristic) curve analysis is mainly used for diagnostic studies in Clinical Chemistry, Pharmacology and Physiology. It has been widely accepted as the standard for describing and comparing the accuracy of diagnostic tests. (Please note that ROC Curve analysis is a feature only available in OriginPro.)

For example, you can use ROC Curve analysis to test a diagnostic to determine if an incident had occurred, or compare the accuracy of two methods that are used to discriminate diseased cases versus healthy cases. The conclusion in each case is based upon the area under the curve and the shape of the curve.

If the ROC curve rises rapidly towards the upper right-hand corner of the graph, or if the value of area under the curve is large, we can say the test performs well. If the area is close to 1.0, it indicates that the test is good. While if the area is to 0.5, it shows that the test is bad.

When you perform ROC curve analysis by Origin, you can set the following features:

Set the State Value to specify which states to be positive. Determine which Threshold Method to be used: Interpolation of Data Points or Speed Mode. You can decide whether to output the ROC Curve as well as Standard Error and Confidence Interval by checking these corresponding check-boxes.

View Larger Image

Further, you can decide where to output your report tables and ROC curve values.

As an example, a researcher wants to perform a study on which diagnostics (method 1 and method 2) can diagnose Rocky Mountain Spotted Fever (RMSF) better. He observed 24 patients that have RMSF and 26 healthy patients. The researcher will examine their serum sodium using two screening techniques to check the relationship of serum sodium and RMSF to determine which technique is better. Please see the images below to see how one would use ROC curve analysis in OriginPro to solve this problem.