Title: Improving the biomarker diagnostic capacity via functional transformations
Authors: Pablo Martinez-Camblor - Geisel School of Medicine Dartmouth College (United States) [presenting]
Abstract: The use of the area under the receiver-operating characteristic, ROC, curve (AUC) as an index of diagnostic accuracy is overwhelming in fields such as biomedical science and machine learning. A larger AUC has become synonymous with a better performance. A functional transformation of the marker values has been proposed for increasing the AUC and then the diagnostic accuracy. The classification process is based on some regions which support the decision made; one subject is classified as positive if its marker is within this region, and as negative otherwise. We study the capacity of improving the classification performance of univariate markers via functional transformations and the impact of this transformation on the final classification regions based on a real-world dataset. Particularly, we consider the problem of determining the gender of a subject based on the Mode frequency of his/her voice. The shape of the cumulative distribution function of this characteristic in both the male and female groups makes the classification problem useful for illustrating the differences between having valuable diagnostic rules and obtaining an optimal AUC. Our point is that improving the AUC by means of a functional transformation can produce classification regions with no practical interpretability. We propose to improve the classification accuracy by making the selection of the classification subsets more flexible while preserving their interpretability.