The Analysis from Nonlinear Distance Metric to Kernel-based Drug Prescription Prediction System
This work provides guidance for medical practitioners and machine learning researchers on selecting appropriate distance metrics for drug prescription prediction based on disease characteristics, potentially improving prediction accuracy in healthcare.
This paper investigates the application of Euclidean and cosine distance metrics for predicting drug prescription outcomes, demonstrating their distinct performance characteristics based on disease type. Euclidean distance is more suitable for short-term diseases with low outcome variation, while cosine distance is preferred for highly variant chronic diseases.
Distance metrics and their nonlinear variant play a crucial role in machine learning based real-world problem solving. We demonstrated how Euclidean and cosine distance measures differ not only theoretically but also in real-world medical application, namely, outcome prediction of drug prescription. Euclidean distance exhibits favorable properties in the local geometry problem. To this regard, Euclidean distance can be applied under short-term disease with low-variation outcome observation. Moreover, when presenting to highly variant chronic disease, it is preferable to use cosine distance. These different geometric properties lead to different submanifolds in the original embedded space, and hence, to different optimizing nonlinear kernel embedding frameworks. We first established the geometric properties that we needed in these frameworks. From these properties interpreted their differences in certain perspectives. Our evaluation on real-world, large-scale electronic health records and embedding space visualization empirically validated our approach.