Abstract
This work targets the development of a neighborhood-based Collaborative Filtering therapy recommender system for clinical decision support. The proposed algorithm estimates outcome of pharmaceutical therapy options in order to derive recommendations. Two approaches, namely a Relief-based algorithm and a metric learning approach are investigated. Both adapt similarity functions to the underlying data in order to determine the neighborhood incorporated into the filtering process. The implemented approaches are evaluated regarding the accuracy of the outcome estimations. The metric learning approach can outperform the Relief-based algorithms. It is, however, inferior regarding explainability of the generated recommendations.
© 2019 by Walter de Gruyter Berlin/Boston
This work is licensed under the Creative Commons Attribution 4.0 Public License.
