A Convolutional Neural Network-Based Triplet-Mining Metric Learning Schema for Measuring Patient Similarity Addressing Personalized Healthcare

Abstract

Prediction of the development risk of some diseases is an important area of Health Care Research. When exploring the personalized care of the patients, precise identification and classification of similarity in patients from their past report is an important process. Electronically stored health information EHRs that has been sampled unevenly as well as which has variable appointment durations, is considered to be unsuitable for measuring the similarity among patients directly, as there is no proper representation that are fitting. In addition, a technique is required that is efficient to evaluate similarities in patient. We propose two new similarities learning environments using deep learning that learn simultaneously the representations of the patients as well as measurement of similarity in pairs. A Convolutional Neural Network (CNN) is used to understand EHRs that contains crucial information which are local thereby providing scholastic illumination in the triplet loss otherwise entropy loss. When the training is completed, distances are calculated as well as similarities scores. Using this similarity information, disease predictions along with patient grouping is performed. Experimentally the results gives an idea that CNN can represent the EHR sequences in a better way and the schema offered are more efficient than the modern metric distance learning.