A Recommender System Approach for Predicting Drug Side Effects. / Galeano Galeano, Diego; Paccanaro, Alberto.

IJCNN 2018: International Joint Conference on Neural Networks. IEEE Xplore, 2018. p. 1-7.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Standard

A Recommender System Approach for Predicting Drug Side Effects. / Galeano Galeano, Diego; Paccanaro, Alberto.

IJCNN 2018: International Joint Conference on Neural Networks. IEEE Xplore, 2018. p. 1-7.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Galeano Galeano, D & Paccanaro, A 2018, A Recommender System Approach for Predicting Drug Side Effects. in IJCNN 2018: International Joint Conference on Neural Networks. IEEE Xplore, pp. 1-7. https://doi.org/10.1109/IJCNN.2018.8489025

APA

Galeano Galeano, D., & Paccanaro, A. (2018). A Recommender System Approach for Predicting Drug Side Effects. In IJCNN 2018: International Joint Conference on Neural Networks (pp. 1-7). IEEE Xplore. https://doi.org/10.1109/IJCNN.2018.8489025

Vancouver

Galeano Galeano D, Paccanaro A. A Recommender System Approach for Predicting Drug Side Effects. In IJCNN 2018: International Joint Conference on Neural Networks. IEEE Xplore. 2018. p. 1-7 https://doi.org/10.1109/IJCNN.2018.8489025

Author

Galeano Galeano, Diego ; Paccanaro, Alberto. / A Recommender System Approach for Predicting Drug Side Effects. IJCNN 2018: International Joint Conference on Neural Networks. IEEE Xplore, 2018. pp. 1-7

BibTeX

@inproceedings{bc6a007376a0483ca5f2ae2eb4de477a,
title = "A Recommender System Approach for Predicting Drug Side Effects",
abstract = "The accurate identification of drug side effects represents a major concern for public health. We propose a collaborative filtering model for large-scale prediction of drug side effects. Our approach provides specific recommendations for side effects of medicines. The proposed latent factor model relies solely on the public drug-side effect relationships from safety data. Applied to 1,525 marketed drugs and 2,050 side effects, we achieved an AUPRC (area under the precision-recall curve) of 0.342 in a hold-out test set, with a sensitivity of 0.73 given a specificity of 0.95, providing state-of-the-art performance in sideeffect prediction. Here we also show that our method provides good performance on drug-specific Anatomical Therapeutic and Chemical (ATC) category and side effect- specific medical category of disorders. Our findings suggest that latent factor models can be useful for predicting unknown adverse drug events.",
keywords = "drug, side effects, recommendation systems, Adverse drug reactions, latent factor models, collaborative filtering",
author = "{Galeano Galeano}, Diego and Alberto Paccanaro",
year = "2018",
doi = "10.1109/IJCNN.2018.8489025",
language = "English",
pages = "1--7",
booktitle = "IJCNN 2018: International Joint Conference on Neural Networks",
publisher = "IEEE Xplore",

}

RIS

TY - GEN

T1 - A Recommender System Approach for Predicting Drug Side Effects

AU - Galeano Galeano, Diego

AU - Paccanaro, Alberto

PY - 2018

Y1 - 2018

N2 - The accurate identification of drug side effects represents a major concern for public health. We propose a collaborative filtering model for large-scale prediction of drug side effects. Our approach provides specific recommendations for side effects of medicines. The proposed latent factor model relies solely on the public drug-side effect relationships from safety data. Applied to 1,525 marketed drugs and 2,050 side effects, we achieved an AUPRC (area under the precision-recall curve) of 0.342 in a hold-out test set, with a sensitivity of 0.73 given a specificity of 0.95, providing state-of-the-art performance in sideeffect prediction. Here we also show that our method provides good performance on drug-specific Anatomical Therapeutic and Chemical (ATC) category and side effect- specific medical category of disorders. Our findings suggest that latent factor models can be useful for predicting unknown adverse drug events.

AB - The accurate identification of drug side effects represents a major concern for public health. We propose a collaborative filtering model for large-scale prediction of drug side effects. Our approach provides specific recommendations for side effects of medicines. The proposed latent factor model relies solely on the public drug-side effect relationships from safety data. Applied to 1,525 marketed drugs and 2,050 side effects, we achieved an AUPRC (area under the precision-recall curve) of 0.342 in a hold-out test set, with a sensitivity of 0.73 given a specificity of 0.95, providing state-of-the-art performance in sideeffect prediction. Here we also show that our method provides good performance on drug-specific Anatomical Therapeutic and Chemical (ATC) category and side effect- specific medical category of disorders. Our findings suggest that latent factor models can be useful for predicting unknown adverse drug events.

KW - drug

KW - side effects

KW - recommendation systems

KW - Adverse drug reactions

KW - latent factor models

KW - collaborative filtering

U2 - 10.1109/IJCNN.2018.8489025

DO - 10.1109/IJCNN.2018.8489025

M3 - Conference contribution

SP - 1

EP - 7

BT - IJCNN 2018: International Joint Conference on Neural Networks

PB - IEEE Xplore

ER -