FISUL: A Framework for Detecting Adverse Drug Events from Heterogeneous Medical Sources Using Feature Importance - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

FISUL: A Framework for Detecting Adverse Drug Events from Heterogeneous Medical Sources Using Feature Importance

(1, 2) , (1, 2) , (2)
1
2

Abstract

Adverse drug events (ADEs) are considered to be highly important and critical conditions, while accounting for around 3.7% of hospital admissions all over the world. Several studies have applied predictive models for ADE detection; nonetheless, only a restricted number and type of features has been used. In the paper, we propose a framework for identifying ADEs in medical records, by first applying the Boruta feature importance criterion, and then using the top-ranked features for building a predictive model as well as for clustering. We provide an experimental evaluation on the MIMIC-III database by considering 7 types of ADEs illustrating the benefit of the Boruta criterion for the task of ADE detection.
Fichier principal
Vignette du fichier
483292_1_En_11_Chapter.pdf (378.97 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02331324 , version 1 (24-10-2019)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Corinne G. Allaart, Lena Mondrejevski, Panagiotis Papapetrou. FISUL: A Framework for Detecting Adverse Drug Events from Heterogeneous Medical Sources Using Feature Importance. 15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.139-151, ⟨10.1007/978-3-030-19823-7_11⟩. ⟨hal-02331324⟩
33 View
10 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More