Deep Neural Network to Identify Patients with Alcohol Use Disorder

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

This paper presents an application of deep neural networks (DNN) to identify patients with Alcohol Use Disorder based on historical electronic health records. Our methodology consists of four stages including data collection, preprocessing, predictive model development, and validation. Data are collected from two sources and labeled into three classes including Normal, Hazardous, and Harmful drinkers. Moreover, problems such as imbalanced classes, noise, and categorical variables were handled. A four-layer fully-connected feedforward DNN architecture was designed and developed to predict Normal, Hazardous, and Harmful drinkers. Results show that our proposed method could successfully classify about 96%, 82%, and 89% of Normal, Hazardous, and Harmful drinkers, respectively, which is better than classical machine learning approaches.

Original languageEnglish
Title of host publicationPublic Health and Informatics
EditorsJohn Mantas, Lăcrămioara Stoicu-Tivadar, Catherine Chronaki, Arie Hasman, Patrick Weber, Parisis Gallos, Mihaela Crişan-Vida, Emmanouil Zoulias, Oana Sorina Chirila
Volume281
Publication date27. May 2021
Pages238-242
ISBN (Print)978-1-64368-184-9
ISBN (Electronic)978-1-64368-185-6
DOIs
Publication statusPublished - 27. May 2021
EventMIE 2021: 31st Medical Informatics Europe Conference Online -
Duration: 29. May 202131. May 2021

Conference

ConferenceMIE 2021: 31st Medical Informatics Europe Conference Online
Period29/05/202131/05/2021
SeriesStudies in Health Technology and Informatics
Volume281
ISSN0926-9630

Fingerprint

Dive into the research topics of 'Deep Neural Network to Identify Patients with Alcohol Use Disorder'. Together they form a unique fingerprint.

Cite this