Text Classification of Cancer Clinical Trials Documents Using Deep Neural Network and Fine Grained Document Clustering

DOI

10.2991/aisr.k.200424.061How to use a DOI?

Keywords

text classification, clinical trials, Deep Neural Network, fine grained document clustering

Abstract

Clinical trials are any research studies involve human participation with health safety outcomes. In clinical trials, there is the most important term called the eligibility criteria (eligible and not eligible). The eligibility criteria for clinical trials are usually written in free text, it requires interpretation from a computer to process them. The purpose of this paper is to classify cancer clinical texts from the public dataset at https://clinicaltrials.gov. The proposed algorithm is Supervised Learning such as K-Nearest Neighbor and Decision Tree, Machine Learning such as Support Vector Machine and Random Forest, Deep Neural Network such as Multilayer Perceptron, and Fine Grained Document Clustering. This research has contributed a new classification model for clinical trial documents and computational value or speed improvement. The results shown the highest accuracy at random forest method 90.5% and the lowest accuracy at multilayer perceptron method that is 72.1%

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jasmir JASMIR
AU  - Siti NURMAINI
AU  - Reza Firsandaya MALIK
AU  - Dodo Zaenal ABIDIN
PY  - 2020
DA  - 2020/05/06
TI  - Text Classification of Cancer Clinical Trials Documents Using Deep Neural Network and Fine Grained Document Clustering
BT  - Proceedings of the Sriwijaya International Conference on Information Technology and Its Applications (SICONIAN 2019)
PB  - Atlantis Press
SP  - 396
EP  - 404
SN  - 1951-6851
UR  - https://doi.org/10.2991/aisr.k.200424.061
DO  - 10.2991/aisr.k.200424.061
ID  - JASMIR2020
ER  -