A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems

Clinical health information systems capture massive amounts of unstructured data from various health and medical facilities. This study utilizes unstructured patient clinical text data to develop an intelligent assistant that can identify possible related diagnoses based on a given text input. The a...

Full description

Saved in:
Bibliographic Details
Main Authors: Pulmano, Christian E, Estuar, Ma. Regina Justina E
Format: text
Published: Archīum Ateneo 2017
Subjects:
Online Access:https://archium.ateneo.edu/discs-faculty-pubs/29
https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1028&context=discs-faculty-pubs
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Ateneo De Manila University
id ph-ateneo-arc.discs-faculty-pubs-1028
record_format eprints
spelling ph-ateneo-arc.discs-faculty-pubs-10282020-02-22T03:01:55Z A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems Pulmano, Christian E Estuar, Ma. Regina Justina E Clinical health information systems capture massive amounts of unstructured data from various health and medical facilities. This study utilizes unstructured patient clinical text data to develop an intelligent assistant that can identify possible related diagnoses based on a given text input. The approach applies a one-vs-rest binary classification technique wherein given an input text data, it is identified whether it can be positively or negatively classified for a given diagnosis. Multi-layer Feed-Forward Neural Network models were developed for each individual diagnosis case. The task of the intelligent assistant is to iterate over all the different models and return those that output a positive diagnosis. To validate the performance of the models, the performance metrics were compared against Naive Bayes, Decision Trees, and K-Nearest Neighbor. The results show that the neural network learner provided better performance scores in both accuracy and area under the curve metric scores. Further, testing on multiple diagnoses also shows that the methodology for developing the diagnosis models can be replicated for development of models for other diseases as well. 2017-01-01T08:00:00Z text application/pdf https://archium.ateneo.edu/discs-faculty-pubs/29 https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1028&context=discs-faculty-pubs Department of Information Systems & Computer Science Faculty Publications Archīum Ateneo artificial neural network intelligent assistant medical diagnosis health intelligent systems Computer Sciences Databases and Information Systems Health Information Technology Medicine and Health Sciences
institution Ateneo De Manila University
building Ateneo De Manila University Library
continent Asia
country Philippines
Philippines
content_provider Ateneo De Manila University Library
collection archium.Ateneo Institutional Repository
topic artificial neural network
intelligent assistant
medical diagnosis
health intelligent systems
Computer Sciences
Databases and Information Systems
Health Information Technology
Medicine and Health Sciences
spellingShingle artificial neural network
intelligent assistant
medical diagnosis
health intelligent systems
Computer Sciences
Databases and Information Systems
Health Information Technology
Medicine and Health Sciences
Pulmano, Christian E
Estuar, Ma. Regina Justina E
A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems
description Clinical health information systems capture massive amounts of unstructured data from various health and medical facilities. This study utilizes unstructured patient clinical text data to develop an intelligent assistant that can identify possible related diagnoses based on a given text input. The approach applies a one-vs-rest binary classification technique wherein given an input text data, it is identified whether it can be positively or negatively classified for a given diagnosis. Multi-layer Feed-Forward Neural Network models were developed for each individual diagnosis case. The task of the intelligent assistant is to iterate over all the different models and return those that output a positive diagnosis. To validate the performance of the models, the performance metrics were compared against Naive Bayes, Decision Trees, and K-Nearest Neighbor. The results show that the neural network learner provided better performance scores in both accuracy and area under the curve metric scores. Further, testing on multiple diagnoses also shows that the methodology for developing the diagnosis models can be replicated for development of models for other diseases as well.
format text
author Pulmano, Christian E
Estuar, Ma. Regina Justina E
author_facet Pulmano, Christian E
Estuar, Ma. Regina Justina E
author_sort Pulmano, Christian E
title A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems
title_short A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems
title_full A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems
title_fullStr A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems
title_full_unstemmed A Multi-model Approach in Developing an Intelligent Assistant for Diagnosis Recommendation in Clinical Health Systems
title_sort multi-model approach in developing an intelligent assistant for diagnosis recommendation in clinical health systems
publisher Archīum Ateneo
publishDate 2017
url https://archium.ateneo.edu/discs-faculty-pubs/29
https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1028&context=discs-faculty-pubs
_version_ 1722366524847554560