Trends Identification in Medical Care

Inês Sena, Ana Pereira

2021

Abstract

Daily, health professionals are sought out by patients, motivated by the will to stay healthy, making numerous diagnoses that can be wrong for several reasons. In order to reduce diagnostic errors, an application was developed to support health professionals, assisting them in the diagnosis, assigning a second diagnostic opinion. The application, called ProSmartHealth, is based on intelligent algorithms to identify clusters and patterns in human symptoms. ProSmartHealth uses the Support Vector Machine ranking algorithm to train and test diagnostic suggestions. This work aims to study the application’s reliability, using two strategies. First, study the influence of pre-processing data analysing the impact in the accuracy method when data is previously processed. The second strategy aims to study the influence of the number of training data on the method precision. This study concludes the use of pre-processing data and the number of training data influence the precision of the model, improving the precision on 8%.

Paper Citation

in Harvard Style

Sena I. and Pereira A. (2021). Trends Identification in Medical Care.In Proceedings of the 10th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES, ISBN 978-989-758-485-5, pages 295-302. DOI: 10.5220/0010384502950302

in Bibtex Style

@conference{icores21,
author={Inês Sena and Ana Pereira},
title={Trends Identification in Medical Care},
booktitle={Proceedings of the 10th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES,},
year={2021},
pages={295-302},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010384502950302},
isbn={978-989-758-485-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Operations Research and Enterprise Systems - Volume 1: ICORES,
TI - Trends Identification in Medical Care
SN - 978-989-758-485-5
AU - Sena I.
AU - Pereira A.
PY - 2021
SP - 295
EP - 302
DO - 10.5220/0010384502950302