Research Article
Recommendation of Medical Exams to Support Clinical Diagnosis Based on Patient’s Symptoms
@INPROCEEDINGS{10.1007/978-3-031-38204-8_8, author={Cristiana Neto and Diana Ferreira and Hugo Cunha and Maria Pires and Susana Marques and Regina Sousa and Jos\^{e} Machado}, title={Recommendation of Medical Exams to Support Clinical Diagnosis Based on Patient’s Symptoms}, proceedings={AI-assisted Solutions for COVID-19 and Biomedical Applications in Smart Cities. Third EAI International Conference, AISCOVID-19 2022, Braga, Portugal, November 16-18, 2022, Proceedings}, proceedings_a={AISCOVID-19}, year={2023}, month={7}, keywords={Recommender System Medical Exams CRISP-DM Classification}, doi={10.1007/978-3-031-38204-8_8} }- Cristiana Neto
Diana Ferreira
Hugo Cunha
Maria Pires
Susana Marques
Regina Sousa
José Machado
Year: 2023
Recommendation of Medical Exams to Support Clinical Diagnosis Based on Patient’s Symptoms
AISCOVID-19
Springer
DOI: 10.1007/978-3-031-38204-8_8
Abstract
Nowadays, it is essential that the error in the decisions made by health professionals is as small as possible. This applies to any medical area, including the recommendation of medical exams based on certain symptoms for the diagnosis of diseases. This study aims to explore the use of different Machine Learning techniques to increase the confidence of the medical exams prescribed by healthcare professionals. A successful implementation of this proposal could reduce the probability of medical errors in what concerns the prescription of medical exams and, consequently, the diagnosis of medical conditions. Thus, in this paper, six Machine Learning models were applied and optimized, namely, RF, DT, k-NN, NB, SVM and RNN, in order to find the most suitable model for the problem at hand. The results obtained with this study were promising, achieving high accuracy values with RF, DT and k-NN.
