Banca de DEFESA: JACKSON HENRIQUE DA SILVA BEZERRA

Uma banca de DEFESA de DOUTORADO foi cadastrada pelo programa.
STUDENT : JACKSON HENRIQUE DA SILVA BEZERRA
DATE: 02/12/2024
TIME: 10:00
LOCAL: Via - auditório virtual usando GOOGLE MEETING - https://meet.google.com/edn-gcrf-ojk
TITLE:

DEVELOPMENT OF PREDICTIVE MODELS AND MACHINE LEARNING USING SRAG DATABASE.

KEY WORDS:

 Machine Learning (ML), Database, Severe Acute Respiratory Syndrome (SARS), Predictive Models.

PAGES: 87
BIG AREA: Outra
AREA: Multidisciplinar
SUMMARY:

Machine Learning (ML) plays an important role in healthcare, providing predictive models created from algorithms and large databases. These models can classify patients for diagnostic or prognostic purposes in various diseases. This research aimed to develop predictive models for death from Severe Acute Respiratory Syndrome (SARS) in vulnerable population groups in the North region of Brazil. To achieve this objective, the study used data from children aged 0 to 3 years, pregnant women and postpartum women provided by the Brazilian Ministry of Health. Among the methodological procedures carried out, we highlight the elaboration of an Integrative Review in the literature on the use of ML in predicting deaths from SARS and the realization of an applied research done through the CRISP-DM methodology that guided the entire process of selection, processing, transformation, application of ML algorithms and evaluation of predictive models. The Random Forest, Logistic Regression, K-Nearest Neighbors, and XGBoost algorithms were used through the Weka software and R code library, where the Random Forest models had superior performance. Cross-validation was used to ensure the reliability of the models. The models were evaluated according to the metrics of sensitivity, specificity, accuracy, precision, F1-Score, and AUC-ROC, the latter being the primary evaluation metric. Finally, a software application prototype for using the models was developed in the Java language so that the knowledge generated by the model reaches health professionals. The results of this study contribute to the reduction of deaths from SARS in the maternal and child population in the North region of Brazil, contributing to the fulfillment of Brazil's goals in the 2030 Agenda regarding the reduction of infant and maternal mortality and the use of Artificial Intelligence (AI) in accordance with OECD guidelines. Keyword: Machine Learning (ML), Database, Severe Acute Respiratory Syndrome (SARS), Predictive Models.

COMMITTEE MEMBERS:
Presidente - 1466944 - FABRICIO MORAES DE ALMEIDA
Interno - 3063165 - DIEGO HENRIQUE DE ALMEIDA
Interno - 1905088 - RONALDO DE ALMEIDA
Externo à Instituição - FABIO MACHADO DE OLIVEIRA
Externo à Instituição - ALEXANDRE PAULO MACHADO - UFMT
Externo à Instituição - RAFAEL AYRES ROMANHOLO - IFRO
Externo à Instituição - WANDERSON ROGER AZEVEDO DIAS - IFRO