Banca de QUALIFICAÇÃO: JACKSON HENRIQUE DA SILVA BEZERRA

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : JACKSON HENRIQUE DA SILVA BEZERRA
DATE: 02/05/2024
TIME: 09:00
LOCAL: sala virtual meet.google.com/wkx-zgkk-eay
TITLE:

DEVELOPMENT OF PREDICTIVE MODELS OF DEATH WITH THE USE OF MACHINE LEARNING FOR PATIENTS WITH SEVERE SYNDROME IN THE NORTHERN REGION

KEY WORDS:

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

PAGES: 60
BIG AREA: Outra
AREA: Multidisciplinar
SUMMARY:

 

Machine Learning (ML) has an important role to play in the health sector, providing and patient prognosis through predictive models. The aim of this research was to develop predictive models for death from Severe Acute Respiratory Syndrome (SARS). by Severe Acute Respiratory Syndrome (SARS) in vulnerable population groups in the northern region of Brazil. Northern region of Brazil. In order to achieve this objective, the study used data from children aged 0 to 3 years, pregnant women and puerperal women. years old, pregnant women and puerperal women provided by the Brazilian Ministry of Health. Among the methodological procedures carried out include the preparation of an Integrative Review review of the literature on the use of MH in predicting deaths from SARS and an applied survey using the CRISP methodology that guided the entire selection process, processing, transformation, application of ML algorithms and evaluation of predictive models. The results include the predictive models generated with the algorithms Randon Forest (RF) and Regression Logistic (RL) algorithms using Weka software and the RR code library, where the RF models performed better. To ensure the reliabilityof the models, cross-validation was used, as well as evaluation using the confusion matrix and data on the accuracy of the models. Finally, a prototype software application for classification of SARS patients was developed in the Java language so that the knowledge generated by the model reaches the hospital environment. The results of this study contribute significantly to the prevention of deaths from SARS in vulnerable populations, by populations, providing practical and effective tools for the clinical management of these cases.

COMMITTEE MEMBERS:
Presidente - 2440330 - MONICA PEREIRA LIMA CUNHA
Interno - 359961 - WANDERLEY RODRIGUES BASTOS
Interno - 3063165 - DIEGO HENRIQUE DE ALMEIDA
Externa à Instituição - ÉRICA PATRÍCIA NAVARRO
Externo à Instituição - RAFAEL JUNQUEIRA BURALLI - USP
Externo à Instituição - DHELIO BATISTA PEREIRA - CEPEM
Externo à Instituição - WANDERSON ROGER AZEVEDO DIAS