Banca de DEFESA: MÁRCIO LUIZ BEZERRA LOPES JÚNIOR

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : MÁRCIO LUIZ BEZERRA LOPES JÚNIOR
DATE: 29/04/2022
TIME: 09:30
LOCAL: meet.google.com/ige-sgvw-qgf
TITLE:

Stratification of Preterm Birth Risk in Brazil Through Unsupervised Learning Methods and Socioeconomic Data

KEY WORDS:

Preterm birth, Clustering, Unsupervised learning, PTB risk, k-Means, Self-Organising Maps, Brazil

PAGES: 81
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUMMARY:

Preterm birth (PTB) is a phenomenon that brings risks and challenges for the survival of the newborn child. Despite many advances in research, not all the causes of PTB are yet clear. It is currently understood that PTB risk is multi-factorial and may also be associated with socioeconomic factors. In order to analyse this possible relationship, this work seeks to stratify PTB risk in Brazil using only socioeconomic data, extracting and analysing those clusters that present relevant PTB divergence, all of which will be found by automatic clustering processes using a series of unsupervised machine learning methods. Through the use of datasets made publicly available by the Federal Government of Brazil, a new dataset was generated with municipality-level socioeconomic data and a PTB occurrence rate. This dataset was processed using two separate clustering methods, both built by assembling unsupervised learning techniques, such as $k$-means, principal component analysis (PCA), density-based spatial clustering of applications with noise (DBSCAN), self-organising maps (SOM) and hierarchical clustering. The methods discovered clusters of municipalities with both high levels and low levels of PTB occurrence. The clusters with high PTB were comprised mostly of municipalities with lower levels of education, worse quality of public services -- such as basic sanitation and garbage collection -- and a less white population. The regional distribution of the clusters was also observed, with clusters of high PTB located mostly in the North and Northeast regions of Brazil. The results indicate a positive influence of the quality of life and the offer of public services on the reduction of PTB risk.

BANKING MEMBERS:
Presidente - 1837240 - MARCELO AUGUSTO COSTA FERNANDES
Interno - 2885532 - IVANOVITCH MEDEIROS DANTAS DA SILVA
Externo à Instituição - ALEXANDRE DIAS PORTO CHIAVEGATTO FILHO - USP
Externo à Instituição - LEONARDO ALVES DIAS
Externa à Instituição - RAQUEL DE MELO BARBOSA - UGR