Título:	Avaliação da associação da concentração de prolactina e a homeostase metabólica utilizando ferramentas de aprendizado de máquina
Autor(es):	Dias, Alan Carvalho
Orientador(es):	Naves, Luciana Ansaneli
Assunto:	Prolactina Resistência à insulina Síndrome metabólica Hiperprolactinemia Aprendizagem de máquina
Data de publicação:	22-Ago-2024
Data de defesa:	6-Jul-2023
Referência:	DIAS, Alan Carvalho. Avaliação da associação da concentração de prolactina e a homeostase metabólica utilizando ferramentas de aprendizado de máquina. 2023. 158 f., il. Dissertação (Mestrado em Ciências da Saúde) — Universidade de Brasília, Brasília, 2023.
Abstract:	Introduction: Recently, a new "metabolic classification" was proposed for prolactin and based on it, hypoprolactinemia and hyperprolactinemia were defined as results approximately < 7 and > 100 ng/mL, respectively, and several metabolic diseases were associated with this range of results, however, the determination of the cutoff points that influence metabolism seem uncertain. Objectives: To investigate the possible correlation between prolactin concentration and glucose and lipid metabolism tests. To establish a "gray zone" representing the inflection points, associating the results of the glycemic and lipid metabolism tests with prolactin. As part of the study, a machine learning tool was created using R language to perform these analyses in an automated manner. Methods: A cross-sectional study was conducted with 65,795 laboratory results from adult patients of both sexes, collected in the first half of 2018 at the Sabin Laboratory. The data, extracted and anonymized from the Laboratory Information System, included lipid parameters (total cholesterol, HDL-c, LDL-c, triglycerides) and biochemical/hormonal (glucose, prolactin, insulin, HOMA-IR). The individual data were stratified into 106 partitions, based on the average concentrations of prolactin and metabolites of lipid and glycemic metabolism for each individual. These averages were used in three separate analyses: initially, they were used to compare the results of the glycemic and lipid metabolism tests within each range of the new metabolic classification of prolactin; then, they served in estimating the inflection point and its respective confidence interval, associating the results of the glycemic and lipid metabolism tests with prolactin concentrations, and in determining the corresponding "gray zones"; finally, they were used in predicting the average results of these glycemic and lipid metabolism tests based on the estimated inflection point. In addition, the individual prolactin results were used to compare prolactin concentrations between the sexes. Results: The analyzed population was aged between 21 and 75 years, composed of 51,366 women and 14,429 men. Hyperprolactinemia (prolactin concentrations greater than 25 ng/mL) was identified in 4,004 of the 51,366 women (7.79%) and in 208 of the 14,429 men (1.41%). Prolactin results were equivalent between sexes. The average results of the glycemic and lipid metabolism tests were significantly higher in the average prolactin result range < 7 ng/mL, with the exception of insulin. In the HomeoFIT-PRL range, the median and distribution of the average results of the glycemic and lipid metabolism tests are predominantly lower compared to the other average prolactin result ranges. Below the "gray zone" represented by the average prolactin results between 9.58 and 12.87 ng/mL, there may be impairments in glycemic metabolism, while for lipid metabolism, the estimated "gray zone" was 13.81 to 18.73 ng/mL. Conclusion: Our research confirms the strong correlation between variations in average prolactin concentrations and tests of glycemic and lipid metabolism in humans, suggesting a mediating role of prolactin in the pathogenesis of impaired glucose and lipid metabolism. The historical average of prolactin concentrations may offer more precise insights for understanding metabolic homeostasis.
Unidade Acadêmica:	Faculdade de Ciências da Saúde (FS)
Informações adicionais:	Dissertação (mestrado) — Universidade de Brasília, Faculdade de Economia, Administração, Ciências Contábeis e Gestão de Políticas Públicas, Programa de Pós-Graduação em Administração, 2024.Dissertação (mestrado) — Universidade de Brasília, Faculdade de Ciências da Saúde, Programa de Pós-Graduação em Ciências da Saúde, 2023.
Programa de pós-graduação:	Programa de Pós-Graduação em Ciências da Saúde
Licença:	A concessão da licença deste item refere-se ao termo de autorização impresso assinado pelo autor com as seguintes condições: Na qualidade de titular dos direitos de autor da publicação, autorizo a Universidade de Brasília e o IBICT a disponibilizar por meio dos sites www.unb.br, www.ibict.br, www.ndltd.org sem ressarcimento dos direitos autorais, de acordo com a Lei nº 9610/98, o texto integral da obra supracitada, conforme permissões assinaladas, para fins de leitura, impressão e/ou download, a título de divulgação da produção científica brasileira, a partir desta data.
Aparece nas coleções:	Teses, dissertações e produtos pós-doutorado

Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.