https://repositorio.ufpb.br/jspui/handle/123456789/11120 2026-04-08T22:39:18Z 2026-04-08T22:39:18Z Santos, João Guilherme Pereira dos https://repositorio.ufpb.br/jspui/handle/123456789/36977 2025-12-23T06:12:26Z 2025-04-29T00:00:00Z

Título: Aplicação web para crítica de bases de dados previdenciários em fundos de pensão Autor(es): Santos, João Guilherme Pereira dos Orientador: Santos Júnior, Luiz Carlos Abstract: The integrity and consistency of registry databases are essential to ensure the reliability of actuarial valuations and the sustainability of benefit plans managed by Pension Funds. In this context, this study proposes a structured data review process using the R programming language, aiming to identify inconsistencies, duplications, and other issues that may compromise the quality of information used in actuarial valuations. The adopted methodology combines established market practices, also incorporating a descriptive analysis of the dataset and validation steps related to changes in participant records. In addition to the technical analysis, the study includes the automated export of results in .xlsx format and the implementation of an interactive interface via Shinyapps, with the goal of making the process accessible to users with varying levels of programming experience. The results demonstrate that automating and systematizing the data review process can significantly contribute to improving the quality of information used in actuarial valuations, promoting greater reliability and efficiency in the management of benefit plans. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-04-29T00:00:00Z Cavalcante, Adrienny de Oliveira https://repositorio.ufpb.br/jspui/handle/123456789/36976 2025-12-23T06:12:22Z 2025-04-28T00:00:00Z

Título: Demanda de medicamentos oncológicos: um estudo a partir da projeção demográfica Autor(es): Cavalcante, Adrienny de Oliveira Orientador: Kataoka, Sheila Sayuri Abstract: The Brazilian healthcare system faces significant challenges considering demographic changes. The demographic transition, marked by the accelerated aging of the population, directly impacts the demand for medical care and pharmaceutical products, especially among the elderly. In this context, the health scenario is further strained by the growing prevalence of Non-Communicable Chronic Diseases, such as cancer, which now represent the leading causes of morbidity and mortality in the country. The Unified Health System and the supplementary healthcare sector must adapt to ensure access and market sustainability in response to the rising incidence of Non-Communicable Chronic Diseases. Accordingly, the objective of this study was to analyse the projected demand for oncological medications based on demographic trends. Data from DataSUS and the Brazilian Institute of Geography and Statistics population census were used to project the demand for oncological drugs through 2070. The results show that cancer incidence rates are significantly higher among older age groups, affecting approximately 1% of the elderly population. Projections from 2024 to 2070 indicate an approximately 478% increase in the number of new cancer cases among individuals aged 80 and over by the final projected year. This growth reflects population aging and the associated challenges of increased longevity. Therefore, it can be concluded that, despite the sharp rise in demand for oncological medications, this growth trend continues only until 2059. After this point, a deceleration is observed through 2070, potentially reflecting the impact of technological advancements and improved treatment efficacy. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-04-28T00:00:00Z Anacleto, Cleo Decker https://repositorio.ufpb.br/jspui/handle/123456789/36359 2025-10-18T06:07:50Z 2025-09-23T00:00:00Z

Título: Previsão de mortalidade no Brasil com séries temporais curtas: uma abordagem com combinação de preditores e transferência de aprendizado Autor(es): Anacleto, Cleo Decker Orientador: Duarte, Filipe Coelho de Lima Abstract: This study addresses the challenge of mortality rate forecasting in Brazil using short time series, exploring and comparing statistical, machine learning, and hybrid methodologies. The central objective was to develop and evaluate a forecasting system that enhances the accuracy of demographic projections, considering the specific characteristics of Brazilian data. Statistical models (Lee-Carter, FDM), classical time series models (ARIMA, ETS), deep learning architec- tures with transfer learning (CNN, GRU, and a hybrid CNN-GRU), and forecast combination techniques were applied. Deep learning models were pre-trained on the Human Mortality Database and fine-tuned with Brazilian data from 2000 to 2015 to forecast the period 2016 to 2019. The results indicate a notable complementarity between approaches. The classical time series models, ETS (and ARIMA, closely), emerged as robust benchmarks, consistently leading in aggregate metrics (RMSE, MAE, and sMAPE), particularly benefiting from the smoothed nature of official data. Deep learning models with transfer learning did not surpass classical models in overall performance but showed localized gains in critical age groups, such as age 0 and the male accident hump. Regarding combinations, a nuanced picture emerged: inverse error weighting reduced RMSE/MAE for males and the total group, while simple averaging remained competitive in sMAPE, especially for females and in aggregate. The study concludes that while established time series models are highly effective for Brazilian mortality data, transfer learning and combination strategies offer complementary value in capturing complex dynamics within specific segments. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-09-23T00:00:00Z Souza, Kewelyn Ferreira dos Santos https://repositorio.ufpb.br/jspui/handle/123456789/36358 2025-10-18T06:07:51Z 2025-09-23T00:00:00Z

Título: Variação dos custos assistenciais de pacientes com Transtorno do Espectro Autista em uma cooperativa médica (2021-2023) Autor(es): Souza, Kewelyn Ferreira dos Santos Orientador: Santos Júnior, Luiz Carlos Abstract: There is a growing demand for treatment for Autism Spectrum Disorder (ASD). Understanding the evolution of healthcare costs associated with this treatment is essential to inform the management of providers and policies for care for individuals with ASD. This study analyzed the structure and evolution of healthcare costs related to ASD treatment in a medical cooperative from 2021 to 2023. The research is characterized as an applied case study with a quantitative, documentary, and retrospective approach. Data were obtained from the cooperative's spreadsheets, enabling cost measurement by type of therapeutic procedure. Descriptive, horizontal, and vertical analyses were applied, in addition to the calculation of the variation in medical-hospital costs (VCMH) and the nonparametric Kruskal-Wallis test. The results showed an increase in healthcare costs from R$1.2 million in 2021 to R$16.2 million in 2023, with a notable increase in psychology, which increased from R$1.2 million to R$11.8 million. The horizontal analysis demonstrated a continued upward trend in spending, while the vertical analysis indicated a concentration of costs in speech-language pathology and occupational therapy. The VCMH calculation indicated a significant variation in both years, associated with an increase in both the frequency of use and the average prices charged. The Kruskal-Wallis test resulted in H = 10.82 (p-value = 0.055), with a 5% significance level, identifying no statistically significant differences in healthcare costs related to ASD, by type of procedure. Because this is a case study, the results are limited in scope to the context of the cooperative analyzed, which limits their generalizability. Future studies with larger samples can strengthen the evidence and support management decisions in supplementary healthcare. Editor: Universidade Federal da Paraíba Tipo: TCC

2025-09-23T00:00:00Z