Comparative analysis prediction of prostate and testicular cancer mortality using machine learning - accuracy study

Aug 4, 2026

Upload by Rowan

Mortality for prostate and testicular cancer remains a major public health concern, with higher rates reported in Brazil’s Northeast region. This study compares machine learning libraries to predict cancer mortality, focusing on the pyMannKendall and Prophet algorithms. Using DATASUS data for Caicó and Rio Grande do Norte between 2000 and 2019, prediction performance is assessed with error metrics and trend estimation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Abstract

Background and objective

Methods

Results

Conclusions

Comparative analysis prediction of prostate and testicular cancer mortality using machine learning: accuracy study Aurélio Gomes de Albuquerque NetoI, David Medeiros NeryII, João Paulo Araújo BrazIII, Carla Ferreira do NascimentoIV, Tiago Almeida de OliveiraV, Brígida Gabriele Albuquerque BarraVI, Leonardo Thiago Duarte Barreto NobreVII, Diego BonfadaVIII, Janine Karla França da Silva BrazIX Escola Multicampi de Ciências Médicas do Rio Grande do Norte, Universidade Federal do Rio Grande do Norte (UFRN), Caicó, RN, Brazil IUndergraduate student, Escola Multicampide Ciências Médicas do Rio Grande do Norte, Universidade Federal do Rio Grande do Norte (UFRN), Caicó (RN), Brazil. [https://orcid.org/0000-0002-6891-1930](https://orcid.org/0000-0002-6891-1930)[ ](https://orcid.org/0000-0002-6891-1930)IIUndergraduate student, Escola Multicampide Ciências Médicas do Rio Grande do Norte, Universidade Federal do Rio Grande do Norte (UFRN), Caicó (RN), Brazil. [https://orcid.org/0000-0001-7541-7175](https://orcid.org/0000-0001-7541-7175)[ ](https://orcid.org/0000-0001-7541-7175)IIIPharmaceutical, Information analyst, Department of Central Pharmacy, Hospital Giselda Trigueiro, Natal (RN), Brazil. [https://orcid.org/0000-0001-8802-0214](https://orcid.org/0000-0001-8802-0214)[ ](https://orcid.org/0000-0001-8802-0214)[IV](IVPhD. Physiotherapist)[PhD. Physiotherapist](IVPhD. Physiotherapist), Universidade do Estado da Bahia (UNEB), Salvador (BA), Brazil. [http://orcid.org/0000-0002-0054-277X](http://orcid.org/0000-0002-0054-277X)[V](VPhD. Statistical and Associate Professor)[PhD. Statistical and Associate Professor](VPhD. Statistical and Associate Professor), Departament of Statistic, Universidade Estadual da Paraíba (UEPB), Campina Grande (PB), Brazil. [https://orcid.org/0000-0003-4147-7721](https://orcid.org/0000-0003-4147-7721)[ ](https://orcid.org/0000-0003-4147-7721)[VI](VIMSc. Speech therapist)[MSc. Speech therapist](VIMSc. Speech therapist), Postgraduate Program in Collective Health, Universidade Federal do Rio Grande do Norte (UFRN), Natal (RN), Brazil. [https://orcid.org/0000-0002-3902-6043](https://orcid.org/0000-0002-3902-6043)[ ](https://orcid.org/0000-0002-3902-6043)VIIPhD. Biomedic, Adjunct Professor, Escola Multicampi de Ciências Médicas do Rio Grande do Norte, Universidade Federal do Rio Grande do Norte (UFRN), Caicó (RN), Brazil. [https://orcid.org/0000-0002-4728-8035](https://orcid.org/0000-0002-4728-8035)[ ](https://orcid.org/0000-0002-4728-8035)VIIIPhD. Nurse, Adjunct Professor, Escola Multicampi de Ciências Médicas do Rio Grande do Norte, Universidade Federal do Rio Grande do Norte (UFRN), Caicó (RN), Brazil. [https://orcid.org/0000-0001-9725-9446](https://orcid.org/0000-0001-9725-9446)[ ](https://orcid.org/0000-0001-9725-9446)IXPhD. Biologist, Adjunct Professor, Escola Multicampi de Ciências Médicas do Rio Grande do Norte, Universidade Federal do Rio Grande do Norte (UFRN), Caicó (RN), Brazil. [https://orcid.org/0000-0002-9570-6465](https://orcid.org/0000-0002-9570-6465) [KEYWORDS](KEYWORDS) ([MeSH](MeSH) terms): Prostatic neoplasm. Testicular neoplasm. Artificial intelligence. AUTHORS’ KEYWORDS: Protastic cancer. Testicular cancer. Python library. ABSTRACT BACKGROUND: The mortality rates of prostate and testicular cancer are higher mortality in the northeast region. OBJECTIVE: We aimed to compare the efficacy of machine learning libraries in predicting testicular and prostate cancer mortality. DESIGN AND SETTING: A comparative analysis of the pyMannKendall and Prophet machine-learning algorithms was conducted to develop predictive models using data from DATASUS (TabNet) to Caicó (Brazil) and Rio Grande do Norte (Brazil) . METHODS: Data on prostate and testicular cancer mortality in men from 2000 to 2019 were collected. The prediction accuracy of the Prophet algorithm was evaluated using the mean squared error (MSE), the root mean squared error and analyzed using the p

FAQs

What is the objective of the study?

To compare the efficacy of machine learning libraries in predicting prostate and testicular cancer mortality.

Which algorithms and data sources are used for the predictive models?

The study compares the pyMannKendall and Prophet algorithms using DATASUS data for Caicó and Rio Grande do Norte from 2000 to 2019.

What main findings were observed for prostate versus testicular cancer mortality trends?

Prostate cancer mortality showed a predicted increase (supported by pyMannKendall), while no significant mortality trend was identified for testicular cancer by either algorithm.

Aug 4, 2026

Upload by Rowan