Artificial neural network applied to prostate cancer diagnosis
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1371Keywords:
Artificial Neural Network, Diagnosis, Prostate cancerAbstract
Objective: Develop a method to assist in the diagnosis of prostate cancer using Artificial Neural Network applied to clinical variables. Method: Retrospective observational research was carried out on 274 medical records from the University Hospital of the Federal University of Maranhão. The following clinical variables were used: age, race, systemic arterial hypertension, diabetes mellitus, smoking, alcohol consumption, digital rectal exam, and total PSA. An Artificial Neural Network model was created for predictive classification. Results: The model presented an accuracy of 80%, sensitivity of 80%, specificity of 80% and area under the ROC curve of 0.9027. Conclusion: Excellent performance was obtained in predicting prostate cancer. This method can be incorporated into clinical practice as doctors and patients can reap the benefits of it by reducing unnecessary biopsies without compromising the ability to diagnose prostate cancer.
References
Kim MH, Yoo S, Choo MS, Cho MC, Son H, Jeong H. The role of the serum 25-OH vitamin D level on detecting prostate cancer in men with elevated prostate-specific antigen levels. Sci Rep. 2022 Aug;12:14089. Available from: https://doi.org/10.1038/s41598-022-17563-8.
Lee C, Light A, Alaa A, Thurtle D, Schaar M, Gnanapragasam VJ. Application of a novel machine learning framework for predicting non-metastatic prostate cancer-specific mortality in men using the Surveillance, Epidemiology, and End Results (SEER) database. The Lancet Digital Health. 2021 Mar;3:158-165. Available from: https://doi.org/10.1016/S2589-7500(20)30314-9.
American Cancer Society. Key Statistics for Prostate Cancer [Internet]. 2024 [cited 2024 Jan 19]. Available from: https://www.cancer.org/cancer/types/prostate-cancer/about/key-statistics.html.
INCA. Câncer de Próstata. Instituto Nacional de Câncer [Internet]. 2023 [cited 2023 Aug 16]. Available from: https://www.inca.gov.br/tipos-de-cancer/cancer-de-prostata.
American Cancer Society. Prostate Cancer Risk Factors. [Internet]. 2023 [cited 2023 Nov 22]. Available from: https://www.cancer.org/cancer/types/prostate-cancer/causes-risks-prevention/risk-factors.html.
Cosma G, McArdle SE, Foulds GA, Hood SP, Reeder S, Johnson C, et al. Prostate Cancer: Early Detection and Assessing Clinical Risk Using Deep Machine Learning of High Dimensional Peripheral Blood Flow Cytometric Phenotyping Data. Front Immunol. 2021 Dec;12:786828. Available from: https://doi.org/10.3389/fimmu.2021.786828.
Correas JM, Halpern EJ, Barr RG, Ghai S, Walz J, Bodard S, Dariane C, Rosette J, Advanced ultrasound in the diagnosis of prostate cancer, World J. Urol. 2020 Apr;39:661-676. Available from: https://doi.org/10.1007/s00345-020-03193-0.
Nasrabadi NM. Pattern Recognition and Machine Learning. Journal of Electronic Imaging. 2007 Oct;16(4):049901. Available from: https://doi.org/10.1117/1.2819119.
Faceli K, Lorena AC, Gama J, Carvalho ACPLF. Inteligência Artificial: Uma Abordagem de Aprendizagem de Máquina. 2ª edição. Editora LTC – Livros Técnicos e Científicos. Rio de Janeiro, 2021.
Fonseca AU, Felix JP, Vieira GS, Rocha BM, Nogueira EA, Araújo CEE, et al. Diagnosticando Tuberculose com Redes Neurais Artificiais e Recursos BPPC. J Health Inform [Internet]. 20º de julho de 2023 [citado 16º de maio de 2024];15(Especial). Disponível em: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/1106
Santos PD, Yahata E, Piheiro TS, Oliveira FS de, Simões PW. Algoritmos de Machine Learning para Predição da Sobrevida do Câncer de Mama. J Health Inform [Internet]. 20º de julho de 2023 [citado 16º de maio de 2024];15(Especial). Disponível em: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/1091
Nacional Cancer Institute. Prostate cancer risk factors. American Cancer Society [Online], 2023. Prostate Cancer. Available from: https://www.cancer.org/cancer/types/prostate-cancer/causes-risks-prevention/risk-factors.html.
Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine learning for medical imaging, Radiographics. 2017 Feb;37(2):505–515. Available from: https://doi.org/10.1148/rg.2017160130.
Kohavi R. A study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection, in: International joint Conference on artificial intelligence. 1995 Aug;2:1137-1145. Available from: https://dl.acm.org/doi/10.5555/1643031.1643047.
Wang X, Yang W, Weinreb J, Han J, Li Q, Kong X, et al. Searching for prostate cancer by fully automated magnetic resonance imaging classification: deep learning versus non-deep learning. Sci Rep. 2017 Nov;7:15415. Available from: https://doi.org/10.1038/s41598-017-15720-y.
Liu J, Wang ZQ, Li M, Zhou MY, Yu YF, Zhan WW. Establishment of two new predictive models for prostate cancer to determine whether to require prostate biopsy when the PSA level is in the diagnostic gray zone (4–10 ng ml−1). Asian Journal of Andrology. 2019 Mar;22(2):213-216. Available from: https://doi.org/10.4103/aja.aja_46_19.
Liu J, Dong B, Qu W, Wang J, Xu Y, Yu S, et al. Using clinical parameters to predict prostate cancer and reduce the unnecessary biopsy among patients with PSA in the gray zone. Sci Rep. 2020 Mar;10:5157. Available from: https://doi.org/10.1038/s41598-020-62015-w.
Park JY, Yoon S, Park MS, Choi H, Bae JH, Moon DG, et al. Development and External Validation of the Korean Prostate Cancer Risk Calculator for High-Grade Prostate Cancer: Comparison with Two Western Risk Calculators in an Asian Cohort. PLOS ONE. 2017 Jan;12(1):0168917. Available from: https://doi.org/10.1371/journal.pone.0168917.
Yoo S, Gujrathi I, Haider MA, Khalvati F. Prostate Cancer Detection using Deep Convolutional Neural Networks. Sci Rep. 2019 Dec;9:19518. Available from: https://doi.org/10.1038/s41598-019-55972-4.
Chen Y, Xu C, Zhang Z, Zhu A, Xu X, Pan J, et al. Prostate cancer identification via photoacoustic spectroscopy and machine learning. Photoacoustics. 2021 Sep;23:100280. Available from: https://doi.org/10.1016/j.pacs.2021.100280.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
