article · OALib
Breast cancer recurrence after surgery is a vital factor in patient management and clinical decision making. To address this in the Tanzanian population, clinical data from 199 breast cancer patients across multiple centres were analysed retrospectively to predict recurrence within two years of surgery. Six distinct machine learning models were developed using data from 139 patients and evaluated on a test set of 60 patients. Key factors identified as influential for predicting recurrence included lymph node metastasis, tumor grade, the total number of lymph nodes, tumor size at diagnosis, and marital status. Among the tested algorithms, the multilayer perceptron model achieved the strongest results, reaching an area under the receiver operating characteristic curve of 0.935 and an accuracy of 0.850. A web-based risk calculator was also built to support clinical application.
Accurately identifying breast cancer patients at high risk of recurrence following surgery allows healthcare teams to tailor treatment strategies and post-operative monitoring. By using machine learning models trained on regional data, clinicians can better understand local risk factors and potentially improve post-surgical management for patients in Tanzania.
This applied research produced a web-based risk calculator intended for clinical use by healthcare professionals managing breast cancer patients. The tool represents an applied and tested prototype evaluated on a multi-centre dataset. Further prospective validation would likely be needed before widespread integration into routine hospital workflows or digital health platforms.
AI-generated from the published abstract. Always read the original work before citing.
Introduction: Breast Cancer (BC) remains a significant health concern worldwide, and accurate prediction of its recurrence after surgery is vital for patient management and treatment decisions.This study aimed to develop a predictive model for assessing the risk of breast cancer recurrence (BCR) after surgery in the Tanzanian population.Methods: This study retrospectively analyzed data collected from BC patients at multiple centers in Tanzania.The outcome was BCR within 2 years after surgery.Six different ML models were established, and their performances were compared.The SHapley Additive explanations (SHAP) method was utilized to interpret the importance of variables.Finally, a web-based risk calculator was developed to facilitate its clinical application.Results: 199 BC patients were included, of which 139 were used for model development and 60 for model evaluation.The BCR incidence was 72.9%.Key predictors of BCR included lymph node metastasis, tumor grade, number of lymph nodes, tumor size at diagnosis, and marital status.In the testing set, the multilayer perceptron (MLP) model demonstrated the highest performance: AUROC (0.935; 95% CI: 0.878 -0.992), AUPRC (0.969; 95% CI: 0.839 -0.995), accuracy (0.850), sensitivity (0.875), specificity (0.800), and F1-score (0.886).The MLP model *These authors have contributed equally to this research paper and share the first authorship.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.4236/oalib.1113728
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
