Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI

Sep 21, 2026

Breast cancer incidence has increased worldwide, and manual diagnosis is time-intensive and requires expertise. This study evaluates and compares five supervised machine learning methods—decision tree, random forest, logistic regression, naive Bayes, and XGBoost—using a primary dataset of 500 patients from Dhaka Medical College Hospital. Classification performance is assessed via accuracy, precision, recall, and F1 score. SHAP analysis is applied to the XGBoost model to interpret predictions and quantify feature impact. Results show XGBoost achieves the best accuracy at 97%.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Predictive modeling for breast cancer classification

Machine learning methods and evaluation metrics

Explainable AI with SHAP interpretation

Results and comparison

[www. nature.com/scientificreports](www. nature.com/scientificreports) OPEN Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI Taminul Islam1, Md. Alif Sheakh2, Mst. SaziaTahosin2, Most. Hasna Hena2, Shopnil Akash3, Yousef A. Bin Jardan4, Gezahign FentahunWondmie 5*, Hiba‑Allah Nafidi6 & Mohammed Bourhia7* Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time‑consuming process, preventing its further spread can be aided by creating machine‑based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital) . Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97% . Keywords Breast cancer prediction, Machine learning, Cancer prediction, Hyperparameter tuning, Explainable AI Breast cancer begins when some cells in the breast start to grow uncontrollably, forming a mass called a tumor1. A breast cancer diagnosis typically falls into one of two main categories—benign (non-cancerous) or malignant (cancerous). Malignant tumors are dangerous as they can spread to distant sites in the body through the bloodstream or lymph system, a process known as metastasis2,3. Figure 1a illustrates the distinction between benign and malignant tumors in terms of the normal cells and tumor cells, and (b) shows the benign and malignant masses. Benign tumors generally stay localized in one area and do not metastasize. Breast cancer manifests through several symptoms—a noticeable lump or mass in the breast, changes in breast size or shape compared to the other breast, alterations in the skin overlying the breast like dimpling or puckering, newly inverted nipple, redness or scaliness of breast skin, breast pain, and nipple discharge other than breast milk4. Breast cancer is the second largest killer of women after cardiovascular disease. And more than 8% of women will experience it. Every year, more than 500,000 women are diagnosed with breast cancer, as stated in the 1School of Computing, Southern Illinois University Carbondale, Carbondale, IL, USA. 2Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh. 3Department of Pharmacy, Faculty of Allied Health Sciences, Daffodil International University, Dhaka, Bangladesh. 4Department of Pharmaceutics, College of Pharmacy, King Saud University, P.O. Box 11451, Riyadh, Saudi Arabia. 5Department of Biology, Bahir Dar University, P.O. Box 79, Bahir Dar, Ethiopia. 6Department of Food Science, Faculty of Agricultural and Food Sciences, Laval University, 2325, Quebec City, QC G1V 0A6, Canada. 7Laboratory of Biotechnology and Natural Resources Valorization, Ibn Zohr University, 80060 Agadir, Morocco.* email: [resercherfent@gmail.com](resercherfent@gmail.com) [www.

FAQs

What dataset and patient source were used for model training and evaluation?

The study uses a primary dataset of 500 patients from Dhaka Medical College Hospital.

Which machine learning models were compared for breast cancer classification?

Five supervised models were evaluated: decision tree, random forest, logistic regression, naive Bayes, and XGBoost.

How does the study use explainable AI to interpret model decisions?

SHAP analysis is applied to the XGBoost model to interpret predictions and measure the impact of each feature on the output.

Sep 21, 2026

Uploaded by Ava Thompson