Application of SHAP for Explainable Machine Learning on Age-Based Subgrouping Mammography Questionnaire Data for Positive Mammography Prediction and Risk Factor Identification

Abstract

Mammography is considered the gold standard for breast cancer screening. Multiple risk factors that affect breast cancer development have been identified; however, there is an ongoing debate regarding the significance of these factors. Machine learning (ML) models and Shapley Additive Explanation (SHAP) methodology can rank risk factors and provide explanatory model results. This study used ML algorithms with SHAP to analyze the risk factors between two different age groups and evaluate the impact of each factor in predicting positive mammography. The ML model was built using data from the risk factor questionnaires of women participating in a breast cancer screening program from 2017 to 2021. Three ML models, least absolute shrinkage and selection operator (lasso) logistic regression, extreme gradient boosting (XGBoost), and random forest (RF), were applied. RF generated the best performance. The SHAP values were then applied to the RF model for further analysis. The model identified age at menarche, education level, parity, breast self-examination, and BMI as the top five significant risk factors affecting mammography outcomes. The differences between age groups ranked by reproductive lifespan and BMI were higher in the younger and older age groups, respectively. The use of SHAP frameworks allows us to understand the relationships between risk factors and generate individualized risk factor rankings. This study provides avenues for further research and individualized medicine.

Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review

“…Explainable/interpretable algorithms used are deep learning explanation algorithms: Of 14 papers, Explainer alone or with Grad-CAM, 29 interpretable deep learning, 30 Grad-CAM, 31 Fisher information network (FIN), 39 AI and Polygenic Risk Scores (PRS) algorithms, 40 DenseNet, 35 Explainability-partial, 34 Explainability-full, 34 VGG-16, 37 fine-tuned MobileNet-V2 convolutional neural network, 33 OMIG explainability 32 and BI-RADS-Net-V2 38 are used in 11 papers (78.57 %), SHAP 41 42 is used in 2 papers (14.3%) and LIME 36 is used in 1 paper (7.14%).…”

“…In Sun et al ’s study, 42 model-agnostic methods versus model-specific methods, post hoc (black box+SHAP) technique and three algorithms, namely, logistic regression, extreme gradient boosting and random forest performance, were evaluated by sensitivity, specificity and AUC. 42 This evaluation was used to evaluate the black box model only. Moreover, SHAP was used for visualising feature importance using a heatmap but it was not tested.…”

“… 40 To further enhance the applicability and accuracy parameters of the model, a larger dataset across multiple centres is necessary to enhance the data quality. 42 While Sun et al ’s study 42 focuses on age groups with the highest incidence of breast cancer, future analysis encompassing older age groups would yield significant conclusions, especially about the postmenopausal population. 42 The retrospective nature of the study 42 makes it prone to selection bias 42 and also a small size dataset used.…”

“…42 While Sun et al's study 42 focuses on age groups with the highest incidence of breast cancer, future analysis encompassing older age groups would yield significant conclusions, especially about the postmenopausal population. 42 The retrospective nature of the study 42 makes it prone to selection bias 42 and also a small size dataset used. 36 The study by Shen et al 35 did not provide an evaluation of patient cohorts stratified by risk factors such as family history of breast cancer and breast and ovarian cancer are the breast cancer (BRCA) gene test results and it was only provided with US images, patients' ages and notes from the operating technician.…”

Explainable machine learning model for identifying key gut microbes and metabolites biomarkers associated with myasthenia gravis

“…Overall, the SHAP method provides insights into the extraction of genetic features that influence predicted outcomes. With the increasing popularity of SHAP, clinical studies have increasingly used this method for explaining model features [41] , [42] . Our analytical framework effectively integrates data from different dimensions and can yield accurate results.…”