Explainable AI for colorectal cancer classification

Colorectal cancer (CRC) ranks second highest in global mortality among nonsex-related cancers. Conventional machine learning (ML) algorithms applied to microbiome-based CRC detection often yield suboptimal accuracy. Conversely, deep neural network (DNN)-based methods encounter limitations due to scarce labeled samples, data imbalance, and dominant features. The lack of interpretability in artificial intelligence models further hinders their adoption in healthcare. This chapter proposes an explainable DNN model for improved CRC detection utilizing stool-based microbiome data. The model employs a square root-based normalization method and a feature extension approach, incorporating customized normalization techniques to enhance prediction performance. These methods effectively address outliers, dominant features, and dimensionality challenges. The square root-based method mitigates the effect of outliers and feature dominance, while the feature extension technique expands the dataset’s feature space, potentially improving feature relevance across samples. Leveraging automatic feature selection by the DNN algorithm, the model performs classification using a subset of available features. Evaluation on publicly available datasets demonstrates the efficacy of the proposed methods, with the square root-based method achieving area under the curve scores of 91.3% and 75.8% on datasets 1 and 2, respectively. The feature extension-based method achieves AUC scores of 90.2% and 74% on the respective datasets.