This study explores the use of explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The researchers employed a Support Vector Machine classifier with Mutual Information (MI) feature selection, trained on all three data modalities, achieving exceptional performance (accuracy = 0.95, AUC = 0.94). When using gene expression and SNP data separately, the models achieved very good performance (AUC = 0.65 and 0.63, respectively). Using Shapley Additive exPlanations (SHAP), significant features were identified, potentially serving as Alzheimer’s disease (AD) biomarkers. Notably, genetic-based biomarkers linked to axon myelination and synaptic vesicle membrane formation could aid early AD detection. The study demonstrates that a genetic-based biomarker approach, integrating machine learning and SHAP, shows promise for precise AD diagnosis, biomarker discovery, and offers novel insights for understanding and treating the disease. This approach addresses the challenges of accurate AD diagnosis, which is crucial given the complexities associated with the disease and the need for non-invasive diagnostic methods.This study explores the use of explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The researchers employed a Support Vector Machine classifier with Mutual Information (MI) feature selection, trained on all three data modalities, achieving exceptional performance (accuracy = 0.95, AUC = 0.94). When using gene expression and SNP data separately, the models achieved very good performance (AUC = 0.65 and 0.63, respectively). Using Shapley Additive exPlanations (SHAP), significant features were identified, potentially serving as Alzheimer’s disease (AD) biomarkers. Notably, genetic-based biomarkers linked to axon myelination and synaptic vesicle membrane formation could aid early AD detection. The study demonstrates that a genetic-based biomarker approach, integrating machine learning and SHAP, shows promise for precise AD diagnosis, biomarker discovery, and offers novel insights for understanding and treating the disease. This approach addresses the challenges of accurate AD diagnosis, which is crucial given the complexities associated with the disease and the need for non-invasive diagnostic methods.