Anemia is a condition which is characterized by insufficient red blood cells or hemoglobin. It creates a substantial health concern specially for children and women. Thus, the early and accurate detection of anemia is crucial for starting the treatment process and getting optimal health outcomes. The existing anemia detection technique is expensive and can create human error. To address these obstructions, this study proposes a novel anemia detection model based on Explainable Boosting Machines (EBM). The proposed EBM model, combined with effective data preprocessing and class balancing techniques, demonstrates exceptional performance in anemia detection. The simulation results on an anemia dataset show that the model can get an impressive accuracy of 98.69%, precision of 97.28%, recall of 100%, and f1-score of 98.61%. The EBM’s explainability feature provides valuable insights into the decision-making process, facilitating a better understanding of the factors influencing anemia diagnosis. This study highlights the potential of EBM-based approaches for accurate and efficient anemia detection, ensuring the improved healthcare outcomes.