Medication recommendation (MR) has undergone rapid advancement in recent years, driven by its significant practical implications in healthcare. However, such high-risk scenarios still experience two critical yet overlooked challenges: the prevalent overconfidence in raw confidence for individual medications and the lack of a robust solution for confidence quantification in medication combinations. This paper represents the first in-depth study addressing this gap. We introduce two innovative methodologies tailored to the unique challenges of MR scenarios: 1) A discernible binning-based calibration method with theoretical guarantees for the confidence of individual medication. It guarantees distinct accuracy levels between adjacent bins and maintains consistent statistical reliability across calibration and test data, enabling calibrated confidence to reflect the correctness of medication recommendations distinctively. 2) A sample-based quantification method for the set confidence of medication combination, which is applicable for various existing performance metrics in MR. Utilizing representative deep MR models as backbones and conducting extensive experiments on the widely recognized MIMIC datasets, we empirically prove the effectiveness and robustness of our proposed methods. Our approaches not only improve the reliability of MR but also pave the way for more informed decision-making in clinical settings.

The widespread adoption of Graph Neural Networks (GNNs) has led to an increasing focus on their reliability. To address the issue of underconfidence in GNNs, various calibration methods have been developed to gain notable reductions in calibration error. However, we observe that existing approaches generally fail to enhance consistently, and in some cases even deteriorate, GNNs' ability to discriminate between correct and incorrect predictions. In this study, we advocate the significance of discriminative ability and the inclusion of relevant evaluation metrics. Our rationale is twofold: 1) Overlooking discriminative ability can inadvertently compromise the overall quality of the model; 2) Leveraging discriminative ability can significantly inform and improve calibration outcomes. Therefore, we thoroughly explore the reasons why existing calibration methods have ineffectiveness and even degradation regarding the discriminative ability of GNNs. Building upon these insights, we conduct GNN calibration experiments across multiple datasets using a straightforward example model, denoted as DC(GNN). Its excellent performance confirms the potential of integrating discriminative ability as a key consideration in the calibration of GNNs, thereby establishing a pathway toward more effective and reliable network calibration.

Molecular structures and Drug-Drug Interactions (DDI) are recognized as important knowledge to guide medication recommendation (MR) tasks, and medical concept embedding has been applied to boost their performance. Though promising performance has been achieved by leveraging Graph Neural Network (GNN) models to encode the molecular structures of medications or/and DDI, we observe that existing models are still defective: 1) to differentiate medications with similar molecules but different functionality; or/and 2) to properly capture the unintended reactions between drugs in the embedding space. To alleviate this limitation, we propose Carmen, a cautiously designed graph embedding-based MR framework. Carmen consists of four components, including patient representation learning, context information extraction, a context-aware GNN, and DDI encoding. Carmen incorporates the visit history into the representation learning of molecular graphs to distinguish molecules with similar topology but dissimilar activity. Its DDI encoding module is specially devised for the non-transitive interaction DDI graphs. The experiments on real-world datasets demonstrate that Carmen achieves remarkable performance improvement over state-of-the-art models and can improve the safety of recommended drugs with a proper DDI graph encoding.