Medication recommendation is a critical function of clinical decision support systems, directly influencing patient safety and treatment efficacy.While large language models (LLMs) show promise in clinical tasks such as summarization and question answering, their ability to make accurate treatment predictions remains limited, in part, due to their lack of specialized medical knowledge and exposure to real-world patient data.We introduce TreatRAG, an interpretable, model-agnostic retrieval-augmented generation (RAG) framework aimed at early-stage development to enhance medication recommendation accuracy using publicly available clinical data; thus, TreatRAG forms a critical foundational step toward future clinical validation and domain expert involvement.TreatRAG retrieves similar patient cases, i.e., so called "digital twins", using interpretable N-gram Jaccard similarity and augments the input prompt to ground LLM predictions in real clinical scenarios.We evaluate our framework on the MIMIC-IV dataset using BioGPT, BioMistral, Phi3, and Flan-T5.TreatRAG-enhanced BioGPT improves its F1-score from 0.14 to 0.34, BioMistral from 0.22 to 0.54, Phi-3 from 0.09 to 0.16, and Flan-T5 from 0.23 to 0.30, while also lowering, often significantly, the hallucination rate.Our model-agnostic framework offers a flexible, effective, and interpretable solution to advance the reliability of LLMs in clinical decision support.

Event Temporal Relation Extraction (ETRE) is paramount but challenging. Within a discourse, event pairs are situated at different distances or the so-called proximity bands. The temporal ordering communicated about event pairs where at more remote (i.e., "long'') or less remote (i.e., "short'') proximity bands are encoded differently. SOTA models have tended to perform well on events situated at either short or long proximity bands, but not both. Nonetheless, real-world, natural texts contain all types of temporal event-pairs. In this paper, we present MulCo : Distilling Mul ti-Scale Knowledge via Co ntrastive Learning, a knowledge co-distillation approach that shares knowledge across multiple event pair proximity bands to improve performance on all types of temporal datasets. Our experimental results show that MulCo successfully integrates linguistic cues pertaining to temporal reasoning across both short and long proximity bands and achieves new state-of-the-art results on several ETRE benchmark datasets.

Learning Electronic Health Records (EHRs) representation is a preeminent yet under-discovered research topic. It benefits various clinical decision support applications, e.g., medication outcome prediction or patient similarity search. Current approaches focus on task-specific label supervision on vectorized sequential EHR, which is not applicable to large-scale unsupervised scenarios. Recently, contrastive learning has shown great success in self-supervised representation learning problems. However, complex temporality often degrades the performance. We propose Graph Kernel Infomax, a self-supervised graph kernel learning approach on the graphical representation of EHR, to overcome the previous problems. Unlike the state-of-the-art, we do not change the graph structure to construct augmented views. Instead, we use Kernel Subspace Augmentation to embed nodes into two geometrically different manifold views. The entire framework is trained by contrasting nodes and graph representations on those two manifold views through the commonly used contrastive objectives. Empirically, using publicly available benchmark EHR datasets, our approach yields performance on clinical downstream tasks that exceeds the state-of-the-art. Theoretically, the variation in distance metrics naturally creates different views as data augmentation without changing graph structures. Practically, our method is non-ad hoc and confirms superior performance on commonly used graph benchmark datasets.