Automatic detection of Adverse Drug Events (ADEs) from social media has become increasingly important for post-market drug safety surveillance and pharmacovigilance. Although existing social media-based ADE detection methods have effectively addressed some challenges such as data sparsity and class imbalance, they still suffer from spurious correlations, where models tend to learn co-occurrence patterns between drugs and symptoms, leading them to incorrectly identify drug inefficacy or therapeutic intent as ADEs. To address this issue, we propose a structured medical knowledge-guided counterfactual generation method that leverages authoritative medical databases and large language models to construct clinically plausible counterfactual samples, thereby mitigating spurious correlations at the data level. Furthermore, we propose a knowledge-enhanced instruction-tuning strategy that injects drug indications as causal cues into model inputs to enhance its causal reasoning capabilities. Experimental results on two benchmark datasets demonstrate that our method consistently outperforms state-of-the-art models, effectively alleviating spurious correlations and exhibiting superior capabilities in drug-symptom relationship identification.

Current research reveals that the herpes zoster vaccine(HZV) can effectively prevent and mitigate Alzheimer's disease(AD). However, the underlying mechanisms linking the HZV and AD remain incompletely understood. We employ a literature-based discovery (LBD) paradigm to investigate these mechanisms. Traditional knowledge graph-based approaches demonstrate strong performance in implicit knowledge discovery tasks. However, existing methods still face critical challenges: (1) The diverse representations of biomedical entities often degrade knowledge graph quality, such as introducing path redundancy; (2) Current path-ranking mechanisms lack rigorous biological plausibility assessment, resulting in a high number of false-positive paths being retained. To address the aforementioned challenges, this paper proposes a Synergistic Integration framework of Knowledge graphs and Large language models (SIKL). First, the PubTator3.0 tool and manual rule-based methods are employed to extract entities and relational triples from abstract content. A knowledge graph is constructed with medical subject headings as nodes, integrating multiple attributes and relations, effectively mitigating path redundancy caused by diverse entity expressions. Next, a twostage LLM-driven path filtering module is designed. In the first stage, a retrieval-augmented large language model assesses whether candidate paths meet causality conditions, performing preliminary filtering to eliminate false positives. The second stage leverages a chain-of-thought large language model to conduct step-by-step reasoning on remaining paths, further evaluating their biological plausibility. Finally, a comprehensive path ranking strategy combines literature support counts and LLM-generated scores to output Top-p high-confidence hypothetical paths. Experimental results reveals that HZV may delay AD progression through pathways such as neuroinflammatory regulation, with partial mechanisms supported by literature.

Adverse drug reactions (ADRs) are harmful reactions that occur with qualified drugs under normal dosage. Due to its significant impact on patients’ health, timely detection for ADRs is of great significance. Current approaches typically introduce sentiment to enhance the detection of ADRs because sentiment information can reflect the subjective feelings of the patient about the drug. However, none of the existing works has considered both explicit and implicit sentiment knowledge. To this end, we propose a novel approach named DSN to adaptively fuse explicit and implicit sentiment knowledge for adverse drug reactions detection. Specifically, for explicit sentiment knowledge, we first propose a dimension extension approach to avoid the information loss problem, and then utilize an aware network based on attention mechanism to obtain a textual representation that incorporates explicit sentiment knowledge; As to implicit sentiment knowledge, we design a fusion network based on a gating mechanism to adaptively learn text and implicit sentiment knowledge in order to help and guide the deeper fusion of text and two kinds of sentiment knowledge. Extensive experiments conducted on TwiMed_Twitter dataset demonstrate the superiority of our proposed DSN over existing methods.

OBJECTIVE: Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual biomedical question answering and conversation tasks. To investigate the effectiveness of the fine-tuned LLMs on diverse biomedical natural language processing (NLP) tasks in different languages, we present Taiyi, a bilingual fine-tuned LLM for diverse biomedical NLP tasks. MATERIALS AND METHODS: We first curated a comprehensive collection of 140 existing biomedical text mining datasets (102 English and 38 Chinese datasets) across over 10 task types. Subsequently, these corpora were converted to the instruction data used to fine-tune the general LLM. During the supervised fine-tuning phase, a 2-stage strategy is proposed to optimize the model performance across various tasks. RESULTS: Experimental results on 13 test sets, which include named entity recognition, relation extraction, text classification, and question answering tasks, demonstrate that Taiyi achieves superior performance compared to general LLMs. The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multitasking. CONCLUSION: Leveraging rich high-quality biomedical corpora and developing effective fine-tuning strategies can significantly improve the performance of LLMs within the biomedical domain. Taiyi shows the bilingual multitasking capability through supervised fine-tuning. However, those tasks such as information extraction that are not generation tasks in nature remain challenging for LLM-based generative approaches, and they still underperform the conventional discriminative approaches using smaller language models.

In the realm of medicine and healthcare, adverse drug reactions (ADRs) are a significant contributor to mortality and morbidity. Consequently, it is of paramount importance to closely observe the adverse effects of marketed drugs to minimize associated risks. While current methods for Adverse Drug Reaction (ADR) detection have demonstrated notable efficacy, a significant number of researchers have failed to acknowledge the integral role that sentiment information plays in this process. In this paper, we propose Sentiment Enhanced Dual Graph Convolutional Networks (SEDGCN), a novel method for ADRs detection by incorporating sentiment information. In particular, we first introduce the concept of prompt learning and reformulate the ADR detection task as an aspect-level sentiment analysis task. Subsequently, we construct a sentimentenhanced dependency matrix for each sentence to capture the sentiment knowledge and syntactic information of the sentence. The matrix is then input into the graph convolutional networks to obtain a graph representation of the sentence. Finally, to capture global information, we construct a heterogeneous graph based on all words and sentences and fuse this heterogeneous graph with the sentence-level graph representation for ADR detection. Extensive experimentation on two publicly available datasets, namely TwiMed and Twitter, yielded F1 scores of 78.24% and 75.43%, respectively. These results underscore the efficacy of our proposed model.