Large language models (LLMs) are increasingly recognized for their advanced language capabilities, offering significant assistance in diverse areas like medical communication, patient data optimization, and surgical planning. Our survey meticulously searched for papers with keywords such as “medical,” “clinical,” “healthcare,” and “LLMs” across various databases, including ACM and Google Scholar. It sought to delve into the latest trends and applications of LLMs in healthcare, analyzing 175 relevant publications to support both practitioners and researchers in the field. We have compiled 56 experimental datasets, various evaluation methods and reviewed cutting-edge LLMs across tasks. Our comprehensive analysis of LLMs in healthcare applications, including medical question-answering, dialogue summarization, electronic health record generation, scientific research, medical education, medical product safety monitoring, clinical health reasoning, and clinical decision support. Furthermore, we have identified the challenges, including data security, inaccurate information, fairness and bias, plagiarism, copyrights, and accountability, and the potential solutions, namely de-identification framework, references,counterfactually fair prompting,opening and ending control codes, and establishing normative standards,to address these open issues,respectively. The findings of this survey exert a profound impact on spurring innovation in practical applications and addressing inherent challenges within the academic and medical communities.

Multimodal Emotion Recognition (MER) leverages multiple input signals to identify the expressed emotions in user-generated data. Currently, effectively addressing both modality heterogeneity and homogeneity on MER tasks is a challenging issue due to the diversity of multimodal inputs in videos. To address this issue, this work proposes an efficient Multimodal Decoupling Method with Knowledge Aggregation and Transfer (MDKAT) for robust multimodal feature learning in emotional videos. MDKAT is consisted of three key steps: modality-independent feature extraction, modality-specific feature extraction, and multi-loss integration for decoupling. In these three steps, four crucial modules are individually designed to improve different aspects of multimodal learning on MER tasks, including a Cross-modal Feature Fusion (CFF) module for enhancing modality-independent features, an Adaptive Masked Self-Attention (AMSA) module for feature refinement, a Knowledge Aggregation (KA) module for ensuring the semantic similarity of modality-independent features, and a Knowledge Transfer (KT) module for balancing the strengths of different modalities. Experimental results on the typical CMU-MOSI and CMU-MOSEI datasets show that MDKAT obtains superior performance over state-of-the-art methods, demonstrating the effectiveness of MDKAT on MER tasks.

Most traditional recommender systems focus specifically on increasing consumer satisfaction by providing a list of relevant content to consumers. However, the perspectives of other multisided marketplace stakeholders are also equally important, i.e., the exposure for suppliers or providers and profit for the platform. The suppliers want their products to be presented to users, and the objective of the platform is to maximize their profit. Nevertheless, because consumers’ preferences and the objectives of providers as well as the platform may conflict with each other, it degrades the utility of the recommendation methods by only considering users’ views. Therefore, in this work, we use a many-objective optimization method to maintain a tradeoff among five objectives for three stakeholders and obtain multiple Pareto front solutions in a single run. We first combine customer lifetime value and user purchase preference to create a new similarity model (Sim_RFMP) to increase the recommendation accuracy of the recommendation list. Furthermore, we propose a many-objective model (NBHXMAOEA) for multistakeholder recommendation. In NBHXMAOEA, we present a novel N-block heuristic crossover operator (NBHX) that recombines blocks of chromosomes based on heuristics. Through extensive experiments, the results demonstrate that our proposed NBHXMAOEA achieves superior performance in terms of average accuracy, diversity, novelty, provider coverage, and platform profit to its competing methods.