With the rapid progress in Natural Language Processing (NLP), Pre-trained Language Models (PLM) such as BERT, BioBERT, and ChatGPT have shown great potential in various medical NLP tasks. This paper surveys the cutting-edge achievements in applying PLMs to various medical NLP tasks. Specifically, we first brief PLMS and outline the research of PLMs in medicine. Next, we categorise and discuss the types of tasks in medical NLP, covering text summarisation, question-answering, machine translation, sentiment analysis, named entity recognition, information extraction, medical education, relation extraction, and text mining. For each type of task, we first provide an overview of the basic concepts, the main methodologies, the advantages of applying PLMs, the basic steps of applying PLMs application, the datasets for training and testing, and the metrics for task evaluation. Subsequently, a summary of recent important research findings is presented, analysing their motivations, strengths vs weaknesses, similarities vs differences, and discussing potential limitations. Also, we assess the quality and influence of the research reviewed in this paper by comparing the citation count of the papers reviewed and the reputation and impact of the conferences and journals where they are published. Through these indicators, we further identify the most concerned research topics currently. Finally, we look forward to future research directions, including enhancing models\' reliability, explainability, and fairness, to promote the application of PLMs in clinical practice. In addition, this survey also collect some download links of some model codes and the relevant datasets, which are valuable references for researchers applying NLP techniques in medicine and medical professionals seeking to enhance their expertise and healthcare service through AI technology.

UNASSIGNED: Large Language Models (LLMs) play a crucial role in clinical information processing, showcasing robust generalization across diverse language tasks. However, existing LLMs, despite their significance, lack optimization for clinical applications, presenting challenges in terms of illusions and interpretability. The Retrieval-Augmented Generation (RAG) model addresses these issues by providing sources for answer generation, thereby reducing errors. This study explores the application of RAG technology in clinical gastroenterology to enhance knowledge generation on gastrointestinal diseases.
UNASSIGNED: We fine-tuned the embedding model using a corpus consisting of 25 guidelines on gastrointestinal diseases. The fine-tuned model exhibited an 18% improvement in hit rate compared to its base model, gte-base-zh. Moreover, it outperformed OpenAI\'s Embedding model by 20%. Employing the RAG framework with the llama-index, we developed a Chinese gastroenterology chatbot named \"GastroBot,\" which significantly improves answer accuracy and contextual relevance, minimizing errors and the risk of disseminating misleading information.
UNASSIGNED: When evaluating GastroBot using the RAGAS framework, we observed a context recall rate of 95%. The faithfulness to the source, stands at 93.73%. The relevance of answers exhibits a strong correlation, reaching 92.28%. These findings highlight the effectiveness of GastroBot in providing accurate and contextually relevant information about gastrointestinal diseases. During manual assessment of GastroBot, in comparison with other models, our GastroBot model delivers a substantial amount of valuable knowledge while ensuring the completeness and consistency of the results.
UNASSIGNED: Research findings suggest that incorporating the RAG method into clinical gastroenterology can enhance the accuracy and reliability of large language models. Serving as a practical implementation of this method, GastroBot has demonstrated significant enhancements in contextual comprehension and response quality. Continued exploration and refinement of the model are poised to drive forward clinical information processing and decision support in the gastroenterology field.

Medical data have unique specificity and professionalism, requiring substantial domain expertise for their annotation. Precise data annotation is essential for anomaly-detection tasks, making the training process complex. Domain generalization (DG) is an important approach to enhancing medical image anomaly detection (AD). This paper introduces a novel multimodal anomaly-detection framework called MedicalCLIP. MedicalCLIP utilizes multimodal data in anomaly-detection tasks and establishes irregular constraints within modalities for images and text. The key to MedicalCLIP lies in learning intramodal detailed representations, which are combined with text semantic-guided cross-modal contrastive learning, allowing the model to focus on semantic information while capturing more detailed information, thus achieving more fine-grained anomaly detection. MedicalCLIP relies on GPT prompts to generate text, reducing the demand for professional descriptions of medical data. Text construction for medical data helps to improve the generalization ability of multimodal models for anomaly-detection tasks. Additionally, during the text-image contrast-enhancement process, the model\'s ability to select and extract information from image data is improved. Through hierarchical contrastive loss, fine-grained representations are achieved in the image-representation process. MedicalCLIP has been validated on various medical datasets, showing commendable domain generalization performance in medical-data anomaly detection. Improvements were observed in both anomaly classification and segmentation metrics. In the anomaly classification (AC) task involving brain data, the method demonstrated a 2.81 enhancement in performance over the best existing approach.

OBJECTIVE: Bispecific antibodies (BsAbs), capable of targeting two antigens simultaneously, represent a significant advancement by employing dual mechanisms of action for tumor suppression. However, how to pair targets to develop effective and safe bispecific drugs is a major challenge for pharmaceutical companies.
METHODS: Using machine learning models, we refined the biological characteristics of currently approved or in clinical development BsAbs and analyzed hundreds of membrane proteins as bispecific targets to predict the likelihood of successful drug development for various target combinations. Moreover, to enhance the interpretability of prediction results in bispecific target combination, we combined machine learning models with Large Language Models (LLMs). Through a Retrieval-Augmented Generation (RAG) approach, we supplement each pair of bispecific targets\' machine learning prediction with important features and rationales, generating interpretable analytical reports.
RESULTS: In this study, the XGBoost model with pairwise learning was employed to predict the druggability of BsAbs. By analyzing extensive data on BsAbs and designing features from perspectives such as target activity, safety, cell type specificity, pathway mechanism, and gene embedding representation, our model is able to predict target combinations of BsAbs with high market potential. Specifically, we integrated XGBoost with the GPT model to discuss the efficacy of each bispecific target pair, thereby aiding the decision-making for drug developers.
CONCLUSIONS: The novelty of this study lies in the integration of machine learning and GPT techniques to provide a novel framework for the design of BsAbs drugs. This holistic approach not only improves prediction accuracy, but also enhances the interpretability and innovativeness of drug design.

Colorectal cancer (CRC) is a malignancy of the digestive system with high incidence rate and mortality, and reliable diagnostic and prognostic markers for CRC are still lacking. Glutamine metabolism is crucial to the occurrence and development of CRC. However, no research has systematically analyzed the biological role of glutamine metabolism-related genes (GMRGs) in CRC.
We downloaded gene expression data and clinical data of CRC patients from the TCGA database. The UCSC database downloads pan-cancer gene expression data and prognosis data. Characteristic GMRGs were screened out using differential analysis and two types of machine learning (SVM-REF and RandomForest). Single-cell RNA-sequencing data from CRC patients were downloaded from GEO data. ROC curve was used to evaluate the diagnostic value. Kaplan-Meier method and univariate Cox regression analysis were used to evaluate the prognostic value. The oncopredict package is used to calculate IC50 values for common drugs in CRC patients.
A total of 31 differentially expressed GMRGs were identified, 9 of which were identified as characteristic GMRGs. Further evaluation of diagnostic and prognostic value finally identified GPT as the most important GMRGs in CRC. scRNA-seq analysis revealed that GPT is almost exclusively expressed in epithelial cells. GPT expression is closely related to the tumor microenvironment and can effectively distinguish the sensitivity of different CRC patients to clinical drugs. In addition, pan-cancer analysis showed that GPT is an excellent diagnostic and prognostic marker for multiple cancers.
GPT is a reliable diagnostic, prognostic marker and therapeutic target in CRC.

ChatGPT has sparked extensive discussions within the healthcare community since its November 2022 release. However, potential applications in the field of psychiatry have received limited attention. Deep learning has proven beneficial to psychiatry, and GPT is a powerful deep learning-based language model with immense potential for this field. Despite the convenience of ChatGPT, this advanced chatbot currently has limited practical applications in psychiatry. It may be used to support psychiatrists in routine tasks such as completing medical records, facilitating communications between clinicians and with patients, polishing academic writings and presentations, and programming and performing analyses for research. The current training and application of ChatGPT require using appropriate prompts to maximize appropriate outputs and minimize deleterious inaccuracies and phantom errors. Moreover, future GPT advances that incorporate empathy, emotion recognition, personality assessment, and detection of mental health warning signs are essential for its effective integration into psychiatric care. In the near future, developing a fully-automated psychotherapy system trained for expert communication (such as psychotherapy verbatim) is conceivable by building on foundational GPT technology. This dream system should integrate practical \'real world\' inputs and friendly AI user and patient interfaces via clinically validated algorithms, voice comprehension/generation modules, and emotion discrimination algorithms based on facial expressions and physiological inputs from wearable devices. In addition to the technology challenges, we believe it is critical to establish generally accepted ethical standards for applying ChatGPT-related tools in all mental healthcare environments, including telemedicine and academic/training settings.

Accurately predicting the antigen-binding specificity of adaptive immune receptors (AIRs), such as T-cell receptors (TCRs) and B-cell receptors (BCRs), is essential for discovering new immune therapies. However, the diversity of AIR chain sequences limits the accuracy of current prediction methods. This study introduces SC-AIR-BERT, a pre-trained model that learns comprehensive sequence representations of paired AIR chains to improve binding specificity prediction. SC-AIR-BERT first learns the \'language\' of AIR sequences through self-supervised pre-training on a large cohort of paired AIR chains from multiple single-cell resources. The model is then fine-tuned with a multilayer perceptron head for binding specificity prediction, employing the K-mer strategy to enhance sequence representation learning. Extensive experiments demonstrate the superior AUC performance of SC-AIR-BERT compared with current methods for TCR- and BCR-binding specificity prediction.

Aspergillus flavus and Aspergillus fumigatus were derived and identified from the ducks infected with fungi. In order to investigate the effectiveness of Chinese herbal medicines against Aspergillus flavus and Aspergillus fumigatus, in vitro antibacterial test and animal infection control test were conducted to study the antibacterial activity of the Chinese medicine mixture which was compatible with Acorus gramineus, Phellodendron chinensis, and Cassia obtusifolia. According to the results, the liver of chickens infected with Aspergillus flavus and Aspergillus fumigatus displayed granulomatous lesions, indicating that the isolation of pathogen from the lungs of sick ducks is also pathogenic to chickens. As suggested by the results of in vitro drug sensitivity test, the mixture 1 MIC80 was the minimum, the MIC80 of Aspergillus flavus was 16 μg/μL, and the MIC80 of Aspergillus fumigatus was 4 μg/μL. In a petri dish of the same concentration, the colony diameter of Aspergillus flavus and Aspergillus fumigatus in Mixture 1 was the minimum. Besides, Aspergillus flavus colonies grew when the concentration was 64 μg/μL, and Aspergillus fumigatus colonies grew when the concentration was 4 μg/μL, which suggests the more significant inhibitory effect of Mixture 1 on Aspergillus flavus and Aspergillus fumigatus. According to the results of animal experiments, there was a significantly lower activity level of Glutamic oxaloacetic transaminase (GOT) and Glutamate pyruvic transaminase (GPT) in the protection group and the treatment group than in the bacterial infection group. As indicated by the blood smear results, there were more neutrophils in the infected group than in the prevention group and the treatment group. Thus, it can be seen from that the Mixture 1 produced preventive and therapeutic effects on the chickens infected with Aspergillus flavus and Aspergillus fumigatus.

The widespread use of social media provides a large amount of data for public sentimentanalysis. Based on social media data, researchers can study public opinions on humanpapillomavirus (HPV) vaccines on social media using machine learning-based approaches that willhelp us understand the reasons behind the low vaccine coverage. However, social media data isusually unannotated, and data annotation is costly. The lack of an abundant annotated dataset limitsthe application of deep learning methods in effectively training models. To tackle this problem, wepropose three transfer learning approaches to analyze the public sentiment on HPV vaccines onTwitter. One was transferring static embeddings and embeddings from language models (ELMo)and then processing by bidirectional gated recurrent unit with attention (BiGRU-Att), called DWEBiGRU-Att. The others were fine-tuning pre-trained models with limited annotated data, called finetuninggenerative pre-training (GPT) and fine-tuning bidirectional encoder representations fromtransformers (BERT). The fine-tuned GPT model was built on the pre-trained generative pretraining(GPT) model. The fine-tuned BERT model was constructed with BERT model. Theexperimental results on the HPV dataset demonstrated the efficacy of the three methods in thesentiment analysis of the HPV vaccination task. The experimental results on the HPV datasetdemonstrated the efficacy of the methods in the sentiment analysis of the HPV vaccination task. Thefine-tuned BERT model outperforms all other methods. It can help to find strategies to improvevaccine uptake.

The aim is to compare atorvastatin versus rosuvastatin on secondary percutaneous coronary intervention (PCI) rate and explore risk factors in coronary heart disease (CHD) patients.
A cohort study with 283 CHD subjects was launched from 2011 to 2015. Cox proportional hazards regression model, Receiver Operating Characteristic (ROC) and nomogram were used to compare the effect of atorvastatin and rosuvastatin on secondary PCI rate and disease risk factors. Even why the two statins had different effects based on gene expression profile analysis has been explored.
Gene FFA (Freely fatty acid), AST (Aspartate Transaminase) and ALT (Alanine transaminase) showed the statistical difference between the four statin groups (P<0.05). In the AA group (Continuous Atorvastatin usage), albumin was a risk factor (Hazard Ratio (HR):1.076, 95%CI (1.001, 1.162), p<0.05). In the AR group (Start with Atorvastatin usage, then change to Rosuvastatin usage), ApoA was a protective factor (HR:0.004, 95%CI (0.001, 0.665), p<0.05). GLB (Galactosidase Beta) was a risk factor (HR:1.262, 95%CI (1.010, 1.576), p<0.05). In RR group (Continuous Rosuvastatin usage), ApoE was a protective factor (HR:0.943, 95%CI (0.890, 1.000), <0.05). ALT was a risk factor (HR:1.030, 95%CI (1.000, 1.060), p<0.05).
Patients in the RA group had the lowest secondary PCI rate. ALT was a risk factor in the RR group. Gene Gpt (Glutamic Pyruvic Transaminase) encoded for one subtype of ALT had a significantly different expression in different statin groups.