Large language models (LLMs) such as ChatGPT, Claude, Llama, and Qwen are emerging as transformative technologies for the diagnosis and treatment of various diseases. With their exceptional long-context reasoning capabilities, LLMs are proficient in clinically relevant tasks, particularly in medical text analysis and interactive dialogue. They can enhance diagnostic accuracy by processing vast amounts of patient data and medical literature and have demonstrated their utility in diagnosing common diseases and facilitating the identification of rare diseases by recognizing subtle patterns in symptoms and test results. Building on their image-recognition abilities, multimodal LLMs (MLLMs) show promising potential for diagnosis based on radiography, chest computed tomography (CT), electrocardiography (ECG), and common pathological images. These models can also assist in treatment planning by suggesting evidence-based interventions and improving clinical decision support systems through integrated analysis of patient records. Despite these promising developments, significant challenges persist regarding the use of LLMs in medicine, including concerns regarding algorithmic bias, the potential for hallucinations, and the need for rigorous clinical validation. Ethical considerations also underscore the importance of maintaining the function of supervision in clinical practice. This paper highlights the rapid advancements in research on the diagnostic and therapeutic applications of LLMs across different medical disciplines and emphasizes the importance of policymaking, ethical supervision, and multidisciplinary collaboration in promoting more effective and safer clinical applications of LLMs. Future directions include the integration of proprietary clinical knowledge, the investigation of open-source and customized models, and the evaluation of real-time effects in clinical diagnosis and treatment practices.
Humans ; Large Language Models ; Tomography, X-Ray Computed

Complex brain diseases seriously endanger human health, and early diagnostic biomarkers and effective treatments are currently lacking. Due to ethical constraints on human research, establishing monkey models is crucial to address these issues. With the rapid development of technology, transgenic monkey models of a range of brain diseases, especially autism spectrum disorder (ASD), have been successfully established. However, to establish practical and effective brain disease models and subsequently apply them to disease mechanism and treatment studies, there is still a lack of a standard tool, i.e., a system for collecting and analyzing the daily behaviors of brain disease model monkeys. Therefore, with the goal of undertaking a comprehensive and quantitative study of behavioral phenotypes, we established a standard daily behavior collection and analysis system, including behavioral data collection protocols and a monkey daily behavior ethogram (MDBE) for rhesus and cynomolgus monkeys, which are the most commonly used non-human primates in model construction. Then, we used ASD as an application example after referring to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision (DSM-5-TR), which is widely used in clinical disease diagnosis to obtain ASD core clinical symptoms. We then established a sub-ethogram (ASD monkey core behavior ethogram (MCBE-ASD)) specifically for quantitative assessment of the core clinical symptoms of an ASD monkey model based on MDBE. Subsequently, we demonstrated the high reproducibility of the system.
Animals ; Autism Spectrum Disorder ; Macaca mulatta ; Disease Models, Animal ; Behavior, Animal ; Macaca fascicularis ; Male ; Humans

Objective To study the diagnostic value of Japan narrow band imaging expert team ( JNET) classification for differentiating pathological type of colorectal lesions. Methods A total of 418 colorectal lesions were retrospectively diagnosed by magnifying endoscopy with narrow band imaging ( ME-NBI) using JNET classification by two inexperienced doctors after a short time of training in JNET classification. Then lesions were diagnosed with Sano classification by the two doctors. Diagnostic results were compared with histologic findings as a golden standard. Results The sensitivity, specificity, and accuracy of JNET classification and Sano classification for neoplastic lesion differentiation were 98. 2％ VS 98. 5％, 77. 8％ VS 66. 7％, and 96. 9％ VS 96. 4％, respectively ( all P>0. 05 ) . These indicators for diagnosing cancerous lesions, including high grade intraepithelial neoplasia, intramucosal carcinoma and submucosal carcinoma, were 66. 7％ VS 80. 2％ ( P=0. 023) , 87. 6％ VS 79. 5％ ( P=0. 006) , and 82. 1％ VS 79. 7％( P=0. 379 ) , respectively, and those for predicting submucosal deep invasive cancers were 34. 8％ VS 39. 1％, 100. 0％ VS 99. 0％, and 96. 4％ VS 96. 3％, respectively ( all P>0. 05) . The diagnostic accuracy of JNET classification for differentiating neoplastic lesions were 95. 2％ in those with diameter <10 mm, 97. 0％ in 10～<20 mm, and 97. 8％ in ≥20 mm (P=0. 483), this finding were 95. 2％, 85. 1％ and 72. 1％ for cancer, respectively ( P<0. 0001 ) , and 100％, 96. 3％, and 94. 4％ for submucosal deep invasive cancer, respectively (P=0. 026). Shape and location of colorectal lesions showed no significant effect on the diagnostic efficacy of JNET classification. Conclusion JNET classification is valuable for doctors without experience of ME-NBI in diagnosing colorectal lesions and the efficiency is slightly superior to Sano classification. However, the accuracy of diagnosis for cancer with diameter ≥20 mm need to be improved.

Japanese encephalitis virus (JEV) is a mosquito-borne, zoonotic flavivirus causing viral encephalitis in humans and reproductive disorder in swine. JEV is prevalent throughout China in human; however, spatiotemporal analysis of JEV in Chinese swine herds has not been reported previously. Herein, we present serological and molecular epidemiological results and estimates of prevalence of JEV infections among swine herds in various regions of China. The results suggest that JEV infections are widespread and genotype I and III strains co-exist in the same regions. Therefore, there is an urgent need to monitor JEV infection status among swine herds in China.
Asian Continental Ancestry Group ; China ; Encephalitis Virus, Japanese ; Encephalitis, Japanese ; Encephalitis, Viral ; Flavivirus ; Genotype ; Humans ; Molecular Epidemiology ; Prevalence ; Spatio-Temporal Analysis ; Swine

Objective:This study aimed to compare the differences in molecular subtypes between Uygur and Han patients with breast cancer. This study was also conducted to provide clinical recommendations. Methods:The new typing standard of St. Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2011 was used to classify the molecular subtypes of 369 breast cancer cases from the First People's Hospital of Kashgar Prefecture, Xinjiang Uygur Autonomous Region, China. Four immunohistochemical markers (ER, PR, HER-2, and Ki-67) were used to divide the patients into four intrinsic subtypes:Luminal A;Luminal B (divided into HER-2 negative subtype and HER-2 positive subtype);HER-2 enriched;and triple negative breast cancer (TNBC) subtype. Statistical analysis was then conducted to evaluate the differences in molecular subtype characteristics of Uygur and Han patients with breast cancer. Results:The proportion of Luminal A, Luminal B with HER-2 negative subtype, Luminal B with HER-2 positive subtype, HER-2 enriched, and TNBC subtype were 12.67%(36/284), 34.51%(98/284), 20.07%(57/284), 14.79%(42/284), and 17.96%(51/284) for 284 Uygur patients with breast cancer;the corresponding proportions were 16.47%(14/85), 37.65%(32/85), 10.59%(9/85), 10.59%(9/85), and 24.71%(21/85) for 85 Han patients with breast cancer, respectively. The HER-2 positive rates of Uygur and Han patients with breast cancer were 34.86%(99/284) and 21.18%(18/85), respectively. The proportions of Luminal B with HER-2 positive subtype and HER-2 positive rate were significantly higher in Uygur patients than in Han patients (P=0.045 and P=0.030, respectively).Conclusion:A larger proportion of Luminal B with HER-2 positive subtype and a higher HER-2 positive rate were observed in Uygur patients with breast cancer than in Han patients with the same disease. HER-2-targeted therapy could be more effective for Uygur patients with breast cancer than for Han patients.

Objective:To investigate the incidence and distribution of malignant tumor in Uygur People and provide a theoretical basis for epidemiological surveys. Methods:A retrospective study was conducted from November 2007 to October 2012 on inpatients with malignant tumors at The First People′s Hospital of Kashgar Prefecture. The top 10 kinds of malignant tumor were found in Uygur People and Han People. Results:A total of 7578 patients were registered, including 6840 (about 90.26%) Uygur People, 628 (nearly 8.29%) Han People, and 110 (about 1.45%) from other minority groups. The top 10 kinds of malignant tumor for Uygur People were gastric cancer, esophageal cancer, leukemia, cervical cancer, malignant lymphoma, primary hepatic carcinoma, breast cancer, head and neck cancer, lung cancer, and colorectal cancers. Meanwhile, the order for Han People were lung cancer, colorectal cancer, breast, gastric, primary hepatic, head and neck, leukemia, cervical, esophageal cancer, and pancreatic cancer. Conclusion:A different epidemic character of malignant tumor existed between Uygur People and Han People in Kashga, Xinjiang.