As the performance of large language models is proven in general domains, we can consider applying them to specific tasks to improve the system’s specialization and responsiveness. In this paper, we will develop a lightweight software system based on RAG (Retrieval-Augmented Generation) to test whether this approach can provide effective advice and protection for patients after discharge. All patient data in this study comes from the neurology department. We will select three diseases — Acute Cerebral Infarction, Atherosclerosis, and Hypertension to test our system, and the generated results will be evaluated by professional doctors. Additionally, we will introduce a memory mechanism to enhance the system’s performance and responsiveness. Finally, we will include suggestions for system improvements and extensions. The experimental results indicate that both the foundational capabilities of large language models (such as Llama 3 and GPT-4) and the system architecture (e.g., the integration of RAG and memory mechanisms) significantly influence overall performance. By comparing different models and architectures, it is observed that the GPT-4 system combined with RAG and memory mechanisms outperforms the baseline in terms of total score and improvements, demonstrating the effectiveness of system architecture optimization in enhancing the models’ ability to handle complex tasks. Since the data still contains sensitive information of patients and hospitals after being desensitized, we cannot show all the test data. However, after obtaining the hospital’s permission, through data desensitization, we showed some of the test data. You can click here to get the prototype we developed and some test data.

This paper reviews the efficacy and mechanisms of herbal medicine in alleviating depression in recent years. Depression is a severe mental disorder with a rising prevalence. Current pharmacological treatments have significant side effects and high costs, resulting in poor patient compliance. Hence, exploring new treatment methods is imperative. Herbal medicine has gained attention due to its individualized treatment, low relapse rate, fewer side effects, and multitarget effects. This paper summarizes the main mechanisms and effects of herbal medicine in the treatment of depression over the past five years, focusing on the monoamine neurotransmitter system, HPA axis, oxidative stress, neuroinflammation, and microglial activation.

Background and Aim: Knee osteoarthritis (KOA) is a degenerative joint disease marked by cartilage degradation, inflammation, and pain, leading to reduced mobility. This study investigates how Qianghuo alleviates KOA induced by meniscal injury in rats.Experimental Procedure: KOA was induced in rats via right hind limb meniscectomy. Rats were divided into Sham, KOA, and Qianghuo treatment groups (1 g/mL, 0.5 mL/d for 21 days). In vitro, IL-1β-induced chondrocyte models were used with Qianghuo (100 mol/L for 48 hours). Behavioral observations, CCK-8 assays, RT-qPCR, and Western blot analyses were performed.Results: KOA rats showed increased VAS scores, quadriceps atrophy, and decreased joint mobility. IL-1βreduced chondrocyte proliferation and increased apoptosis, inflammation, oxidative stress, and matrix degradation. Qianghuo treatment reversed these effects.Conclusion: Qianghuo alleviates KOA by promoting chondrocyte proliferation, inhibiting apoptosis, reducing inflammation and oxidative stress, and preventing matrix degradation, highlighting its potential in KOA treatment.

As the most common type of mental illness, anxiety disorders have received widespread attention for a long time. With the deepening of research, the theoretical basis of anxiety disorder has been gradually improved, and a mature and systematic theoretical system has been formed. The purpose of this article is to systematically review the discovery, development and research history of anxiety disorders, deeply explore their definition, classification, differences and connections with other mental diseases, and elaborate on the pathogenesis of anxiety disorders, including the comprehensive effects of neurobiological, psychosocial and genetic factors. In addition, the clinical manifestations of anxiety disorders, such as the persistence of fear and restlessness, and their impact on individual functioning were reviewed. In terms of treatment, this article comprehensively reviews the current commonly used drug treatment and psychological intervention strategies, and discusses the development trend and future research direction of individualized treatment. In conclusion, this paper provides comprehensive scientific support and profound theoretical guidance for the theoretical research and clinical practice of anxiety disorders

This study aimed to explore the effect of treadmill exercise on anxiety in rats. Thirty SPF male rats aged 2 months with a body mass of (225±25) g were randomly divided into control group (CG, n=10), chronic sleep deprivation group (CSD, n=10) and sleep deprivation exercise group (CSD+E, n=10) after adaptive feeding for 1 week. The CSD model of rats in CSD group and CSD+E group was made by multi platform water environment method. Sleep deprivation of 18 h per day (from 12:00 pm. to 6:00 am. the next day) for 8 weeks. The effect of running on the anxiety-like behaviour of CSD rats was examined in the open field test (OFT) and the elevated plus maze (EPM) experiment. Hematoxylin-eosin (HE) staining, Annexin V/PI flow cytometry, immunofluorescence staining, Western blot, RT-qPCR and other methods were used to detect the effects of treadmill exercise on the morphology of hippocampus, apoptosis related factors caspase-12, Bax, Bcl-1, inflammatory factors (IL-6, TNF-a), Wnt β- catenin, p- β-catenin. The results of HE staining showed that the brain tissue of the control rats was structurally intact, with thick layers of cone cells, relatively dense, neatly arranged and compact, the cell edge structures were intact and clearly visible, with no obvious abnormal changes. The cone cell layer of brain tissue in the chronic sleep deprivation group was thin, with relatively low cell density, disorganized and sparse arrangement, and blurred cell edges. The symptoms of the above pathological changes in brain tissue of rats in sleep deprivation exercise group gradually alleviated. OFT results showed that compared with CG group, the number of activities in the central region of CSD group was significantly reduced (P<0.01), and the total distance of exercise was significantly shortened (P<0.01). EPM results showed that compared with CG group, OT and CE in CSD group decreased significantly (P<0.01). CCK-8 results showed that compared with CG group, the activity of neurons in CA1 area of hippocampus in CSD group was significantly decreased (P<0.01), while that in CSD+E group was significantly increased (P<0.01); Annexin V/PI flow cytometry results showed that compared with CG group, the apoptosis of neurons in CA1 area of hippocampus in CSD group increased (P<0.01), and that in CSD+E group decreased significantly (P<0.01);Western blot results showed that caspase-12, Bax, IL-6, IL-1β and TNF-a were highly expressed and Bcl-1 was lowly expressed in hippocampal tissues of rats in the CSD group compared with the CG group (P<0.01), Wnt, β-catenin and p-β-catenin were lowly expressed in hippocampal tissues of rats in the CSD group, and Gsk-3βprotein expression was significantly higher (p<0.01). The results of RT-qPCR showed that caspase-12 mRNA, Bax mRNA, IL-6 mRNA, TNF-a mRNA and IL-1β mRNA were highly expressed and Bcl-1 mRNA was lowly expressed in hippocampal tissues of rats in the CSD group compared with the CG group (P<0.01). Compared with the CG group, Wnt mRNA and β-catenin mRNA were significantly lowly expressed and Gsk-3βmRNA was significantly highly expressed in hippocampal tissue of CSD rats (P<0.01). Our findings indicated that 8 weeks of aerobic exercise significantly improved anxiety-like depression in CSD rats by increasing neuronal activity, inhibiting apoptosis, reducing the inflammatory response and activating the Wnt/β-catenin pathway.

This study introduces an evaluation framework for multimodal models in medical imaging diagnostics. We developed a pipeline incorporating data preprocessing, model inference, and preference-based evaluation, expanding an initial set of 500 clinical cases to 3,000 through controlled augmentation. Our method combined medical images with clinical observations to generate assessments, using Claude 3.5 Sonnet for independent evaluation against physician-authored diagnoses. The results indicated varying performance across models, with Llama 3.2-90B outperforming human diagnoses in 85.27% of cases. In contrast, specialized vision models like BLIP2 and Llava showed preferences in 41.36% and 46.77% of cases, respectively. This framework highlights the potential of large multimodal models to outperform human diagnostics in certain tasks.