Medical artificial intelligence （AI） is a new type of application formed by the combination of machine learning， computer vision， natural language processing， and other technologies with clinical medical treatment. With the continuous iteration and development of relevant technologies， medical AI has shown great potential in improving the efficiency of diagnosis and treatment， and service quality， but it also increases the possibility of triggering ethical issues. Ethical issues resulting from the clinical application of medical AI were analyzed， including the lack of algorithmic interpretability and transparency of medical AI， leading to information asymmetry and cognitive discrepancies； the concerning status of security and privacy protection of medical data； and the complex and unclear division of responsibilities due to the collaborative participation of multiple subjects in the clinical application of medical AI， resulting in increased difficulty in the identification of medical accidents and clarification of responsibilities. The paper proposed the principles of not harming patients’ interests， physician’s subjectivity， fairness and inclusiveness， and rapid response. It also explored the strategies and implementation paths for responding to the ethical issues of medical AI from multiple perspectives， including standardizing the environment and processes， clarifying responsibility attribution， continuously assessing the impact of data protection， guaranteeing data security， ensuring model transparency and interpretability， carrying out multi-subject collaboration， as well as the principles of being driven by ethical values and adhering to the “human health-centeredness.” It aimed to provide guidance for the healthy development of medical AI， ensuring technological progress while effectively managing and mitigating accompanying ethical risks， thereby promoting the benign development of medical AI technology and better serving the healthcare industry and patients.

Objective To explore the application of artificial intelligence quantitative analysis in the prognostic assessment of patients with connective tissue disease-associated interstitial lung disease(CTD-ILD).Methods A total of 67 patients with CTD-ILD were retrospectively selected.All subjects underwent high-resolution computed tomography(HRCT)scanning and were categorized into three groups,namely mild,moderate and severe groups,based on the results of pulmonary function tests.The survival rates of patients in each group were compared using Kaplan-Meier curves and analysis of variance.The univariate analysis was employed to assess the rela-tionships between artificial intelligence parameters and patient prognosis.Significant results were then incorporated into a multifacto-rial Cox regression model to construct the most accurate predictive model.Results A significant difference in survival rate was observed among the three groups(P<0.05).Univariate analysis revealed that the volume and percentage of lung infection in deceased patients were significantly greater than those in surviving patients,while the lung volume in deceased patients was significantly smaller than that in surviving patients.The analysis showed left lung volume and the percentage of lesion components CT value≤-750 HU as risk factors for prognosis,and the combination of these two factors as the most effective predictive model.Conclusion The artificial intelligence analysis system for lung lesions provides a new systematic and quantitative method for the prognostic assessment of CTD-ILD patients,which can be used for the prognostic assessment and follow-up of CTD-ILD patients.

In recent years,significant breakthroughs have been achieved in the immunotherapy for Alzheimer's disease.In line with global advancements,two anti-amyloid-β monoclonal antibodies have been approved and successfully launched in China for clinical use.Lecanemab and Donanemab were officially used in June 2024 and April 2025 in China,respectively.In order to standardize the rational and safe application of anti-amyloid-β monoclonal antibodies for Alzheimer's disease in China,this article integrates recom-mendations from the clinical trials and real-world experience from the author's team and domestic peers to further update the recom-mendations for the clinical use of anti-amyloid-β monoclonal antibody based on the 2024 version.It includes indications for therapy,pre-treatment evaluation and preparation,administration protocols and safety measures during treatment,and post-treatment monitor-ing strategies.

Objective:To study the effects of manual inspection and special equipment inspection for light guiding components of hard endoscope after cleaning and disinfection,so as to provide scientific data and evidence for the application of special inspection equipment of hard endoscope in Central Sterile Supply Department(CSSD).Methods:A total of 100 hard endoscopes after cleaning and disinfection,which were in CSSD of the Fifth Medical Center of Chinese PLA General Hospital during July and August 2024,were selected.Each light guiding components of hard endoscope was respectively inspected by manual method and special functional detector for endoscope(inspection method with equipment).The positive rates of fog,stains and glass shards,and overall failure rate of light guiding components of hard endoscope,as well as the difference with the effect of clinical use,between two kinds of inspection methods were compared.Results:In 100 hard endoscopes,the inspection method with equipment found 2 cases were overall failure,which fog,strains and glass shards were respectively 2,0 and 0.The overall failure rate,and the positive rates of fog,stains and glass shards of the inspection method with equipment were respectively 2%,2%,0 and 0,which all lower than overall failure rate(23%),and the positive rates of fog(17%),stains(2%)and glass shards(4%)of manual inspection.There was significant difference in overall failure rate and positive rat of fog between the two kinds of inspection methods(x2=18.286,11.399,P＜0.05).The overall failure rate that was reflected by clinical users was 3%,which was significant lower than 23%of manual inspection,and the difference of that between two methods was significant(x2=15.959,P＜0.05).Conclusion:The inspection for light guiding components of hard endoscopes after cleaning and disinfection can be carried out by manual inspection and special inspection equipment,and results of special inspection equipment is getting closer the usage effect of clinical users.It has a series of advantages include being intuitive,easy use,high accuracy,convenient observation,and archivable.

Alzheimer's disease(AD)is the most common cause of cognitive impairment in the elderly,and the formation of intracellular neurofibrillary tangles(NFT)due to the hyperphos-phorylation of Tau is one of its important pathological features.Compared to β-amyloid,the hyperphosphorylation of Tau and the resulting NFT are more closely related to the decline in cognitive ability.This review focuses on anti-AD drugs targeting Tau,em-phasizing the latest progress in inhibiting the hyperphosphoryla-tion of Tau protein,alleviating the aggregation of Tau protein,re-ducing the cytoskeletal damage caused by the hyperphosphoryla-tion of Tau protein by stabilizing microtubules,and immunothera-py,in the hope of providing new insights into drug research for AD and related cognitive disorders associated with Tau protein.

Aim To establish a simple and practical method for visualizing neurovascular coupling in the mouse barrel cortex in vivo.Methods Male C57BL/6J mice received stereotaxic in-jections of pAAV-hSyn-jGCaMP7s-WPRE into the barrel cortex to monitor neuronal activity.Three weeks post-injection,a crani-al window was implanted,and TRITC-Dextran 155 ku was ad-ministered intravenously to visualize the vasculature and blood flow dynamics.A custom-built whisker stimulator was used to e-voke controlled neuronal excitation.Two-photon microscopy was employed to monitor neuronal and vascular responses to whisker stimulation in real-time.Results Neuronal calcium signals and plasma signals were clearly observed using two-photon microsco-py.Whisker stimulation led to a significant increase in neuronal calcium signals in the barrel cortex,indicating effective neuronal activation.This neuronal excitation was accompanied by a syn-chronous increase in blood vessel diameter,blood flow velocity and overall blood flow.Conclusions This study successfully establishes a three-dimensional visualization framework(spatial,temporal,and functional)for in vivo visualization of neurovascu-lar coupling in the mouse barrel cortex,which provides a useful tool for investigating the pathophysiological mechanisms of neuro-vascular dysfunction and evaluating the efficacy of potential ther-apies.

Aim To generate a dual-reporter mouse model for tracing microglia and neurons to analyze their dynamic changes in real-time and to investigate the functional role of microglia-neuron interactions through microglial depletion.Methods Mi-croglia reporter mice were crossed with neuron reporter mice to generate Tmem119-e(2A-tdTomato-2A-DTR);Thy1-GFP dual-reporter mice.Genotyping was performed using tail DNA.Con-focal and two-photon microscopy were used to examine neuronal morphology.In vivo two-photon imaging was employed to observe the distribution of microglia and neurons in the brain.Diphtheria toxin(DT)was intraperitoneally injected to deplete microglia.Results The dual-reporter mice were successfully generated with the correct genotype.Both microglia and neurons were visu-alized,and microglia were specifically depleted by DT.Conclu-sions The successful establishment of a dual-reporter mouse model for tracing neurons and microglia will facilitate real-time in vivo observation of microglial and neuronal changes under physiological or pathological conditions,elucidating their specific roles in brain homeostasis.

Objective To explore the application of artificial intelligence quantitative analysis in the prognostic assessment of patients with connective tissue disease-associated interstitial lung disease(CTD-ILD).Methods A total of 67 patients with CTD-ILD were retrospectively selected.All subjects underwent high-resolution computed tomography(HRCT)scanning and were categorized into three groups,namely mild,moderate and severe groups,based on the results of pulmonary function tests.The survival rates of patients in each group were compared using Kaplan-Meier curves and analysis of variance.The univariate analysis was employed to assess the rela-tionships between artificial intelligence parameters and patient prognosis.Significant results were then incorporated into a multifacto-rial Cox regression model to construct the most accurate predictive model.Results A significant difference in survival rate was observed among the three groups(P<0.05).Univariate analysis revealed that the volume and percentage of lung infection in deceased patients were significantly greater than those in surviving patients,while the lung volume in deceased patients was significantly smaller than that in surviving patients.The analysis showed left lung volume and the percentage of lesion components CT value≤-750 HU as risk factors for prognosis,and the combination of these two factors as the most effective predictive model.Conclusion The artificial intelligence analysis system for lung lesions provides a new systematic and quantitative method for the prognostic assessment of CTD-ILD patients,which can be used for the prognostic assessment and follow-up of CTD-ILD patients.

Aim To generate a dual-reporter mouse model for tracing microglia and neurons to analyze their dynamic changes in real-time and to investigate the functional role of microglia-neuron interactions through microglial depletion.Methods Mi-croglia reporter mice were crossed with neuron reporter mice to generate Tmem119-e(2A-tdTomato-2A-DTR);Thy1-GFP dual-reporter mice.Genotyping was performed using tail DNA.Con-focal and two-photon microscopy were used to examine neuronal morphology.In vivo two-photon imaging was employed to observe the distribution of microglia and neurons in the brain.Diphtheria toxin(DT)was intraperitoneally injected to deplete microglia.Results The dual-reporter mice were successfully generated with the correct genotype.Both microglia and neurons were visu-alized,and microglia were specifically depleted by DT.Conclu-sions The successful establishment of a dual-reporter mouse model for tracing neurons and microglia will facilitate real-time in vivo observation of microglial and neuronal changes under physiological or pathological conditions,elucidating their specific roles in brain homeostasis.