With the emergence of deep learning techniques based on convolutional neural networks, artificial intelligence (AI) has driven transformative developments in the field of medical image analysis. Recently, large language models (LLMs) such as ChatGPT have also started to achieve distinction in this domain. Increasing research shows the undeniable role of AI in reshaping various aspects of medical image analysis, including processes such as image enhancement, segmentation, detection in image preprocessing, and postprocessing related to medical diagnosis and prognosis in clinical settings. However, despite the significant progress in AI research, studies investigating the recent advances in AI technology in the aforementioned aspects, the changes in research hotspot trajectories, and the performance of studies in addressing key clinical challenges in this field are limited. This article provides an overview of recent advances in AI for medical image analysis and discusses the methodological profiles, advantages, disadvantages, and future trends of AI technologies.
Artificial Intelligence ; Humans ; Image Processing, Computer-Assisted/methods* ; Neural Networks, Computer ; Deep Learning ; Diagnostic Imaging/methods*

Space medicine,as a comprehensive discipline ensuring the safety,health,and efficient performance of astronauts during manned space missions,focuses on elucidating the underlying mechanisms of multi-system physiological effects induced by extreme space environments and developing corresponding protective strategies.With China's space program transitioning into an application and development phase,space medical experiments—a critical domain within space applications—face significant opportunities and challenges.This paper reviews the international development trend in the field of medical experiments and the progress in China from perspectives including platform system construction,utilization of novel technologies,and scientific discoveries.It further outlines the engineering framework,guiding ideology,and key research directions for space medical experiments under China's Space Station Application and Development Project.Deliberations and prospects center on the in-depth analysis of the adaptation law of life in space flight,the application of big data and artificial intelligence technology,the emerging challenges it faces,and the scientific research organization models.This work aims to provide a reference for the development of space medical experiment field in China.

To investigate the impact of mild-to-moderate frailty on the long-term prognosis of hospitalized elderly patients with type 2 diabetes mellitus(T2DM).

With the rapid development of social economy， the number of patients with nervous system diseases has increased， and the incidence of the population has a trend of younger， which has a serious impact on life health and social economy. Artemisinin is an active antimalarial component extracted and isolated from Artemisia annua， a Chinese medicinal material. Artemisinin and its derivatives， in addition to the antimalarial effect， also have anti-parasitic， anti-fungal， anti-viral， hypoglycemic， hypolipidemic， anti-tumor， and anti-inflammatory effects， showing a wide range of pharmacological activities. In the past five years， research on the new pharmacological effects of artemisinin and its derivatives has been deepening， and the efficacy of artemisinin and its derivatives in nervous system diseases has attracted much attention， including anti-neuroinflammation， anti-oxidative stress， maintaining the stability of the blood-brain barrier， regulating the release of neurotransmitters， repairing neuronal damage， and promoting neuronal regeneration. These pharmacological effects indicate that artemisinin and its derivatives are potentially capable of neuroprotection. By sorting out literature on the pharmacological activity of artemisinin and its derivatives in nervous system during 2019－2024， this paper systematically summarized the protective effects of artemisinin and its derivatives against nervous system diseases such as stroke， neurodegenerative diseases， neuroimmunological diseases， neuralgia， and nervous system tumors. This review is expected to provide clues and evidence for new indication expansion of artemisinin drugs， innovative drug development， and clinical treatment of nervous system diseases.

The impact of air pollution on human health has always been a research hotspot in the global health field. Outdoor air pollutants composed of multiple components can enter the human body through various pathways. Cardiovascular diseases are a group of diseases caused by outdoor air pollutants. Studies have shown that the incidence of cardiovascular diseases， including hypertension， arrhythmia， and heart failure， is significantly increased among people exposed to air pollution environments. Air pollutants such as fine particulate matter， nitrogen dioxide， ozone， carbon monoxide， and sulfur dioxide are closely related to the occurrence of cardiovascular diseases， and short-term and long-term exposure causes different cardiovascular risks. By reviewing the relevant research reports from 2019 to 2024， this article summarizes the epidemiological evidence of cardiovascular diseases caused by different air pollutants. It generalizes the pathways through which air pollutants accelerate the progression of cardiovascular diseases. These pathways include oxidative stress， inflammatory response， thrombosis， extracellular vesicle release， endoplasmic reticulum stress， apoptosis， endothelial dysfunction， autonomic nervous system imbalance， and their interactions. Based on the different mechanisms of air pollution on cardiovascular diseases， the article analyzes the main progress in drug intervention and summarizes the roles of various active ingredients and compound prescriptions of traditional Chinese medicine in treating air pollution-related cardiovascular diseases， providing reference for the research on the mechanisms and drug interventions of air pollution-related cardiovascular diseases.

Objective Explore a non-contact physiological and psychological detection model based on facial video in simulations of weightlessness effects,research new methods for non-contact heart rate and negative mood state detection in long-term simulations of weightlessness effect analysis.Methods Construct a non-contact physiological and psychological data collection system for fusion analysis of visible light and thermal infrared videos.Collect physiological and psychological data of volunteers in the"Earth Star-Ⅱ"90-day head-down bed rest experiment.A non-contact heart rate detection model based on GCN facial multi-region feature fusion and a non-contact negative mood state detection model considering data reliability were constructed,and the effectiveness of the models were validated with finger clip heart rate and POMS-SF scale as labels.Results The experimental results show that the average difference in the Bland-Altman plot of the non-contact heart rate detection model is-1.26 bpm,and 96.3%of value error detection data falls within the 95%confidence interval,indicating a high consistency between the model detected heart rate and the finger clip heart rate.The non-contact negative mood state detection model achieves an accuracy of>0.85 for detecting tension,depression,anger,and fatigue.Features such as heart rate,AU06,eye gaze,and head pose were observed to be important to mood state detection.Conclusion Non-contact physiological and psychological detection methods not only can be utilized for long-term physiological analysis in simulations of weightlessness effects,but also provide a novel technical approach for on-orbit astronauts health assurance during long-term space flight in the future.

Objective:To evaluate the clinical application of urine sediment score (USS) in early diagnosis, etiological differentiation, staging and prognosis of acute kidney injury (AKI), and to investigate the diagnostic efficacy of independent USS and its combination with blood urea nitrogen(Bun) serum creatinine(sCr) and uric acid(UA) in AKI.Methods:From August 23 to September 28, 2023, 9 020 morning urine samples of hospitalized patients in the First Hospital of Jilin University were detected by Sysmex UF5000.A total of 3 226 ssamples with small and round cell (SRC) > 1/μl and/or CAST>1/μl were screened for microscopic examination, and 404 cases with positive renal tubular epithelial cells and/or cast were enrolled in this study. There were 218 males and 186 females, aged 59.5 (49.0, 71.0) years. The 404 cases were divided into the USS AKI group (345 cases) and the USS non-AKI group (59 cases) according to the USS results based on the microscopic findings. According to Kidney Disease: Improving Global Outcomes (KDIGO) criteria, they were divided into KDIGO criteria AKI group (63 cases) and KDIGO criteria non-AKI group (341 cases), and the AKI group was divided into renal AKI group (33 cases) and non-renal AKI group (30 cases). According to the clinical diagnosis recorded in the medical records, they were divided into clinically diagnosed AKI group (29 cases) and clinically diagnosed non-AKI group (375 cases).The χ 2 test or Fisher exact test was used to compare USS in different AKI causes and stages. Logistic regression was used to calculate the odds ratio of renal AKI and stage 3 AKI. The area under the receiver operating characteristic curve was used to evaluate the sensitivity and specificity of USS, sCr, UA and Bun alone and in combination in the diagnosis of AKI, and the best cut-off value, sensitivity and specificity in the diagnosis of AKI were calculated. P < 0.05 was considered statistically significant. Results:The USS was used to identify the etiology of KDIGO standard AKI group,and there were significant differences in USS between renal AKI group and non-renal AKI group (χ 2=11.070, P<0.001). Compared to USS=1, the odds ratio of renal AKI was 8.125 when USS≥2 (95% CI 2.208—29.901). There was a statistically significant difference in the comparison of USS between groups in each stage of the AKI staging study based on USS (χ 2=15.724, P<0.05). Compared to USS=1, the odds ratio of stage 3 AKI was 9.714 when USS≥2 (95% CI 1.145-82.390). The AUC of independent USS in the diagnosis of AKI was 0.687 (95% CI 0.618-0.757, P<0.001), the specificity was 65.7% and the sensitivity was 61.9%. The AUC of USS combined with Bun, sCr, UA in the diagnosis of AKI was 0.794 (95% CI 0.608-0.980, P<0.05), the specificity was 82.4%, and the sensitivity was 88.9%. Conclusions:There wasan increased likelihood of renal AKI or stage 3 AKI while USS≥2,and whose combination with Bun, sCr and UA will improve the diagnostic efficiency of AKI.

Objective:To explore the experience of elderly patients with diabetes after the first use of real-time continuous glucose monitoring (rt-CGM) through qualitative research.Methods:From January to December 2022, 20 elderly patients with diabetes who received rt-CGM in Beijing Friendship Hospital Affiliated to Capital Medical University were selected as the research object with objective sampling. Semi-structured, personalized, one-to-one in-depth interviews were used to collect data. The qualitative research content analysis method was used to summarize interview data, extract and explain the theme.Results:In this interview, a total of five themes were obtained. There were two themes before continuous glucose monitoring, namely high recognition of rt-CGM by patients and the expectation of understanding blood glucose fluctuations, which was the main purpose for patients to receive rt-CGM. After continuous glucose monitoring, there were three themes, namely, the negative emotions caused by abnormal blood glucose alarms during rt-CGM, disagreements among patients regarding the calibration method of measuring finger blood glucose four times a day during rt-CGM, and patients questioning the accuracy of rt-CGM data.Conclusions:Elderly patients with diabetes are willing to receive rt-CGM, but there are still many misunderstandings. Medical and nursing staff should develop targeted nursing strategies from various aspects such as improving patients ' psychological state, enhancing patients ' correct understanding of treatment, and strengthening standardized training for nurses, so as to increase patients ' treatment compliance and effectively control blood glucose.

Inflammatory bowel disease(IBD)is a serious disorder,and exploration of active compounds to treat it is necessary.An acidic polysaccharide named SUSP-4 was purified from Selaginella uncinata(Desv.)Spring,which contained galacturonic acid,galactose,xylose,arabinose,and rhamnose with the main chain structure of →4)-α-D-GalAp-(1 → and →6)-β-D-Galp-(1 → and the branched structure of →5)-α-L-Araf-(1 →.Animal experiments showed that compared with Model group,SUSP-4 significantly improved body weight status,disease activity index(DAI),colonic shortening,and histopathological damage,and elevated occludin and zonula occludens protein 1(ZO-1)expression in mice induced by dextran sulfate sodium salt(DSS).16S ribosomal RNA(rRNA)sequencing indicated that SUSP-4 markedly downregulated the level of Akkermansia and Alistipes.Metabolomics results confirmed that SUSP-4 obviously elevated thiamine levels compared with Model mice by adjusting thiamine metabolism,which was further confirmed by a targeted metabolism study.Fecal transplantation experiments showed that SUSP-4 exerted an anti-IBD effect by altering the intestinal flora in mice.A mechanistic study showed that SUSP-4 markedly inhibited macrophage activation by decreasing the levels of phospho-nuclear factor kappa-B(p-NF-κB)and cyclooxygenase-2(COX-2)and elevating NF-E2-related factor 2(Nrf2)levels compared with Model group.In conclusion,SUSP-4 affected thiamine metabolism by regulating Akker-mania and inhibited macrophage activation to adjust NF-κB/Nrf2/COX-2-mediated inflammation and oxidative stress against IBD.This is the first time that plant polysaccharides have been shown to affect thiamine metabolism against IBD,showing great potential for in-depth research and development applications.

OBJECTIVES: The magnesium depletion score (MDS) is considered more reliable than traditional approaches for predicting magnesium deficiency in humans. We explored the associations of MDS and dietary magnesium intake with diabetes. METHODS: We obtained data from 18,853 participants in the National Health and Nutrition Examination Survey 2011-2018. Using multivariate regression and stratified analysis, we investigated the relationships of both MDS and magnesium intake with diabetes. To compute prevalence ratios (PRs), we employed modified Poisson or log-binomial regression. We characterized the non-linear association between magnesium intake and diabetes using restricted cubic spline analysis. RESULTS: Participants with MDS ≥2 exhibited a PR of 1.26 (95% confidence interval [CI], 1.19 to 1.34) for diabetes. Per-standard deviation (SD) increase in dietary magnesium intake was associated with a lower prevalence of diabetes (PR, 0.91; 95% CI, 0.87 to 0.96). Subgroup analyses revealed a positive association between MDS ≥2 and diabetes across all levels of dietary magnesium intake, including the lowest (PR, 1.35; 95% CI, 1.18 to 1.55), middle (PR, 1.23; 95% CI, 1.12 to 1.35), and highest tertiles (PR, 1.25; 95% CI, 1.13 to 1.37; pinteraction<0.001). Per-SD increase in magnesium intake was associated with lower diabetes prevalence in participants with MDS <2 (PR, 0.92; 95% CI, 0.87 to 0.98) and those with MDS ≥2 (PR, 0.91; 95% CI, 0.84 to 0.98; pinteraction=0.030). CONCLUSIONS MDS is associated with diabetes, particularly among individuals with low magnesium intake. Adequate dietary magnesium intake may reduce diabetes risk, especially in those with high MDS.