Objective To construct a mammography image classification assistant system suitable for Chinese population,and explore the potential of artificial intelligence technology to assist early screening of breast cancer in China.Methods Curated breast imaging subset of digital database for screening mammography(CBIS-DDSM),Mammographic image analysis society database(MIAS)and other international open datasets were used to conduct model training respectively in order to reproduce the mainstream in-depth learning methods in the current literature.The model was also tested on the Chinese breast mammography database(CBMD)provided by Huajiao Technology Co.,Ltd,and the performance was compared.Aiming at the problem that the Chinese population data are not ideal in the performance test of the open dataset training model,an optimization strategy based on the sliding window adjustment mechanism was implemented in combination with the characteristics of Chinese population data.Then a two-stage migration learning method was designed to improve the overall performance of the model,and then development of our system was carried out.Results With the sliding window adjustment mechanism and the CBMD training model after two-stage transfer learning,the accuracy of our developed system was improved from 0.50 of the open datasets to 0.80,precision from 0.54 to 0.82,sensitivity from 0.52 to 0.80,F1 value from 0.52 to 0.80,and AUC value from 0.51 to 0.89 based on the Chinese population dataset as the test set.Conclusion Through the introduction of sliding window adjustment mechanism and two-stage migration learning strategy,the performance of the breast molybdenum target image classification model has been significantly improved in the Chinese population dataset,and our system primarily achieves the purpose of assisting the classification of breast molybdenum target images for the Chinese population.

With the rapid advancement and iterative development of new artificial intelligence technologies, there remains a regulatory vacuum in corresponding governance measures among governments worldwide. Simultaneously, a technological and governance gap exists between developing countries and developed economies. In response, the World Health Organization (WHO) has released "Ethics and Governance of Artificial Intelligence for Health: Guidance on Large Multi-Modal Models" to assist governments in strengthening governance capabilities in this field. This paper provides an in-depth analysis of the Guidance, aiming to identify challenges and risks associated with the application of multimodal large models in healthcare. Guided by ethical principles for advancing health through artificial intelligence, the paper examines the three-tier governance framework and recommendations outlined in the Guidance. Additionally, it evaluates the current state of AI governance in China, offering insights and reference points for improving AI governance in China′s healthcare sector.

Objective To explore the time-varying characteristics and correlation degree of autonomous rehabili-tation behavior and related symptoms of middle-aged stroke patients,and to provide a basis for clinical transitional nursing and precise rehabilitation.Methods Ecological momentary assessment was used to select 57 middle-aged stroke patients who underwent rehabilitation treatment in the Rehabilitation Medicine Department of a tertiary com-prehensive hospital in Wuhan from March 15 to August 30,2024,using convenience sampling method.Their au-tonomous rehabilitation behavior and related symptoms(fatigue,pain,emotion,sensation)were continuously monitored for 2 weeks.A hierarchical linear model was used to analyze the correlation between behavior and symptoms.Results The autonomous rehabilitation behavior of middle-aged stroke patients showed a fluctuating increasing trend,and the symptom score showed a slow decreasing trend.The hierarchical linear model showed that compared with female patients,male patients have longer duration of autonomous rehabilitation behavior(P＜0.05).The number and duration of autonomous rehabilitation behaviors in patients without fatigue were higher(P＜0.05).The number of autonomous rehabilitation behaviors in patients without pain was higher than that in patients with pain(P＜0.05).The number of autonomous rehabilitation behavior items among patients who perceived more pleasure in rehabilitation was higher than that among patients with greater difficulty in rehabilitation challenges(P＜0.05).Patients with high rehabilitation confidence have higher numbers and duration of autonomous rehabilitation behaviors compared to pa-tients with low rehabilitation confidence(P＜0.05).Conclusion There are significant individual differences and dy-namic changes in the autonomous rehabilitation behavior and related symptoms of middle-aged stroke patients.Nurs-ing staff should accurately implement personalized rehabilitation services during the transition period,enhance pa-tients'autonomy and self-management ability in home-based rehabilitation,in order to improve the overall rehabilita-tion effect.

Objective:To explore the value of prenatal three-dimensional ultrasonography（3DUS）in displaying auricular morphotyping and dimensions for predicting congenital aural atresia（CAA）.Methods:A retrospective collection of 227 fetuses who underwent ultrasound scans and retained auricular 3DUS volumes from January 2018 to December 2023 at the First Affiliated Hospital of Sun Yat-sen University was conducted. Fetuses were divided into two groups：a CAA group（52 fetuses，62 auricles）and a non-CAA group（175 fetuses，202 auricles），based on the presence or absence of external auditory canal identified through postnatal examination. According to 3DUS auricular contour and presence or absence of the concha，the auricles were divided into 4 types：type Ⅰ，C-shaped auricle with a concha；type Ⅱ，Irregular auricle with a concha；type Ⅲ，C-shaped auricle without a concha；type Ⅳ，Irregular auricle without a concha. And auricular length（AL）and width（AW）were measured to calculate the product of the auricular length and width（ALW）. Normal reference ranges for ALW from the non-CAA group were developed. Differences of the auricular morphotyping and Z-score of ALW（ALWZ）were compared between the two groups. Receiver operating characteristic（ROC）curves were used to evaluate the diagnostic efficiency of auricular morphotyping，ALWZ and the regression model. A Logistic regression model for CAA based on auricular morphotyping and ALWZ were established.Results:The auricular morphotyping and ALWZ between the two groups were different statistically（both P<0.05）. The AUC of the auricular morphotyping and ALWZ predicting CAA were 0.960（95% CI = 0.923 - 0.997）and 0.975（95% CI = 0.959 - 0.991）individually. Formula for CAA prediction model combining the two indicators（5.379 × morphotyping - 2.386 × ALWZ - Conclusions:The auricular morphotyping and dimensions can effectively predict CAA.

Objective:To develop a deep learning-based artificial intelligence system for assessing image quality in early pregnancy ultrasound，and to evaluate its performance in anatomical structure identification and quality control.Methods:A retrospective study was conducted by collecting 17 910 static ultrasound images of 8 quality-control planes from fetuses at 11 to 13 +6 weeks of gestation who underwent routine first-trimester ultrasound examinations at the First Affiliated Hospital of Sun Yat-sen University from June 2018 to June 2024. The dataset was divided into a training set（12 536 images），a test set（3 582 images），and a validation set（1 792 images）in a 7∶2∶1 ratio to develop a prenatal-screening artificial intelligence system（PSAIS）and to evaluate its performance in the automatic recognition and quality control of standard planes during early pregnancy. The average precision and mean average precision（mAP）were used to measure the model's ability to recognize the anatomical structures on each plane. Intraclass correlation coefficient（ICC）and Kappa statistics were used to assess the consistency between PSAIS and expert-level sonographers in both plane image quality assessment and standardization. The efficiency of PSAIS was also compared to manual quality control. Results:In the test set，the mAP values for recognizing the anatomical structures of the 8 quality-control planes all exceeded 0.800. In the validation set，PSAIS demonstrated moderate to good agreement with two experts in image quality evaluation：the ICC ranged from 0.713 to 0.843 for one expert and 0.678 to 0.788 for the other，while the Kappa values ranged from 0.590 to 0.768 and 0.530 to 0.702，respectively. In terms of plane standardization scoring，PSAIS showed particularly high agreement with expert ratings on the transventricular view（compliance rate 94.6%，Kappa=0.860）and the four-chamber cardiac view with blood flow（compliance rate 94.1%，Kappa=0.778），with agreement above 70% for the remaining planes. Compared with manual quality-control，PSAIS significantly increased processing speed：the total processing time was only 413 seconds，markedly less than the 77 008 seconds and 94 918 seconds required for manual QC（ P<0.001）. Conclusions:The PSAIS system performs well in recognizing and controlling the quality of standard ultrasound planes in early pregnancy，demonstrating high consistency with expert evaluations and significantly improved processing efficiency. It has potential application value in enhancing the quality and efficiency of early pregnancy screening.

[Purpose]To explore the association between body weight change and long-term risk of esophageal cancer mortality based on Linxian General Population Nutrition Intervention study.[Methods]A total of 21 028 healthy residents aged 40～69 years old at baseline in Linxian of Henan Province were recruited as the study cohort,their body weight were measured in late 1985 and early 1991,and the esophageal cancer mortality was prospectively followed up until March 2016.The cohort was divided into four groups according to weight difference between the two measure-ments,the body weight maintenance group(change＜2 kg)was used as the reference group.The Cox proportional risk model was used to estimate the hazard ratio(HR)and 95％confidence inter-val(CI)for death from esophageal cancer in the weight loss ≥2 kg group,weight gain 2～5 kg group and weight gain ≥5 kg group.[Results]A total of 1 681 esophageal cancer deaths oc-curred during the follow-up after the last weight measurement.After adjusting for baseline age and sex,the risk of esophageal cancer death was 13％(HR=0.87,95％CI:0.77～1.00)and 16％(HR=0.84,95％CI:0.72～1.00)lower in the weight gain 2～5 kg and ≥5 kg groups compared to the weight maintenance group,respectively.The risk of esophageal cancer death was 23％higher in the weight loss ≥2 kg group than in the weight maintenance group(HR=1.23,95％CI:1.09～1.38).After adjusting for age,sex,baseline BMI group,smoking status,alcohol consumption,family history of cancer,education level,commune and nutritional intervention arms,weight loss ≥2 kg was still associated with a significantly increased risk of esophageal cancer death(HR=1.19,95％CI:1.06～1.34).Subgroup analysis showed there was no statistically significant interaction between changes in body weight and age,sex,and baseline BMI status on the risk of esophageal cancer death.[Conclusion]Weight loss is associated with an increased risk of esophageal cancer death.People in the high incidence area of esophageal squamous cell carcinoma should maintain their current weight or gain weight appropriately while maintaining a healthy weight state to reduce the risk of esophageal cancer death.

Asthma is a chronic inflammatory disease of the airway involving various cellular players. Among the different phenotypes of asthma, neutrophilic asthma is often associated with severe airway inflammation and a notable resistance to corticosteroid treatment. Macrophages, as innate immune cells, play a crucial role in the pathogenesis of neutrophilic asthma. They regulate neutrophil recruitment and activation to promote the progression of airway inflammation. During this process, macrophages also undergo changes in aspects such as efferocytosis. We reviewed the recent research progresses regarding the role of macrophages in the pathogenesis of neutrophilic asthma, aiming to provide valuable insights for future studies in this area.
Humans ; Asthma/pathology* ; Neutrophils/pathology* ; Macrophages/immunology* ; Animals ; Phagocytosis

Objective:To systematically integrate the qualitative research results on the exercise experience and needs of patients with Parkinson's disease at home and abroad, and to provide a reference for formulating exercise management plans that are in line with the feelings of patients with Parkinson's disease.Methods:Computer retrieval was conducted in databases including China National Knowledge Infrastructure, Wanfang Data, VIP, China Biology Medicine disc, Web of Science, PubMed, Cochrane Library, Medline, Embase, and ProQuest for qualitative studies on the exercise experience of patients with Parkinson's disease. The retrieval time limit was from the establishment of the databases to August 8, 2024.Results:A total of 14 articles were included, and 34 research results were extracted. Similar research results were grouped into 11 new categories and integrated into 4 integrated results, namely the incentive factors for patients with Parkinson's disease to participate in exercise, the perceived benefits of patients with Parkinson's disease in exercise, the perceived difficulties of patients with Parkinson's disease in exercise, and the needs of patients with Parkinson's disease to participate in exercise.Conclusions:Exercise has a positive effect on improving the physical and mental conditions of patients with Parkinson's disease. Medical staff should fully consider the needs of patients and formulate safe and reasonable exercise plans to improve the motor life ability of patients with Parkinson's disease.

Objective:To summarize ICU acquired weakness (ICU-AW) assessment tools from both domestic and international sources, providing a reference for healthcare providers in evaluating ICU-AW.Methods:Using Arksey and O'Malley's framework for scope reviews, a computer search was conducted in PubMed, Web of Science, Embase, Cochrane Library, CINAHL, China National Knowledge Infrastructure, Wanfang Database, VIP, and China Biology Medicine disc for relevant information on ICU-AW assessment tools. The search period was from the establishment of the databases to March 31, 2024. Two researchers independently summarized and analyzed the included literature.Results:A total of 14 articles were included, of which seven focused on the development/construction of prediction models, and seven were related to assessment tools, involving 17 different ICU-AW assessment tools.Conclusions:Researchers should develop and construct ICU-AW risk assessment tools with low bias risk and high clinical applicability based on existing ICU-AW assessment tools, providing effective instruments for the precise health management of ICU patients.

With the rapid advancement and iterative development of new artificial intelligence technologies, there remains a regulatory vacuum in corresponding governance measures among governments worldwide. Simultaneously, a technological and governance gap exists between developing countries and developed economies. In response, the World Health Organization (WHO) has released "Ethics and Governance of Artificial Intelligence for Health: Guidance on Large Multi-Modal Models" to assist governments in strengthening governance capabilities in this field. This paper provides an in-depth analysis of the Guidance, aiming to identify challenges and risks associated with the application of multimodal large models in healthcare. Guided by ethical principles for advancing health through artificial intelligence, the paper examines the three-tier governance framework and recommendations outlined in the Guidance. Additionally, it evaluates the current state of AI governance in China, offering insights and reference points for improving AI governance in China′s healthcare sector.