1.Expert consensus on the application of artificial intelligence in lung cancer screening, diagnosis, and treatment (2026 edition)
Wenzhao ZHONG ; Haibo WANG ; Yi HU ; Hao ZHANG ; Jigang DAI ; Junqiang FAN ; Guibin QIAO ; Fan YANG ; Jian HU ; Fengwei TAN ; Xuening YANG ; Qiang PU ; Zihao CHEN ; Hongxia TIAN ; Lunxu LIU ; Hecheng LI ; Xiaolong YAN ; Zongyang YU ; Zhenbin QIU ; Yihua SUN ; Jing HU ; Yuhang SHI ; Zhifei GUO ; Peng ZHANG ; Kezhong CHEN ; Shugeng GAO ; Yilong WU
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery 2026;33(06):848-856
With the continuous deepening of the concept of precision diagnosis and treatment for lung cancer, how to achieve higher efficiency and accuracy in the screening, diagnosis, and treatment pathways in clinical practice has become an important issue that urgently needs to be overcome. The current clinical difficulty lies in the fact that despite continuous advancements in imaging and molecular diagnostic technologies, there are still limitations in manual efficiency and subjective experience when it comes to massive data analysis and multi-scale feature extraction. Artificial intelligence (AI), especially algorithm systems based on deep learning, is an innovative technology capable of deeply empowering medical big data. This method utilizes algorithms such as convolutional neural networks, combined with radiomics, pathomics, and multi-modal data fusion analysis, demonstrating immense potential in early precise detection and benign-malignant differentiation of pulmonary nodules, digital pathological subtype recognition and non-invasive prediction of driver genes, precise 3D surgical planning and automatic delineation of radiotherapy target volumes, as well as dynamic risk warning during follow-up. This innovative technology provides a brand-new solution for realizing intelligent and individualized lung cancer diagnosis and treatment models. This consensus, based on the latest evidence from evidence-based medicine and combined with the development trends in the AI field and real-world clinical needs, was ultimately formed by gathering the consensus opinions of multidisciplinary experts in radiology, pathology, thoracic surgery, and other fields. The main content covers the application specifications of AI in the three core scenarios of lung cancer screening, diagnosis, and treatment, the technical standards for data collection and algorithm validation, as well as the ethical and regulatory challenges faced at the current stage. It aims to clarify the applicable boundaries of AI as a clinical auxiliary decision support tool, providing scientific guidance and standardized exploration directions for peers currently engaged in or planning to carry out AI-assisted clinical diagnosis, treatment, and translation of lung cancer.
2.Epidemiological characteristics of common viral respiratory infections before and after the COVID-19 pandemic in Huzhou,Zhejiang Province
Min-yi YANG ; Yan LIU ; Su-yi ZHANG ; Qiang WANG ; Guang-tao LIU ; Bo ZHENG ; Xin-yu WANG ; Dan-ni ZHAO ; Jian-yong SHEN ; Wei-bing WANG
Fudan University Journal of Medical Sciences 2025;52(6):819-828
Objective To investigate and compare the epidemiological characteristics of common respiratory viruses among influenza-like illness(ILI)and severe acute respiratory infection(SARI)cases in Huzhou,Zhejiang Province before and after the COVID-19 pandemic,so as to provide a basis for formulating and adjusting the prevention and control strategies for viral respiratory infectious diseases.Methods ILI and SARI cases at two influenza surveillance sentinel hospitals in Huzhou and had throat swab samples collected during Nov 2017 to Feb 2020(pre-COVID-19 pandemic period)and Dec 2022 to Apr 2024(post-COVID-19 mitigation phase)were selected as the participants.Seven common viral respiratory pathogens were tested,including influenza A virus(H1N1 and H3N2 subtypes),influenza B virus(Victoria lineage,FluB),respiratory syncytial virus(RSV),rhinovirus(HRV),adenovirus(ADV),and severe acute respiratory syndrome coronavirus-2(SARS-CoV-2).The positive rates of respiratory pathogens before and after the COVID-19 pandemic were compared across different age groups and different time.Results A total of 7 948 ILI samples and 2 294 SARI samples were included.The overall positive rate of ILI samples increased from 33.6%to 47.1%,primarily due to the increase in influenza and COVID-19 infections;the overall positive rate of SARI samples decreased from 31.4%to 24.8%,mainly due to the reduction in HRV and ADV infections.During the post-COVID-19 mitigation phase,SARS-CoV-2(22.1%),H3N2(12.7%),and FluB(6.0%)were the primary pathogens in ILI samples,while RSV(7.1%),H3N2(5.3%),and HRV(4.5%)dominated in SARI samples.During the post-COVID-19 mitigation phase,the influenza virus circulation period was shortened.Before the COVID-19 pandemic,RSV was mainly detected in autumn and winter,while during the post-COVID-19 mitigation phase,out-of-season RSV epidemics were observed in spring and summer.Co-infection rate in ILI cases increased significantly in the post-COVID-19 mitigation phase,predominantly consisting of co-infections of COVID-19 and influenza A virus,while co-infection rate in SARI cases showed a decline.Conclusion We found important epidemiological changes in respiratory viruses in Huzhou during the post-COVID-19 mitigation phase compared to pre-COVID-19 period,including increased positive rates of influenza and COVID-19,and disruptions to the seasonal patterns of influenza and RSV.The prevention and control strategies should be adjusted in a timely manner based on the monitoring data.
3.Study on the spillover effects of DRG payment reform:Evidence from the level and structure of medical expenses among non-local inpatients
Xue LUO ; Qiang YAO ; Miao ZHANG ; Hai-ni JIANG ; Xiao-dan ZHANG ; Yi PEI
Chinese Journal of Health Policy 2025;18(11):48-56
Objective:This study aims to investigate the spillover effects of the Diagnosis-Related Groups payment reform on medical expenditures.Methods:Based on the medical record data of inpatients in a tertiary Grade A hospital in Wuhan,Hubei Province,the Difference-in-Differences method was applied to estimate the impact of the DRG reform on medical expenditures for non-local patients.Results:After the implementation of DRG payment,the total medical expenses(β=-0.13),out-of-pocket expenses(β=-0.22),drug expenses(β=-0.25),consumable expenses(β=-0.26)decreased significantly.Meanwhile,the reduction ranges of the level and proportion of out-of-pocket expenses for non-local inpatients were significantly larger than those for local inpatients.However,the reduction range of the proportion of drug expenses for non-local inpatients was significantly smaller than that for local inpatients.The gaps between the two groups in terms of the level of out-of-pocket expenses and the proportion of drug expenses gradually narrowed.Conclusion:The DRG payment reform has produced a significant spillover effect,leading to a decrease in the medical expense level and an improvement in the expense structure for non-local inpatients.However,the medical expenses of non-local inpatients remain relatively high.It is suggested to accelerate the inclusion of non-local inpatients in disease-specific payment management and strengthen the coordination between the hospital's internal operation management and the reform of medical insurance payment methods.
4.Investigation of focal spatial patterns and symptom mapping in acute ischemic stroke of different etiologies
Yi ZHOU ; Qiang XU ; Min CAO ; Liang JIANG ; Dajing WANG ; Xiaoqing CHENG ; Jianrui LI ; Wusheng ZHU ; Xindao YIN ; Zhiqiang ZHANG
Chinese Journal of Radiology 2025;59(6):688-695
Objective:To investigate the impact of different etiologies on the spatial distribution pattern of infarcts and the mapping pattern of focal symptoms in acute ischemic stroke (AIS) using a population-based standardized spatial analysis of MRI.Methods:This was a cross-sectional study. Clinical [age, sex distribution, admission National Institutes of Health Stroke Scale (NIHSS) score and 90-day modified Rankin Scale (mRS) score at discharge, etc.] and imaging data of 2 610 patients with AIS attending 9 Medical Centers from January 2015 to December 2021 were retrospectively analyzed. All patients were categorized into 1 718 cases of large artery atherosclerosis (LAA) type, 335 cases of cardioembolism (CE) type, and 557 cases of small artery occlusion (SAO) type according to TOAST typing. All patients underwent diffusion-weighted imaging, and the detected infarct lesions were segmented and aligned to the standardized space using artificial intelligence-assisted methods, and the spatial distribution frequency heatmaps of lesion locations in patients with different TOAST subtypes were plotted and compared with each other by χ2 test. Lesion-symptom image brain maps with different clinical symptoms were further plotted, and differences of lesion-symptom image relationships among different TOAST subtypes were observed and compared with each other by interaction effect. Results:In all patients, the favored sites of infarct lesions were the bilateral middle cerebral artery region in the anterior circulation and the occipital and brainstem regions in the posterior circulation. Compared with the LAA type, the CE type lesions were more likely to occur in the anterior cerebral artery region, the occipital lobe, and the cerebellum posterior, while the SAO type lesions were more likely to occur in the perforator artery supply area. The lesion-symptom mapping results showed that AIS patients with infarct lesions in the frontoparieto-temporal region in the presence of a left middle cerebral artery supply had higher admission NIHSS scores and higher discharge 90-day mRS scores for the LAA type than for the CE type( P<0.05); AIS patients with infarcted lesions in the brainstem region and some cerebellar regions in the presence of vertebrobasilar artery supply had higher admission NIHSS scores and higher discharge 90-day mRS scores for the CE type than for the LAA type( P<0.05). Conclusion:At the population level, brain mapping reveals specific infarct distribution patterns and differences in lesion-symptom mapping patterns of different etiologies AIS patients, providing imaging evidence for the understanding of AIS pathogenetic mechanisms and clinical management.
5.Analysis of short-term efficacy and safety of transnasal endoscopic approach and the combined transconjunctival-endoscopic approach in resection of benign orbital apex lesions
Qiang ZUO ; Zhidi ZHANG ; Jichao ZHOU ; Hailing JIANG ; Yi WANG ; Yinghong ZHANG
Chinese Journal of Otorhinolaryngology Head and Neck Surgery 2025;60(9):1070-1077
Objective:To evaluate the early efficacy and safety of the exclusively transnasal endoscopic approach and the combined transconjunctival-endoscopic approach in the resection of benign orbital apex lesions.Methods:A retrospective analysis was conducted on 51 patients who underwent transnasal endoscopic resection of benign lesions in the orbital apex at Peking University Third Hospital from May 2021 to December 2024. The study population was composed of 17 males and 34 females, with the age of (39.4±12.4) years (range: 4 to 65 years). Pathology diagnoses were identified as orbital cavernous hemangioma (OCH, n=38), schwannoma ( n=8), solitary fibrous tumor ( n=1), mucocele ( n=1), optic nerve sheath meningioma ( n=1), pseudotumor ( n=1), and organized hematoma ( n=1). Two surgical approaches were compared as the exclusively transnasal endoscopic resection ( n=27) and the combined transconjunctival-endoscopic approach (combined approach, n=24). Preoperative and postoperative evaluations were conducted for the best corrected visual acuity (BCVA), visual field, intraocular pressure (IOP), and exophthalmos before and after surgery. Demographic characteristics, tumor features, and postoperative complications were analyzed between the two surgical groups. Differences in Orbital Resection by Intranasal Technique (ORBIT) stage between the two surgical approaches were analyzed. SPSS 27.0 software was used for statistical analysis. Results:Among the 51 patients, 3 schwannomas underwent intracapsular resection (1 via exclusively transnasal endoscopic approach, and 2 via combined approach), and the remaining 48 patients underwent complete tumor resection. Significant postoperative improvements were observed in BCVA, visual field, IOP and exophthalmos ( t value was 2.96, 4.34, 4.85, and 4.63, respectively, all P<0.05). The combined approach required longer operative time but showed comparable intraoperative blood loss. Tumors resected via the combined approach were larger in volume, though not statistically significant. Postoperative complications (e.g., diplopia, mydriasis) were more frequent in the combined approach group but resolved within a short-term period. There was no significant difference in ORBIT stage between the two groups ( P=0.178). Conclusions:Both exclusively transnasal and combined transconjunctival-endoscopic approaches prove safe and effective for benign orbital apex lesions resection. The combined approach ensures complete tumor removal.
6.Effects of Aqueous Extract of Corn Silk Combined with Training on Exercise Function and Glycolipid Metabolism in Mice with Metabolic Syndrome
Yi-lin LIU ; Zi-ling SONG ; Ting ZHOU ; Ji-ping CHEN ; Zi-han LIN ; Yu-xuan ZHANG ; Ji-qiang ZENG ; Shan-rong ZHANG ; Zhi-peng WU ; Chen LU ; Ying ZHU
Progress in Modern Biomedicine 2025;25(15):2411-2420
Objective:To investigate the effects of combination therapy with aqueous extract of corn silk(CS)and training on exercise capacity and glycolipid metabolism in mice with metabolic syndrome(MS).Methods:In this study,db/db mice were used as the animal model of MS.The mice were administered aqueous extract of CS via gavage and subjected to different intensities of training for 12 weeks(3 months).The specific experimental design was as follows:24 db/db mice were randomly divided into four groups on average:negative control group(NC),aqueous extract of CS group(CS),aqueous extract of CS+moderate-intensity training group(CS+MT),and CS aqueous extract of CS+high-intensity training group(CS+HT).The maximum running speed,forelimb grip strength,body weight and fasting blood glucose of mice were measured before and after treatment.After the intervention,oral glucose tolerance test(OGTT)and insulin tolerance test(ITT)were conducted to assess glucose metabolism,while serum triglyceride(TG),total cholesterol(TC),high-density lipoprotein cholesterol(HDL-C),and low-density lipoprotein cholesterol(LDL-C)levels were measured to evaluate lipid metabolism.Results:After 3 months of intervention,there were significant differences in the maximum running speed and forelimb grip strength among the four groups(P<0.05).The maximum running speed and forelimb grip strength of CS group,CS+MT group and CS+HT group were higher than those of NC group(P<0.05).The CS+MT group exhibited higher forelimb grip strength,and the CS+HT group showed higher maximum running speed and forelimb grip strength compared to the CS group(P<0.05),while no significant difference was found between the CS+MT and CS+HT groups(P>0.05).Significant differences in body weight were observed among the four groups after 3 months of intervention(P<0.05).Specifically,the CS+MT and CS+HT groups exhibited significantly lower body weight compared to both the NC and CS groups(P<0.05),with the CS+MT group having the lowest body weight(P<0.05).Fasting blood glucose levels also differed significantly among the groups after 2 and 3 months of intervention(P<0.05).The CS,CS+MT,and CS+HT groups had lower fasting blood glucose levels compared to the NC group(P<0.05),with the CS+MT and CS+HT groups showing the lowest levels(P<0.05).No significant difference was found between the CS+MT and CS+HT groups(P>0.05).After 3 months of intervention,significant differences in the area under the curve(AUC)of OGTT and ITT were observed among the four groups(P<0.05).The AUC of OGTT and ITT were significantly lower in the CS,CS+MT,and CS+HT groups compared to the NC group(P<0.05).The CS+MT and CS+HT groups exhibited the lowest AUC values for both OGTT and ITT(P<0.05),with the CS+MT group showing the lowest AUC for OGTT(P<0.05).Significant differences in serum lipid levels were observed among the four groups after 3 months of intervention(P<0.05).TG,TC,and LDL-C levels were significantly lower,while HDL-C levels were higher in the CS,CS+MT,and CS+HT groups compared to the NC group(P<0.05).The CS+MT group had the lowest TG levels and the highest HDL-C levels compared to the CS+HT group(P<0.05),with no significant differences in TC and LDL-C levels between these two groups(P>0.05).Conclusion:Aqueous extract of CS combined with different intensity training can significantly improve the exercise capacity and glycolipid metabolism of MS mice and reduce body weight,especially CS combined with MT treatment is more effective in improving lipid metabolism.In addition,when combined with HT,aqueous extract of CS can also play an auxiliary role in reducing the side effects of high-intensity exercise and improving the therapeutic effect.
7.AI-enabled prevention and management of nutritional complications in metabolic-bariatric surgery:technological innovation and clinical practice
Jinghao XU ; Danlu LIU ; Qiang DU ; Qianyi WAN ; Rui ZHAO ; Guixiang ZHANG ; Zhong CHENG ; Yi CHEN
Chinese Journal of General Surgery 2025;34(4):632-639
Metabolic-bariatric surgery(MBS)has become an important treatment for pathological obesity and metabolic diseases.However,common postoperative nutritional complications—such as protein-energy malnutrition,iron deficiency anemia,and vitamin B12 deficiency—significantly affect patients' long-term prognosis.Traditional nutritional management models rely on static monitoring and standardized supplementation,which are insufficient to address individual variability and dynamic postoperative changes.Artificial intelligence(AI),through integrating multimodal data(such as biochemical indicators,imaging information,and wearable device monitoring)and intelligent modeling,offers new approaches for dynamic monitoring,risk prediction,and personalized intervention.Based on literature from 2017 to 2025,this article systematically evaluates the application of AI in perioperative nutritional management for MBS,covering key technologies including machine learning,deep learning,and natural language processing.It also analyzes current challenges in clinical translation,such as data fragmentation,lack of model interpretability,and limited long-term validation.In the future,enhanced multi-center collaboration,the development of standardized databases,and explainable models will be essential to advancing nutritional management in MBS from empirical practice to precision medicine.
8.AI-enabled prevention and management of nutritional complications in metabolic-bariatric surgery:technological innovation and clinical practice
Jinghao XU ; Danlu LIU ; Qiang DU ; Qianyi WAN ; Rui ZHAO ; Guixiang ZHANG ; Zhong CHENG ; Yi CHEN
Chinese Journal of General Surgery 2025;34(4):632-639
Metabolic-bariatric surgery(MBS)has become an important treatment for pathological obesity and metabolic diseases.However,common postoperative nutritional complications—such as protein-energy malnutrition,iron deficiency anemia,and vitamin B12 deficiency—significantly affect patients' long-term prognosis.Traditional nutritional management models rely on static monitoring and standardized supplementation,which are insufficient to address individual variability and dynamic postoperative changes.Artificial intelligence(AI),through integrating multimodal data(such as biochemical indicators,imaging information,and wearable device monitoring)and intelligent modeling,offers new approaches for dynamic monitoring,risk prediction,and personalized intervention.Based on literature from 2017 to 2025,this article systematically evaluates the application of AI in perioperative nutritional management for MBS,covering key technologies including machine learning,deep learning,and natural language processing.It also analyzes current challenges in clinical translation,such as data fragmentation,lack of model interpretability,and limited long-term validation.In the future,enhanced multi-center collaboration,the development of standardized databases,and explainable models will be essential to advancing nutritional management in MBS from empirical practice to precision medicine.
9.Establishment of a rapid fluorescence immunochromatographic assay for avian influenza virus subtype H5N6
Hui LI ; Li LIU ; Yi-sheng ZHOU ; Zhi-hong ZHANG ; Qian-qian SI ; Ru-xia WANG ; Zhi-qiang DENG ; Yi-bing FAN ; Liang JIN ; Jie SUN ; Chun-hua YANG
Chinese Journal of Zoonoses 2025;41(3):243-248,283
In view of the characteristics of H5N6 subtype avian influenza virus(AIV)that it has both high pathogenicity and the risk of cross-species transmission,posing a serious threat to the poultry farming industry and public health security,in order to effectively prevent and control the spread of H5N6 avian influenza,a rapid,sensitive and specific detection technolo-gy was established in this study.The specific monoclonal antibodies against the neuraminidase N6 protein of avian influenza A virus subtype H5N6 were obtained through hybridoma and monoclonal antibody technology.These antibodies were coupled and labeled with carboxyl-functionalized fluorescent quantum dots,along with previously prepared specific antibodies against the hemagglutinin H5 protein.A rapid fluorescence immunochromatographic detection method for the H5N6 subtype of avian influ-enza virus was established according to the principle of double-antibody sandwich immunochromatography.This method a-chieved a detection sensitivity of 1 ng/mL for recombinant hemagglutinin H5 subtype protein and 0.1 ng/mL for recombinant neuraminidase N6 subtype protein.Moreover,the method exhibited no cross-reactivity with other influenza subtypes or patho-gens,such as Newcastle disease(ND),infectious bronchitis(IB),and infectious laryngotracheitis(ILT),thus demonstrating good specificity.The method effectively identified the highly pathogenic avian influenza virus H5 subtype and directly distin-guished the H5N6 subtype with good accuracy.The fluorescent quantum dot immunochromatographic typing detection method established herein met the sensitivity,specificity,and accuracy requirements for H5N6 subtype detection,and can be further used for rapid detection of the H5 and H5N6 subtypes of avian influenza virus.
10.Super-minimally invasive laparoscopic surgery:technical innovations and clinical research progress
Pan LU ; Lin CHEN ; Yingjie HUANG ; Kai LI ; Mingchao YI ; Dean MU ; Qiang WANG ; Wei ZHANG
Chinese Journal of General Surgery 2025;34(10):2265-2271
With the continuous evolution of minimally invasive surgical concepts,operative techniques are progressively advancing from"minimal injury"toward"scarless"approaches.Super-minimally laparoscopic surgery(SMLS)is a novel surgical modality developed on the basis of conventional laparoscopic techniques through the innovation and recombination of operative elements,aiming to achieve smaller trauma and improved cosmetic outcomes.Utilizing the umbilical skin fold as a natural scar-concealing site,SMLS establishes no more than two primary operating channels(maximum diameter≤15 mm),supplemented by auxiliary ports≤2 mm in diameter on the abdominal wall.Combined with innovative separable surgical instruments and high-definition visualization systems,this approach provides a systematic solution to key issues such as residual access-site scarring.This review summarizes the development,technical innovations,current clinical applications,and potential aesthetic value of SMLS in the evolution of minimally invasive surgery,aiming to offer theoretical insights and research reference for its future promotion and technical refinement.

Result Analysis
Print
Save
E-mail