1.A Comparative Study of Artificial Intelligence-based Classification Versus Manual Classification of Medical Adverse Events: Taking the DeepSeek Large Language Model As an Example
Rui WANG ; Xutong TAN ; Congpu ZHAO ; Shuchang WANG ; Zheng CHEN ; Xiaojun MA ; Zhiling CAI
Medical Journal of Peking Union Medical College Hospital 2026;17(3):828-833
To analyze the application value of artificial intelligence (AI)-based classification in the categorization of medical adverse events. Medical adverse events reported to the Adverse Event Reporting System of Peking Union Medical College Hospital from September 1, 2023, to August 31, 2024, were retrospectively collected as the study subjects. After de-identification of adverse events meeting the inclusion criteria, conventional manual classification and AI-based classification using a large language model (DeepSeek-R1 Full-Context Internet Edition) were performed. The time required for classification using both methods was recorded, and the consistency and discrepancies between the two methods were compared. Using manual classification as the gold standard, the accuracy of AI-based classification was comprehensively evaluated. A total of 273 medical adverse events were analyzed. Manual classification took 38 838 seconds in total, with an average of 14.22 seconds per event. AI-based classification took 600 seconds in total, with an average of 2.19 seconds per event. The two methods showed consistent classification in 202 events and inconsistent classification in 71 events, yielding an overall agreement rate of 73.99% and a Kappa coefficient of 0.646 (95% CI: 0.575-0.717), with a standard error of 0.0362. Using manual classification as the gold standard, AI-based classification achieved accuracy ranging from 80% to 100%, precision from 30% to 100%, recall from 40% to 100%, F1 scores from 0.46 to 0.79, and specificity from 46% to 98%. Notably, AI-based classification demonstrated balanced and overall excellent performance in the categorization of device-related and drug-related adverse events. The DeepSeek large language model can assist in improving the efficiency of medical adverse event classification, showing promising application potential, particularly in the categorization of device-related and drug-related adverse events.
2.Influencing factors and prognosis of postoperative complications in elderly(≥75 years)patients with renal cell carcinoma after laparoscopic surgery
Zhiying WU ; Min QIU ; Dameng PAN ; Xiaojun TIAN ; Lei ZHAO ; Hongxian ZHANG ; Shudong ZHANG ; Lulin MA
Journal of Modern Urology 2026;31(6):503-509
Objective To analyze the postoperative complications and survival outcomes of elderly patients with renal cell carcinoma undergoing laparoscopic surgery, and to identify the influencing factors, so as to provide reference for improving the safety of laparoscopic surgery in such patients. Methods A retrospective analysis was conducted on the clinical, surgical, and pathological data of 153 patients aged ≥75 years who underwent laparoscopic nephrectomy for renal cell carcinoma at our hospital during 2012 and 2025.Logistic regression analyses were performed to identify factors influencing postoperative complications, and a nomogram was constructed and validated to predict the complications.Kaplan-Meier method was used to draw the survival curve, and the effects of different surgical approaches on the prognosis and the survival difference in the age subgroups (75-<80 years, ≥80 years) were analyzed.Cox regression analyses were conducted to determine factors affecting survival outcomes. Results Among the 153 patients, 15 developed postoperative complications, including 5 severe cases. Multivariate logistic regression identified Charlson Comorbidity Index (CCI) ≥3 and prolonged operation time as independent risk factors for postoperative complications (P<0.05).The C-index of the logistic regression model constructed based on these factors (age, CCI≥3 and operation time) was 0.77 (95%CI:0.64-0.90), with an average absolute error of 1.6%.Subgroup analysis revealed superior overall survival in patients aged 75-<80 years undergoing partial nephrectomy compared to radical nephrectomy (P=0.005 6).No statistically significant difference in overall survival was observed among patients ≥80 years who received different surgical approaches (P=0.062).Multivariate Cox regression analysis identified preoperative low albumin levels, preoperative renal insufficiency, tumor diameter>4 cm, and pathological stage as independent risk factors for overall survival (P<0.05). Conclusion Laparoscopic surgery is safe and effective for elderly patients with renal cell carcinoma, with survival outcomes correlated to nutritional status, renal function, tumor size and pathological staging.Patients aged ≥80 years still derive surgical benefit, and no survival differences exist between different surgical approaches in this age group.
3.Differences in inflammatory indicators and prognostic factors between pulmonary and extrapulmonary ARDS caused by sepsis
Honglei QI ; Xiaojuan YANG ; Xiaojun YANG ; Xigang MA ; Xiaohong WANG ; Huan DING ; Jinyuan ZHU
Chongqing Medicine 2025;54(6):1300-1306
Objective To investigate the influencing factors of pulmonary and extrapulmonary acute re-spiratory distress syndrome(ARDS)caused by sepsis.Methods A total of 126 patients with ARDS admitted to the Department of Critical Care Medicine,General Hospital of Ningxia Medical University,from January 2022 to June 2024 were selected.Patients were divided into pulmonary ARDS and extrapulmonary ARDS groups based on the etiology of ARDS.General data,inflammatory indicators,and prognostic outcomes were compared between the two groups.COX regression analysis was used to identify prognostic factors.Results A-mong the 126 patients,72 were diagnosed with pulmonary ARDS and 54 with extrapulmonary ARDS.The pulmonary ARDS group had significantly lower SOFA scores,fewer organ dysfunctions,a lower incidence of arrhythmia,shorter mechanical ventilation duration,higher Murray scores,and higher Charlson Comorbidity Index(CCI)compared to the extrapulmonary ARDS group(P<0.05).Inflammatory markers,including pro-calcitonin(PCT),C-reactive protein(CRP),interleukin(IL)-4,IL-6,IL-10,and tumor necrosis factor-α(TNF-α),were significantly lower in the pulmonary ARDS group,while interferon-γ(INF-γ)levels were higher(P<0.05).For pulmonary ARDS,CCI and TNF-α were identified as independent risk factors for prog-nosis(P<0.05),with the combination of CCI and TNF-α yielding the highest predictive accuracy(AUC=0.81,95%CI:0.71-0.91).For extrapulmonary ARDS,CCI and CRP were independent risk factors(P<0.05),and their combination achieved the highest predictive performance(AUC=0.91,95%CI:0.84-0.98).Conclusion Inflammatory profiles between pulmonary and extrapulmonary ARDS caused by sepsis are different.CCI and TNF-α are independent risk factors for mortality in pulmonary ARDS,while CCI and CRP are independent risk factors in extrapulmonary ARDS.
4.Effect of transcutaneous auricular vagus nerve stimulation combined with dual-task training on upper limb func-tion in patients with ischemic stroke
Congcong ZOU ; Xiaojun WANG ; Jinrong MA ; Shangbo LU ; Yong DING ; Hani WANG ; Jianfei SONG
Chinese Journal of Rehabilitation Theory and Practice 2025;31(5):513-519
Objective To explore the effect of transcutaneous auricular vagus nerve stimulation(taVNS)combined with dual-task training(DTT)on upper limb function recovery in patients with ischemic stroke.Methods From January to October,2024,60 ischemic stroke patients with upper limb dysfunction admitted to Zhejiang Rehabilitation Medical Center were selected and randomly divided into control group(n=30)and observation group(n=30).Both groups received conventional rehabilitation training.The control group underwent sham-taVNS combined with DTT,while the observation group received active taVNS combined with DTT,for four weeks.Before and after treatment,they were assessed with Fugl-Meyer Assessment-Upper Extremities(FMA-UE),Action Research Arm Test(ARAT),modified Barthel Index(MBI)and motor-evoked potential(MEP)tests.Results The FMA-UE scores,ARAT scores,MBI scores,MEP amplitude and MEP latency improved in both groups af-ter treatment(|t|>3.670,P<0.01),and were superior in the observation group than in the control group(|t|>3.081,P<0.01).Conclusion The combination of taVNS and DTT can significantly improve upper limb function,enhance activities of daily living,and promote neurological recovery in patients with ischemic stroke.
5.Analysis of Inpatient Mortality Cases in a Tertiary General Hospital in Beijing Based on Diagnosis-related Groups
Yufei ZHANG ; Jiong ZHOU ; Xiaojun MA ; Xiaoran WANG
Medical Journal of Peking Union Medical College Hospital 2025;16(3):697-702
To analyze inpatient mortality cases in a tertiary general hospital in Beijing based on diagnosis-related groups (DRG), with the aim of providing references for healthcare quality management. We retrospectively collected DRG data of hospitalized patients admitted to a tertiary general hospital in Beijing from January 1, 2015, to December 31, 2023. Mortality cases were analyzed according to mortality risk stratification, with a focus on the temporal trends, departmental distribution, and DRG composition of low/medium-low mortality risk cases. Among 927 304 DRG-classified hospitalizations, 2346 cases resulted in death (stratified into 130 low-risk, 209 medium-low-risk, 411 medium-high-risk, and 1596 high-risk cases), yielding an overall mortality rate of 0.25%. The mortality rates were 0.02% (130/680 939) in the low-risk group and 0.16% (209/130 449) in the medium-low-risk group. From 2015 to 2023, the mortality rate showed a significant downward trend ( Critical care units accounted for the highest proportion of mortality cases, with surgical patients having complications/comorbidities representing the major DRG-related factors for low/medium-low-risk deaths. Hospitals should prioritize these findings by identifying areas for improvement, implementing multidisciplinary case reviews, and strengthening patient safety measures.
6.Molecular mechanisms of microbial mercury resistance and their prospective applications in remediation of mercury-contaminated soils.
Di WANG ; Huan LUO ; Xiaojun SHI ; Zhenlun LI ; Ying MA
Chinese Journal of Biotechnology 2025;41(4):1323-1339
Mercury (Hg)-contaminated soil poses a significant threat to the environment and human health. Hg-resistant microorganisms have the ability to survive under the stress of inorganic and organic Hg and effectively reduce Hg levels and toxicity. Compared to physical and chemical remediation methods, microbial remediation technologies have garnered increasing attention in recent years due to their lower cost, remarkable efficacy, and minimal environmental impact. This paper systematically elucidates the molecular mechanisms of Hg resistance in microbes, with a focus on their potential applications in phytoremediation of Hg-contaminated soils through plant-microbe interactions. Furthermore, it highlights the critical role of microbes in enhancing the effectiveness of transgenic plants for Hg remediation, aiming to provide a theoretical foundation and scientific basis for the bioremediation of Hg-contaminated soils.
Mercury/toxicity*
;
Biodegradation, Environmental
;
Soil Pollutants/isolation & purification*
;
Soil Microbiology
;
Plants, Genetically Modified/metabolism*
;
Bacteria/genetics*
7.Recombinant yeast-cell microcapsules carrying the DNA vaccine against enterotoxigenic Escherichia coli.
Xiafang ZHAO ; Lihong DU ; Baoxia MA ; Shaona JIA ; Yufei LIU ; Yufei ZHU ; Xiaotao MA ; Xiaojun YANG ; Kun XU
Chinese Journal of Biotechnology 2025;41(6):2388-2404
The enterotoxigenic Escherichia coli (ETEC) infection is a major factor restricting the development of animal husbandry. However, the abuse of antibiotics will lead to the antibiotic residues and emergence of antibiotic-resistant bacteria. The existing vaccines face challenges in stimulating intestinal immunity, demonstrating limited prevention effects. Therefore, it is indispensable to develop a new vaccine that is safe and suitable as a feed additive to activate intestinal immunity. This study constructed yeast-cell microcapsules (YCM) carrying the DNA vaccine against ETEC by genetic engineering. Furthermore, animal experiments were carried out to explore the regulatory effects of feeding YCM on the intestinal immune system and intestinal microbiota. Saccharomyces cerevisiae was selected as the oral delivery vehicle (microcapsules) of the DNA vaccine. The codon-optimized nucleic acid sequence of K88, the main antigen of mammal-derived ETEC, was synthesized, and the yeast shuttle vector containing the corresponding DNA vaccine expression cassette was constructed by DNA recombination. The recombinant strain of YCM was prepared by transforming JMY1. Additionally, the characteristics of the YCM strain and its feasibility as an oral vaccine were comprehensively evaluated by the fluorescence reporter assay, gastrointestinal fluid tolerance assay, intestinal epithelial cell adhesion assay, intestinal retention assessment, antiserum detection, and intestinal microbiota detection. The experimental results showed that the DNA vaccine expression cassette was expressed in mammals, and the recombinant strain of YCM could tolerate up to 8 hours of gastrointestinal fluid digestion and had good adhesion to intestinal epithelial cells. The results of mouse feeding experiments indicated that the recombinant strain of YCM could stay in the intestinal tract for at least two weeks, and the DNA vaccine expression cassette carried by YCM entered the intestinal immune system and triggered an immune response to induce the production of specific antibodies. Moreover, feeding YCM recombinant bacteria also improved the abundance of gut microbiota in mice, demonstrating a positive effect in regulating intestinal flora. In summary, we prepared the recombinant strain of YCM carrying the DNA vaccine against ETEC and comprehensively evaluated its characteristics and feasibility as an oral vaccine. Feeding the recombinant YCM could induce specific immune responses and regulate intestinal microbiota. The findings provide a reference for the immunoprevention of ETEC-related animal diseases.
Animals
;
Enterotoxigenic Escherichia coli/genetics*
;
Saccharomyces cerevisiae/metabolism*
;
Vaccines, DNA/genetics*
;
Mice
;
Escherichia coli Infections/immunology*
;
Escherichia coli Vaccines/genetics*
;
Capsules
;
Mice, Inbred BALB C
;
Female
8.Clinical Decision-making for Anti-infective Therapy in Patients with Positive Blood Cultures
Medical Journal of Peking Union Medical College Hospital 2025;16(5):1096-1101
Bloodstream infections(BSIs) are associated with high morbidity and mortality. The widespread emergence of antimicrobial resistance has significantly increased the complexity of treating BSIs, making the development of precise antimicrobial treatment strategies based on positive blood culture results a critical clinical challenge. Additionally, it is imperative to systematically correct traditional misconceptions to optimize treatment outcomes and alleviate the pressure of antimicrobial selection. This article provides an in-depth exposition across the following dimensions, including bloodstream infection diagnosis, infection source identification, antimicrobial treatment regimen formulation, etc., to optimize the diagnostic and therapeutic process for patients with positive blood culture results.
9.Chinese expert consensus on integrated case management by a multidisciplinary team in CAR-T cell therapy for lymphoma.
Sanfang TU ; Ping LI ; Heng MEI ; Yang LIU ; Yongxian HU ; Peng LIU ; Dehui ZOU ; Ting NIU ; Kailin XU ; Li WANG ; Jianmin YANG ; Mingfeng ZHAO ; Xiaojun HUANG ; Jianxiang WANG ; Yu HU ; Weili ZHAO ; Depei WU ; Jun MA ; Wenbin QIAN ; Weidong HAN ; Yuhua LI ; Aibin LIANG
Chinese Medical Journal 2025;138(16):1894-1896
10.Development and validation of a prediction score for subtype diagnosis of primary aldosteronism.
Ping LIU ; Wei ZHANG ; Jiao WANG ; Hongfei JI ; Haibin WANG ; Lin ZHAO ; Jinbo HU ; Hang SHEN ; Yi LI ; Chunhua SONG ; Feng GUO ; Xiaojun MA ; Qingzhu WANG ; Zhankui JIA ; Xuepei ZHANG ; Mingwei SHAO ; Yi SONG ; Xunjie FAN ; Yuanyuan LUO ; Fangyi WEI ; Xiaotong WANG ; Yanyan ZHAO ; Guijun QIN
Chinese Medical Journal 2025;138(23):3206-3208

Result Analysis
Print
Save
E-mail