1.Construction and application of a nursing consultation information system based on information interaction needs
Chan HUANG ; Yanyu CHI ; Yudi MIN ; Peiye CAO ; Jun LIU ; Rongxin ZHENG ; Haiyan ZHANG
Chinese Journal of Nursing 2025;60(6):645-651
Objective To construct a nursing consultation information system based on consultation process and information interaction needs and explore its application effect.Methods The nursing consultation process and information interaction needs were analyzed;the information process,content modules and information interaction interface were designed;the structured records for nursing consultation were developed.The system was officially applied in January 2024.The application effect was evaluated by comparing the completion time of nursing consultations,nursing consultation record quality score,nursing consultation evaluation completion rate,and satisfaction rate before(August 2023 to October 2023)and after(January 2024 to March 2024)the application of the information system.Results After the application of the nursing consultation information system,the implementation rate of nursing consultation for inpatients increased from 1.27% before the application of the system to 1.47%(P=0.019).The completion time of nursing consultation in the whole hospital reduced from 351(225,421)minutes before the application of the system to 310(156,402)minutes(P<0.001),and there was a statistically significant difference in the completion time of nursing consultation among the 3 specialties of intravenous therapy,blood purification,and diabetes nursing(P<0.05).The quality score of nursing consultation records increased from 90.5(82.0,100)points to 95.5(92.0,100)points(P<0.001).The completion rate of nursing consultation evaluation was higher than those before the system application,with statistical significance(21.6% vs 78.4%,P<0.001).Conclusion Nursing consultation information system based on information interaction needs can improve the implementation of nursing consultation for inpatients,shorten the completion time of nursing consultations,improve the writing quality of nursing consultation records and the completion rate of nursing consultation evaluation,and it succeeded in real-time quality monitoring.
2.Expert Consensus on the Ethical Requirements for Generative AI-Assisted Academic Writing
You-Quan BU ; Yong-Fu CAO ; Zeng-Yi CHANG ; Hong-Yu CHEN ; Xiao-Wei CHEN ; Yuan-Yuan CHEN ; Zhu-Cheng CHEN ; Rui DENG ; Jie DING ; Zhong-Kai FAN ; Guo-Quan GAO ; Xu GAO ; Lan HU ; Xiao-Qing HU ; Hong-Ti JIA ; Ying KONG ; En-Min LI ; Ling LI ; Yu-Hua LI ; Jun-Rong LIU ; Zhi-Qiang LIU ; Ya-Ping LUO ; Xue-Mei LV ; Yan-Xi PEI ; Xiao-Zhong PENG ; Qi-Qun TANG ; You WAN ; Yong WANG ; Ming-Xu WANG ; Xian WANG ; Guang-Kuan XIE ; Jun XIE ; Xiao-Hua YAN ; Mei YIN ; Zhong-Shan YU ; Chun-Yan ZHOU ; Rui-Fang ZHU
Chinese Journal of Biochemistry and Molecular Biology 2025;41(6):826-832
With the rapid development of generative artificial intelligence(GAI)technologies,their widespread application in academic research and writing is continuously expanding the boundaries of sci-entific inquiry.However,this trend has also raised a series of ethical and regulatory challenges,inclu-ding issues related to authorship,content authenticity,citation accuracy,and accountability.In light of the growing involvement of AI in generating academic content,establishing an open,controllable,and trustworthy ethical governance framework has become a key task for safeguarding research integrity and maintaining trust within the academic community.This expert consensus outlines ethical requirements across key stages of AI-assisted academic writing-including topic selection,data management,citation practices,and authorship attribution.It aims to clarify the boundaries and ethical obligations surrounding AI use in academic writing,ensuring that technological tools enhance efficiency without compromising in-tegrity.The goal is to provide guidance and institutional support for building a responsible and sustainable research ecosystem.
3.Distribution characteristics of smoking behavior among adult twins in China
Shunkai LIU ; Wenjing GAO ; Weihua CAO ; Jun LYU ; Canqing YU ; Shengfeng WANG ; Tao HUANG ; Dianjianyi SUN ; Chunxiao LIAO ; Yuanjie PANG ; Ruqin GAO ; Min YU ; Jinyi ZHOU ; Xianping WU ; Zhong DONG ; Fan WU ; Dezheng WANG ; Zhihua XU ; Yu LIU ; Jianrui WANG ; Jie YIN ; Shengli YIN ; Liming LI
Chinese Journal of Preventive Medicine 2025;59(7):1090-1096
This study aims to describe the population and regional distribution characteristics of smoking behavior among adult twins in the China Twin Registry (CNTR), as well as the concordance rates for smoking behavior in monozygotic and dizygotic twins, and estimate the heritability. The study population included adult twins in CNTR who had smoking questionnaire data. A random-effects regression model was used to describe the distribution of smoking behavior among different subgroups based on various characteristics. The concordance of smoking behavior between different zygosity groups was calculated, and heritability was estimated. A total of 28 444 twin pairs were included in this study, with an average age of (36.6±12.0) years. Among male twins, 41.2% were current smokers, while only 1.2% of females smoked. Higher smoking rates were observed among male smokers in the 50-59 age group ( z=23.0, P<0.001), northern regions ( z=2.9, P<0.01), rural areas ( z=-5.2, P<0.001), those who were divorced/widowed ( z=3.8, P<0.001), and first-born twins ( z=-4.3, P<0.001), while lower smoking rates were found in those with higher education ( z=-16.1, P<0.001) and unmarried individuals ( z=-16.0, P<0.001). The smoking concordance rate for male monozygotic twins was 69.6%, significantly higher than the 57.3% concordance rate for dizygotic twins ( χ 2=105.0, P<0.05). The heritability of smoking behavior in male twins was estimated at 28.9% (95% CI: 24.3%-33.4%). Stratified analyses showed differences in heritability across regions and age groups: the heritability in northern regions was 32.6% (95% CI: 27.3%-38.0%), higher than the 21.0% (95% CI: 12.4%-29.5%) observed in southern regions; the highest heritability of 35.1% (95% CI: 26.3%-43.9%) was found in the 18-29 age group, with heritability decreasing with age. In conclusion, the smoking rate and influencing factors in the twin population are similar to those in the general population, with unique characteristics, such as higher smoking rates in first-born twins. Genetic factors have a significant impact on smoking behavior.
4.Distribution characteristics and heritability of alcohol consumption behavior in adult twins in China
Yuanchen LI ; Wenjing GAO ; Weihua CAO ; Jun LYU ; Canqing YU ; Shengfeng WANG ; Tao HUANG ; Dianjianyi SUN ; Chunxiao LIAO ; Yuanjie PANG ; Ruqin GAO ; Min YU ; Jinyi ZHOU ; Xianping WU ; Zhong DONG ; Fan WU ; Dezheng WANG ; Zhihua XU ; Yu LIU ; Yanxia MA ; Jie YIN ; Shengli YIN ; Liming LI
Chinese Journal of Epidemiology 2025;46(1):73-80
Objective:To describe the distribution characteristics of alcohol consumption in adult twins in the Chinese National Twin Registry (CNTR), and further explore the influence of genetic factors on alcohol consumption in adult twins.Methods:The subjects of the study were twins registered by CNTR in 11 project areas across China from 2010 to 2018. A total of 56 966 twins (28 483 pairs) aged 18 years and above who answered questions about drinking behavior were included, and the random effect model was used to describe the population and regional distribution characteristics of alcohol consumption. Intra-pair analysis was performed to calculate the concordance rate and heritability of their alcohol consumption.Results:The age of all subjects was (36.6±12.0) years, and current drinkers accounted for 16.6% (9 461/56 966) of all subjects. In men, those aged 50-59 years, those in northern China, those living in rural area, those with low education level and those with high BMI, the proportions of current drinkers were higher. After excluding 468 pairs of twins who had stopped alcohol use and 21 764 pairs of twins who had no drink or had small amount drink, an intra-pair analysis was conducted in 4 929 pairs of same-sex twins, and found that the concordance rate of alcohol consumption was 64.0% (2 059/3 215) in monozygotic twins, and 52.6% (902/1 714) in dizygotic twins, the difference was significant ( P<0.001), and the heritability of alcohol consumption was 24.1% (95% CI: 18.9%- 29.3%). The further stratified analysis found that in southern men, the heritability was highest in those aged 40-49 years (36.1%, 95% CI: 21.6%-50.7%), while in northern men, the heritability was highest in those aged 50-59 years (34.2%, 95% CI: 18.1%-50.3%). Conclusions:In adult twins in China, there were population and regional differences in the distribution of alcohol consumption behavior, and alcohol consumption was influenced by genetic factors, and gender, age and region had potential modifying effects.
5.Consensus on informed consent for orthodontic treatment
Yang CAO ; Bing FANG ; Zuolin JIN ; Hong HE ; Yuxing BAI ; Lin WANG ; Haiping LU ; Zhihe ZHAO ; Tianmin XU ; Weiran LI ; Min HU ; Jinlin SONG ; Jun WANG ; Fang JIN ; Ding BAI ; Xianglong HAN ; Yuehua LIU ; Bin YAN ; Jie GUO ; Jiejun SHI ; Yongming LI ; Zhihua LI ; Xiuping WU ; Jiangtian HU ; Linyu XU ; Lin LIU ; Yi LIU ; Yanqin LU ; Wensheng MA ; Shuixue MO ; Liling REN ; Shuxia CUI ; Yongjie FAN ; Jianguang XU ; Lulu XU ; Zhijun ZHENG ; Peijun WANG ; Rui ZOU ; Chufeng LIU ; Lunguo XIA ; Li HU ; Weicai WANG ; Liping WU ; Xiaoxing KOU ; Jiali TAN ; Yuanbo LIU ; Bowen MENG ; Yuantao HAO ; Lili CHEN
Chinese Journal of Stomatology 2025;60(12):1327-1336
This consensus was developed by the Orthodontic Society of the Chinese Stomatological Association to provide a systematic, scientific, and practical guideline for informed consent in orthodontic care. Orthodontic treatment is typically lengthy, highly individualized, and involves multiple factors such as growth and development, occlusal function, and facial esthetics. Rapid technological advances and diverse risk profiles make the traditional reliance on orthodontist experience or institutional templates insufficient to ensure patients′ full understanding and autonomous decision-making. To address this, the expert panel conducted extensive reviews of domestic and international guidelines, analyzed representative dispute cases, and performed multicenter patient-clinician surveys. Using a multi-round Delphi method, the group established a standardized informed consent framework covering the initial consultation, treatment, and retention phases. The consensus emphasizes that informed consent is not only a fundamental legal and ethical requirement but also a key step in building trust, improving patient compliance, and enhancing treatment satisfaction. Orthodontists should clearly and comprehensively explain treatment plans, potential risks, uncertainties, and associated costs, while respecting the autonomy of patients or guardians, and maintain continuous communication and dynamic evaluation throughout the treatment process. The release of this consensus provides unified and authoritative guidance for clinical orthodontics, helping to standardize informed consent, enhance its transparency, safeguard patient rights, reduce medical risks, and promote high-quality, sustainable development of orthodontic practice.
6.Cordycepin attenuates gentamicin-induced kidney injury by inhibiting oxidative stress and ferroptosis
Lin YUE ; Cao-mei XU ; Min-yan QIAN ; Wen-ting ZHANG ; Xiao ZHENG ; Lu-jun CHEN ; Jing-ting JIANG ; Nan HU
Chinese Pharmacological Bulletin 2025;41(1):65-70
Aim To investigate the effect of cordycepin(COR)on gentamicin(GEN)-induced nephrotoxicity and the molecular mechanism of inhibiting oxidative stress and ferroptosis induced by GEN.Methods The oral SD rats were divided into a control group,GEN group,and GEN+COR group.Following the success-ful setting up of the animal model,the serum creatinine(CR)and urea nitrogen(BUN)levels of rats were measured,and renal tissue injury was assessed using HE staining.In addition,the contents of malondialde-hyde and glutathione in kidney tissues of SD rats in each group were detected,and the expressions of fer-roptosis markers GPX4 and SLC7A11 were analyzed by Western blot.Results Compared with the control group,CR and BUN in GEN-stimulated group signifi-cantly increased(P<0.01),and the level of CR and BUN was effectively reduced after 50 mg·kg-1 COR oral administration.HE results also showed that COR could alleviate the kidney tissue damage caused by GEN.COR could reverse the increase of malondialde-hyde level and the decrease of glutathione level caused by GEN in rat kidney tissue,and COR could restore the decrease of GPX4 and SLC7A11 protein levels induced by GEN.Conclusion COR can reduce GEN-induced kidney injury by inhibiting oxidative stress and ferrop-tosis.
7.Guideline for Adult Weight Management in China
Weiqing WANG ; Qin WAN ; Jianhua MA ; Guang WANG ; Yufan WANG ; Guixia WANG ; Yongquan SHI ; Tingjun YE ; Xiaoguang SHI ; Jian KUANG ; Bo FENG ; Xiuyan FENG ; Guang NING ; Yiming MU ; Hongyu KUANG ; Xiaoping XING ; Chunli PIAO ; Xingbo CHENG ; Zhifeng CHENG ; Yufang BI ; Yan BI ; Wenshan LYU ; Dalong ZHU ; Cuiyan ZHU ; Wei ZHU ; Fei HUA ; Fei XIANG ; Shuang YAN ; Zilin SUN ; Yadong SUN ; Liqin SUN ; Luying SUN ; Li YAN ; Yanbing LI ; Hong LI ; Shu LI ; Ling LI ; Yiming LI ; Chenzhong LI ; Hua YANG ; Jinkui YANG ; Ling YANG ; Ying YANG ; Tao YANG ; Xiao YANG ; Xinhua XIAO ; Dan WU ; Jinsong KUANG ; Lanjie HE ; Wei GU ; Jie SHEN ; Yongfeng SONG ; Qiao ZHANG ; Hong ZHANG ; Yuwei ZHANG ; Junqing ZHANG ; Xianfeng ZHANG ; Miao ZHANG ; Yifei ZHANG ; Yingli LU ; Hong CHEN ; Li CHEN ; Bing CHEN ; Shihong CHEN ; Guiyan CHEN ; Haibing CHEN ; Lei CHEN ; Yanyan CHEN ; Genben CHEN ; Yikun ZHOU ; Xianghai ZHOU ; Qiang ZHOU ; Jiaqiang ZHOU ; Hongting ZHENG ; Zhongyan SHAN ; Jiajun ZHAO ; Dong ZHAO ; Ji HU ; Jiang HU ; Xinguo HOU ; Bimin SHI ; Tianpei HONG ; Mingxia YUAN ; Weibo XIA ; Xuejiang GU ; Yong XU ; Shuguang PANG ; Tianshu GAO ; Zuhua GAO ; Xiaohui GUO ; Hongyi CAO ; Mingfeng CAO ; Xiaopei CAO ; Jing MA ; Bin LU ; Zhen LIANG ; Jun LIANG ; Min LONG ; Yongde PENG ; Jin LU ; Hongyun LU ; Yan LU ; Chunping ZENG ; Binhong WEN ; Xueyong LOU ; Qingbo GUAN ; Lin LIAO ; Xin LIAO ; Ping XIONG ; Yaoming XUE
Chinese Journal of Endocrinology and Metabolism 2025;41(11):891-907
Body weight abnormalities, including overweight, obesity, and underweight, have become a dual public health challenge in Chinese adults: overweight and obesity lead to a variety of chronic complications, while underweight increases the risks of malnutrition, sarcopenia, and organ dysfunction. To systematically address these issues, multidisciplinary experts in endocrinology, sports science, nutrition, and psychiatry from various regions have held multiple weight management seminars. Based on the latest epidemiological data and clinical evidence, they expanded the guideline to include assessment and intervention strategies for underweight, in addition to the core content of obesity management. This guideline outlines the etiological mechanisms, evaluation methods, and multidimensional management strategies for overweight and obesity, covering key areas such as diagnosis and assessment, medical nutrition therapy, exercise prescription, pharmacological intervention, and psychological support. It is intended to provide a scientific and standardized approach to weight management across the adult population, aiming to curb the rising prevalence of obesity, mitigate complications associated with abnormal body weight, and improve nutritional status and overall quality of life.
8.Correlation analysis of clinical features between wet and dry gangrene in diabetic foot.
Yu-Zhen WANG ; Cheng-Lin JIA ; Yong-Kang ZHANG ; Jun-Lin DENG ; Zong-Hao DAI ; Cheng ZHAO ; Ye-Min CAO
China Journal of Orthopaedics and Traumatology 2025;38(9):884-890
OBJECTIVE:
To explore clinical characteristics, lesion sites and correlation differences of different types of diabetic foot gangrene, and to provide evidence-based basis for clinical classification of diabetic foot gangrene.
METHODS:
A retrospective analysis was conducted on 266 patients with newly diagnosed diabetic foot gangrene who were admitted from January 2018 to December 2018, including 183 males and 83 females, aged from 35 to 92 years old with an average of (69.55±10.84) years old, and they were divided into wet gangrene group and dry gangrene group according to the different natures of gangrene. There were 139 patients in wet gangrene group, including 98 males and 41 females, aged from 35 to 90 years old with an average of (68.95±10.93) years old. There were 127 patients in dry gangrene group, including 85 males and 42 females, aged from 38 to 92 years old with an average of (70.21±10.75) years old. Body mass index (BMI), waist-to-hip ratio (WHR), body temperature, skin temperature difference between the affected and healthy sides of the lower extremities, and Wagner grade between two groups were recorded to evaluate symptoms and signs. The white blood cell count (WBC), neutrophil percentage (NEUT%), and C-reactive protein (C-reactive protein), erythrocyte sedimentation rate (ESR), procalcitonin (PCT), and interleukin-6 (IL-6) in peripheral blood between two groups were detected and compared to evaluate the infection status;the severity of diabetic peripheral neuropathy (DPN) was evaluated by using Toronto Clinical Scoring System (TCSS);the degree of pain in patients with diabetic foot gangrene was evaluated by numerical rating scale (NRS); ankle-brachial index (ABI) and popliteal artery blood flow velocity were used to evaluate the degree of arterial lesions. Spearman correlation analysis was used to analyze the correlations between gangrene TCSS, ABI and age, BMI, WHR, body temperature, calf skin temperature difference, WBC, NEUT%, CRP, ESR, PCT, IL-6, NRS, and Wagner classification indicators.
RESULTS:
The body temperature, skin temperature difference between the affected and healthy sides of the lower extremities, Wagner grade, WBC, NEUT%, CRP, ESR, PCT, IL-6, TCSS score, ABI, and popliteal artery blood flow velocity in wet gangrene group were higher than those in dry gangrene group (P<0.01), and BMI, WHR, and NRS score in dry gangrene group were higher than those in wet gangrene group;the differences were all statistically significant (P<0.01). The results of Spearman correlation analysis showed TCSS score of gangrene patients was correlated with body temperature (r=0.214), calf skin temperature difference (r=0.364), WBC (r=0.240), NEUT% (r=0.291), CRP (r=0.347), ESR (r=0.167), PCT (r=0.241), IL-6 (r=0.316), and popliteal fossa arterial blood flow velocity (r=0.261) and Wagner grade (r=0.273) were positively correlated, and the differences were statistically significant (P<0.01). ABI was negatively correlated with age (r=-0.183), BMI (r=-0.252), WHR (r=-0.288), and NRS score (r=-0.354), and the differences were statistically significant (P<0.01).
CONCLUSION
Diabetic foot gangrene is an extremely difficult and critical disease. Wet gangrene has a significant synergic effect with infection and neuropathy, while dry gangrene is closely related to vascular occlusion. The main contradiction of gangrene could be revealed through blood vessels, nerves and infection, providing evidence-based basis for the selection of debridement timing, anti-infection strategies and revascularization, with the aim of reducing the risk of amputation.
Humans
;
Male
;
Female
;
Aged
;
Middle Aged
;
Diabetic Foot/diagnosis*
;
Aged, 80 and over
;
Adult
;
Retrospective Studies
;
Gangrene/physiopathology*
;
C-Reactive Protein
9.Association of Body Mass Index with All-Cause Mortality and Cause-Specific Mortality in Rural China: 10-Year Follow-up of a Population-Based Multicenter Prospective Study.
Juan Juan HUANG ; Yuan Zhi DI ; Ling Yu SHEN ; Jian Guo LIANG ; Jiang DU ; Xue Fang CAO ; Wei Tao DUAN ; Ai Wei HE ; Jun LIANG ; Li Mei ZHU ; Zi Sen LIU ; Fang LIU ; Shu Min YANG ; Zu Hui XU ; Cheng CHEN ; Bin ZHANG ; Jiao Xia YAN ; Yan Chun LIANG ; Rong LIU ; Tao ZHU ; Hong Zhi LI ; Fei SHEN ; Bo Xuan FENG ; Yi Jun HE ; Zi Han LI ; Ya Qi ZHAO ; Tong Lei GUO ; Li Qiong BAI ; Wei LU ; Qi JIN ; Lei GAO ; He Nan XIN
Biomedical and Environmental Sciences 2025;38(10):1179-1193
OBJECTIVE:
This study aimed to explore the association between body mass index (BMI) and mortality based on the 10-year population-based multicenter prospective study.
METHODS:
A general population-based multicenter prospective study was conducted at four sites in rural China between 2013 and 2023. Multivariate Cox proportional hazards models and restricted cubic spline analyses were used to assess the association between BMI and mortality. Stratified analyses were performed based on the individual characteristics of the participants.
RESULTS:
Overall, 19,107 participants with a sum of 163,095 person-years were included and 1,910 participants died. The underweight (< 18.5 kg/m 2) presented an increase in all-cause mortality (adjusted hazards ratio [ aHR] = 2.00, 95% confidence interval [ CI]: 1.66-2.41), while overweight (≥ 24.0 to < 28.0 kg/m 2) and obesity (≥ 28.0 kg/m 2) presented a decrease with an aHR of 0.61 (95% CI: 0.52-0.73) and 0.51 (95% CI: 0.37-0.70), respectively. Overweight ( aHR = 0.76, 95% CI: 0.67-0.86) and mild obesity ( aHR = 0.72, 95% CI: 0.59-0.87) had a positive impact on mortality in people older than 60 years. All-cause mortality decreased rapidly until reaching a BMI of 25.7 kg/m 2 ( aHR = 0.95, 95% CI: 0.92-0.98) and increased slightly above that value, indicating a U-shaped association. The beneficial impact of being overweight on mortality was robust in most subgroups and sensitivity analyses.
CONCLUSION
This study provides additional evidence that overweight and mild obesity may be inversely related to the risk of death in individuals older than 60 years. Therefore, it is essential to consider age differences when formulating health and weight management strategies.
Humans
;
Body Mass Index
;
China/epidemiology*
;
Male
;
Female
;
Middle Aged
;
Prospective Studies
;
Rural Population/statistics & numerical data*
;
Aged
;
Follow-Up Studies
;
Adult
;
Mortality
;
Cause of Death
;
Obesity/mortality*
;
Overweight/mortality*
10.MRI-based radiomics and deep learning model construction:non-invasive differentiation of molecular subtypes in primary intracranial diffuse large B-cell lymphoma
Yanwei ZENG ; Zhijian XU ; Xin CAO ; Kun LÜ ; Huiming LI ; Min GAO ; Shenghong JU ; Jun LIU ; Daoying GENG
China Oncology 2025;35(8):735-742
Background and purpose:Diffuse large B-cell lymphoma(DLBCL)is subclassified into germinal center B-cell-like(GCB)and non-GCB subtypes,which differ in prognosis and treatment response.However,current distinction still relies on invasive pathological assays.This study developed radiomics and deep-learning models based on multiparametric magnetic resonance imaging(MRI)to non-invasively differentiate the two subtypes preoperatively,thereby reducing dependence on histopathological examination.Methods:This study retrospectively included patients with pathologically confirmed DLBCL diagnosed at Huashan Hospital,Fudan University,and other institutions between March 2013 and December 2024.Using multiparametric MRI data,we developed DLBCL-subtype classification models that combined 4 radiomics-based machine-learning algorithms:support vector machine(SVM),logistic regression(LR),Gaussian process(GP)and Naive Bayes(NB),with 3 deep-learning architectures[densely-connected convolutional networks 121(DenseNet121),residual network 101(ResNet101)and EfficientNet-b5].Additionally,two radiologists with different experience levels independently classified DLBCL on MRI in a blinded fashion.Model and radiologist performance were quantified using the area under the receiver operating characteristic curve(AUC),accuracy(ACC),and F1-score to evaluate their ability to distinguish GCB from non-GCB subtypes.This study was approved by the Ethics Committee of Huashan Hospital of Fudan University(No.KY2024-663),and all patients signed informed consents.Results:A total of 173 patients were enrolled(55 with GCB subtype and 118 with non-GCB subtype).Radiomics and deep learning methods effectively distinguished DLBCL subtypes.Among these,the GP radiomics model(based on T1-CE+T2-FLAIR+ADC sequences)and DenseNet121 deep learning model(based on T1-CE+T2-FLAIR+ADC sequences)demonstrated optimal performance.Both achieved excellent results on the internal validation set(GP:AUC=0.900,ACC=0.896,F1=0.840;DenseNet121:AUC=0.846,ACC=0.854,F1=0.774)and maintained robustness on the external validation set.Furthermore,the classification efficacy of the optimal AI model surpassed that of experienced radiologists(highest physician AUC=0.678).Conclusion:Radiomics and deep-learning models based on multiparametric MRI features can effectively differentiate GCB from non-GCB subtypes of DLBCL.Among them,GP and DenseNet121 exhibit outstanding performance,especially when integrating multi-sequence feature sets for classifying DLBCL subtypes on complex imaging data.

Result Analysis
Print
Save
E-mail