1.Prediction of Mismatch Repair Deficiency Status in Endometrial Cancer Using Multiparametric MRI Radiomics and Deep Learning: A Multimodal Model with Preliminary Validation
Liru WANG ; Shangying YANG ; Boyu CHEN ; Fuze CONG ; Xinran LI ; Xinyu LIU ; Huadan XUE ; Zhengyu JIN ; Yang XIANG ; Yonglan HE ; Yuan LI
Medical Journal of Peking Union Medical College Hospital 2026;17(4):976-984
To explore the clinical value of a multimodal predictive model based on multiparametric magnetic resonance imaging(MRI) radiomics combined with deep learning(DL) features for the preoperative noninvasive assessment of mismatch repair-deficient(MMRd) status in endometrial cancer(EC). Patients diagnosed with EC at Peking Union Medical College Hospital from January 2015 to December 2021 were retrospectively enrolled and randomly divided into a training set and a validation set at a ratio of 8∶2. Relevant clinical data were collected, and radiomics features and DL features were extracted from preoperative contrast-enhanced T1-weighted imaging(CE-T1WI), fat-suppressed T2-weighted imaging(fs-T2WI), and diffusion-weighted imaging(DWI) sequences. High-dimensional feature selection and dimensionality reduction were performed sequentially using the recursive feature elimination(RFE) algorithm to generate a radiomics score(Rad-score) and a deep learning score(DL-score), respectively. Multivariate logistic regression was utilized to construct a clinical model, a pure radiomics model, a clinical-radiomics model, and an integrated multimodal model incorporating clinical indicators, Rad-score, and DL-score. Model performance was assessed and compared using area under receiver operating characteristic curve(AUC) and DeLong test. A total of 509 patients were enrolled in this study, comprising 413 in the training cohort and 96 in the validation cohort. Independent predictors: Multivariate analysis indicated that preoperative fasting blood glucose level, histological grade, lymph node metastasis status, Rad-score, and DL-score were all independent significant predictors of MMRd status in EC patients. The integrated multimodal model demonstrated optimal predictive performance with an AUC of 0.699(95% CI: 0.635-0.763) in the training set, which was superior to the clinical model(AUC=0.629, 95% CI: 0.561-0.697) and the pure radiomics model(AUC=0.641, 95% CI: 0.575-0.706). In the validation set, the integrated model maintained good generalizability, achieving an AUC of 0.655(95% CI: 0.535-0.775), and its diagnostic efficacy was higher than that of the clinical model(AUC=0.578, 95% CI: 0.450-0.705) and the pure radiomics model(AUC=0.611, 95% CI: 0.488-0.734). According to the DeLong test, the incorporation of DL features resulted in the clinicalradiomicsdeep learning model performing better than both the clinicalonly model( The initially developed clinical-radiomics-deep learning model exhibits a certain predictive potential for the MMRd status in patients with EC. The inclusion of DL features may help complement the limitations of traditional evaluations, offering a preliminary radiological reference for preoperative non-invasive screening. However, given the current diagnostic performance, its overall accuracy and clinical generalizability warrant further validation in multi-center, large-sample external cohort studies.
2.Current status and prospects of perioperative depression, anxiety and related interventions in lung cancer patients
Xinyu YUAN ; Zijian XU ; Nengke LIN ; Zhiming CHEN ; Zhizhi WANG ; Jiansong XU ; Jinyu CHEN ; Shaobin LI ; Siyang FENG ; Di LU ; Kaican CAI
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery 2026;33(09):1388-1394
Psychological problems are significant factors that contribute to the occurrence of postoperative complications, reduced quality of life, and prolonged hospital stays. Lung cancer patients who require surgery often experience high psychological stress related to both the disease and the treatment, making them more susceptible to depression and anxiety. Therefore, timely intervention to address these psychological issues is crucial for promoting postoperative recovery and improving patients' quality of life. This paper will review the current status, impact, and interventions for depression and anxiety-related psychological problems in lung cancer surgery patients.
3.Analysis of epidemic trend and spatiotemporal distribution characteristics of pertussis in Shandong Province from 2015 to 2024
Lei FENG ; Meng XIE ; Yi LIU ; Yan ZHANG ; Xinyu YUAN ; Aiqiang XU ; Li ZHANG ; Hongfu SUN
Chinese Journal of Preventive Medicine 2025;59(11):1840-1847
Objective:To analyze the epidemic trend and spatiotemporal distribution characteristics of pertussis in Shandong Province from 2015 to 2024.Methods:Data on pertussis cases in Shandong Province from 2015 to 2024 were collected from the China Information System for Disease Control and Prevention. The ArcGIS spatiotemporal method was used to analyze the epidemic trend and spatiotemporal distribution characteristics of pertussis, and determine the hotspots of incidence.Results:From 2015 to 2024, 46 172 cases of pertussis were reported in Shandong Province, with an average annual incidence rate of about 4.60/100 000. The reported incidence rate showed an overall upward trend, and in 2024, the reported incidence rate reached the highest level in history (19.20/100 000) since the implementation of children′s planning immunization. The areas with high incidence rates were mainly located in the central and western regions of Shandong Province, including Jinan city, Liaocheng city, Tai′an city, Zibo city, Binzhou city, Jining city, Dezhou city, Zaozhuang city, and Dongying city. The global spatial autocorrelation analysis showed that the Moran′s I index of incidence rate of pertussis in Shandong Province in each year from 2015 to 2024 was >0.00, showing obvious spatial clustering. Local spatial autocorrelation analysis showed that the "high high" clustering areas were mainly distributed in some counties (cities, districts) in the central and western regions of Shandong Province, which were hotspots for pertussis incidence in Shandong Province. The spatial trend surface analysis showed that the annual incidence rate of pertussis in each year basically decreased from west to east. In the early stage of the north-south direction, there was a curved trend of low north-south and high in the middle. In the middle and later stages, the northern part was mostly in a higher position, indicating that the central and western regions were the high-risk areas for pertussis in Shandong Province. Conclusions:The pertussis epidemic in Shandong Province from 2015 to 2024 has obvious spatiotemporal clustering, and the central and western regions are the key areas for pertussis prevention and control.
4.Treatment of Diabetic Kidney Disease with Active Ingredients of Astragali Radix Based on Inflammation: A Review
Xinze YUAN ; Chenchen LIU ; Shengnan WANG ; Xinyu SUN
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(2):295-302
Diabetic kidney disease (DKD) is one of the common microvascular complications of diabetes mellitus (DM) and a primary cause of chronic kidney disease (CKD) and end-stage renal disease (ESRD). Inflammation is currently a hot topic in exploring the pathogenesis of DKD. Macrophages, T cells, interleukins, tumor necrosis factor, NOD-like receptor protein 3 (NLRP3) inflammasome, Janus kinase/signal transducer and activator of transcription (JAK/STAT) signaling pathway, and nuclear factor-kappa B (NF-κB)-related signaling pathway all play a role in regulating the inflammation of DKD and accelerating its progression. Astragali Radix, a Chinese herbal medicine, is widely used in the treatment of DKD and possesses strong anti-inflammatory effects. Studies have revealed that active ingredients of Astragali Radix, including polysaccharides, astragaloside Ⅳ, total flavonoids, calycosin, and quercetin, can regulate multiple signaling pathways to ameliorate the microinflammatory state and alleviate kidney damage, thereby slowing down the progression of DKD. This article systematically reviews the factors influencing the inflammation in DKD and analyzes recent research findings and mechanisms concerning active ingredients of Astragali Radix in the management of DKD inflammation, aiming to offer novel insights and directions for the prevention, treatment, and research of DKD.
5.Prediction of occupant lumbar spine injuries based on machine learning and analysis of influencing factors
Haiyan LI ; Xinyu ZHANG ; Ting KE ; Yanxin WANG ; Lijuan HE ; Wenle LÜ ; Shihai CUI ; Shijie YUAN
Chinese Journal of Medical Physics 2025;42(3):388-396
Based on CT scan data,a bionic model of lumbar spine injuries with high biofidelity is developed and validated through cadaver experiments.Decoupling the constraint system that affects occupants during collisions due to inertial forces and the subsequent pressure exerted by the seat upon returning to position,a simulated fall experiment is designed.The simulated outcomes are trained and predicted using deep learning algorithms,and the accuracy of the trained neural network prediction model is verified.Key parameters are analyzed for correlation using principal component analysis and cross-reverse methods.The results shows that the predicted lumbar spine injury model obtained from training has high reliability(R2>0.9).Comprehensive analysis reveals that after experiencing axial impact,the L4 vertebral body bears the highest impact load and can be used as a representative measure of lumbar spine injury.Among the environmental variables,the axial force on the L4 lumbar spine is mainly affected by torso mass and fall height,both of which have positive correlations.Torso mass,fall height,and posture angle all have positive effects on internal energy.Conversely,torso mass and fall height have negative correlations with stress.These research findings provide a scientific basis for further elucidating lumbar spine injury mechanisms in intelligent cockpit environments,devising corresponding safety protection measures,and evaluating occupant safety in automobiles.
6.Prediction of uric acid for elderly patients with acute coronary syndrome
Xinyu WANG ; Mulei CHEN ; Hongbin LIU ; Weiming LI ; Hongjiang WANG ; Xin WANG ; Jia LIU ; Yuting YUAN ; Juan WANG
Chinese Journal of Geriatric Heart Brain and Vessel Diseases 2025;27(3):290-293
Objective To investigate the predictive value of uric acid for cardiovascular events in the elderly patients with ACS.Methods An observational follow-up study was conducted on 3440 ACS inpatients and outpatients admitted in the Heart Center of Beijing Chaoyang Hospital and the First Medical Center of Chinese PLA General Hospital from June 2017 to October 2022.According to the occurrence of cardiovascular events,they were divided into a cardiovascular event group(529 patients)and a non-cardiovascular event group(2911 patients).Their clinical data were collected for Cox risk proportional regression analysis.Results The cardiovascular event group had significantly uric acid when compared with the non-cardiovascular event group(P<0.01).Af-ter adjusting the traditional risk factors and plasma biomarkers,uric acid was still a significant predictor for clinical endpoints(HR=2.634,95%CI:1.870-3.744,P<0.01)and for cardiovascu-lar events(HR=1.508,95%CI:1.357-1.660,P<0.01).Furthermore,uric acid was significantly correlated with acute heart failure,cardiovascular death and all-cause death(P<0.01).Conclusion Uric acid is a risk predictor for cardiovascular events in elderly ACS patients,and can provide ear-ly warning information and diagnostic value for acute cardiovascular events.
7.Influence of non-motor symptoms on the change trajectory of early activities of daily living in patients with Parkinson disease
Miao HU ; Pingqiao YUAN ; Xinyu LI ; Mi CUI ; Baoqin WU
Chinese Journal of Practical Nursing 2025;41(28):2213-2219
Objective:To explore the influence of non-motor symptoms on the change trajectory of early activities of daily living in patients with Parkinson disease, and to provide a reference for medical staff to implement intervention measures for people with low levels of activities of daily living in the preclinical stage.Methods:The longitudinal follow-up data of 431 patients with Parkinson disease in the Parkinson's progression Markers Initiative from baseline to five consecutive years after enrollment were selected by convenience sampling method in July 2024, including the scores of aceivities of daily living, the Rapid Eye Movement Sleep Behavioral Disorder Screening Questionnaire, etc. A latent class growth model classified change trajectory of activities of daily living, and the influencing factors were analyzed by univariate and binary Logistic regression.Results:Among the 431 patients, 260 were male and 171 were female, with an average age of (61.30 ± 9.60) years. The scores of activities of daily living of the patients at baseline, 12 months after enrollment, 36 months after enrollment, and 60 months after enrollment were (5.97 ± 4.30), (7.20 ± 4.61), (8.90 ± 5.60), and (10.57 ± 6.93) points, respectively. The model identified two types of trajectories: rapid decline in low activities of daily living group (25.3%, 109/431) and slow decline in lower activities of daily living group (74.7%, 322/431). The binary Logistic regression results showed that apathy ( OR=0.374, 95% CI 0.189-0.739), fatigue ( OR=0.261, 95% CI 0.138-0.495), University of Pennsylvania Smell Identification Test ( OR=1.039, 95% CI 1.005-1.074), the Rapid Eye Movement Sleep Behavioral Disorder Screening Questionnaire ( OR=0.880, 95% CI 0.795-0.973), and the gastrointestinal score of the Scales for Outcomes in PD-Autonomic ( OR=0.724, 95% CI 0.630-0.832) were independent influencing factors for the classification of the change trajectory of activities of daily living in patients with Parkinson disease (all P<0.05). Conclusions:Patients with Parkinson disease exhibit a decreasing trend in early activities of daily living, emphasizing the need for targeted interventions in those with fatigue, apathy, and high Rapid Eye Movement Sleep Behavioral Disorder Screening Questionnaire and Scales for Outcomes in Parkinson disease-Autonomic gastrointestinal scores to possibly decelerate disease advancement.
8.Clinical efficacy of artery-first approach pancreaticoduodenectomy combined with venous resection and reconstruction for pancreatic head malignancies
Xinyu LIU ; Yining KANG ; Shuai YUAN ; Xiaohan SHI ; Suizhi GAO ; Xiaochao KANG ; Kailian ZHENG ; Shiwei GUO ; Gang JIN
Chinese Journal of Pancreatology 2025;25(3):167-174
Objective:To investigate the safety and efficacy of the artery-first approach pancreaticoduo-denectomy (PD) combined with portal vein/superior mesenteric vein (PV/SMV) resection and reconstruction for pancreatic head malignancies.Methods:A retrospective analysis was conducted on 322 patients who underwent PD with PV/SMV resection and reconstruction at the Hepatobiliary Pancreatic Surgery Department of the First Hospital Affiliated to Naval Medical University between January 2016 and December 2022. Patients were divided into the artery-first approach PD group (AFA-PD group, n=165) and standard PD group (SPD group, n=157) based on surgical approach. Baseline characteristics, surgical outcomes, postoperative outcomes, pathological results and survival data were compared between two groups. Results:Compared to the SPD group, the AFA-PD group exhibited significantly reduced intraoperative blood loss (500 ml vs 600 ml), lower rates of obvious intraoperative blood loss (≥1 000 ml: 25.45% vs 40.13%), and decreased transfusion requirements (26.67% vs 52.87%). Postoperatively, the AFA-PD group demonstrated lower incidence of grade B/C pancreatic fistula (10.30% vs 19.75%) and higher textbook outcome achievement (78.79% vs 66.24%). Pathologically, the AFA-PD group achieved superior lymph node yield (20 nodes vs 18 nodes) and higher R 0 resection rates (79.39% vs 64.33%), particularly at the posterior pancreatic margin (96.97% vs 91.72%, P=0.040), SMA margin (92.07% vs 82.17%), and SMV margin (88.48% vs 78.98%). Multivariate logistic regression identified arterial invasion >180°, venous invasion >180°, lymph node metastasis, and the artery-first approach as independent predictors of R 0 resection. The AFA-PD group showed prolonged median survival (19.17 month vs 15.73 month). All aforementioned differences were statistically significant (all P value <0.05). Conclusions:The artery-first approach PD combined with PV/SMV resection and reconstruction is safe and effective for pancreatic head malignancies, significantly improving R 0 resection rates and patients' survival outcomes.
9.Prediction of uric acid for elderly patients with acute coronary syndrome
Xinyu WANG ; Mulei CHEN ; Hongbin LIU ; Weiming LI ; Hongjiang WANG ; Xin WANG ; Jia LIU ; Yuting YUAN ; Juan WANG
Chinese Journal of Geriatric Heart Brain and Vessel Diseases 2025;27(3):290-293
Objective To investigate the predictive value of uric acid for cardiovascular events in the elderly patients with ACS.Methods An observational follow-up study was conducted on 3440 ACS inpatients and outpatients admitted in the Heart Center of Beijing Chaoyang Hospital and the First Medical Center of Chinese PLA General Hospital from June 2017 to October 2022.According to the occurrence of cardiovascular events,they were divided into a cardiovascular event group(529 patients)and a non-cardiovascular event group(2911 patients).Their clinical data were collected for Cox risk proportional regression analysis.Results The cardiovascular event group had significantly uric acid when compared with the non-cardiovascular event group(P<0.01).Af-ter adjusting the traditional risk factors and plasma biomarkers,uric acid was still a significant predictor for clinical endpoints(HR=2.634,95%CI:1.870-3.744,P<0.01)and for cardiovascu-lar events(HR=1.508,95%CI:1.357-1.660,P<0.01).Furthermore,uric acid was significantly correlated with acute heart failure,cardiovascular death and all-cause death(P<0.01).Conclusion Uric acid is a risk predictor for cardiovascular events in elderly ACS patients,and can provide ear-ly warning information and diagnostic value for acute cardiovascular events.
10.Comparison of clinical outcomes and complications between translaminar endoscopic lumbar discectomy and microdiscectomy in the treatment of recurrent lumbar disc herniation
Xinzhi ZHANG ; Xinyu YANG ; Suomao YUAN ; Lianlei WANG ; Yonghao TIAN ; Xinyu LIU
Chinese Journal of Orthopaedics 2025;45(1):1-9
Objective:To compare the clinical efficacy of percutaneous endoscopic interlaminar discectomy (PEID) and posterior small incision microdiscectomy (MD) in the treatment of recurrent lumbar disc herniation.Methods:A retrospective analysis was conducted on the data of 132 patients who underwent revision surgery for recurrent lumbar disc herniation at the same segment at Qilu Hospital of Shandong University between July 2012 and August 2022. The patients were treated with either PEID or MD. The PEID group consisted of 90 patients, including 51 males and 39 females, with a mean age of 42.7±11.3 years and a mean body mass index (BMI) of 23.7±3.4 kg/m 2. The surgical segments were L 4-5 in 38 cases and L 5S 1 in 52 cases. The primary surgeries included open discectomy in 7 cases, laminectomy with bone graft in 3 cases, MD in 35 cases, and PEID in 45 cases. The MD group consisted of 42 patients, including 30 males and 12 females, with a mean age of 41.2±12.6 years and a mean BMI of 24.3±4.7 kg/m 2. The surgical segments were L 4-5 in 19 cases and L 5S 1 in 23 cases. The primary surgeries included open discectomy in 2 cases, laminectomy with bone graft in 1 case, MD in 17 cases, and PEID in 22 cases. The visual analogue scale (VAS) scores for low back pain and leg pain, Oswestry disability index (ODI), immediate postoperative VAS score for surgical wound pain, intraoperative blood loss, surgical wound length, operation duration, length of hospital stay, and various complications before and after surgery were compared between the PEID and MD groups. Results:The operation duration in the PEID group was 81.7±11.3 min, that in the MD group was 85.2±9.5 min, but the difference was not statistically significant ( t=1.740, P=0.081). The intraoperative blood loss in the PEID group was 4.4±2.9 ml, the surgical wound length was 0.9±0.2 cm, and the length of hospital stay was 3.1±1.3 d, all significantly less than those in the MD group (26.6±10.3 ml, 3.4±1.1 cm, and 8.7±1.6 d, respectively), with statistically significant differences ( P<0.05). Both groups were followed up, with a mean follow-up duration of 24.4±5.5 months in the PEID group and 24.5±4.9 months in the MD group, and there was no statistically significant difference between the two groups ( t=0.101, P=0.920). Both the PEID and MD groups showed significant improvements in postoperative VAS scores for leg pain, VAS scores for low back pain, and ODI compared with preoperative values ( P<0.05). Additionally, the VAS score for surgical wound pain on the first postoperative day in the PEID group was 1.2±0.4, which was lower than that in the MD group (2.9±0.6), with a statistically significant difference ( t=19.261, P<0.001). The incidence rates of muscle weakness, postoperative sensory abnormalities, and dural tears in the PEID group were 12%(11/90), 27%(24/90), and 6%(5/90), respectively, significantly lower than those in the MD group [31%(13/42), 40%(17/42), and 33%(14/42), respectively], with statistically significant differences ( P<0.05). However, there were no statistically significant differences between the two groups in the incidence rates of recurrence, residual nucleus pulposus, spinal cord-like hypertension syndrome, subcutaneous wound infection, or intervertebral space infection ( P>0.05). No patients in either group developed retroperitoneal hematoma postoperatively. Conclusion:For patients with recurrent lumbar disc herniation after primary posterior surgery, PEID demonstrates equally excellent clinical efficacy compared with MD, with smaller surgical trauma and a lower incidence of complications.

Result Analysis
Print
Save
E-mail