Objective:To construct and validate an artificial intelligence diagnostic system based on multi-feature integration for diagnosing gastric whitish neoplastic lesions under white-light endoscopy.Methods:Gastroscopic images from Renmin Hospital of Wuhan University and the Seventh Medical Center of Chinese PLA General Hospital were collected from November 2012 to July 2021. A total of 823 images of gastric whitish lesions from 267 patients were finally selected. Five white-light endoscopic features associated with gastric whitish lesions were selected through a literature search, including lesion location, boundary clarity, surface texture, roundness, and depression status. Images with manually annotated features were used to train machine learning models, with the optimal model selected as the multi-feature fitting diagnostic system, which assigned diagnostic weights to each feature. A conventional deep learning model was trained with the same dataset. The diagnostic performance of the two models were compared, and eight endoscopists of varying expertise were invited to participate in human-machine comparisons.Results:Accuracy, sensitivity, and specificity of the multi-feature fitting diagnostic system were 82.11% (101/123), 78.43% (40/51), and 84.72% (61/72), respectively. Feature weights in descending order were depression (0.71), lesion location (0.11), surface roughness (0.08), boundary clarity (0.06), and subcircular shape (0.04). The diagnostic accuracy of the system was significantly higher than that of non-expert endoscopists (82.11% VS 74.31%, Z=-2.785, P=0.008) and comparable to that of expert endoscopists (82.11% VS 83.20%, Z=-0.696, P=0.700). There was no significant difference in accuracy between the multi-feature fitting diagnostic system and the traditional deep learning model [82.11% (101/123) VS 82.93% (102/123), P=1.000]. Conclusion:The feature-weighted artificial intelligence diagnostic system for gastric whitish neoplastic lesions demonstrates clinically relevant diagnostic accuracy under white-light endoscopy.

BACKGROUND:Medial tibial stress syndrome is a common chronic lower limb injury among runners,potentially linked to the"muscle traction theory."However,this hypothesis has not been fully confirmed.OBJECTIVE:To investigate whether the contraction characteristics of the soleus,posterior tibialis,and flexor digitorum longus muscles during running are correlated with stress levels at the medial tibial border and influence the occurrence and development of medial tibial stress syndrome using musculoskeletal simulation systems and finite element analysis.METHODS:Motion capture data of six subjects running at different speeds were input into the Anybody Modeling System for inverse dynamic simulations during the stance phase at running speeds of 2.5,3.5,and 4.5 m/s.The calculated boundary conditions were combined with finite element models to examine the stress distribution on the medial tibia.Partial least squares regression was used to analyze the correlation between independent variables(muscle force and elastic potential energy)and the dependent variable(tibial stress).RESULTS AND CONCLUSION:(1)There were statistically significant differences in tibial stress levels across different speeds during the stance phase(1％-50％)(P=0.044,F=3.834,ηp2=0.040).(2)Among the three speeds,the average correlation between soleus muscle force and tibial stress was the highest(r=12.999),followed by the correlation between posterior tibialis muscle force and tibial stress(r=-10.735),flexor digitorum longus muscle force(r=-9.751),posterior tibialis elastic potential energy(r=8.012),soleus elastic potential energy(r=9.076),and flexor digitorum longus elastic potential energy(r=-4.782).(3)The results indicate that with increasing running speed,tibial stress levels rise.The contraction of the soleus muscle and the release of absorbed elastic potential energy during running have a significant impact on the development of medial tibial stress syndrome,whereas the roles of the posterior tibialis and flexor digitorum longus muscles have been overestimated.Overall,the study supports the hypothesis that the contraction of the soleus muscle plays a crucial role in the development of medial tibial stress syndrome,consistent with the"muscle traction"hypothesis.

Objective:To investigate the clinical characteristics of hospital-acquired pulmonary embolism(HA-PE) and identify the risk factors associated with in-hospital mortality.Methods:The retrospective cohort study was used. The clinical and follow-up data were collected of 60 patients with primary diseases who were admitted to the General Surgery Ward of Beijing Friendship Hospital affiliated to Capital Medical University from January 2015 to December 2021. These patients were planned for surgical treatment and were diagnosed with HA-PE during their hospitalization. A total of 60 patients were included in the study, comprising 18 males and 42 females.The age was (69.7±10.9)years, ranging from 45 to 91 years. Baseline clinical parameters were collected and recorded. Measurement data with normal distribution were expressed as mean ± standard deviation ( ± s), measurement data with skewed distribution were expressed as M( Q1, Q3), and count data were expressed as examples and percentages(%). Univariate Logistic regression analysis was used to screen out the risk factors related to in-hospital PE mortality, and multivariate logistic regression model was used to analyze the independent risk factors related to death of HA-PE patients. Results:Fourteen patients did not undergo surgery for primary disease due to HA-PE, the time from admission to HA-PE diagnosis was 7.0(4.0, 10.0) days. 20 patients were underwent implantation of an inferior vena cava filter, all filters used were retrievable. Successful removal of filters was achieved in 10 patients, the duration of filter placement was recorded as (19.6±3.4) days. All patients had high-risk sPESI scores, and 6 patients died from HA-PE during their hospitalization period. Multivariate analysis revealed that symptoms such as chest tightness and dyspnea ( OR=1.83, 95% CI: 1.45-10.15, P=0.039); Elevated TNI levels( OR=1.75, 95% CI: 1.46-7.78, P=0.036) and severe thrombocytopenia ( OR=3.6, 95% CI: 2.46-6.06, P=0.009) were independently correlated with in-hospital PE mortality. Conclusions:The in-hospital mortality rate of HA-PE patients is comparable to primary pulmonary embolism. Following standardized treatment, both the recurrence and mortality rates of pulmonary embolism within one year are significantly reduced. Notably, chest tightness and dyspnea, elevated TNI levels, and severe thrombocytopenia are independent risk factors for in-hospital mortality in HA-PE patients.

BACKGROUND:Medial tibial stress syndrome is a common chronic lower limb injury among runners,potentially linked to the"muscle traction theory."However,this hypothesis has not been fully confirmed.OBJECTIVE:To investigate whether the contraction characteristics of the soleus,posterior tibialis,and flexor digitorum longus muscles during running are correlated with stress levels at the medial tibial border and influence the occurrence and development of medial tibial stress syndrome using musculoskeletal simulation systems and finite element analysis.METHODS:Motion capture data of six subjects running at different speeds were input into the Anybody Modeling System for inverse dynamic simulations during the stance phase at running speeds of 2.5,3.5,and 4.5 m/s.The calculated boundary conditions were combined with finite element models to examine the stress distribution on the medial tibia.Partial least squares regression was used to analyze the correlation between independent variables(muscle force and elastic potential energy)and the dependent variable(tibial stress).RESULTS AND CONCLUSION:(1)There were statistically significant differences in tibial stress levels across different speeds during the stance phase(1％-50％)(P=0.044,F=3.834,ηp2=0.040).(2)Among the three speeds,the average correlation between soleus muscle force and tibial stress was the highest(r=12.999),followed by the correlation between posterior tibialis muscle force and tibial stress(r=-10.735),flexor digitorum longus muscle force(r=-9.751),posterior tibialis elastic potential energy(r=8.012),soleus elastic potential energy(r=9.076),and flexor digitorum longus elastic potential energy(r=-4.782).(3)The results indicate that with increasing running speed,tibial stress levels rise.The contraction of the soleus muscle and the release of absorbed elastic potential energy during running have a significant impact on the development of medial tibial stress syndrome,whereas the roles of the posterior tibialis and flexor digitorum longus muscles have been overestimated.Overall,the study supports the hypothesis that the contraction of the soleus muscle plays a crucial role in the development of medial tibial stress syndrome,consistent with the"muscle traction"hypothesis.

Objective:To construct and validate an artificial intelligence diagnostic system based on multi-feature integration for diagnosing gastric whitish neoplastic lesions under white-light endoscopy.Methods:Gastroscopic images from Renmin Hospital of Wuhan University and the Seventh Medical Center of Chinese PLA General Hospital were collected from November 2012 to July 2021. A total of 823 images of gastric whitish lesions from 267 patients were finally selected. Five white-light endoscopic features associated with gastric whitish lesions were selected through a literature search, including lesion location, boundary clarity, surface texture, roundness, and depression status. Images with manually annotated features were used to train machine learning models, with the optimal model selected as the multi-feature fitting diagnostic system, which assigned diagnostic weights to each feature. A conventional deep learning model was trained with the same dataset. The diagnostic performance of the two models were compared, and eight endoscopists of varying expertise were invited to participate in human-machine comparisons.Results:Accuracy, sensitivity, and specificity of the multi-feature fitting diagnostic system were 82.11% (101/123), 78.43% (40/51), and 84.72% (61/72), respectively. Feature weights in descending order were depression (0.71), lesion location (0.11), surface roughness (0.08), boundary clarity (0.06), and subcircular shape (0.04). The diagnostic accuracy of the system was significantly higher than that of non-expert endoscopists (82.11% VS 74.31%, Z=-2.785, P=0.008) and comparable to that of expert endoscopists (82.11% VS 83.20%, Z=-0.696, P=0.700). There was no significant difference in accuracy between the multi-feature fitting diagnostic system and the traditional deep learning model [82.11% (101/123) VS 82.93% (102/123), P=1.000]. Conclusion:The feature-weighted artificial intelligence diagnostic system for gastric whitish neoplastic lesions demonstrates clinically relevant diagnostic accuracy under white-light endoscopy.

BACKGROUND: Lung cancer is a disease with a high incidence rate in Yunnan province, yet there is a paucity of large-scale studies on its clinical epidemiology. This research aims to investigate the epidemiological characteristics of patients who underwent lung cancer surgery at Yunnan Cancer Hospital over the past decade, thereby providing a theoretical basis for the prevention and treatment of lung cancer. METHODS: Clinical data were collected from 15,967 patients who underwent lung cancer surgery at Yunnan Cancer Hospital between 2013 and 2022. A statistical analysis was conducted on the patients' general data, surgical information, pathological types of lung cancer, and other clinical epidemiological characteristics. RESULTS: Among the 15,967 cases of lung cancer, 46.3% were male and 53.7% were female, with the male-to-female ratio ranging from 0.68 to 1.61:1. The median age was 56 years (interquartile range: 49-63), and 37.0% of the patients were in the age group of 50-59 years. Since 2017, there has been an annual increase in the proportion of patients under the age of 60 years. The smoking status of the patients showed that 28.1% were smokers and 71.9% were non-smokers. Qujing city accounted for 41.4% and Kunming city for 23.2% of the cases in Yunnan province, with 29.6% of patients originating from Xuanwei and Fuyuan areas of Qujing city. The distribution of affected lung lobes was as follows: right upper lobe 28.2%, right middle lobe 6.3%, right lower lobe 20.1%, left upper lobe 22.7%, and left lower lobe 16.4%. The use of thoracoscopic surgery increased from 30.8% to 96.3%, with single-port thoracoscopic surgery comprising 61.3%. Lobectomy was performed in 64.2% of cases, wedge resection in 17.2%, and segmentectomy in 12.2%. The proportion of lobectomy decreased from 83.1% to 46.1%. The proportion of patients in stages 0-I increased from 43.5% to 82.8%, while stages II-IV decreased from 56.5% to 17.2%. Adenocarcinoma increased from 75.6% to 88.3%, and squamous cell carcinoma decreased from 21.5% to 8.6%. Among adenocarcinoma patients, 60.9% were female. Among sguamous cell carcinoma patients, 90.6% were male. The peak age for adenocarcinoma was 50-59 years, and for squamous cell carcinoma, it was 60-69 years. The smoking rate was higher among squamous cell carcinoma patients (65.9%) compared to adenocarcinoma patients (22.3%). Adenocarcinoma patients had a higher proportion in stages 0-I (76.3%), while squamous cell carcinoma patients were more prevalent in stages II-III (64.1%). CONCLUSIONS The findings indicate an increasing proportion of female patients with adenocarcinoma, a younger age of onset, a higher proportion of non-smoking lung cancer patients, and an increased proportion of stages 0-I lung cancer. These trends may reflect the epidemiological characteristics of patients undergoing lung cancer surgery in Yunnan and surrounding areas over the past decade.
Humans ; Female ; Male ; Lung Neoplasms/pathology* ; Middle Aged ; China/epidemiology* ; Aged ; Adult ; Aged, 80 and over

Objective:To evaluate the value of ultrasonography in the differential diagnosis of cystic biliary atresia (CBA) and choledochal cyst (CC) in infants.Methods:CBA or CC children <3 months of age diagnosed by surgery in Union Hospital, Tongji Medical College, Huazhong University of Science and Technology from 2015 to 2023 were collected, and the differences in general conditions and ultrasound manifestations between CBA group and CC group were retrospectively analyzed.Results:Among the 55 children, 30 were in CBA group and 25 were in CC group. The mean length diameter and width diameter of cysts in the CBA group were about (1.45±1.05)cm and (1.04±0.73)cm, respectively, which were significantly smaller than those in the CC group (5.41±2.98)cm and (3.21±2.90)cm ( P<0.001). The incidence of fibrous plaque (50.0%, 15/30) and abnormal gallbladder morphology (73.3%, 22/30) in the CBA group was significantly higher than that in the CC group [4.0%(1/25) and 16.0%(4/25), respectively]. The incidence of intrahepatic biliary mud deposition (52.0%, 13/25) and intrahepatic biliary duct dilation (64.0%, 16/25) in the CC group was significantly higher than that in the CBA group [0, 3.3%(1/30), respectively]. Conclusions:There are some differences in ultrasonography between CBA and CC children. The length and width of cysts in children with CC are significantly larger than those in children with CBA, and biliary mud deposits or intrahepatic bile duct dilatation are seen in the cysts. The incidence of fibrous plaque and abnormal gallbladder morphology in CBA children is significantly higher than that in CC children.

Objective:To analyze the correlation of poorly differentiated cluster(PDC)grade with clinicopathological features and prognosis of patients with colon cancer.Methods:Hematoxylin-eosin-stained specimens and data from 102 patients with colon cancer who under-went surgery at the Affiliated Hospital of Anhui West Health Vocational College between December 2016 and July 2021 were analyzed in this study.The PDC grades of tumor tissues were determined in all colon cancer cases.Additionally,associations between the PDC grade and clinicopathological features of patients were analyzed via Chi-square test and Logistic regression analysis,whereas the association between the PDC grade and patient prognosis was evaluated using Cox regression analysis.Results:In total,52 cases were identified as PDC G1,14 as PDC G2,and 36 as PDC G3.Tumor budding(TB)was independently and positively associated with PDC,whereas tumor infiltrating lympho-cytes(TIL)were independently and negatively associated with PDC(all P<0.05).Lymph node metastasis or presence of cancerous nodules(hazard ratio[HR]=2.377;95%confidence interval[CI]=1.237-4.568;P=0.009),distant metastasis(HR=7.455;95%CI=2.597-21.399;P<0.001),and the PDC grade(HR=2.095;95%CI=1.099-3.994;P=0.025)were independent risk factors for colon cancer progression.Conclu-sions:Our findings suggest that both TIL and TB affect the colon cancer PDC grade.Therefore,evaluating the PDC grade in cancer tissues can facilitate the prognostic stratification of patients with colon cancer.

As the backbone force of China's social and economic construction, the health status of workers is closely related to the nation's productivity and social development. Currently, cancers have become one of the major diseases threatening the health of workers. However, there are still many shortcomings in the cancer screening services for the workers. To standardize cancer screening services for workers, ensure the quality of screening services, and improve the overall screening effectiveness, 19 institutions, including Peking Union Medical College Hospital of the Chinese Academy of Medical Sciences, have jointly formulated the Group Standard "Specification for service of cancer screening for workers (T/CHAA 023-2023)". This standard follows the principles of "legality, scientific rigor, advancement, and feasibility" and combines the frontier scientific advances in cancer screening. It clarifies the relevant requirements for service principles, service design, service delivery, service management, service evaluation, and improving worker cancer screening. Implementing this group standard will help connect the common screening needs of workers, employers, and cancer screening service providers, standardize the screening process, improve screening quality, and ultimately increase the early diagnosis rate and survival rate of cancer patients. Consequently, this group standard will help safeguard workers' health rights and interests, ensure the labor force resources, promote the comprehensive coordinated and sustainable development of society, and contribute to realizing the "Healthy China 2030" strategic policy.

Lung cancer associated with cystic airspaces (LCCA) is a type of lung cancer characterized by the presence of cystic cavities in or around the tumor on imaging. Due to its high potential for misdiagnosis or underdiagnosis, the prognosis of LCCA patients is poor, necessitating further large-scale clinical studies to elucidate its characteristics. Currently, four imaging classification systems exist, and there has been a progressive increase in attention towards LCCA, particularly with regard to the study of its imaging features. The results indicate a correlation between the pathological features and imaging findings of LCCA; however, research on driver gene mutations and molecular subtyping associated with lung cancer remains insufficient. Due to the challenges associated with early diagnosis and the poorer prognosis compared to general types of lung cancer, this paper comprehensively reviews the research progress on LCCA, including its definition, etiology, pathogenesis, imaging features, histological and pathological features, treatment, and prognosis, aiming to serve as a valuable resource for clinical decision-making.
.
Humans ; Lung Neoplasms/genetics* ; Tomography, X-Ray Computed/methods* ; Prognosis