Objective To evaluate the predictive ability and clinical application value of artificial intelligence (AI) systems in the benign and malignant differentiation and pathological type of pulmonary nodules, and to summarize clinical application experience. Methods A retrospective analysis was conducted on the clinical data of patients with pulmonary nodules admitted to the Department of Thoracic Surgery, Second Hospital of Lanzhou University, from February 2016 to February 2025. Firstly, pulmonary nodules were divided into benign and non-benign groups, and the discriminative abilities of AI systems and clinicians were compared. Subsequently, lung nodules reported as precursor glandular lesions (PGL), microinvasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) in postoperative pathological results were analyzed, comparing the efficacy of AI systems and clinicians in predicting the pathological type of pulmonary nodules. Results In the analysis of benign/non-benign pulmonary nodules, clinical data from a total of 638 patients with pulmonary nodules were included, of which there were 257 males (10 patients and 1 patient of double and triple primary lesions, respectively) and 381 females (18 patients and 1 patient of double and triple primary lesions, respectively), with a median age of 55.0 (47.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis of the two groups of variables showed that, except for nodule location, the differences in the remaining variables were statistically significant (P<0.05). Multivariate logistic regression analysis showed that age, nodule type (subsolid pulmonary nodule), average density, spicule sign, and vascular convergence sign were independent influencing factors for non-benign pulmonary nodules, among which age, nodule type (subsolid pulmonary nodule), spicule sign, and vascular convergence sign were positively correlated with non-benign pulmonary nodules, while average density was negatively correlated with the occurrence of non-benign pulmonary nodules. The area under the receiver operating characteristic curve (AUC) of the malignancy risk value given by the AI system in predicting non-benign pulmonary nodules was 0.811, slightly lower than the 0.898 predicted by clinicians. In the PGL/MIA/IAC analysis, clinical data from a total of 411 patients with pulmonary nodules were included, of which there were 149 males (8 patients of double primary lesions) and 262 females (17 patients of double primary lesions), with a median age of 56.0 (50.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis results showed that, except for gender, nodule location, and vascular convergence sign, the differences in the remaining variables among the three groups of PGL, MIA, and IAC patients were statistically significant (P<0.05). Multinomial multivariate logistic regression analysis showed that the differences between the parameters in the PGL group and the MIA group were not statistically significant (P>0.05), and the maximum diameter and average density of the nodules were statistically different between the PGL and IAC groups (P<0.05), and were positively correlated with the occurrence of IAC as independent risk factors. The average AUC value, accuracy, recall rate, and F1 score of the AI system in predicting lung nodule pathological type were 0.807, 74.3%, 73.2%, and 68.5%, respectively, all better than the clinical physicians’ prediction of lung nodule pathological type indicators (0.782, 70.9%, 66.2%, and 63.7% respectively). The AUC value of the AI system in predicting IAC was 0.853, and the sensitivity, specificity, and optimal cutoff value were 0.643, 0.943, and 50.0%, respectively. Conclusion This AI system has demonstrated high clinical value in predicting the benign and malignant nature and pathological type of lung nodules, especially in predicting lung nodule pathological type, its ability has surpassed that of clinical physicians. With the optimization of algorithms and the adequate integration of multimodal data, it can better assist clinical physicians in formulating individualized diagnostic and treatment plans for patients with lung nodules.

ObjectiveTo investigate the correlation between genetic polymorphism of heat shock proteins 70 (HSP70) and susceptibility to occupational noise-induced hearing loss (ONIHL). Methods A total of 229 ONIHL workers were selected as the case group and 229 healthy workers with similar age, years of noise exposure, and noise exposure levels were selected as the control group using the case-control study method. Occupational health examinations were conducted on both groups, and peripheral blood of individuals was collected for DNA extraction. The genotypes of three single nucleotide polymorphisms of the HSP70 were detected using the MassArray system. Results The allele frequency distribution of HSP70 rs2227956, rs1043618, and rs1061581 in the control group was in Hardy-Weinberg equilibrium (all P>0.05). The genotype and allele frequency distribution of rs2227956 was significantly different between the two groups (all P<0.05), while no significant difference was found for rs1043618 and rs1061581 (all P>0.05). After adjusting for age, years of noise exposure, individual noise exposure level, smoking, and drinking, individuals with AG and AG+GG genotypes of rs2227956 had a higher risk of ONIHL than those with AA genotype (all P<0.05). The risk of ONIHL was higher in individuals with G allele of rs2227956 than in those with A allele (P<0.05). No correlation was found between rs1043618 and rs1061581 polymorphisms and the risk of ONIHL (all P>0.05). Conclusion The rs2227956 polymorphism of the HSP70 gene is correlated with susceptibility to ONIHL in noise-exposed workers, and the G allele is a risk factor for ONIHL in this population.

Objective To investigate the dynamic changes in infarct core volume in patients with acute ischemic stroke due to large vascular occlusion(AIS-LVO)after treatment and analyze its related factors.Methods A total of 180 elderly AIS-LVO patients admitted to our department from January 2022 to December 2023 were recruited in this study.The age,past history,baseline National Institutes of Health Stroke Scale score,time from onset to admission,time from onset to CT perfusion imaging,and collateral circulation status of all patients were collected.After treat-ment,their final infarct core volume was 16.39±4.35 ml,and the growth rate of infarct core was 0.75±0.23 ml/h,and according to the growth rate,89 cases were assigned into group A(＞0.7 ml/h)and 91 cases into group B(≤0.7 ml/h).The dynamic changes in infarct core volume after treatment was evaluated with infarct core growth rate,and multivariate logistic regression was used to analyze the related factors affecting the dynamic changes.Results Group A had signifi-cantly higher baseline NIHSS score,longer time from onset to admission,longer time from onset to CT perfusion[14.52±2.40 vs 13.60±3.28,P=0.033;(3.16±0.44)h vs(3.01±0.39)h,P=0.017;(4.14±0.36)h vs(4.03±0.36)h,P=0.042],and lower collateral circulation score when compared with group B(2.11±0.35 vs 2.66±0.47,P=0.001).Multivariate logistic regression analysis showed that time from onset to admission(OR=0.311,95％CI:0.123-0.781,P=0.013)and collateral circulation score(OR=17.911,95％CI:7.717-41.943,P=0.001)were influencing factors for the change of infarct core volume in AIS-LVO patients after treatment.Conclusion The infarct core volume in patients with AIS-LVO presents dynamic changes after treatment,and it is related to the time from onset to admission and collateral circulation score.

Objective:To examine the expression of human leukocyte antigen G (HLA-G) in the peripheral blood and cancerous tissues of patients with papillary thyroid carcinoma (PTC) .Methods:The expression of soluble HLA-G (sHLA-G) in the peripheral blood of 50 individuals with PTC (PTC group) , 25 patients with benign thyroid tumors (BTT group) from Department of Thyroid and Breast Surgery, Beilun branch of the First Affiliated Hospital of Zhejiang University and 20 healthy controls (healthy control group) from physical examination center was assessed by ELISA. Immunohistochemical examination of HLA-G levels was also performed on tissue specimens from patients in the PTC and BTT groups, and their correlation with clinicopathological features of thyroid cancer was analyzed. SPSS 19.0 was used for statistical analysis. The measurement data of normal distribution were tested by two independent samples t test. Chi square test was used to compare the rates between the two groups. Results:The sHLA-G expression in peripheral blood was 21.33 (±5.54) , 22.73 (±4.99) , and 18.29 (±4.43) ng/mL in the preoperative PTC, BTT, and healthy control groups, respectively. Compared to the healthy group, sHLA-G levels were considerably higher in the PTC and BTT groups, with statistically significant differences (totally P < 0.05) . There was no significant difference in statistically sHLA-G levels between the BTT and PTC groups ( P > 0.05) . The positive HLA-G expression rate in PTC tissues was 78% (39/50) . There was no evidence of HLA-G expression in common tissues adjacent to PTC. HLA-G was not expressed in benign tumors. HLA-G was linked with the PTC tumor diameter, and the rate of positive expression was considerably greater with tumor diameters >1 cm than with those ≤1 cm ( P<0.05) . The rate of HLA-G positive expression was not significantly correlated with sex, age, multiple foci, extra-glandular invasion, metastasis of lymph nodes, or the TNM stage in PTC individuals ( P > 0.05) . Conclusions:HLA-G is significantly expressed at high levels in PTC tissues, is correlated with the tumor diameter, and may probably have a significant role in this disease. Peripheral blood sHLA-G may be associated with thyroid tumorigenesis, and its value in PTC requires further verification.

Objective:To develop a curriculum integration attitude assessment scale for students in nursing school of China and to test its reliability and validity.Methods:The first draft of scale was developed with the methods of literature review and Delphi technique. From June to November 2018, we selected 575 interns from three nursing schools undergoing curriculum integration in Heilongjiang Province as respondents by convenience sampling. The reliability and validity of this scale were tested.Results:The curriculum integration attitude assessment scale for nursing students included three dimensions and 20 items. The content validity index of the total scale was 0.943 and that of items ranged from 0.8 to 1.0. Exploratory factor analysis extracted three factors including value tendency, participation tendency and emotional tendency with 77.602% for the cumulative variance contribution.The Cronbach's α coefficient of the total scale was 0.928 and that of dimensions ranged from 0.942 to 0.954; the Spearman-Brown coefficient of the total scale was 0.879 and that of dimensions ranged from 0.921 to 0.933; the test-retest reliability coefficient of the total scale was 0.789 and that of dimensions ranged from 0.549 to 0.779.Conclusions:The curriculum integration attitude assessment scale for nursing students has high reliability and validity which can be used to assess nursing students' attitude with curriculum integration so as to provide a scientific basis for further optimize curriculum system and a reference for similar teaching assessment.

Objective: To understand the prevalence of gynecologic diseases among married female workers. Methods: The data of married female workers who underwent occupational health examination in a physical examination center from January to December 2017 were collected. The relationship between the detection of common gynecological diseases, age and occupational types examined by gynecological routine, TCT, breast B-mode ultrasound, uterus and appendix B-mode ultrasound were analyzed. Results: Among the 1142 female workers, the total detection rate of reproductive tract infections was 67.25% (768/1142), the total detection rate of breast-related diseases was 75.22% (859/1142) ; the total detection rate of gynecological tumors and benign lesions was 14.71% (168/1142). The detection rate of breast hyperplasia was the highest 67.08% (766/1142), followed by vaginitis 51.66% (590/1142). Among the abnormalities detected in breast-related diseases, gynecological tumors and benign lesions, the highest detection rate was found in public institutions (85.66% and 27.13%), and the lowest was found in factory workers (70.24% and 7.89%). With the increase of age, the detection rate of breastrelated diseases (breast hyperplasia, breast cyst), gynecological tumors, benign lesions (uterine myoma), and Nessler's cyst abnormalities in married female workers increased (χ²_trend=7.647、21.653、107.411、53.802, P<0.05), while the detection rate of columnar epithelium of cervix decreased (χ²_trend=7.404, P<0.05). There was no significant difference in the total detection rate of reproductive tract infectious diseases (vaginitis, cervical polyps, cervical hypertrophy) among married famale workers of different ages (P<0.05) . Conclusion The common gynecological diseases of married female workers are affected by many factors such as age and occupation. Health examination and health education should be carried out regularly to reduce the incidence of gynecological diseases among female workers according to different ages and occupations.

Objective: To investigated the effect of long-term low-concentration mixed benzene exposure on peripheral blood of male workers. Methods: A case-control study was conducted to select 452 male workers exposed to mixed benzene (benzene, toluene, xylene) for five consecutive years from January 2012 to December 2016 in an automobile manufacturer as case group, and 438 male administrative and logistic managers who underwent physical examination during the same period as control group. The peripheral blood of the two groups was tested and compared, and the occupational hazards in the workplace were detected. Results: There were low dose exposure to mixed benzene in the enterprise, but the test results met the occupational exposure limit requirements. During the five years from 2010 to 2016, between the two groups of workers, the mean values of WBC, NEUT, RBC and Hb were statistically different (P<0.05). There was no statistical difference (P>0.05) in the mean value of PLT. The abnormal rate of main peripheral blood indexes in the control group was higher than that in the exposed group. There were significant differences in NEUT, RBC and Hb (P< 0.05), but no significant differences in WBC and PLT (P>0.05). Conclusion It can not be concluded that long-term low-concentration mixed benzene exposure can cause the change of peripheral blood index.

Objective To explore the integration of the digital imaging medical records system and the hospital information system ( HIS), for a hospital-wide information platform for digital medical records management. Methods All the medical records were classified as " to copy and not to copy" by sampling, and an item corresponding table was developed for both HIS medical record files and imaging records copying types. The imaging copying system for paper-based medical records only covers those must-copy ones, while those medical record files without need to be copied were directly transcoded via the interface to the imaging medical records system from the HIS system. This makes digital imaging medical records complete. Results The digital imaging medical record system is thus integrated, and the cost of making imaging medical records was sizably reduced without compromising the quality and integrity of medical records. Conclusions Imaging medical records produced by copying paper-based ones are integrated with those directly sent via the interface to the imaging medical records system, forming complete digital imaging records, at a much lower cost.

Objective: To discuss the prevalence and influential factors of stroke among population in Jiangxi Province. Methods: Four cities in urban areas and four counties in rural areas were selected firstly, in which two districts or townships were selected; and then three communities or villages were chosen from each district and township, respectively, using the simple random sampling (SRS) method. Finally 15 269 subjects aging 15 years old or above, living in Jiangxi Province ≥6 months were randomly selected to participate in this survey from November 2013 to August 2014. Information of population characteristics, life behavior way, individual disease history were collected through questionnaire survey, and height, weight, waist circumference, blood pressure, body fat rate, visceral fat index and so on were measured by instruments. Risk factors of stroke prevalence were analyzed by the unconditioned logistic regression analysis. Results: A total of 15 269 participants (6 267 males) from 15 364 eligible participants were included in the statistical analysis. Out of which, 7 793 participants came from urban areas, and their average age was (53.04±17.91) years old. In this study, 226 stroke patients (117 males) were found among15 269 participants, including 122 urban participants and 104 rural participants, whose average age was (67.76±9.74) years old. The prevalence of stroke was 1 480.12/100 000 in 2014, which was separately 1 866.92/100 000 and 1 210.84/100 000 among males and females. The prevalence of people aging (45-49) years old was 413.79/100 000 (6/1 450) , while which among people aging 75 years old and above was 3 311.62/100 000 (61/1 842) . The prevalence of stroke among residents in Jiangxi presented an uprising tendency with age increasing (linear-by-linear association χ²=62.23, P<0.01). The research showed that when other influencing factors including gender, BMI, waist circumference, pulse-pressure difference, VAI, and sleeping time in non-working days were controlled, hypertensive patients had a higher risk of stroke than people without hypertension (OR=6.88, 95%CI: 4.90-9.67), drinkers had a higher risk of stroke than non-drinkers (OR=1.56, 95%CI: 1.17-2.08), compared with people <65 years old, people aged 65-74 years old and ≥75 years old had a higher risk of stroke, the value of OR (95%CI) were 1.88 (1.36-2.59) and 1.97 (1.39-2.80), respectively, compared with people with normal body fat percentage, people whose body fat percentage on high side and people who with high body fat percentage had a higher risk of stroke, the value of OR (95%CI) were 1.71 (1.18-2.48) and 1.74 (1.18-2.56), respectively, people with sleep time >8 h had a higher risk of stroke than those with sleep time of 6-8 h. Conclusion There was a high stroke prevalence among residents in Jiangxi province. Hypertension, drinking, age, BFP and sleep duration were associated with stroke prevalence. Corresponding measures for high-risk population and risk factors should be strengthened to prevent and control the stroke.