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.

Background Current evidence on whether occupational sulfur dioxide (SO₂) exposure affects the risk of hypertension is still limited, and the research results of the effect of environmental SO₂ exposure on risk of hypertension remain inconsistent. Objective To analyze the association between self-reported occupational exposure to SO₂ and the risk of hypertension, and the potential dose-response relationship between the years of exposure to SO₂ and the risk of hypertension. Methods Based on the Jinchang cohort, a nested case-control study design was adopted. A total of 841 newly diagnosed hypertension patients were followed up as the case group, and the control group was selected with 1∶1 individual matching based on non-occupational factors and occupational factors, respectively. The former matching conditions included age ±2 years old, same gender, working age ±2 years, and home address in the same sub-district. The latter was limited to working in the same workshop on the basis of the former conditions. Finally, the former included 717 controls and the latter included 488 controls. A unified questionnaire was used to collect general demographic characteristics, lifestyle habits, history of diabetes, family history of hypertension, and information on occupational exposure to SO₂ (self-reported history of occupational exposure to SO₂ and years of exposure to SO₂). Conditional logistic regression model was used to analyze the association between occupational exposure to SO₂ and hypertension, and the dose-response relationship between the years of SO₂ exposure and the risk of hypertension. Results In the nested case-control study matching with the non-occupational factors, the OR of hypertension in workers with self-reported occupational exposure to SO₂ was 2.39 (95%CI: 1.68-3.39); while when matching with the occupational factors, the OR of hypertension in workers with self-reported occupational exposure to SO₂ was 1.48 (95%CI: 1.04-2.12). The results of the dose-response relationship showed that as the SO₂ exposure years increased from 1-9 years, 10-19 years, 20-29 years, and 30 years and above, in the nested case-control study matching with non-occupational factors, the ORs of hypertension were 1.85 (95%CI: 0.68-5.08), 1.46 (95%CI: 0.58-3.67), 1.64 (95%CI: 1.00-2.67), and 4.95 (95%CI: 2.63-9.31), respectively; in the nested case-control study matching with occupational factors, the ORs of hypertension were 0.98 (95%CI: 0.40-2.41), 1.84 (95%CI: 0.72-4.70), 1.37 (95%CI: 0.82-2.29), and 2.44 (95%CI: 1.37-4.35), respectively. The two dose-response relationships were positive by χ² trend test (P_trend<0.05). Conclusion Self-reported occupational exposure to SO₂ is associated with the risk of hypertension in the study population, and the hypertension risk increases with the increase of SO₂ exposure years.

Objective: The relationship between outdoor temperature and blood pressure (BP) has been inconclusive. We analyzed data from a prospective cohort study in northwestern China to investigate the effect of outdoor temperature on BP and effect modification by season. Methods: A total of 32,710 individuals who participated in both the baseline survey and the first follow-up in 2011-2015 were included in the study. A linear mixed-effect model and generalized additive mixed model (GAMM) were applied to estimate the association between outdoor temperature and BP after adjusting for confounding variables. Results: The mean differences in systolic blood pressure (SBP) and diastolic blood pressure (DBP) between summer and winter were 3.5 mmHg and 2.75 mmHg, respectively. After adjusting for individual characteristics, meteorological factors and air pollutants, a significant increase in SBP and DBP was observed for lag 06 day and lag 04 day, a 0.28 mmHg (95% Conclusions This study demonstrated a significant negative association between outdoor temperature and BP in a high-altitude environment of northwest China. Moreover, BP showed a significant seasonal variation. The association between BP and temperature differed by season and individuals' demographic characteristics (age, gender, BMI), unhealthy behaviors (smoking and alcohol consumption), and chronic disease status (CVDs, hypertension, and diabetes).
Adult ; Blood Pressure/physiology* ; China/epidemiology* ; Environmental Exposure/statistics & numerical data* ; Female ; Humans ; Male ; Middle Aged ; Prospective Studies ; Risk Factors ; Seasons ; Temperature

China/epidemiology* ; Diabetes Mellitus, Type 2/etiology* ; Dyslipidemias/epidemiology* ; Humans ; Incidence ; Prospective Studies

Objective: To explore the association between fatty liver and type 2 diabetes mellitus (T2DM) in the baseline-population of Jinchang cohort study. Methods: Data from all the participants involved in the baseline-population of Jinchang cohort study was used, to compare the risks of T2DM in fatty liver and non fatty liver groups and to explore the interaction between family history or fatty liver of diabetes and the prevalence of T2DM. Results: Among all the 46 861 participants, 10 574 were diagnosed as having fatty liver (22.56%), with the standardized rate as 20.66%. Another 3 818 participants were diagnosed as having T2DM (8.15%) with standardized rate as 6.90%. The prevalence of T2DM increased in parallel with the increase of age (trend χ(2)=2 833.671, trend P<0.001). The prevalence of T2DM in the fatty liver group was significantly higher than that in the non-fatty liver group, both in men or women and in the overall population. Compared with the group of non-fatty liver, the risks of T2DM in fatty liver group were seen 1.78 times higher in males, 2.33 times in women and 2.10 times in the overall population, after adjustment for factors as age, levels of education, smoking, drinking, physical exercise, BMI, family history of diabetes and some metabolic indicators (pressure, TC, TG, uric acid, ALT, AST, gamma-glutamyl transferase). Date from the interaction model showed that fatty liver and family history of diabetes present a positive additive interaction on T2DM (RERI=1.18, 95%CI: 0.59-1.78; AP=0.24, 95%CI: 0.14-0.34; S=1.43, 95%CI: 1.21-1.69). Conclusions: Fatty liver could significantly increase the risk of T2DM and a positive additive interaction was also observed between fatty liver and family history of diabetes on T2DM. It was important to strengthen the prevention program on T2DM, in order to effectively control the development of fatty liver.
China/epidemiology* ; Cohort Studies ; Diabetes Mellitus, Type 2/ethnology* ; Fatty Liver/ethnology* ; Female ; Humans ; Male ; Non-alcoholic Fatty Liver Disease/epidemiology* ; Prevalence ; Risk Factors

Environmental exposure to heavy metals has been linked to a wide range of human health hazards. We detected the levels of 15 metals in urine samples from 500 representative sub-samples in an ongoing occupational cohort study (Jinchang Cohort) to directly evaluate metal exposure levels. Fifteen metals, namely As, Ba, Be, Cd, Cs, Cr, Co, Cu, Pb, Mn, Ni, Se, Tl, U, and Zn, were detected by inductively coupled plasma quadruple mass spectrometry. The results showed that median creatinine adjustment and geometric mean urinary metal levels were higher in the heavy metal-exposed group, except Se and Zn, than other reported general or occupational populations. Further studies should address the effects of heavy metals on human health.
China ; Cohort Studies ; Environmental Pollutants ; blood ; Humans ; Metals, Heavy ; blood ; Occupational Exposure

OBJECTIVETo understand the current status of the disease burden of liver cancer in Jinchang cohort.

METHODSAll the liver cancer death data from 2001 to 2013 and medical records of liver cancer cases from 2001 to 2010 in Jinchang cohort were collected for the analyses of the mortality, standardized mortality, potential years of life lost (PYLL) and working PYLL (WPYLL) associated with liver cancer. Spearman correlation and the average growth rate were used to analyze the trends.

RESULTSA total of 207 liver cancer deaths occurred in Jinchang cohort from 2001 to 2013, accounting for 16.68% of total cancer deaths. There were 259 liver cancer inpatients, accounting for 6.79% of the total cancer cases inpatients, in which 83 died (32.05%). Liver cancer death mainly occurred in males, accounting for 88.89%, and the liver cancer deaths in females accounted for 11.11%. The standardized mortality rate was 42.32/100,000 in males and 15.31/100,000 in females. The growth rate of liver cancer mortality was 5.62% from 2001 to 2013. Liver cancer deaths mainly occurred in age groups 60-69 years (26.57%) and 50-59 years (24.15%). The PYLL was 2906.76 person-years, the average PYLL was 14.04 years. The WPYLL was 1477.00 person-years and the average WPYLL was 7.14 years. The direct economic burden of liver cancer was 6270.78 Yuan per person, 301.75 Yuan per day. The average stay of hospitalization was 21.32 days.

CONCLUSIONThe mortality rate of liver cancer is increasing and the disease burden is still heavy.

Aged ; China ; epidemiology ; Cohort Studies ; Cost of Illness ; Female ; Hospitalization ; economics ; statistics & numerical data ; Humans ; Liver Neoplasms ; economics ; mortality ; Male ; Middle Aged

OBJECTIVETo understand the current status of lung cancer disease burden in Jinchang cohort.

METHODSIn this historical cohort study, the mortality data of the lung cancer from 2001 to 2013 and medical records of the lung cancer cases from 2001 to 2010 in Jinchang cohort were used, analyze mortality, direct economic burden, potential years of life lost (PYLL) and working PYLL (WPYLL) associated with lung cancer.

RESULTSA total of 434 lung cancer deaths occurred in Jinchang cohort from 2001 to 2013. The crude mortality rate of lung cancer was 78.06 per 100,000 from 2001 to 2013, with the increasing rate of 4.77%. The mortality rate of lung cancer in males and females were about 108.90 per 100,000 and 26.08 per 100,000 with the increasing rate of 4.24% and 6.91%, respectively. During the thirteen years, the PYLL and average PYLL (APYLL) of lung cancer were 3 721.71 person-years and 8.58 years. The APYLL of lung cancer in females (15.94 years) was higher than that in males (7.87 years). The WPYLL and the average WPYLL (AWPYLL) of lung cancer were 1161.00 person-years and 2.68 years, respectively. The AWPYLL of lung cancer was also higher in females than in males. The direct economic burden of lung cancer from 2001 to 2010 in Jinchang cohort was 6309.39 Yuan per case with no increased trend.

CONCLUSIONLung cancer is the main health problem in Jinchang cohort, causing heavy disease burden.

China ; epidemiology ; Cohort Studies ; Cost of Illness ; Female ; Humans ; Lung Neoplasms ; economics ; mortality ; Male

OBJECTIVETo describe the baseline data of cancers in the Jinchang Cohort, this paper examined trends in cancer mortality among adults investigated in Jinchang, Gansu province from 2001 to 2010.

METHODSMortality data were collected from company departments through administrative documents, death certificates, etc. Trend analyses of cancer mortality were performed on the basis of 925 cancer deaths between 2001 and 2010.

RESULTSThe crude mortality rate of cancer continuously increased from 161.86 per 100,000 in 2001 to 315.32 per 100,000 in 2010, with an average increase of 7.69% per year in the Jinchang Cohort (16.41% in females compared to 6.04% in males), but the age-standardized mortality rate increased only in females. Thirteen leading cancers accounted for 92.10% of all cancer deaths. The five leading causes of cancer mortality in males were lung, gastric, liver, esophageal, and colorectal cancer, whereas those in females were lung, liver, gastric, breast, and esophageal cancer.

CONCLUSIONThe overall cancer mortality rate increased from 2001 to 2010 in the Jinchang Cohort, with greater rate of increase in females than in males. Lung, breast, and gastric cancer, in that order, were the leading causes of increased cancer mortality in females.

Adult ; China ; epidemiology ; Cohort Studies ; Female ; Humans ; Male ; Neoplasms ; epidemiology ; mortality ; Retrospective Studies ; Time Factors