Objective:To analyze the prediction of pathological classification of ground glass nodules based on artificial intelligence computed tomography (CT) quantitative parameters combined with histogram parameters.Methods:The clinical data of 268 suspected patients with ground glass nodules admitted to Foshan Fosun Chancheng Hospital from June 2021 to June 2023 were retrospectively selected as the research subjects. They were divided into pre invasive lesions group (100 cases) and invasive lesions group(168 cases) according to pathological classification. Basic data of patients with different pathological classifications and the CT characteristics were compared, the prediction of pathological classification of ground glass nodules based on CT quantitative parameters combined and histogram parameters were analyzed by receiver operating characteristic (ROC) curve.Results:The edge and boundary of the tumor, shape of the lesion, the peripheral signs of the lesion and the boundary between the two groups had statistical differences ( P<0.05). The CT quantitative parameters of maximum diameter, lesion volume, average CT value in the invasive lesions group and pre invasive lesions group had statistical differences: (15.29 ± 3.20) cm vs. (9.75 ± 2.14) cm, (1.54 ± 0.31) cm 3 vs. (0.51 ± 0.10) cm 3, (- 328.16 ± 46.35) HU vs. (-541.25 ± 100.30) HU, P<0.05. The CT histogram parameters of inproportion of solid components, entropy and maximum CT value in the invasive lesions group and pre invasive lesions group had statistical differences: (66.39 ± 13.25)% vs. (42.65 ± 11.20)%, 4.31 ± 0.52 vs. 3.32 ± 0.39, (-75.34 ± 21.27) HU vs. (-141.72 ± 32.43)HU, P<0.05. Compared with the single prediction of CT quantitative parameters and CT histogram parameters, the combined prediction of the two parameters had higher value in predicting different pathological subtypes of ground glass nodules (the area under the curve was 0.877, P = 0.001). Conclusions:The combined detection of CT quantitative parameters and histogram parameters based on artificial intelligence can effectively evaluate the invasion status of ground glass nodules, which is beneficial for improving the detection of different pathological types of ground glass nodules.

Objective:To investigate the relationship between the serum levels of vascular endothelial growth factor (VEGF), matrix metalloproteinase-9 (MMP-9), S100 calcium binding protein B (S100B) with glycolipid metabolism, pregnancy outcome in pregnant women with gestational diabetes.Methods:The clinical data of 153 pregnant women with gestational diabetes (research group) and 153 healthy pregnant women (control group) in the Second Affiliated Hospital of Xi ′an Medical University from January 2020 to October 2023 were retrospectively analyzed. The serum levels of VEGF, MMP-9 and S100B were measured by enzyme linked immunosorbent assay, and the fasting blood glucose, triglyceride, total cholesterol, high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), fasting insulin and glycated hemoglobin were measured, and the homeostasis model assessment insulin resistance index (HOMA-IR) was calculated. The adverse outcomes of pregnant women with gestational diabetes were recorded. Pearson method was used to analyze the correlation between glycolipid metabolism indexes and VEGF, MMP-9, S100B in pregnant women with gestational diabetes. Multivariate Logistic regression was used to analyze the independent risk factors of adverse pregnancy outcome in pregnant women with gestational diabetes. Receiver operating characteristic (ROC) curve was drawn to analyze the predictive value of VEGF, MMP-9 and S100B on adverse pregnancy outcome in pregnant women with gestational diabetes. Results:The fasting blood glucose, fasting insulin, glycated hemoglobin, HOMA-IR, triglyceride, total cholesterol, LDL-C, VEGF, MMP-9 and S100B in research group were significantly higher than those in control group: (9.42 ± 0.65) mmol/L vs. (4.13 ± 0.46) mmol/L, (16.58 ± 2.37) mU/L vs. (13.41 ± 2.05) mU/L, (7.28 ± 0.46)% vs. (4.35 ± 0.39)%, 4.83 ± 0.42 vs. 2.71 ± 0.37, (3.41 ± 0.67) mmol/L vs. (2.85 ± 0.63) mmol/L, (5.54 ± 1.56) mmol/L vs. (5.12 ± 1.50) mmol/L, (3.14 ± 0.97) mmol/L vs. (2.86 ± 0.93) mmol/L, (184.02 ± 30.25) ng/L vs. (156.33 ± 26.41) ng/L, (45.78 ± 7.56) μg/L vs. (29.36 ± 5.03) μg/L and (117.51 ± 25.12) ng/L vs. (89.74 ± 22.46) ng/L, the HDL-C was significantly lower than that in control group: (1.34 ± 0.27) mmol/L vs. (1.42 ± 0.30) mmol/L, and there were statistical differences ( P<0.01 or <0.05). Pearson correlation analysis result showed that VEGF, MMP-9, S100B in pregnant women with gestational diabetes were positively correlated with fasting blood glucose, fasting insulin, glycated hemoglobin, HOMA-IR, triglyceride, total cholesterol and LDL-C ( P<0.01), negatively correlated with HDL-C ( P<0.01). Among 153 pregnant women with gestational diabetes, 49 had adverse pregnancy outcome, and 104 had good pregnancy outcome. The VEGF, MMP-9 and S100B in pregnant women with adverse pregnancy outcome were significantly higher than those in pregnant women with good pregnancy outcome: (212.75 ± 28.63) ng/L vs. (170.49 ± 26.58) ng/L, (52.37 ± 7.14) μg/L vs. (42.68 ± 6.35) μg/L and (136.83 ± 23.62) ng/L vs. (108.41 ± 21.35) ng/L, and there were statistical differences ( P<0.01). Multivariate Logistic regression analysis result showed that VEGF, MMP-9 and S100B were independent risk factors for adverse pregnancy outcome in pregnant women with gestational diabetes ( OR = 7.013, 5.382 and 6.129; 95% CI 5.206 to 9.447, 3.449 to 8.398 and 3.520 to 10.673; P<0.01). ROC curve analysis result showed that the area under the curve of VEGF, MMP-9 combined S100B in predicting adverse pregnancy outcome in pregnant women with gestational diabetes was significantly larger than that of VEGF, MMP-9 and S100B alone (0.945 vs. 0.863, 0.847 and 0.801; P<0.05 or <0.01), with sensitivity of 89.80% and specificity of 91.30%. Conclusions:The high serum levels of VEGF, MMP-9 and S100B are associated with abnormal glycolipid metabolism and adverse pregnancy outcome in pregnant women with gestational diabetes, and the combination of the three indexes has a high predictive value for adverse pregnancy outcome.

Objective:To investigate the clinical value of enhanced magnetic resonance imaging (MRI)-based deep learning model in preoperative prediction of proliferative hepatocellular carcinoma (HCC).Methods:The retrospective cohort study was conducted. The clinical data of 906 HCC patients who were admitted to The First Affiliated Hospital of Army Medical University and The Second Affiliated Hospital of Chongqing Medical University from May 2017 to October 2022 were collected. There were 769 males and 137 females, aged (53.2±10.9)years. Of the 906 patients, 815 cases who were admitted to The First Affiliated Hospital of Army Medical University were divided into the training set of 634 patients and the internal validation set of 181 patients using a random number table method with a ratio of 8:2, and 91 patients who were admitted to The Second Affiliated Hospital of Chongqing Medical University were divided into the external validation set. The training set was used to construct the prediction model, while the validation set was used to validate the prediction model. Observation indicators: (1) analysis of factors influencing the pathological classification of HCC patients; (2) deep learning imaging features of HCC patients; (3) evaluation of the efficacy of prediction model for proliferative HCC; (4) validation of the prediction model for proliferative HCC; (5) prognosis of HCC patients. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Multivariate analysis was conducted using the binary Logistic regression model. The model perfor-mance was evaluated through five-fold cross-validation, and receiver operating characteristic (ROC) curve was plotted to assess the diagnostic value of the model based on the area under curve (AUC), sensitivity, and specificity. The Delong test was used to compare the diagnostic performance of models. The Hosmer-Lemeshow test was employed to evaluate the calibration of models. The optimal cutoff value of the prediction model was determined by the maximum Youden index, with the value >0.175 indicating high-risk patients and value ≤0.175 indicating low-risk patients.The Kaplan-Meier method was used to calculate the survival rate and the Log-rank test was used for survival analysis. Results:(1) Analysis of factors influencing the pathological classification of HCC patients. Of 634 patients in the training set, there were 190 cases of proliferative HCC and 444 cases of non-proliferative HCC. Results of multivariate analysis showed that alpha fetoprotein (AFP) ≥400 μg/L and tumor diameter >5 cm were independent risk factors for pathological type of HCC as proli-ferative [ odds ratio=1.73, 1.88, 95% confidence interval ( CI) as 1.19-2.50, 1.30-2.71, P<0.05]. (2) Deep learning imaging features of HCC patients. In the training set of 634 patients, the probability predicted by MRI-based deep learning model was 84.8%(30.5%,95.4%) for proliferative HCC and 5.8%(3.2%,12.5%) for non-proliferative HCC, showing a significant difference between them ( Z=-16.01, P<0.05). (3) Evaluation of the efficacy of prediction model for proliferative HCC. In the training set, the AUC of clinical prediction model for proliferative HCC was 0.63(95% CI as 0.59-0.68, P<0.05), with sensitivity of 54.74% and specificity of 64.19%. The AUC of MRI-based deep learning prediction model was 0.90(95% CI as 0.87-0.93, P<0.05), with sensitivity of 80.53% and specificity of 86.94%. The AUC of combined MRI-based deep learning with clinical prediction model was 0.90 (95% CI as 0.87-0.93, P<0.05), with sensitivity of 83.16% and specificity of 86.04%. Results of Delong test showed that there was a significant difference between the combined MRI-based deep learning with clinical prediction model and the clinical prediction model ( P<0.05), and there was no signifi-cant difference between the combined MRI-based deep learning with clinical prediction model and the MRI-based deep learning prediction model ( P>0.05). Results of Hosmer-Lemeshow test showed good calibration for the clinical prediction model, the MRI-based deep learning prediction model and the combined MRI-based deep learning with clinical prediction model ( χ2=0.84, 6.38, 3.93, P>0.05), indicating that the predicted probabilities of these three prediction models matched the actual risk well. (4) Validation of the prediction model for proliferative HCC. Results of validation of the prediction model in internal validation set showed the AUC of MRI-based deep learning prediction model for proliferative HCC was 0.84(95% CI as 0.77-0.91, P<0.05), with sensitivity of 82.35% and specificity of 77.69%. Results of validation of the prediction model in external validation set showed the AUC of MRI-based deep learning prediction model for proliferative HCC was 0.81(95% CI as 0.71-0.92, P<0.05), with sensitivity of 70.00% and specificity of 81.69%. (5) Prognosis of HCC patients. Of the 906 patients, the 1-, 3-, and 5-year recurrence-free survival rates for 645 proliferative HCC patients were 56.9%, 31.4%, and 29.1%, respectively, and the 1-, 3-, and 5-year recurrence-free survival rates for 261 non-proliferative HCC patients were 88.8%, 68.6%, and 56.0%, respectively. There were significant differences in recurrence-free survival time between proliferative HCC and non-proliferative HCC patients of the training set, internal validation set and external validation set ( P<0.05). The 1-, 3-, 5-year recurrence-free survival rates for 331 high-risk HCC patients were 64.6%, 50.4%, 43.6%, versus 88.5%, 71.9%, 62.7% for 575 low-risk HCC patients. There were significant differences in recurrence-free survival time between high-risk HCC patients and low-risk HCC patients of the training set, internal validation set and external validation set ( P<0.05). Conclusion:The MRI-based deep learning model can effectively predict proliferative HCC and recurrence-free survival of patients before the surgery.

Objective:To investigate the characteristics of cardiopulmonary exercise testing and risk factors for decreased aerobic capacity in children with non-acute asthma exacerbations, to assess their cardiopulmonary health and to provide a basis for improvement.Methods:A case-control study.Sixty-one children with non-acute asthma exacerbations treated at the Outpatient Department of Children′s Hospital of Soochow University from October 2022 to December 2023 and 22 control children during the same period were included.Binary Logistic regression was employed to assess risk factors for decreased aerobic capacity in children with asthma.Results:Among the included 61 children with non-acute asthma exacerbations, there were 33 cases in the chronic persistent phase (chronic persistent phase group) and 28 in the clinical remission phase(clinical remission group).There were 22 children in the control group.During the peak exercise phase of the cardiopulmonary exercise testing, the mean kilogram body weight oxygen uptake (VO 2/kg), the percentage of predicted kilogram body weight oxygen uptake, and metabolic equivalents (Met) in the chronic persistent phase group were lower than those in the control and clinical remission phase groups.The mean VO 2/kg recovery from the cardiopulmonary exercise testing in the first minute in the chronic persistent phase group was lower than that in the control and clinical remission phase groups.The median Met and ventilation per minute recovery in the chronic persistent phase group were lower than those in the control group.The median heart rate recovery in asthma children was lower than that in control children.The percentage of cardiopulmonary exercise testing abnormalities was higher in asthma children with symptoms after excise than that in asthma children without symptoms after excise.The percentage of decreased ventilation efficiency in asthma children with symptoms after excise was higher than that in asthma children without symptoms after excise.Multivariate regression analysis showed that a higher body mass index (BMI) ( OR=1.577, 95% CI: 1.113-2.235, P=0.010) and a higher peak respiratory reserve ( OR=1.103, 95% CI: 1.018-1.195, P=0.017) were risk factors of decreased aerobic capacity.The risk of decreased aerobic capacity in the chronic persistent phase was 7.949 times higher than that in the clinical remission phase ( OR=7.949, 95% CI: 1.290-48.996, P=0.025). Conclusions:The aerobic capacity is decreased and ventilatory recovery is slower in children with chronic persistent asthma than those in healthy children.The heart rate recovery in asthma children is slower than that in healthy children.A high BMI, a high peak respiratory reserve, and chronic persistence of asthma are independent risk factors for decreased aerobic capacity in children with non-acute asthma exacerbations.asthma.

Objective:To investigate the relationship between the serum levels of vascular endothelial growth factor (VEGF), matrix metalloproteinase-9 (MMP-9), S100 calcium binding protein B (S100B) with glycolipid metabolism, pregnancy outcome in pregnant women with gestational diabetes.Methods:The clinical data of 153 pregnant women with gestational diabetes (research group) and 153 healthy pregnant women (control group) in the Second Affiliated Hospital of Xi ′an Medical University from January 2020 to October 2023 were retrospectively analyzed. The serum levels of VEGF, MMP-9 and S100B were measured by enzyme linked immunosorbent assay, and the fasting blood glucose, triglyceride, total cholesterol, high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), fasting insulin and glycated hemoglobin were measured, and the homeostasis model assessment insulin resistance index (HOMA-IR) was calculated. The adverse outcomes of pregnant women with gestational diabetes were recorded. Pearson method was used to analyze the correlation between glycolipid metabolism indexes and VEGF, MMP-9, S100B in pregnant women with gestational diabetes. Multivariate Logistic regression was used to analyze the independent risk factors of adverse pregnancy outcome in pregnant women with gestational diabetes. Receiver operating characteristic (ROC) curve was drawn to analyze the predictive value of VEGF, MMP-9 and S100B on adverse pregnancy outcome in pregnant women with gestational diabetes. Results:The fasting blood glucose, fasting insulin, glycated hemoglobin, HOMA-IR, triglyceride, total cholesterol, LDL-C, VEGF, MMP-9 and S100B in research group were significantly higher than those in control group: (9.42 ± 0.65) mmol/L vs. (4.13 ± 0.46) mmol/L, (16.58 ± 2.37) mU/L vs. (13.41 ± 2.05) mU/L, (7.28 ± 0.46)% vs. (4.35 ± 0.39)%, 4.83 ± 0.42 vs. 2.71 ± 0.37, (3.41 ± 0.67) mmol/L vs. (2.85 ± 0.63) mmol/L, (5.54 ± 1.56) mmol/L vs. (5.12 ± 1.50) mmol/L, (3.14 ± 0.97) mmol/L vs. (2.86 ± 0.93) mmol/L, (184.02 ± 30.25) ng/L vs. (156.33 ± 26.41) ng/L, (45.78 ± 7.56) μg/L vs. (29.36 ± 5.03) μg/L and (117.51 ± 25.12) ng/L vs. (89.74 ± 22.46) ng/L, the HDL-C was significantly lower than that in control group: (1.34 ± 0.27) mmol/L vs. (1.42 ± 0.30) mmol/L, and there were statistical differences ( P<0.01 or <0.05). Pearson correlation analysis result showed that VEGF, MMP-9, S100B in pregnant women with gestational diabetes were positively correlated with fasting blood glucose, fasting insulin, glycated hemoglobin, HOMA-IR, triglyceride, total cholesterol and LDL-C ( P<0.01), negatively correlated with HDL-C ( P<0.01). Among 153 pregnant women with gestational diabetes, 49 had adverse pregnancy outcome, and 104 had good pregnancy outcome. The VEGF, MMP-9 and S100B in pregnant women with adverse pregnancy outcome were significantly higher than those in pregnant women with good pregnancy outcome: (212.75 ± 28.63) ng/L vs. (170.49 ± 26.58) ng/L, (52.37 ± 7.14) μg/L vs. (42.68 ± 6.35) μg/L and (136.83 ± 23.62) ng/L vs. (108.41 ± 21.35) ng/L, and there were statistical differences ( P<0.01). Multivariate Logistic regression analysis result showed that VEGF, MMP-9 and S100B were independent risk factors for adverse pregnancy outcome in pregnant women with gestational diabetes ( OR = 7.013, 5.382 and 6.129; 95% CI 5.206 to 9.447, 3.449 to 8.398 and 3.520 to 10.673; P<0.01). ROC curve analysis result showed that the area under the curve of VEGF, MMP-9 combined S100B in predicting adverse pregnancy outcome in pregnant women with gestational diabetes was significantly larger than that of VEGF, MMP-9 and S100B alone (0.945 vs. 0.863, 0.847 and 0.801; P<0.05 or <0.01), with sensitivity of 89.80% and specificity of 91.30%. Conclusions:The high serum levels of VEGF, MMP-9 and S100B are associated with abnormal glycolipid metabolism and adverse pregnancy outcome in pregnant women with gestational diabetes, and the combination of the three indexes has a high predictive value for adverse pregnancy outcome.

Objective:To analyze the prediction of pathological classification of ground glass nodules based on artificial intelligence computed tomography (CT) quantitative parameters combined with histogram parameters.Methods:The clinical data of 268 suspected patients with ground glass nodules admitted to Foshan Fosun Chancheng Hospital from June 2021 to June 2023 were retrospectively selected as the research subjects. They were divided into pre invasive lesions group (100 cases) and invasive lesions group(168 cases) according to pathological classification. Basic data of patients with different pathological classifications and the CT characteristics were compared, the prediction of pathological classification of ground glass nodules based on CT quantitative parameters combined and histogram parameters were analyzed by receiver operating characteristic (ROC) curve.Results:The edge and boundary of the tumor, shape of the lesion, the peripheral signs of the lesion and the boundary between the two groups had statistical differences ( P<0.05). The CT quantitative parameters of maximum diameter, lesion volume, average CT value in the invasive lesions group and pre invasive lesions group had statistical differences: (15.29 ± 3.20) cm vs. (9.75 ± 2.14) cm, (1.54 ± 0.31) cm 3 vs. (0.51 ± 0.10) cm 3, (- 328.16 ± 46.35) HU vs. (-541.25 ± 100.30) HU, P<0.05. The CT histogram parameters of inproportion of solid components, entropy and maximum CT value in the invasive lesions group and pre invasive lesions group had statistical differences: (66.39 ± 13.25)% vs. (42.65 ± 11.20)%, 4.31 ± 0.52 vs. 3.32 ± 0.39, (-75.34 ± 21.27) HU vs. (-141.72 ± 32.43)HU, P<0.05. Compared with the single prediction of CT quantitative parameters and CT histogram parameters, the combined prediction of the two parameters had higher value in predicting different pathological subtypes of ground glass nodules (the area under the curve was 0.877, P = 0.001). Conclusions:The combined detection of CT quantitative parameters and histogram parameters based on artificial intelligence can effectively evaluate the invasion status of ground glass nodules, which is beneficial for improving the detection of different pathological types of ground glass nodules.

Objective:To investigate the clinical value of enhanced magnetic resonance imaging (MRI)-based deep learning model in preoperative prediction of proliferative hepatocellular carcinoma (HCC).Methods:The retrospective cohort study was conducted. The clinical data of 906 HCC patients who were admitted to The First Affiliated Hospital of Army Medical University and The Second Affiliated Hospital of Chongqing Medical University from May 2017 to October 2022 were collected. There were 769 males and 137 females, aged (53.2±10.9)years. Of the 906 patients, 815 cases who were admitted to The First Affiliated Hospital of Army Medical University were divided into the training set of 634 patients and the internal validation set of 181 patients using a random number table method with a ratio of 8:2, and 91 patients who were admitted to The Second Affiliated Hospital of Chongqing Medical University were divided into the external validation set. The training set was used to construct the prediction model, while the validation set was used to validate the prediction model. Observation indicators: (1) analysis of factors influencing the pathological classification of HCC patients; (2) deep learning imaging features of HCC patients; (3) evaluation of the efficacy of prediction model for proliferative HCC; (4) validation of the prediction model for proliferative HCC; (5) prognosis of HCC patients. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Multivariate analysis was conducted using the binary Logistic regression model. The model perfor-mance was evaluated through five-fold cross-validation, and receiver operating characteristic (ROC) curve was plotted to assess the diagnostic value of the model based on the area under curve (AUC), sensitivity, and specificity. The Delong test was used to compare the diagnostic performance of models. The Hosmer-Lemeshow test was employed to evaluate the calibration of models. The optimal cutoff value of the prediction model was determined by the maximum Youden index, with the value >0.175 indicating high-risk patients and value ≤0.175 indicating low-risk patients.The Kaplan-Meier method was used to calculate the survival rate and the Log-rank test was used for survival analysis. Results:(1) Analysis of factors influencing the pathological classification of HCC patients. Of 634 patients in the training set, there were 190 cases of proliferative HCC and 444 cases of non-proliferative HCC. Results of multivariate analysis showed that alpha fetoprotein (AFP) ≥400 μg/L and tumor diameter >5 cm were independent risk factors for pathological type of HCC as proli-ferative [ odds ratio=1.73, 1.88, 95% confidence interval ( CI) as 1.19-2.50, 1.30-2.71, P<0.05]. (2) Deep learning imaging features of HCC patients. In the training set of 634 patients, the probability predicted by MRI-based deep learning model was 84.8%(30.5%,95.4%) for proliferative HCC and 5.8%(3.2%,12.5%) for non-proliferative HCC, showing a significant difference between them ( Z=-16.01, P<0.05). (3) Evaluation of the efficacy of prediction model for proliferative HCC. In the training set, the AUC of clinical prediction model for proliferative HCC was 0.63(95% CI as 0.59-0.68, P<0.05), with sensitivity of 54.74% and specificity of 64.19%. The AUC of MRI-based deep learning prediction model was 0.90(95% CI as 0.87-0.93, P<0.05), with sensitivity of 80.53% and specificity of 86.94%. The AUC of combined MRI-based deep learning with clinical prediction model was 0.90 (95% CI as 0.87-0.93, P<0.05), with sensitivity of 83.16% and specificity of 86.04%. Results of Delong test showed that there was a significant difference between the combined MRI-based deep learning with clinical prediction model and the clinical prediction model ( P<0.05), and there was no signifi-cant difference between the combined MRI-based deep learning with clinical prediction model and the MRI-based deep learning prediction model ( P>0.05). Results of Hosmer-Lemeshow test showed good calibration for the clinical prediction model, the MRI-based deep learning prediction model and the combined MRI-based deep learning with clinical prediction model ( χ2=0.84, 6.38, 3.93, P>0.05), indicating that the predicted probabilities of these three prediction models matched the actual risk well. (4) Validation of the prediction model for proliferative HCC. Results of validation of the prediction model in internal validation set showed the AUC of MRI-based deep learning prediction model for proliferative HCC was 0.84(95% CI as 0.77-0.91, P<0.05), with sensitivity of 82.35% and specificity of 77.69%. Results of validation of the prediction model in external validation set showed the AUC of MRI-based deep learning prediction model for proliferative HCC was 0.81(95% CI as 0.71-0.92, P<0.05), with sensitivity of 70.00% and specificity of 81.69%. (5) Prognosis of HCC patients. Of the 906 patients, the 1-, 3-, and 5-year recurrence-free survival rates for 645 proliferative HCC patients were 56.9%, 31.4%, and 29.1%, respectively, and the 1-, 3-, and 5-year recurrence-free survival rates for 261 non-proliferative HCC patients were 88.8%, 68.6%, and 56.0%, respectively. There were significant differences in recurrence-free survival time between proliferative HCC and non-proliferative HCC patients of the training set, internal validation set and external validation set ( P<0.05). The 1-, 3-, 5-year recurrence-free survival rates for 331 high-risk HCC patients were 64.6%, 50.4%, 43.6%, versus 88.5%, 71.9%, 62.7% for 575 low-risk HCC patients. There were significant differences in recurrence-free survival time between high-risk HCC patients and low-risk HCC patients of the training set, internal validation set and external validation set ( P<0.05). Conclusion:The MRI-based deep learning model can effectively predict proliferative HCC and recurrence-free survival of patients before the surgery.

Objective:To investigate the characteristics of cardiopulmonary exercise testing and risk factors for decreased aerobic capacity in children with non-acute asthma exacerbations, to assess their cardiopulmonary health and to provide a basis for improvement.Methods:A case-control study.Sixty-one children with non-acute asthma exacerbations treated at the Outpatient Department of Children′s Hospital of Soochow University from October 2022 to December 2023 and 22 control children during the same period were included.Binary Logistic regression was employed to assess risk factors for decreased aerobic capacity in children with asthma.Results:Among the included 61 children with non-acute asthma exacerbations, there were 33 cases in the chronic persistent phase (chronic persistent phase group) and 28 in the clinical remission phase(clinical remission group).There were 22 children in the control group.During the peak exercise phase of the cardiopulmonary exercise testing, the mean kilogram body weight oxygen uptake (VO 2/kg), the percentage of predicted kilogram body weight oxygen uptake, and metabolic equivalents (Met) in the chronic persistent phase group were lower than those in the control and clinical remission phase groups.The mean VO 2/kg recovery from the cardiopulmonary exercise testing in the first minute in the chronic persistent phase group was lower than that in the control and clinical remission phase groups.The median Met and ventilation per minute recovery in the chronic persistent phase group were lower than those in the control group.The median heart rate recovery in asthma children was lower than that in control children.The percentage of cardiopulmonary exercise testing abnormalities was higher in asthma children with symptoms after excise than that in asthma children without symptoms after excise.The percentage of decreased ventilation efficiency in asthma children with symptoms after excise was higher than that in asthma children without symptoms after excise.Multivariate regression analysis showed that a higher body mass index (BMI) ( OR=1.577, 95% CI: 1.113-2.235, P=0.010) and a higher peak respiratory reserve ( OR=1.103, 95% CI: 1.018-1.195, P=0.017) were risk factors of decreased aerobic capacity.The risk of decreased aerobic capacity in the chronic persistent phase was 7.949 times higher than that in the clinical remission phase ( OR=7.949, 95% CI: 1.290-48.996, P=0.025). Conclusions:The aerobic capacity is decreased and ventilatory recovery is slower in children with chronic persistent asthma than those in healthy children.The heart rate recovery in asthma children is slower than that in healthy children.A high BMI, a high peak respiratory reserve, and chronic persistence of asthma are independent risk factors for decreased aerobic capacity in children with non-acute asthma exacerbations.asthma.

Objective To investigate the composition of symptom clusters in early postoperative breast cancer patients and analyze the sentinel symptoms of each cluster of symptoms. Methods A total of 309 patients who underwent mastectomy were conveniently sampled and surveyed using the Chinese version of the Anderson Symptom Inventory. Principal component analysis and varimax orthogonal rotation were employed to analyze the symptom clusters, and their associations were analyzed using the Apriori algorithm model to identify the sentinel symptoms of each cluster of symptoms. Results Three symptom clusters were identified in early postoperative breast cancer patients: neuro-sleep symptom cluster [fatigue (weakness)-distress-pain-sleepiness-restless sleep], sensory-perception symptom cluster (numbness-forgetfulness-shortness of breath-sadness-dry mouth), and digestive system symptom cluster (nausea-vomiting-loss of appetite). Fatigue was the sentinel symptom of the neuro-sleep symptom cluster, numbness was the sentinel symptom of the sensory-perception symptom cluster, and nausea was the sentinel symptom of the digestive system symptom cluster. Conclusion Early postoperative breast cancer patients experience multiple symptom clusters, with sentinel symptoms existing in each cluster. Healthcare staff should develop intervention measures based on sentinel symptoms to improve the efficiency of symptom management and reduce the degree of symptom distress for patients.