A Deep-Learning Model for Diagnosing Fresh Vertebral Fractures on Magnetic Resonance Images.

BACKGROUND: The accurate diagnosis of fresh vertebral fractures (VFs) was critical to optimizing treatment outcomes. Existing studies, however, demonstrated insufficient accuracy, sensitivity, and specificity in detecting fresh fractures using magnetic resonance imaging (MRI), and fall short in localizing the fracture sites. METHODS: This prospective study comprised 716 patients with fresh VFs. We obtained 849 Short TI Inversion Recovery (STIR) image slices for training and validation of the AI model. The AI models employed were yolov7 and resnet50, to detect fresh VFs. RESULTS: The AI model demonstrated a diagnostic accuracy of 97.6% for fresh VFs, with a sensitivity of 98% and a specificity of 97%. The performance of the model displayed a high degree of consistency when compared to the evaluations by spine surgeons. In the external testing dataset, the model exhibited a classification accuracy of 92.4%, a sensitivity of 93%, and a specificity of 92%. CONCLUSIONS: Our findings highlighted the potential of AI in diagnosing fresh VFs, offering an accurate and efficient way to aid physicians with diagnosis and treatment decisions.

Nutrition education guided by Dietary Guidelines for Chinese Residents on metabolic syndrome characteristics, adipokines and inflammatory markers.

OBJECTIVE: The objective of this study was to test whether "Dietary Guidelines for Chinese Residents" have beneficial effects on anthropometric and metabolic variables, adipokines and inflammatory markers in metabolic syndrome patients. METHODS AND PROCEDURES: A multi-stage sampling method was applied to select metabolic syndrome patients in two districts of Shanghai. Two hundred and seventy-two metabolic syndrome patients were divided into control and intervention groups according to their district. Nutrition education guided by "Dietary Guidelines for Chinese Residents" was performed in the intervention group for one year. RESULTS: Nutrition-related knowledge, attitudes and behavior were improved in the intervention group. Potassium intake and food to total energy ratio for grain, vegetable and fruit increased while sodium intake as well as fat to total energy ratio decreased in the intervention group compared to the control group (p<0.05). Correspondently, the intervention group significantly improved its waist circumference, waist to hip ratio, high-density lipoprotein cholesterol, adiponectin, leptin and tumor necrosis factor-α compared to the control group (p<0.05). Waist circumference changes from baseline to end of the study in the intervention and the control groups were -3.9±0.3 and -2.3±0.4 cm respectively. There was a significant difference between the two groups (p=0.004). Means of waist circumference, waist to hip ratio, leptin and tumor necrosis factor-α were lower, and high density lipoprotein-cholesterol was higher in the intervention group than the control group (p<0.05). CONCLUSION: This study confirmed "Dietary Guidelines for Chinese Residents" had beneficial effects on anthropometric, lipids, adipokines and inflammatory markers in metabolic syndrome patients.

[Correlation of plasma adiponectin and components of metabolic syndrome].

OBJECTIVE: To identify the relationship of adiponectin and the components of metabolic syndrome (MS). METHODS: Cluster random sampling was applied in two districts of Shanghai. Two communities were selected. After investigating and physical examination, 235 MS subjects were obtained. Correlation analysis and principle components regression analysis were used to analyze the relationship between adiponectin and components of MS (waist circumference, blood pressure, blood glucose and lipid). RESULTS: Adiponectin in male was (2.82 +/- 1.73) microg/ml, lower than in female [(5.12 +/- 3.51) microg/ml] with statistical difference (Z = -5.25, P = 0.00). Adiponectin levels [(4.38 +/- 3.23) microg/ ml] correlated with abdominal obesity, including waist circumference [(93.37 +/- 7.76) cm] (r(s) = - 0.18, t(r) = -2.79, P = 0.01) and waist hip ratio (0.91 +/- 0.05) (r(s) = -0.28, t(r) = -4.44, P = 0.00), but did not correlate significantly with body mass index (BMI) [(26.85 +/- 3.10) kg/m2] (r(s) = -0.10, t(r) = - 1.45, P = 0. 15). Adiponectin correlated negatively with insulin resistance related indexes, including fasting glucose [(5.48 +/- 1.72) mmol/L] (r(s) = -0.13, t(r) = -2.00, P = 0.05), fasting insulin [(11.52 +/- 5.34) mU/L] (r(s) = -0. 15, t(r) = - 2.31, P = 0.02), homeostasis model assessment of insulin resistance (HOMA-IR) (2.90 +/- 2.07) (r(s) = -0.17, t(r) = -2.63, P = 0.01) and triglyceride [(2.11 +/- 1.24) mmol/L] (r(s) = -0.24, t(r) = -3.77, P = 0.00). The correlations were not observed between adiponectin with total cholesterol [(5.01 +/- 1.19) mmol/L] ( r(s) = -0.05, t(r) = -0.78, P = 0.44), high density lipoprotein-cholesterol (HDL-C) [(1.21 +/- 0.32) mmol/L] (r(s) = 0.06, t(r) = 0.93, P = 0.36), systolic blood pressure [(131.40 +/- 14.93) mm Hg, 1 mm Hg = 0.133 kPa] (r(s) = -0.02, t(r) = -0.34, P = 0.73) and diastolic blood pressure [(86.77 +/- 9.14)mm Hg] (r(s) = -0.02, t(r) = -0.27, P = 0.78). CONCLUSION: Adiponectin should correlate negatively with abdominal obesity and insulin resistance, but not directly correlate with blood pressure in MS.

[Association of peroxisome proliferator-activated-receptors-gamma C161-->T gene polymorphism with metabolic syndrome and dietary predisposition].

OBJECTIVE: To study the genotype frequencies of peroxisome proliferators-activated -receptors-gamma C161-->T gene and its possible association with the metabolic syndrome and dietary intakes. METHODS: The PCR-PFLP method was used to detect the polymorphism of PPARgammaC161-->T gene of 224 adults with metabolic syndrome and 224 normal adults in Shanghai. Their physical examinations, dietary investigation and the serum biochemistry were analyzed. RESULTS: (1) The genotype frequencies of PPARgamma C161-->T CC, CT and TT were 32.4%, 49.6% and 18.0% respectively, which were in agreement with Hardy-Weinberg equilibrium. There was no significant difference in the distribution of genotypes or allele between the metabolic syndrome group and the control group, and the result was the same between male and female subjects. (2) The levels of body mass index,waist width and hip width were significantly different among three genotypes groups. Subjects of the CT genotype had the highest levels. (3) There was significant difference in the negative correlation with the intake of protein and serum TG levels in the metabolic syndrome group. CONCLUSION: The results suggested PPARgamma gene C161-->T should be associated with body mass index, waist width and hip width. It might contribute to the heterogeneity in diet response to TG.