Objective:To develop a multi-parameter diagnostic model for pediatric McCune-Albright syndrome(MAS) using machine learning techniques based on laboratory data from MAS patients, with the goal of providing a rapid and reliable auxiliary diagnostic tool for clinical practice.Methods:In this retrospective study, 232 children diagnosed with MAS at the Department of Pediatrics, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine from March 2023 to November 2024 were enrolled as the positive group. After removing duplicate or missing data, 119 cases were finally selected for statistical analysis as the positive group. Meanwhile, 113 children with normal physical examinations during the same period were selected as the control group. The clinical manifestations of the classic " triad" in the positive group were documented. Fasting serum samples were obtained from both groups at 8: 00 AM for laboratory testing, including bone metabolism-related and hormone-related indicators, which served as candidate features. Baseline descriptive analysis was conducted on the hormone-related indicators. For the bone metabolism indicators, six machine learning models—support vector machine(SVM), XGBoost, decision tree, random forest, Logistic regression, and K-nearest neighbor(KNN)—were constructed using R software. XGBoost subgroup analysis was performed based on the triad symptoms. The contribution of individual features to model predictions was visualized using SHAP diagrams. Results:SHAP visualization indicated that age, serum phosphorus, osteocalcin, and β-C-terminal cross-linked telopeptide of type Ⅰ collagen had the greatest average impact on model predictions. Among the six models, the SVM model achieved the highest diagnostic performance, with a sensitivity of 0.742 9, a specificity of 0.909 1, and an area under the curve (AUC) of 0.917.Conclusion:This study demonstrates that machine learning models, based on data from the positive patients and normal controls, can effectively distinguish MAS patients from healthy controls. The diagnostic model developed offers clinicians a valuable tool for early detection of MAS in children, contributing to earlier diagnosis, timely intervention, and improved clinical management.

McCune-Albright syndrome(MAS) is a postzygotic somatic mutation disorder caused by activating mutations in the GNAS gene, which encodes the α subunit of the stimulatory G protein. Its clinical features typically include polyostotic fibrous dysplasia, cafe-au-lait skin pigmentation, and endocrine hyperactivity, such as Cushing′s syndrome, hyperthyroidism, and growth hormone excess. Here, we report two rare cases of MAS complicated with adrenocorticotropic hormone(ACTH)-independent Cushing syndrome, and provide a review and analysis of previously reported MAS cases associated with Cushing′s syndrome.

Objective:To investigate the imaging characteristics of fibrous dysplasia(FD) in children with McCune-Albright syndrome(MAS) and the correlation between FD severity and bone metabolism markers, so as to provide a basis for clinical diagnosis and treatment.Methods:A total of 46 children(38 females and 8 males) with MAS with FD who were admitted to the Department of Pediatrics of Ruijin Hospital, Shanghai Jiao Tong University School of Medicine from January 2010 to December 2016 were included in the retrospective study, and all of them met the diagnostic criteria for either the MAS triad or dual manifestations. The extent and characteristics of FD lesions were evaluated by imaging analysis(X-ray and CT). The distribution of café-au-lait spots and endocrine abnormalities were recorded. The serum bone metabolism levels [total procollagen type 1 amino-terminal propeptide(TP1NP), osteocalcin, β-C-terminal telopeptide(β-CTX), alkaline phosphatase(ALP)], and other related indicators such as calcium, phosphorus, magnesium, and fibroblast growth factor(FGF23) levels were detected, and the association between FD severity and indicators was evaluated by Spearman correlation analysis.Results:Among the 46 children, there were 24 cases of triad(FD+ café-au-lait spots + precocious puberty) and 22 cases of dual manifestations(11 cases of FD+ café-au-lait spots or precocious puberty). The age of onset of FD patients(24 cases) with bilateral long bones and skull FD was significantly earlier than that in the unilateral FD group [(3.33±1.34)years vs(5.26±2.34)years, P<0.01], and all of them had extensive café-au-lait spots across the midline. Polyostotic FD accounted for 71.7%(33/46), mainly cystic expansive lesions involving the femur(30 cases) and tibia(24 cases), and skull FD(25 cases) mostly showed ground-glass changes; Monostotic FD(13 cases) was more common in the skull(5 cases) and phalanges(5 cases). FD severity was significantly positively correlated with ALP( ρ=0.554, P=0.002), and negatively correlated with serum phosphorus( ρ=-0.522, P=0.006). All 6 children with severe fractures had FGF23-mediated hypophosphatemia [(1.03±0.12) mmol/L vs control(1.52±0.15) mmol/L, P=0.003]. Conclusions:Extensive café-au-lait spots(across the midline) in children with MAS are strongly associated with early-onset polyostotic FD; FD severity was strongly associated with bone turnover markers(TP1NP, β-CTX, ALP) and FGF23-mediated hypophosphatemia. Early comprehensive skeletal assessment and regular FGF23 monitoring are recommended for children with MAS presenting with extensive cutaneous café-au-lait spots.

Objective:To develop a multi-parameter diagnostic model for pediatric McCune-Albright syndrome(MAS) using machine learning techniques based on laboratory data from MAS patients, with the goal of providing a rapid and reliable auxiliary diagnostic tool for clinical practice.Methods:In this retrospective study, 232 children diagnosed with MAS at the Department of Pediatrics, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine from March 2023 to November 2024 were enrolled as the positive group. After removing duplicate or missing data, 119 cases were finally selected for statistical analysis as the positive group. Meanwhile, 113 children with normal physical examinations during the same period were selected as the control group. The clinical manifestations of the classic " triad" in the positive group were documented. Fasting serum samples were obtained from both groups at 8: 00 AM for laboratory testing, including bone metabolism-related and hormone-related indicators, which served as candidate features. Baseline descriptive analysis was conducted on the hormone-related indicators. For the bone metabolism indicators, six machine learning models—support vector machine(SVM), XGBoost, decision tree, random forest, Logistic regression, and K-nearest neighbor(KNN)—were constructed using R software. XGBoost subgroup analysis was performed based on the triad symptoms. The contribution of individual features to model predictions was visualized using SHAP diagrams. Results:SHAP visualization indicated that age, serum phosphorus, osteocalcin, and β-C-terminal cross-linked telopeptide of type Ⅰ collagen had the greatest average impact on model predictions. Among the six models, the SVM model achieved the highest diagnostic performance, with a sensitivity of 0.742 9, a specificity of 0.909 1, and an area under the curve (AUC) of 0.917.Conclusion:This study demonstrates that machine learning models, based on data from the positive patients and normal controls, can effectively distinguish MAS patients from healthy controls. The diagnostic model developed offers clinicians a valuable tool for early detection of MAS in children, contributing to earlier diagnosis, timely intervention, and improved clinical management.

McCune-Albright syndrome(MAS) is a postzygotic somatic mutation disorder caused by activating mutations in the GNAS gene, which encodes the α subunit of the stimulatory G protein. Its clinical features typically include polyostotic fibrous dysplasia, cafe-au-lait skin pigmentation, and endocrine hyperactivity, such as Cushing′s syndrome, hyperthyroidism, and growth hormone excess. Here, we report two rare cases of MAS complicated with adrenocorticotropic hormone(ACTH)-independent Cushing syndrome, and provide a review and analysis of previously reported MAS cases associated with Cushing′s syndrome.

Objective:To investigate the imaging characteristics of fibrous dysplasia(FD) in children with McCune-Albright syndrome(MAS) and the correlation between FD severity and bone metabolism markers, so as to provide a basis for clinical diagnosis and treatment.Methods:A total of 46 children(38 females and 8 males) with MAS with FD who were admitted to the Department of Pediatrics of Ruijin Hospital, Shanghai Jiao Tong University School of Medicine from January 2010 to December 2016 were included in the retrospective study, and all of them met the diagnostic criteria for either the MAS triad or dual manifestations. The extent and characteristics of FD lesions were evaluated by imaging analysis(X-ray and CT). The distribution of café-au-lait spots and endocrine abnormalities were recorded. The serum bone metabolism levels [total procollagen type 1 amino-terminal propeptide(TP1NP), osteocalcin, β-C-terminal telopeptide(β-CTX), alkaline phosphatase(ALP)], and other related indicators such as calcium, phosphorus, magnesium, and fibroblast growth factor(FGF23) levels were detected, and the association between FD severity and indicators was evaluated by Spearman correlation analysis.Results:Among the 46 children, there were 24 cases of triad(FD+ café-au-lait spots + precocious puberty) and 22 cases of dual manifestations(11 cases of FD+ café-au-lait spots or precocious puberty). The age of onset of FD patients(24 cases) with bilateral long bones and skull FD was significantly earlier than that in the unilateral FD group [(3.33±1.34)years vs(5.26±2.34)years, P<0.01], and all of them had extensive café-au-lait spots across the midline. Polyostotic FD accounted for 71.7%(33/46), mainly cystic expansive lesions involving the femur(30 cases) and tibia(24 cases), and skull FD(25 cases) mostly showed ground-glass changes; Monostotic FD(13 cases) was more common in the skull(5 cases) and phalanges(5 cases). FD severity was significantly positively correlated with ALP( ρ=0.554, P=0.002), and negatively correlated with serum phosphorus( ρ=-0.522, P=0.006). All 6 children with severe fractures had FGF23-mediated hypophosphatemia [(1.03±0.12) mmol/L vs control(1.52±0.15) mmol/L, P=0.003]. Conclusions:Extensive café-au-lait spots(across the midline) in children with MAS are strongly associated with early-onset polyostotic FD; FD severity was strongly associated with bone turnover markers(TP1NP, β-CTX, ALP) and FGF23-mediated hypophosphatemia. Early comprehensive skeletal assessment and regular FGF23 monitoring are recommended for children with MAS presenting with extensive cutaneous café-au-lait spots.

Population aging in China has led to an increase in the incidence of abdominal aortic aneurysm(AAA).AAA rupture is one of the most severe life-threatening diseases,with high mortality.The main histopathological features of AAA include elastin degradation,smooth muscle cell depletion,extracellular matrix digestion,and mural leukocyte accumulation.Clinically,drug therapy is still lacking,and open/endovascular repair remains the most effective treatment strategy for AAA management.Notably however,the detailed molecular mechanism of AAA remains unclear,representing an important bottleneck affecting the development of potential drug targets.Animal models are the most powerful tools for clarifying the pathogenesis of AAA,and although some medium-to-large laboratory animal models(e.g.,rabbits,guinea pigs,dogs,pigs)have been established for AAA studies,rodent models(mice and rats)are still the main models used in this field.Current method of inducing AAA include intra-infrarenal aortic infusion of elastase,subcutaneous infusion of angiotensin Ⅱ,periaortic calcium chloride painting,and decellularized aortic xenografting;however,AAA tends to stabilize in most models after ceasing pre-induced stimulation(medical or surgical),and there remains a need for ideal animal models that maintain continuous aortic dilation and even rupture.AAA animal models are helpful for elucidating the pathogenesis of AAA,screening new drug targets,and promoting clinical translation.This review aims to discuss the application of current AAA modeling method and their translational relevance.

【Objective】 To compare the histological characteristics of porcine pancreatic elastase （PPE） induced abdominal aortic aneurysms （AAA） and angiotensin Ⅱ （AngⅡ） induced AAA in mice. 【Methods】 In the PPE group， the mouse abdominal aorta segment from the infrarenal abdominal aorta to the iliac artery was isolated and its branch arteries were ligated to avoid leakage during PPE perfusion. We perfused the isolated aorta segment with a PPE solution at a concentration of 1.5 U/mL for 5 min and then closed the abdominal cavity. The diameter of the abdominal aorta was measured before and 14 days after the surgery， and the perfusion segment of the arteries was collected at day 14 after the surgery. The histological characteristics of the aneurysm were analyzed and graded by histological and immunohistochemical methods. In the AngⅡ group， ten apolipoprotein E knockout mice were prepared， and AngⅡ [1 000 ng/(kg·min)] was infused with osmotic pumps for 28 days. The aorta was separated and the aneurysm aorta segment was analyzed. The wild type mice were used as normal health controls. 【Results】 In the PPE group， the diameter of the PPE perfused aorta segments increased and was significantly larger than the basal diameter ［（0.52±0.02） mm vs. （1.23±0.11） mm］ at day 14 after surgery. All the ten mice developed AAA after PPE application. The histological results showed typical pathological features of AAA in PPE perfused mice， such as elastic fiber breakage， smooth muscle exhaustion， and increased inflammation. Six of the ten mice developed aneurysms after AngⅡ infusion （6/10）. The aneurysms/dilatations were mostly in the suprarenal abdominal aorta， but also in the thoracic aorta and aortic arch. The histology analysis showed that the formation of arterial dissection was common after AngⅡ infusion， and the typical vascular “false lumen” was found. The breakage of elastic fibers， the exhaustion of smooth muscle damage， and the inflammatory response were not as typical as the PPE model in AngⅡ perfused animals. 【Conclusion】 The histological characteristics of PPE induced AAA are very typical and well present the inflammatory process in the development of aneurysm. The AngⅡ model is suitable for the study of aneurysms combined with aortic dissection. Both models have their own advantages and can complement each other.

Objective:To investigate the applicability of time series model in predicting incidence of nosocomial infection in a cancer center in Shanghai, and to provide the references for early warning and prevention.Methods:The nosocomial infection data of inpatients of a tertiary oncology hospital in Shanghai from 2013 to 2018 were collected. The autoregressive integrated moving average (ARIMA) model and the exponential smoothing model were established by SPSS 22.0 expert modeler. The fitting predictions were compared between these two time series models to select the optimal one. The nosocomial infection data from January 2019 to June 2019 were used to test the predictive effect of the model.Results:A total of 379 477 cancer inpatients were studied, 3 170 of which acquired nosocomial infection and the incidence was 0.84% from 2013 to 2018. Additive Holt-Winters method exponential smoothing model was the better model with R2of 0.82. Using this model, the predicted value fitted well with observed value from January 2019 to June 2019, and the mean relative percentage error was 15.22%. Conclusion:Additive Holt-Winters method exponential smoothing model could be used to fit and predict the tendency of nosocomial infection among cancer patients, which can provide reference for surveillance of nosocomial infection in oncology hospitals.

Objective:To detect the genes of common genetic diseases in newborns with the high-throughput sequencing technology based on target gene capture, to study the incidence rate of such diseases, the carrying rate and variant types of pathogenic mutations related to such diseases, and to explore the application value of the high-throughput sequencing technology in screening genetic diseases of newborns.Methods:The heel blood of 1 793 newborns born in Guangdong province from June 2019 to April 2020 were collected, and the exon regions of 138 common genetic disease-related genes in neonates were detected using the high-throughput sequencing technology based on target gene capture.The pathogenicity of the mutations was interpreted according to the " Classification Criteria and Guidelines for Genetic Variation(2017)" , in which known disease and probable disease were considered as positive mutations.The positive mutations were verified by Sanger sequencing technology, and the test results were analyzed with statistical methods.Results:Among the 1 793 newborns, 978 were male and 815 were female.A total of 158 positive cases were screened(8.81%), and 11 positive diseases were detected.Among the positive diseases, there were 41 cases(2.29%)of autosomal recessive deafness type 1A, 40 cases(2.23%)of Gilbert syndrome or Crigler-Najjar syndrome, and 33 cases(1.84%)of glucose-6-phosphate dehydrogenase deficiency(1.84%), 19 cases(1.06%)of familial hypercho-lesterolemia, 18 cases(1.00%) of sodium taurocholate cotransporter peptide deficiency disease, 2 cases(0.11%)of mitochondrial non-syndromic deafness, 2 cases(0.11%)of Citrin deficiency, 1 case(0.06%)of holocarboxylase synthase deficiency, 1 case(0.06%)of β-thalassemia and 1 case(0.06%)of metachromatic leukodystrophies.Of all studied cases, 972 carried one or more positive mutations, involving 85 kinds of diseases in total.The diseases with a high carrying rate were Gilbert syndrome or Crigler-Najjar syndrome(359 cases, 20.02%), autosomal recessive deafness type 1A(302 cases, 16.84%), and sodium taurocholate cotransport peptide deficiency disease(291 cases, 16.22%). The high-frequency mutation sites were UGT1A1 gene c. 211G> A, GJB2 gene c .109G> A and SLC10A1 gene c. 800C> T. Conclusions:The common genetic diseases detected in neonates from Guangdong province are autosomal recessive deafness type 1A, Gilbert syndrome or Crigler-Najjar syndrome, glucose-6-phosphate dehydrogenase deficiency, familial hypercholesterolemia, and sodium taurocholate cotransport peptide deficiency.There are high-frequency carrying mutation sites in the population.Preliminary genetic screening of common neonatal genetic diseases can accumulate data and experience for the development of newborn genetic screening.