Osteoporosis is a major public health concern that significantly increases the risk of fractures. The aim of this study was to develop a Machine Learning based predictive model to screen individuals at high risk of osteoporosis based on chronic disease data, thus facilitating early detection and personalized management. A total of 10,000 complete patient records of primary healthcare data in the German Disease Analyzer database (IMS HEALTH) were included, of which 1293 diagnosed with osteoporosis and 8707 without the condition. The demographic characteristics and chronic disease data, including age, gender, lipid disorder, cancer, COPD, hypertension, heart failure, CHD, diabetes, chronic kidney disease, and stroke were collected from electronic health records. Ten different machine learning algorithms were employed to construct the predictive mode. The performance of the model was further validated and the relative importance of features in the model was analyzed. Out of the ten machine learning algorithms, the Stacker model based on Logistic Regression, AdaBoost Classifier, and Gradient Boosting Classifier demonstrated superior performance. The Stacker model demonstrated excellent performance through ten-fold cross-validation on the training set and ROC curve analysis on the test set. The confusion matrix, lift curve and calibration curves indicated that the Stacker model had optimal clinical utility. Further analysis on feature importance highlighted age, gender, lipid metabolism disorders, cancer, and COPD as the top five influential variables. In this study, a predictive model for osteoporosis based on chronic disease data was developed using machine learning. The model shows great potential in early detection and risk stratification of osteoporosis, ultimately facilitating personalized prevention and management strategies.

Object: Osteosarcoma is a malignant tumor originating from the bones, commonly found in children and adolescents, especially in rapidly growing bone areas such as the knees and upper arms. In this study, we aim to delineate the evolution and convergence of research themes in osteosarcoma metabolomics over the past decade, identify major contributors, and forecast emerging trends that could direct future research efforts.Method: The bibliometric method has been applied to systematically analyze the literature in the field of osteosarcoma metabolomics. The relevant literatures were collected from the Web of Science Core Collection, spanning from January 1, 2014, to December 31, 2023. Tools such as CiteSpace, Bibliometrix, and VOSviewer were used for the visual analysis of the collected literatures. The focused information includes institutions, journals, countries, authors, keywords, and citations.Result: Various aspects in the field of osteosarcoma metabolism were analyzed. Shanghai Jiao Tong University has published the most papers in the past ten years, followed by Central South University and Zhejiang University. Among the sources, the international journal of molecular sciences publishes the most articles, and oncotarget is the journal with the highest H index. According to Bradford’s law, there are 34 core journals identified. A total of 5501 authors participated in the creation of papers in this field. The distribution of authors follows Lotka`s Law, and 85.3% of authors have only one article. 46% of the corresponding authors are from China, but most of these corresponding authors are not good at international cooperation. China also has the largest number of publications, followed by the United States. It can be confirmed that China dominates this field. Among the keywords, “expression” is the keyword that has received the most attention in the past ten years. All keywords can be divided into 9 clusters. Based on the explosive words and hot topics each year, we speculate that future research will focus on the tumor microenvironment, molecular mechanisms and autophagy, targeted therapies and inhibitors.Conclusion: In summary, this study comprehensively analyzed the current state of research in the field of osteosarcoma metabolism through bibliometric methods. The findings revealed the development trends and research hotspots in this field, which may provide valuable references for future research directions.

Purpose: Human gut microbiota has been shown to be significantly associated with various inflammatory diseases. Therefore, this study aimed to develop an excellent auxiliary tool for the diagnosis of juvenile idiopathic arthritis (JIA) based on fecal microbial biomarkers.Method: The fecal metagenomic sequencing data associated with JIA were extracted from NCBI, and the sequencing data were transformed into the relative abundance of microorganisms by professional data cleaning (KneadData, Trimmomatic and Bowtie2) and comparison software (Kraken2 and Bracken). After that, the fecal microbes with high abundance were extracted for subsequent analysis. The extracted fecal microbes were further screened by least absolute shrinkage and selection operator (LASSO) regression, and the selected fecal microbe biomarkers were used for model training. In this study, we constructed six different machine learning (ML) models, and then selected the best model for constructing a JIA diagnostic tool by comparing the performance of the models based on a combined consideration of area under receiver operating characteristic curve (AUC), accuracy, specificity, F1 score, calibration curves and clinical decision curves. In addition, to further explain the model, Permutation Importance analysis and Shapley Additive Explanations (SHAP) were performed to understand the contribution of each biomarker in the prediction process.Result: A total of 231 individuals were included in this study, including 203 JIA patients and Non-JIA individuals. In the analysis of diversity at the genus level, the alpha diversity represented by Shannon value was not significantly different between the two groups, while the belt diversity was slightly different. After selection by LASSO regression, 10 fecal microbe biomarkers were selected for model training. By comparing six different models, the XGB model showed the best performance, which average AUC, accuracy and F1 score were 0.976, 0.914 and 0.952, respectively, thus being used to construct the final JIA diagnosis model.Conclusion: A JIA diagnosis model based on XGB algorithm was constructed with excellent performance, which may assist physicians in early detection of JIA patients and improve the prognosis of JIA patients.

Background: Osteosarcoma (OS), a bone tumor with high ability of invasion and metastasis, has seriously affected the health of children and adolescents. Many studies have suggested a connection between OS and the epithelial-mesenchymal transition (EMT). We aimed to integrate EMT-Related genes (EMT-RGs) to predict the prognosis, immune infiltration, and therapeutic response of patients with OS.Methods: We used consensus clustering to identify potential EMT-Related OS molecular subtypes. Somatic mutation, tumor immune microenvironment, and functional enrichment analyses were performed for each subtype. We next constructed an EMT-Related risk signature and evaluated it by Kaplan-Meier (K-M) analysis survival and receiver operating characteristic (ROC) curves. Moreover, we constructed a nomogram to more accurately predict OS patients’ clinical outcomes. Response effects of immunotherapy in OS patients was analyzed by Tumor Immune Dysfunction and Exclusion (TIDE) analysis, while sensitivity for chemotherapeutic agents was analyzed using oncoPredict. Finally, the expression patterns of hub genes were investigated by single-cell RNA sequencing (scRNA-seq) data analysis.Results: A total of 53 EMT-RDGs related to prognosis were identified, separating OS samples into two separate subgroups. The EMT-high subgroup showed favourable overall survival and more active immune response. Significant correlations were found between EMT-Related DEGs and functions as well as pathways linked to the development of OS. Additionally, a risk signature was established and OS patients were divided into two categories based on the risk scores. The signature presented a good predictive performance and could be recognized as an independent predictive factor for OS. Furthermore, patients with higher risk scores exhibited better sensitivity for five drugs, while no significant difference existed in immunotherapy response between the two risk subgroups. scRNA-seq data analysis displayed different expression patterns of the hub genes.Conclusion: We developed a novel EMT-Related risk signature that can be considered as an independent predictor for OS, which may help improve clinical outcome prediction and guide personalized treatments for patients with OS.