Bing Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bing Li has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Chao Qin
Department of Joint, Tianjin Hospital, Tianjin, China
2 shared publications- Jun Liu
Clinical College of Orthopedics, Tianjin Medical University, Tianjin, China
2 shared publications - Jun Liu
Department of Joint, Tianjin Hospital, Tianjin, China
2 shared publications Li Wang
Tianjin Medical University, Tianjin, China
2 shared publicationsMingkuan Zhao
National Elite Institute of Engineering, Chongqing University, Chongqing, China
2 shared publicationsTao Yang
Orthopedics Department, Tianjin Hospital, Tianjin, China
2 shared publications
Latest Publications
- Open Access
- 26 June 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-10
Identifying significant structural factors associated with knee pain severity in patients with osteoarthritis using machine learning
Our main objective was to use machine learning methods to identify significant structural factors associated with pain severity in knee osteoarthritis patients. Additionally, we assessed the potential of various classes of imaging data using machine learning techniques to gauge knee pain severity. The data of semi-quantitative assessments of knee radiographs, semi-quantitative assessments of knee magnetic resonance imaging (MRI), and MRI images from 567 individuals in the Osteoarthritis Initiative (OAI) were utilized to train a series of machine learning models. Models were constructed using five machine learning methods: random forests (RF), support vector machines (SVM), logistic regression (LR), decision tree (DT), and Bayesian (Bayes). Employing tenfold cross-validation, we selected the best-performing models based on the area under the curve (AUC). The study results indicate no significant difference in performance among models using different imaging data. Subsequently, we employed a convolutional neural network (CNN) to extract features from magnetic resonance imaging (MRI), and class activation mapping (CAM) was utilized to generate saliency maps, highlighting regions associated with knee pain severity. A radiologist reviewed the images, identifying specific lesions colocalized with the CAM. The review of 421 knees revealed that effusion/synovitis (30.9%) and cartilage loss (30.6%) were the most frequent abnormalities associated with pain severity. Our study suggests cartilage loss and synovitis/effusion lesions as significant structural factors affecting pain severity in patients with knee osteoarthritis. Furthermore, our study highlights the potential of machine learning for assessing knee pain severity using radiographs.
- 26 June 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-10
Open AccessIdentifying significant structural factors associated with knee pain severity in patients with osteoarthritis using machine learning
Our main objective was to use machine learning methods to identify significant structural factors associated with pain severity in knee osteoarthritis patients. Additionally, we assessed the potential of various classes of imaging data using machine learning techniques to gauge knee pain severity. The data of semi-quantitative assessments of knee radiographs, semi-quantitative assessments of knee magnetic resonance imaging (MRI), and MRI images from 567 individuals in the Osteoarthritis Initiative (OAI) were utilized to train a series of machine learning models. Models were constructed using five machine learning methods: random forests (RF), support vector machines (SVM), logistic regression (LR), decision tree (DT), and Bayesian (Bayes). Employing tenfold cross-validation, we selected the best-performing models based on the area under the curve (AUC). The study results indicate no significant difference in performance among models using different imaging data. Subsequently, we employed a convolutional neural network (CNN) to extract features from magnetic resonance imaging (MRI), and class activation mapping (CAM) was utilized to generate saliency maps, highlighting regions associated with knee pain severity. A radiologist reviewed the images, identifying specific lesions colocalized with the CAM. The review of 421 knees revealed that effusion/synovitis (30.9%) and cartilage loss (30.6%) were the most frequent abnormalities associated with pain severity. Our study suggests cartilage loss and synovitis/effusion lesions as significant structural factors affecting pain severity in patients with knee osteoarthritis. Furthermore, our study highlights the potential of machine learning for assessing knee pain severity using radiographs.
- Open Access
- 7 February 2024
- Published by Frontiers Media SA in Frontiers in Public Health
- Vol. 12, 1348236
Exploring the potential of the sit-to-stand test for self-assessment of physical condition in advanced knee osteoarthritis patients using computer vision
Introduction: Knee osteoarthritis (KOA) is a prevalent condition often associated with a decline in patients’ physical function. Objective self-assessment of physical conditions poses challenges for many advanced KOA patients. To address this, we explored the potential of a computer vision method to facilitate home-based physical function self-assessments.Methods: We developed and validated a simple at-home artificial intelligence approach to recognize joint stiffness levels and physical function in individuals with advanced KOA. One hundred and four knee osteoarthritis (KOA) patients were enrolled, and we employed the WOMAC score to evaluate their physical function and joint stiffness. Subsequently, patients independently recorded videos of five sit-to-stand tests in a home setting. Leveraging the AlphaPose and VideoPose algorithms, we extracted time-series data from these videos, capturing three-dimensional spatiotemporal information reflecting changes in key joint angles over time. To deepen our study, we conducted a quantitative analysis using the discrete wavelet transform (DWT), resulting in two wavelet coefficients: the approximation coefficients (cA) and the detail coefficients (cD).Results: Our analysis specifically focused on four crucial joint angles: “the right hip,” “right knee,” “left hip,” and “left knee.” Qualitative analysis revealed distinctions in the time-series data related to functional limitations and stiffness among patients with varying levels of KOA. In quantitative analysis, we observed variations in the cA among advanced KOA patients with different levels of physical function and joint stiffness. Furthermore, there were no significant differences in the cD between advanced KOA patients, demonstrating different levels of physical function and joint stiffness. It suggests that the primary difference in overall movement patterns lies in the varying degrees of joint stiffness and physical function among advanced KOA patients.Discussion: Our method, designed to be low-cost and user-friendly, effectively captures spatiotemporal information distinctions among advanced KOA patients with varying stiffness levels and functional limitations utilizing smartphones. This study provides compelling evidence for the potential of our approach in enabling self-assessment of physical condition in individuals with advanced knee osteoarthritis.
- 7 February 2024
- Published by Frontiers Media SA in Frontiers in Public Health
- Vol. 12, 1348236
Open AccessExploring the potential of the sit-to-stand test for self-assessment of physical condition in advanced knee osteoarthritis patients using computer vision
Introduction: Knee osteoarthritis (KOA) is a prevalent condition often associated with a decline in patients’ physical function. Objective self-assessment of physical conditions poses challenges for many advanced KOA patients. To address this, we explored the potential of a computer vision method to facilitate home-based physical function self-assessments.Methods: We developed and validated a simple at-home artificial intelligence approach to recognize joint stiffness levels and physical function in individuals with advanced KOA. One hundred and four knee osteoarthritis (KOA) patients were enrolled, and we employed the WOMAC score to evaluate their physical function and joint stiffness. Subsequently, patients independently recorded videos of five sit-to-stand tests in a home setting. Leveraging the AlphaPose and VideoPose algorithms, we extracted time-series data from these videos, capturing three-dimensional spatiotemporal information reflecting changes in key joint angles over time. To deepen our study, we conducted a quantitative analysis using the discrete wavelet transform (DWT), resulting in two wavelet coefficients: the approximation coefficients (cA) and the detail coefficients (cD).Results: Our analysis specifically focused on four crucial joint angles: “the right hip,” “right knee,” “left hip,” and “left knee.” Qualitative analysis revealed distinctions in the time-series data related to functional limitations and stiffness among patients with varying levels of KOA. In quantitative analysis, we observed variations in the cA among advanced KOA patients with different levels of physical function and joint stiffness. Furthermore, there were no significant differences in the cD between advanced KOA patients, demonstrating different levels of physical function and joint stiffness. It suggests that the primary difference in overall movement patterns lies in the varying degrees of joint stiffness and physical function among advanced KOA patients.Discussion: Our method, designed to be low-cost and user-friendly, effectively captures spatiotemporal information distinctions among advanced KOA patients with varying stiffness levels and functional limitations utilizing smartphones. This study provides compelling evidence for the potential of our approach in enabling self-assessment of physical condition in individuals with advanced knee osteoarthritis.
- Open Access
- 26 September 2023
- Published by Wiley in Orthopaedic Surgery
- Vol. 15 (11) , 2947-2959
Analysis of Zinc and Stromal Immunity in Disuse Osteoporosis: Mendelian Randomization and Transcriptomic Analysis
Objective: Disuse osteoporosis is known to be primarily caused by a lack of exercise. However, the causal relationships between zinc and immunity and disuse osteoporosis remain unknown. This study investigated these relationships and their potential mechanisms.Methods: This study was an integrative study combining genome‐wide association studies and transcriptomics. Two‐sample Mendelian randomization analysis (MR) was used to analyze the causal relationships between exposures (zinc, immunity, physical activity) and the outcome (osteoporosis) with the aid of single‐nucleotide polymorphisms (SNPs) as instrumental variables (IVs). Four models, MR‐Egger, inverse variance weighted, weighted median and MR‐Pleiotrophy RESidual Sum and Outlier (MRPRESSO), were used to calculate odds ratio values. Sensitivity and heterogeneity analyses were also performed using MRPRESSO and MR‐Egger methods. The mRNA transcriptomic analysis was subsequently conducted. Zinc metabolism scores were acquired through single‐sample Gene Set Enrichment Analysis algorithms. Stromal scores were obtained using the R Package “estimate” algorithms. Important Kyoto Encyclopedia of Genes and Genomes and Gene Ontology pathways were also derived through gene set variation analysis. Cytoscape software helped construct the transcription factor (TF)–mRNA–microRNA (miRNA) network. Virtual screening and molecular docking were performed. Polymerase chain reaction validation was also carried out in vivo.Results: Causal relationships were demonstrated between zinc and exercise (95% confidence interval [CI] = 1.30–2.95, p = 0.001), exercise and immunity (95% CI = 0.36–0.80, p = 0.002), exercise and osteoporosis (95% CI = 0.97–0.99, p = 0.0007), and immunity disorder and osteoporosis (95% CI = 1.30–2.03, p = 0.00002). One hundred and seventy‐nine mRNAs in important modules were screened. Combining the differential expressional genes (DEGs) and the Boruta selection, six DEGs were screened (AHNAK, CSF2, ADAMTS12, SRA1, RUNX2, and SLC39A14). TF HOXC10 and miRNA hsa‐miR‐204 were predicted. Then, the TF–mRNA–miRNA network was successfully constructed. RUNX2 and SLC39A14 were identified as hub mRNAs in the TF–mRNA–miRNA network. Eventually, the novel small drug C6O4NH5 was designed according to the pharmacophore structure of SLC39A14. The docking energy for the novel drug was −5.83 kcal/mol. SLC39A14 and RUNX2 were downregulated (of statistical significance p‐value < 0.05) in our animal experiment.Conclusion: This study revealed that zinc had a protective causal relationship with disuse osteoporosis by promoting exercise and immunity. SLC39A14 and RUNX2 mRNA participated in this zinc‐related mechanism.
- 26 September 2023
- Published by Wiley in Orthopaedic Surgery
- Vol. 15 (11) , 2947-2959
Open AccessAnalysis of Zinc and Stromal Immunity in Disuse Osteoporosis: Mendelian Randomization and Transcriptomic Analysis
Objective: Disuse osteoporosis is known to be primarily caused by a lack of exercise. However, the causal relationships between zinc and immunity and disuse osteoporosis remain unknown. This study investigated these relationships and their potential mechanisms.Methods: This study was an integrative study combining genome‐wide association studies and transcriptomics. Two‐sample Mendelian randomization analysis (MR) was used to analyze the causal relationships between exposures (zinc, immunity, physical activity) and the outcome (osteoporosis) with the aid of single‐nucleotide polymorphisms (SNPs) as instrumental variables (IVs). Four models, MR‐Egger, inverse variance weighted, weighted median and MR‐Pleiotrophy RESidual Sum and Outlier (MRPRESSO), were used to calculate odds ratio values. Sensitivity and heterogeneity analyses were also performed using MRPRESSO and MR‐Egger methods. The mRNA transcriptomic analysis was subsequently conducted. Zinc metabolism scores were acquired through single‐sample Gene Set Enrichment Analysis algorithms. Stromal scores were obtained using the R Package “estimate” algorithms. Important Kyoto Encyclopedia of Genes and Genomes and Gene Ontology pathways were also derived through gene set variation analysis. Cytoscape software helped construct the transcription factor (TF)–mRNA–microRNA (miRNA) network. Virtual screening and molecular docking were performed. Polymerase chain reaction validation was also carried out in vivo.Results: Causal relationships were demonstrated between zinc and exercise (95% confidence interval [CI] = 1.30–2.95, p = 0.001), exercise and immunity (95% CI = 0.36–0.80, p = 0.002), exercise and osteoporosis (95% CI = 0.97–0.99, p = 0.0007), and immunity disorder and osteoporosis (95% CI = 1.30–2.03, p = 0.00002). One hundred and seventy‐nine mRNAs in important modules were screened. Combining the differential expressional genes (DEGs) and the Boruta selection, six DEGs were screened (AHNAK, CSF2, ADAMTS12, SRA1, RUNX2, and SLC39A14). TF HOXC10 and miRNA hsa‐miR‐204 were predicted. Then, the TF–mRNA–miRNA network was successfully constructed. RUNX2 and SLC39A14 were identified as hub mRNAs in the TF–mRNA–miRNA network. Eventually, the novel small drug C6O4NH5 was designed according to the pharmacophore structure of SLC39A14. The docking energy for the novel drug was −5.83 kcal/mol. SLC39A14 and RUNX2 were downregulated (of statistical significance p‐value < 0.05) in our animal experiment.Conclusion: This study revealed that zinc had a protective causal relationship with disuse osteoporosis by promoting exercise and immunity. SLC39A14 and RUNX2 mRNA participated in this zinc‐related mechanism.
- RetractedOpen Access
- 12 May 2022
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2022, 1-16
Exploring the Association between Glutathione Metabolism and Ferroptosis in Osteoblasts with Disuse Osteoporosis and the Key Genes Connecting them
Disused osteoporosis is a kind of osteoporosis, a common age-related disease. Neurological disorders are major risk factors for osteoporosis. Though there are many studies on disuse osteoporosis, the genetic mechanisms for the association between glutathione metabolism and ferroptosis in osteoblasts with disuse osteoporosis are still unclear. The purpose of this study is to explore the key genes and other related mechanism of ferroptosis and glutathione metabolism in osteoblast differentiation and disuse osteoporosis. By weighted gene coexpression network analysis (WGCNA), the process of osteoblast differentiation-related genes was studied in GSE30393. And the related functional pathways were found through the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis. By combining GSE1367 and GSE100933 together, key genes which were separately bound up with glutathione metabolism and ferroptosis were located. The correlation of these key genes was analyzed by the Pearson correlation coefficient. GSTM1 targeted agonist glutathione (GSH) selected by connectivity map (CMap) analysis was used to interfere with the molding disused osteoporosis process in MC3T3-E1 cells. RT-PCR and intracellular reactive oxygen species (ROS) were performed. Two important pathways, glutathione metabolism and ferroptosis pathways, were found. GSTM1 and TFRC were thought as key genes in disuse osteoporosis osteoblasts with the two mechanisms. The two genes have a strong negative correlation. Our experiment results showed that the expression of TFRC was consistent with the negative correlation with the activation process of GSTM1. The strong relationship between the two genes was proved. Glutathione metabolism and ferroptosis are important in the normal differentiation of osteoblasts and the process of disuse osteoporosis. GSTM1 and TFRC were the key genes. The two genes interact with each other, which can be seen as a bridge between the two pathways. The two genes participate in the process of reducing ROS in disuse osteoporosis osteoblasts.
- 12 May 2022
- Published by Wiley in Computational and Mathematical Methods in Medicine
- Vol. 2022, 1-16
RetractedOpen AccessExploring the Association between Glutathione Metabolism and Ferroptosis in Osteoblasts with Disuse Osteoporosis and the Key Genes Connecting them
Disused osteoporosis is a kind of osteoporosis, a common age-related disease. Neurological disorders are major risk factors for osteoporosis. Though there are many studies on disuse osteoporosis, the genetic mechanisms for the association between glutathione metabolism and ferroptosis in osteoblasts with disuse osteoporosis are still unclear. The purpose of this study is to explore the key genes and other related mechanism of ferroptosis and glutathione metabolism in osteoblast differentiation and disuse osteoporosis. By weighted gene coexpression network analysis (WGCNA), the process of osteoblast differentiation-related genes was studied in GSE30393. And the related functional pathways were found through the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis. By combining GSE1367 and GSE100933 together, key genes which were separately bound up with glutathione metabolism and ferroptosis were located. The correlation of these key genes was analyzed by the Pearson correlation coefficient. GSTM1 targeted agonist glutathione (GSH) selected by connectivity map (CMap) analysis was used to interfere with the molding disused osteoporosis process in MC3T3-E1 cells. RT-PCR and intracellular reactive oxygen species (ROS) were performed. Two important pathways, glutathione metabolism and ferroptosis pathways, were found. GSTM1 and TFRC were thought as key genes in disuse osteoporosis osteoblasts with the two mechanisms. The two genes have a strong negative correlation. Our experiment results showed that the expression of TFRC was consistent with the negative correlation with the activation process of GSTM1. The strong relationship between the two genes was proved. Glutathione metabolism and ferroptosis are important in the normal differentiation of osteoblasts and the process of disuse osteoporosis. GSTM1 and TFRC were the key genes. The two genes interact with each other, which can be seen as a bridge between the two pathways. The two genes participate in the process of reducing ROS in disuse osteoporosis osteoblasts.