Developing the new diagnostic model by integrating bioinformatics and machine learning for osteoarthritis DOI Creative Commons

Jian Du,

Tian Zhou, Wei Zhang

и другие.

Journal of Orthopaedic Surgery and Research, Год журнала: 2024, Номер 19(1)

Опубликована: Дек. 18, 2024

Osteoarthritis (OA) is a common cause of disability among the elderly, profoundly affecting quality life. This study aims to leverage bioinformatics and machine learning develop an artificial neural network (ANN) model for diagnosing OA, providing new avenues early diagnosis treatment. From Gene Expression Omnibus (GEO) database, we first obtained OA synovial tissue microarray datasets. Differentially expressed genes (DEGs) associated with were identified through utilization Limma package weighted gene co-expression analysis (WGCNA). Subsequently, protein-protein interaction (PPI) employed identify most relevant potential feature ANN diagnostic receiver operating characteristic (ROC) curve constructed evaluate performance model. In addition, expression levels verified using real-time quantitative polymerase chain reaction (qRT-PCR). Finally, immune cell infiltration was performed CIBERSORT algorithm explore correlation between cells. The WGCNA total 72 DEGs related which 12 up-regulated 60 down-regulated. Then, PPI 21 hub genes, three algorithms finally screened four (BTG2, CALML4, DUSP5, GADD45B). based on these genes. AUC training set 0.942, validation 0.850. qRT-PCR results demonstrated significant downregulation BTG2, GADD45 mRNA in samples compared normal samples, while CALML4 level exhibited upregulation. Immune revealed B cells memory, T gamma delta, naive, Plasma cells, CD4 memory resting, NK abnormal activated may be progression OA. GADD45B as good developed, perspective personalized treatment

Язык: Английский

A nomogram incorporating CT-based peri-hematoma radiomics features to predict functional outcome in patients with intracerebral hemorrhage DOI
Xiaona Xia,

Jieqiong Liu,

Jiufa Cui

и другие.

European Journal of Radiology, Год журнала: 2024, Номер 183, С. 111871 - 111871

Опубликована: Дек. 6, 2024

Язык: Английский

Процитировано

3

Objectively assessing visual analogue scale of knee osteoarthritis pain using thermal imaging DOI
Bitao Ma, Jiajie Chen,

Xiaoxiao Yan

и другие.

Displays, Год журнала: 2024, Номер 84, С. 102770 - 102770

Опубликована: Июнь 8, 2024

Язык: Английский

Процитировано

2

Targeting Molecular Collagen Defects from the Initiation of Knee Osteoarthritis DOI Open Access
Kui Huang, Rongmao Qiu,

Yijie Fang

и другие.

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Июнь 14, 2024

Abstract Knee osteoarthritis (OA) is the most prevalent degenerative joint disease. When morphological changes become apparent on radiographs, no approved treatment can reverse disease process. Early diagnosis an unmet need demanding new molecular and imaging biomarkers to define OA from earliest stages. In this context, we focus collagen, basic building block of all tissues, interrogate how development affects collagen’s folding, a previously underexplored area. Here, through whole-joint mapping with peptide that recognizes unfolded collagen molecules, report discovery denaturation in cartilage before proteolysis major histopathological degeneration animal models patients. Mechanistically, reveal such defects be driven by mechanical overloading without collagenase degradation are intimately associated glycosaminoglycan loss. We showcase advantages using as early-stage hallmark for vivo therapeutic evaluation magnetic resonance (MRI) subtle challenging detect conventional morphology-based MRI. These results highlight biomolecular integrity crucial dimension characterizing foundation diagnosing beyond.

Язык: Английский

Процитировано

1

Transcriptome combined with single cell to explore hypoxia-related biomarkers in osteoarthritis DOI
Xingyu Liu, Guangdi Li,

Riguang Liu

и другие.

Journal of Chromatography B, Год журнала: 2024, Номер 1246, С. 124274 - 124274

Опубликована: Авг. 15, 2024

Язык: Английский

Процитировано

1

Basic research is the foundation and driving force for clinical translation DOI Creative Commons
Gang Li

Journal of Orthopaedic Translation, Год журнала: 2024, Номер 45, С. A1 - A2

Опубликована: Март 1, 2024

Язык: Английский

Процитировано

0

Comparative Analysis of Repeatability in CT Radiomics and Dosiomics Features under Image Perturbation: A Study in Cervical Cancer Patients DOI Open Access
Zongrui Ma, Jiang Zhang, Xi Liu

и другие.

Cancers, Год журнала: 2024, Номер 16(16), С. 2872 - 2872

Опубликована: Авг. 18, 2024

This study aims to evaluate the repeatability of radiomics and dosiomics features via image perturbation patients with cervical cancer. A total 304 cancer planning CT images dose maps were retrospectively included. Random translation, rotation, contour randomization applied before feature extraction. The was assessed using intra-class correlation coefficient (ICC). Pearson (r) adopted quantify between characteristics repeatability. In general, lower compared features, especially after small-sigma Laplacian-of-Gaussian (LoG) wavelet filtering. More repeatable (ICC > 0.9) observed when extracted from original, Large-sigma LoG filtered, LLL-/LLH-wavelet filtered images. Positive correlations found entropy high-repeatable number in both (r = 0.56, 0.68). Radiomics showed higher features. These findings highlight potential for robust quantitative imaging analysis patients, while suggesting need further refinement approaches enhance their

Язык: Английский

Процитировано

0

Exploring Trends and Gaps in Osteoarthritis Biomarker Research (1999-2024): A Citation Analysis of Top 50 Cited Articles DOI Creative Commons

Wenjin Hu,

Jiyong Yang, Li Liu

и другие.

Cartilage, Год журнала: 2024, Номер unknown

Опубликована: Окт. 18, 2024

Purpose This study aimed to comprehensively analyze the landscape of osteoarthritis (OA) biomarker research through citation analysis top-cited articles, identifying trends and gaps in this field. Methods The Web Science Core Collection was utilized retrieve top 50 cited articles on OA biomarkers. Data extraction included publication characteristics, metrics, categorization. Statistical analyses were conducted discern correlations assess significance. Results spanned years 1999 2020, collectively 4849 accumulating a total 6177 citations, resulting an average 123.5 citations per document. Citations article varied between 78 359, with density ranging from 3.9 23.93. Analysis revealed comparable impact recent older publications. Predominant cartilage-related blood-based biomarkers, while inflammation-related, radiomics, multi-omics emerged as potential future directions. In BIPEDS classification, identified biomarkers evaluating intervention efficacy safety. Conclusion Despite significant advancements, there is no universally acknowledged for OA. Addressing exploration crucial enhancing management strategies. provides insights into prevailing directions guiding investigations therapeutic development.

Язык: Английский

Процитировано

0

Developing the new diagnostic model by integrating bioinformatics and machine learning for osteoarthritis DOI Creative Commons

Jian Du,

Tian Zhou, Wei Zhang

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 26, 2024

Abstract Background: Osteoarthritis (OA) is a common cause of disability among the elderly, profoundly affecting quality life. This study aims to leverage bioinformatics and machine learning develop an artificial neural network (ANN) model for diagnosing OA, providing new avenues early diagnosis treatment. Methods:From Gene Expression Omnibus (GEO) database, we first obtained OA synovial tissue microarray datasets. Differentially expressed genes (DEGs) associated with were identified through utilization Limma package weighted gene co-expression analysis (WGCNA). Subsequently, protein-protein interaction (PPI) employed identify most relevant potential signature OA,and ANN diagnostic receiver operating characteristic (ROC) curve constructed evaluate performance model. Finally, immune cell infiltration was performed using CIBERSORT algorithm explore correlation between cells. Results: The WGCNA total 72 DEGs related OA,of which 12 up-regulated 60 down-regulated. Then, PPI 21 hub genes, three algorithms finally screened four feature (BTG2, CALML4, DUSP5, GADD45B). The based on these genes. AUC training set 0.942, validation 0.850. Immune revealed B cells memory, T gamma delta, naive, Plasma cells, CD4 memory resting, NK abnormal activated may be progression OA. Conclusions: In this study, BTG2, GADD45B as excellent has been developed. Therefore, established in research can serve reliable reference provide novel perspective pathogenesis

Язык: Английский

Процитировано

0

Developing the new diagnostic model by integrating bioinformatics and machine learning for osteoarthritis DOI Creative Commons

Jian Du,

Tian Zhou, Wei Zhang

и другие.

Journal of Orthopaedic Surgery and Research, Год журнала: 2024, Номер 19(1)

Опубликована: Дек. 18, 2024

Osteoarthritis (OA) is a common cause of disability among the elderly, profoundly affecting quality life. This study aims to leverage bioinformatics and machine learning develop an artificial neural network (ANN) model for diagnosing OA, providing new avenues early diagnosis treatment. From Gene Expression Omnibus (GEO) database, we first obtained OA synovial tissue microarray datasets. Differentially expressed genes (DEGs) associated with were identified through utilization Limma package weighted gene co-expression analysis (WGCNA). Subsequently, protein-protein interaction (PPI) employed identify most relevant potential feature ANN diagnostic receiver operating characteristic (ROC) curve constructed evaluate performance model. In addition, expression levels verified using real-time quantitative polymerase chain reaction (qRT-PCR). Finally, immune cell infiltration was performed CIBERSORT algorithm explore correlation between cells. The WGCNA total 72 DEGs related which 12 up-regulated 60 down-regulated. Then, PPI 21 hub genes, three algorithms finally screened four (BTG2, CALML4, DUSP5, GADD45B). based on these genes. AUC training set 0.942, validation 0.850. qRT-PCR results demonstrated significant downregulation BTG2, GADD45 mRNA in samples compared normal samples, while CALML4 level exhibited upregulation. Immune revealed B cells memory, T gamma delta, naive, Plasma cells, CD4 memory resting, NK abnormal activated may be progression OA. GADD45B as good developed, perspective personalized treatment

Язык: Английский

Процитировано

0