Computational and Mathematical Methods in Medicine

Journal Information
ISSN / EISSN: 1748670X / 17486718
Published by: Hindawi Limited
Total articles ≅ 4,119

Latest articles in this journal

Na Ren, ,
Computational and Mathematical Methods in Medicine, Volume 2022, pp 1-12; https://doi.org/10.1155/2022/3938492

Abstract:
Artificial intelligence (AI) technology has huge scope in developing models to predict the survival rate of critically ill patients in the intensive care unit (ICU). The availability of electronic clinical data has led to the widespread use of various machine learning approaches in this field. Innovative algorithms play a crucial role in boosting the performance of models. This study uses a stacked ensemble model to predict mortality in ICU by incorporating the clinical severity scoring results, in which several machine learning algorithms are employed to compare the performance. The experimental results show that the stacked ensemble model achieves good performance compared with the model without integrating the severity scoring results, which has the area under curve (AUC) of 0.879 and 0.862, respectively. To improve the performance of prediction, two feature subsets are obtained based on different feature selection techniques, labeled as SetS and SetT. Evaluation performances show that the SEM based on the SetS achieves a higher AUC value (0.879 and 0.860). Finally, the SHapley Additive exPlanations (SHAP) analysis is employed to interpret the correlation between the risk features and the outcome.
Yu Zhang, Yongfang Xie, Xiaorong Huang, Langlang Zhang, Kunxian Shu
Computational and Mathematical Methods in Medicine, Volume 2022, pp 1-32; https://doi.org/10.1155/2022/7300788

Abstract:
Hepatocellular carcinoma (LIHC) is the fifth common cancer worldwide, and it requires effective diagnosis and treatment to prevent aggressive metastasis. The purpose of this study was to construct a machine learning-based diagnostic model for the diagnosis of liver cancer. Using weighted correlation network analysis (WGCNA), univariate analysis, and Lasso-Cox regression analysis, protein-protein interactions network analysis is used to construct gene networks from transcriptome data of hepatocellular carcinoma patients and find hub genes for machine learning. The five models, including gradient boosting, random forest, support vector machine, logistic regression, and integrated learning, were to identify a multigene prediction model of patients. Immunological assessment, TP53 gene mutation and promoter methylation level analysis, and KEGG pathway analysis were performed on these groups. Potential drug molecular targets for the corresponding hepatocellular carcinomas were obtained by molecular docking for analysis, resulting in the screening of 2 modules that may be relevant to the survival of hepatocellular carcinoma patients, and the construction of 5 diagnostic models and multiple interaction networks. The modes of action of drug-molecule interactions that may be effective against hepatocellular carcinoma core genes CCNA2, CCNB1, and CDK1 were investigated. This study is expected to provide research ideas for early diagnosis of hepatocellular carcinoma.
Ai Chen, Weibin Wu, Siming Lin,
Computational and Mathematical Methods in Medicine, Volume 2022, pp 1-17; https://doi.org/10.1155/2022/3677532

Abstract:
Hypoxic pulmonary hypertension (HPH) is a fatal chronic pulmonary circulatory disease, characterized by hypoxic pulmonary vascular constriction and remodeling. Studies performed to date have confirmed that endothelial dysfunction plays crucial roles in HPH, while the underlying mechanisms have not been fully revealed. The microarray dataset GSE11341 was downloaded from the Gene Expression Omnibus (GEO) database to identify differentially expressed genes (DEGs) between hypoxic and normoxic microvascular endothelial cell, followed by Gene Ontology (GO) annotation/Kyoto Encyclopedia of Genes and Genomes (KEGG), Gene Set Enrichment Analysis (GSEA) pathway enrichment analysis, and protein-protein interaction (PPI) network construction. Next, GSE160255 and RT-qPCR were used to validate hub genes. Meanwhile, GO/KEGG and GSEA were performed for each hub gene to uncover the potential mechanism. A nomogram based on hub genes was established. Furthermore, mRNA-miRNA network was predicted by miRNet, and the Connectivity Map (CMAP) database was in use to identify similarly acting therapeutic candidates. A total of 148 DEGs were screened in GSE11341, and three hub genes (VEGFA, CDC25A, and LOX) were determined and validated via GSE160255 and RT-qPCR. Abnormalities in the pathway of vascular smooth muscle contraction, lysosome, and glycolysis might play important roles in HPH pathogenesis. The hub gene-miRNA network showed that hsa-mir-24-3p, hsa-mir-124-3p, hsa-mir-195-5p, hsa-mir-146a-5p, hsa-mir-155-5p, and hsa-mir-23b-3p were associated with HPH. And on the basis of the identified hub genes, a practical nomogram is developed. To repurpose known and therapeutic drugs, three candidate compounds (procaterol, avanafil, and lestaurtinib) with a high level of confidence were obtained from the CMAP database. Taken together, the identification of these three hub genes, enrichment pathways, and potential therapeutic drugs might have important clinical implications for HPH diagnosis and treatment.
Retraction
Computational and Mathematical Methods in Medicine
Computational and Mathematical Methods in Medicine, Volume 2022, pp 1-1; https://doi.org/10.1155/2022/9898271

Zhen-Zhen Yuan, Zhao Yang, Si Wu
Computational and Mathematical Methods in Medicine, Volume 2022, pp 1-12; https://doi.org/10.1155/2022/1873004

Abstract:
Background. With the aging of the social population, Osteoarthritis (OA) has already become a vital health and economic problem globally. Shujin Dingtong recipe (SJDTR) is an effective formula to treat OA in China. Although studies have shown that SJDTR can significantly alleviate OA symptoms, its mechanism still remains unclear. Purpose. This study is aimed at investigating the potential mechanism of SJDTR for the treatment of OA based on network pharmacology and molecular docking. Methods. Main ingredients of SJDTR were retrieved from the Traditional Chinese Medicine Systems Pharmacology (TCMSP) database. OA disease targets were obtained from the Gene Expression Omnibus (GEO) database. The overlapped targets and signaling pathways were explored using Protein-Protein Interaction (PPI) network, Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG). Following this, the core targets were employed to dock with corresponding components via molecular docking in order to further explore the mechanism of SJDTR in the treatment of OA. Results. From network pharmacology, we found 100 active components of SJDTR, 31 drug and OA-related targets, 1161 GO items, and 91 signaling pathways. Based on the analysis with PPI network and molecular docking, TP53, CCNB1, and MMP-2 were selected for the core targets of SJDTR against OA. Molecular docking demonstrated that Quercetin, Baicalein, and Luteolin, had good binding with the TP53, CCNB1, and MMP-2 protein, respectively. Conclusion. To conclude, our study suggested the main ingredients of SJDTR might alleviate the progression of OA through multiple targets and pathways. Additionally, network pharmacology and molecular docking, as new approaches, were adopted for systematically exploring the potential mechanism of SJDTR for the treatment of OA.
Taotao Dong, Linlin Wang, Ruowen Li, Qingqing Liu, Yiyue Xu, Yuan Wei, Xinlin Jiao, Xiaofeng Li, Yida Zhang, Youzhong Zhang, et al.
Computational and mathematical methods in medicine, Volume 2022, pp 1-14; https://doi.org/10.1155/2022/4364663

Abstract:
Background. Cervical cancer ranks as the 4th most common female cancer worldwide. Early stage cervical cancer patients can be treated with operation, but clinical staging system is not a good predictor of patients’ survival. We aimed to develop a novel prognostic model to predict the prognosis for operable cervical cancer patients with better accuracy than clinical staging system. Methods. A total of 13,952 operable cervical cancer patients were retrospectively enrolled in this study. The whole dataset was randomly split into a training set ( n=9,068 , 65%), validation set ( n=2,442 , 17.5%), and testing set ( n=2,442 , 17.5%). Cox proportional hazard (CPH) model and random survival forest (RSF) model were used as baseline models for the prediction of overall survival (OS). Then, a deep survival learning model (DSLM) was developed for OS prediction. Finally, a novel prognostic model was explored based on this DSLM. Results. The C-indexes for the CPH and RSF model were 0.731 and 0.753, respectively. DSLM, which had four layers that had 50 neurons in each layer, achieved a C-index of 0.782 in the validation set and a C-index of 0.758 in the testing set. The novel prognostic model based on DSLM showed better performances than the conventional clinical staging system (area under receiver operating curves were 0.826 and 0.689, respectively). Personalized survival curves for individual patient using this novel model also showed notably different survival slopes. Conclusions. Our study developed a novel, practical, personalized prognostic model for operable cervical cancer patients. This novel prognostic model may have the potential to provide a more prognostic information to oncologists.
Yu Hu, Yunxi Lan, QiQi Ran, Qianrong Gan, Wei Huang
Computational and mathematical methods in medicine, Volume 2022, pp 1-24; https://doi.org/10.1155/2022/2615580

Abstract:
Background. Chronic obstructive pulmonary disease (COPD) is becoming a major public health burden worldwide. It is urgent to explore more effective and safer treatment strategy for COPD. Notably, Xuefu Zhuyu Decoction (XFZYD) is widely used to treat respiratory system diseases, including COPD, in China. Objective. This study is aimed at comprehensively evaluating the therapeutic effects and molecular mechanism of XFZYD on COPD. Methods. Original clinical studies were searched from eight literature databases. Meta-analysis was conducted using the Review Manager software (version 5.4.1). Network pharmacology and molecular docking experiments were utilized to explore the mechanisms of action of XFZYD. Results. XFZYD significantly enhanced the efficacy of clinical treatment and improved the pulmonary function and hypoventilation of COPD patients. In addition, XFZYD significantly improved the hypercoagulability of COPD patients. The subgroup analysis suggested that XFZYD exhibited therapeutic effects on both stable and acute exacerbation of COPD. XFZYD exerted its therapeutic effects on COPD through multicomponent, multitarget, and multipathway characteristics. The intervention of the PI3K-AKT pathway may be the critical mechanism. Conclusion. The application of XFZYD based on symptomatic relief and supportive treatment is a promising clinical decision. More preclinical and clinical studies are still needed to evaluate the safety and therapeutic effects of long-term use of XFZYD on COPD.
Retraction
Computational and Mathematical Methods in Medicine
Computational and mathematical methods in medicine, Volume 2022, pp 1-1; https://doi.org/10.1155/2022/9898723

Back to Top Top