scholarly journals Role of Plasma Proteomics in Predicting the Prognosis of Older Adult Patients with Chronic Coronary Syndrome

2021 ◽  
Author(s):  
Yulun Cai ◽  
Benchuan Hao ◽  
Jianqiao Chen ◽  
Yuerui Li ◽  
Hongbin Liu
Keyword(s):  
Machine Learning ◽  
Prospective Cohort ◽  
Quantitative Proteomics ◽  
Prognostic Model ◽  
Risk Model ◽  
Prognostic Biomarkers ◽  
Enzyme Linked Immunosorbent Assay ◽  
Coronary Syndrome ◽  
Chd Risk ◽  
Plasma Proteomics

Abstract Background: Chronic coronary syndrome (CCS) is a newly proposed concept and is hallmarked by more long-term major adverse cardiovascular events (MACEs), calling for accurate prognostic biomarkers for initial risk stratification.Methods: Data-independent acquisition liquid chromatography tandem mass spectrometry (DIA LC-MS/MS) quantitative proteomics was performed on 38 patients with CCS; 19 in the CCS events group and 19 in the non-events group as the controls. We also developed a machine-learning-based pipeline to identify proteins as potential biomarkers and validated the target proteins by enzyme-linked immunosorbent assay (ELISA) in an independent prospective cohort (n = 352).Results: Fifty-seven differentially expressed proteins were identified by quantitative proteomics and three final biomarkers were preliminarily selected from the machine-learning-based pipeline. Further validation with the prospective cohort showed that endothelial protein C receptor (EPCR) and cholesteryl ester transfer protein (CETP) levels at admission were significantly higher in the CCS events group than they were in the non-events group, whereas the carboxypeptidase B2 (CPB2) level was similar in the two groups. A correlation analysis showed that CETP was positively related to high-density lipoprotein cholesterol and triglyceride, and EPCR was positively related to fibrinogen. In the Cox survival analysis, EPCR and CETP were independent risk factors for MACEs. The cumulative risk duration of patients with high EPCR and CETP levels was significantly shorter than that of patients with low EPCR and CETP levels. We constructed a new prognostic model by combining the Framingham coronary heart disease (CHD) risk model with EPCR and CETP levels. This new model significantly improved the C-statistics for MACE prediction compared with that of the Framingham CHD risk model alone (AUC 0.732 vs. 0.684, p<0.05).Conclusions: Plasma proteomics was used to find biomarkers of predicting MACEs in patients with CCS. EPCR and CETP were identified as promising prognostic biomarkers for CCS. The Framingham CHD risk model combined with EPCR and CETP levels was shown to be a high-performance prognostic model for CCS.

scholarly journals Construction autophagy-related prognostic risk signature combined with clinicopathological validation analysis for survival prediction of kidney renal papillary cell carcinoma patients

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Hongjun Fei ◽  
Songchang Chen ◽  
Chenming Xu
Keyword(s):  
Cell Carcinoma ◽  
Prognostic Value ◽  
Prognostic Model ◽  
Risk Model ◽  
Cox Regression ◽  
Prognostic Biomarkers ◽  
Survival Prediction ◽  
Pathway Enrichment Analysis ◽  
Cox Regression Analysis ◽  
Related Risk

Abstract Background Little data is available on prognostic biomarkers and effective treatment options for Kidney Renal Papillary Cell Carcinoma (KIRP) patients, to find potential prognostic biomarkers and new targets was an urgent mission for KIRP therapy. Methods The differentially expressed autophagy-related genes (DEARGs) were screened out according to the RNA sequencing data in The Cancer Genome Atlas database, then identified survival-related DEARGs to establish a prognostic model for survival predicting of KIRP patients. Then we verified the robustness and validity of the prognostic risk model through clinicopathological data. At last, we evaluate the prognostic value of genes that formed the prognostic risk model individually. Results We analyzed the expression of 232 autophagy-related genes (ARGs) in 289 KIRP and 32 non-tumor tissue cases, and 40 mRNAs were screened out as DEARGs. The functional and pathway enrichment analysis was done and protein–protein interaction network was constructed for all DEARGs. To sift candidate DEARGs associated with KIRP patients’ survival and create an autophagy-related risk prognostic model, univariate and multivariate Cox regression analysis were did separately. Eventually 3 desirable independent prognostic DEARGs (P4HB, NRG1, and BIRC5) were picked out and used for construct the autophagy-related risk model. The accuracy of the prognostic risk model for survival prediction was assessed by Kaplan–Meier plotter, receiver-operator characteristic curve, and clinicopathological correlational analyses. The prognostic value of above 3 genes was verified individually by survival analysis and expression analysis on mRNA and protein level. Conclusions The autophagy-related prognostic model is accurate and applicable, it can predict OS independently for KIRP patients. Three independent prognostic DEARGs can benefit for facilitate personalized target treatment too.

scholarly journals New risk model is able to identify patients with a low risk of progression in systemic sclerosis

RMD Open ◽  
2021 ◽  
Vol 7 (2) ◽  
pp. e001524
Author(s):  
Nina Marijn van Leeuwen ◽  
Marc Maurits ◽  
Sophie Liem ◽  
Jacopo Ciaffi ◽  
Nina Ajmone Marsan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systemic Sclerosis ◽  
High Risk ◽  
Disease Progression ◽  
Risk Model ◽  
Immunosuppressive Drugs ◽  
Low Risk ◽  
Expert Assessment ◽  
Risk Of Progression

ObjectivesTo develop a prediction model to guide annual assessment of systemic sclerosis (SSc) patients tailored in accordance to disease activity.MethodsA machine learning approach was used to develop a model that can identify patients without disease progression. SSc patients included in the prospective Leiden SSc cohort and fulfilling the ACR/EULAR 2013 criteria were included. Disease progression was defined as progression in ≥1 organ system, and/or start of immunosuppression or death. Using elastic-net-regularisation, and including 90 independent clinical variables (100% complete), we trained the model on 75% and validated it on 25% of the patients, optimising on negative predictive value (NPV) to minimise the likelihood of missing progression. Probability cutoffs were identified for low and high risk for disease progression by expert assessment.ResultsOf the 492 SSc patients (follow-up range: 2–10 years), disease progression during follow-up was observed in 52% (median time 4.9 years). Performance of the model in the test set showed an AUC-ROC of 0.66. Probability score cutoffs were defined: low risk for disease progression (<0.197, NPV:1.0; 29% of patients), intermediate risk (0.197–0.223, NPV:0.82; 27%) and high risk (>0.223, NPV:0.78; 44%). The relevant variables for the model were: previous use of cyclophosphamide or corticosteroids, start with immunosuppressive drugs, previous gastrointestinal progression, previous cardiovascular event, pulmonary arterial hypertension, modified Rodnan Skin Score, creatine kinase and diffusing capacity for carbon monoxide.ConclusionOur machine-learning-assisted model for progression enabled us to classify 29% of SSc patients as ‘low risk’. In this group, annual assessment programmes could be less extensive than indicated by international guidelines.

Abstract 3481: A Prospective Comparison of NMR-Measured LDL Particle Number, Apolipoprotein B100, and Standard Lipids with Incident CHD in 27,673 Initially Healthy Women

Circulation ◽  
2007 ◽  
Vol 116 (suppl_16) ◽  
Author(s):  
Samia Mora ◽  
James Otvos ◽  
Julie E Buring ◽  
Nader Rifai ◽  
Paul M Ridker
Keyword(s):  
Prospective Cohort ◽  
Large Scale ◽  
Particle Number ◽  
Proton Nuclear Magnetic Resonance ◽  
Resonance Spectroscopy ◽  
Healthy Women ◽  
Prospective Comparison ◽  
Chd Risk ◽  
Hazard Ratios ◽  
Apolipoprotein B100

Background While ATP-III recommends measurement of total and HDL cholesterol (HDL-C) as part of coronary risk assessment, measurement of LDL particle number (LDL-P) is not currently recommended. Methods and Results In a prospective cohort of 27,673 initially healthy women, baseline LDL-P was measured by proton nuclear magnetic resonance spectroscopy, apolipoprotein B100 (ApoB) was measured using an immunoturbidimetric assay, and standard lipids were directly measured. LDL-P correlated with LDL cholesterol (LDL-C; r=0.62), ApoB (0.84), non HDL-C (0.74), and total:HDL-C ratio (0.80). During a mean follow-up of 11 years, 668 incident coronary heart disease (CHD) events occurred. Using the lowest quintile as the reference, and adjusting for age, smoking, blood pressure, diabetes, menopause, hormone use, and body mass index, the association of LDL-P with CHD was stronger than LDL-C (Table ), and comparable in magnitude to ApoB, non HDL-C and total:HDL-C ratio. In a subgroup analysis of women with LDL-C<100 mg/dL, elevations in LDL-P, ApoB, non HDL-C, or total:HDL-C ratio were all separately associated with higher CHD risk (P<0.001 for all). Both LDL-P and ApoB remained associated with CHD after additionally adjusting for total cholesterol, HDL-C, and triglycerides (hazard ratios for top vs bottom quintile: 2.03 [95% CI 1.27–3.24] for LDL-P, and 3.08 [95% CI 1.92– 4.93] for ApoB) overall, and similarly in women with LDL-C<100 mg/dL (2.77 [95%CI 1.05–7.29] for LDL-P and 2.62 [95%CI 0.97–7.05] for ApoB). Conclusions In this large-scale prospective cohort, elevations in NMR-measured LDL particle number were significantly associated with incident CHD, with a magnitude of risk not substantially different from ApoB, non HDL-C, or total:HDL-C ratio. Among women with LDL-C <100mg/dL, elevations in LDL-P, ApoB, non HDL-C, and total:HDL-C ratio all carried higher CHD risk. Risk Factor-Adjusted Hazard Ratios for Incident CHD

Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma

2017 ◽  
Vol 403 ◽  
pp. 21-27 ◽  
Author(s):  
Bin Zhang ◽  
Xin He ◽  
Fusheng Ouyang ◽  
Dongsheng Gu ◽  
Yuhao Dong ◽  
...  
Keyword(s):  
Machine Learning ◽  
Nasopharyngeal Carcinoma ◽  
Prognostic Biomarkers ◽  
Machine Learning Classifiers ◽  
Learning Classifiers
Sign in / Sign up

Export Citation Format

Share Document