Search

Coronary artery disease (CAD) is a global health issue. Lipid peroxidation produces various by-products that associate with CAD, such as 4-hydroxynonenal (HNE) and malondialdehyde (MDA). The autoantibodies against HNE and MDA-modified peptides may be useful in the diagnosis of CAD. This study included 41 healthy controls (HCs) and 159 CAD patients with stenosis rates of <30%, 30–70%, and >70%. The plasma level of autoantibodies against four different unmodified and HNE-modified peptides were measured in this study, including CFAH1211–1230, HPT78–108, IGKC2–19, and THRB328–345. Furthermore, feature ranking, feature selection, and machine learning models have been utilized to exploit the diagnostic performance. Also, we combined autoantibodies against MDA and HNE-modified peptides to improve the models' performance. The eXtreme Gradient Boosting (XGBoost) model received a sensitivity of 78.6% and a specificity of 90.4%. Our study demonstrated the combination of autoantibodies against oxidative modification may improve the model performance. [ABSTRACT FROM AUTHOR]

Coronary artery disease (CAD) is one of the most common subtypes of cardiovascular disease. The progression of CAD initiates from the plaque of atherosclerosis and coronary artery stenosis, and eventually turns into acute myocardial infarction (AMI) or stable CAD. Alpha-1-antichymotrypsin (AACT) has been highly associated with cardiac events. In this study, we proposed incorporating clinical data on AACT levels to establish a model for estimating the severity of CAD. Thirty-six healthy controls (HCs) and 162 CAD patients with stenosis rates of <30%, 30–70%, and >70% were included in this study. Plasma concentration of AACT was determined by enzyme-linked immunosorbent assay (ELISA). The receiver operating characteristic (ROC) curve analysis and associations were conducted. Further, five machine learning models, including decision tree, random forest, support vector machine, XGBoost, and lightGBM were implemented. The lightGBM model obtained a sensitivity of 81.4%, a specificity of 67.3%, and an area under the curve (AUC) of 0.822 for identifying CAD patients with a stenosis rate of <30% versus >30%. In this study, we provided a demonstration of a monitoring model with clinical data and AACT. [ABSTRACT FROM AUTHOR]

Bladder cancer has been increasing globally. Urinary cytology is considered a major screening method for bladder cancer, but it has poor sensitivity. This study aimed to utilize clinical laboratory data and machine learning methods to build predictive models of bladder cancer. A total of 1336 patients with cystitis, bladder cancer, kidney cancer, uterus cancer, and prostate cancer were enrolled in this study. Two-step feature selection combined with WEKA and forward selection was performed. Furthermore, five machine learning models, including decision tree, random forest, support vector machine, extreme gradient boosting (XGBoost), and light gradient boosting machine (GBM) were applied. Features, including calcium, alkaline phosphatase (ALP), albumin, urine ketone, urine occult blood, creatinine, alanine aminotransferase (ALT), and diabetes were selected. The lightGBM model obtained an accuracy of 84.8% to 86.9%, a sensitivity 84% to 87.8%, a specificity of 82.9% to 86.7%, and an area under the curve (AUC) of 0.88 to 0.92 in discriminating bladder cancer from cystitis and other cancers. Our study provides a demonstration of utilizing clinical laboratory data to predict bladder cancer. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms have been applied to predicting coronary artery disease (CAD). Our purpose was to utilize autoantibody isotypes against four different unmodified and malondialdehyde (MDA)-modified peptides among Taiwanese with CAD and healthy controls (HCs) for CAD prediction. In this study, levels of MDA, MDA-modified protein (MDA-protein) adducts, and autoantibody isotypes against unmodified peptides and MDA-modified peptides were measured with enzyme-linked immunosorbent assay (ELISA). To improve the performance of ML, we used decision tree (DT), random forest (RF), and support vector machine (SVM) coupled with five-fold cross validation and parameters optimization. Levels of plasma MDA and MDA-protein adducts were higher in CAD patients than in HCs. IgM anti-IGKC76–99 MDA and IgM anti-A1AT284–298 MDA decreased the most in patients with CAD compared to HCs. In the experimental results of CAD prediction, the decision tree classifier achieved an area under the curve (AUC) of 0.81; the random forest classifier achieved an AUC of 0.94; the support vector machine achieved an AUC of 0.65 for differentiating between CAD patients with stenosis rates of 70% and HCs. In this study, we demonstrated that autoantibody isotypes imported into machine learning algorithms can lead to accurate models for clinical use. [ABSTRACT FROM AUTHOR]

Simple Summary: Colorectal cancer (CRC) is currently the third leading cause of cancer death worldwide. Early diagnosis of CRC is important for increasing the opportunity for treatment and receiving a good prognosis. The aim of our study was to develop a detection method that combined wheat germ agglutinin (WGA) chromatography with mass spectrometry (MS) for early detection of CRC. Further, machine learning algorithms and logistic regression were applied to combine multiple biomarkers we discovered. We validated in a population of 286 plasma samples the diagnostic performance of peptides corresponding to WGA-captured protein and its combination, which received a sensitivity of 84.5% and a specificity of 97.5% in the diagnoses of CRC. Proteomic biomarkers combined with algorithms can provide a powerful tool for discriminating patients with CRC and health controls (HCs). Measurements of WGA-captured PF4, ITIH4, and APOE with MS are then useful for early detection of CRC. Additionally, our study revealed the potential of applying lectin chromatography with MS for disease diagnosis. Colorectal cancer (CRC) is currently the third leading cause of cancer-related mortality in the world. U.S. Food and Drug Administration-approved circulating tumor markers, including carcinoembryonic antigen, carbohydrate antigen (CA) 19-9 and CA125 were used as prognostic biomarkers of CRC that attributed to low sensitivity in diagnosis of CRC. Therefore, our purpose is to develop a novel strategy for novel clinical biomarkers for early CRC diagnosis. We used mass spectrometry (MS) methods such as nanoLC-MS/MS, targeted LC-MS/MS, and stable isotope-labeled multiple reaction monitoring (MRM) MS coupled to test machine learning algorithms and logistic regression to analyze plasma samples from patients with early-stage CRC, late-stage CRC, and healthy controls (HCs). On the basis of our methods, 356 peptides were identified, 6 differential expressed peptides were verified, and finally three peptides corresponding wheat germ agglutinin (WGA)-captured proteins were semi-quantitated in 286 plasma samples (80 HCs and 206 CRCs). The novel peptide biomarkers combination of PF454–62, ITIH4429–438, and APOE198–207 achieved sensitivity 84.5%, specificity 97.5% and an AUC of 0.96 in CRC diagnosis. In conclusion, our study demonstrated that WGA-captured plasma PF454–62, ITIH4429–438, and APOE198–207 levels in combination may serve as highly effective early diagnostic biomarkers for patients with CRC. [ABSTRACT FROM AUTHOR]