Isotypes of autoantibodies against novel differential 4-hydroxy-2-nonenal-modified peptide adducts in serum is associated with rheumatoid arthritis in Taiwanese women

Autoantibodies to Oxidatively Modified Peptide: Potential Clinical Application in Coronary Artery Disease

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.

Artificial Intelligence in Rheumatoid Arthritis: Current Status and Future Perspectives: A State-of-the-Art Review

Investigation of the potential applications of artificial intelligence (AI), including machine learning (ML) and deep learning (DL) techniques, is an exponentially growing field in medicine and healthcare. These methods can be critical in providing high-quality care to patients with chronic rheumatological diseases lacking an optimal treatment, like rheumatoid arthritis (RA), which is the second most prevalent autoimmune disease. Herein, following reviewing the basic concepts of AI, we summarize the advances in its applications in RA clinical practice and research. We provide directions for future investigations in this field after reviewing the current knowledge gaps and technical and ethical challenges in applying AI. Automated models have been largely used to improve RA diagnosis since the early 2000s, and they have used a wide variety of techniques, e.g., support vector machine, random forest, and artificial neural networks. AI algorithms can facilitate screening and identification of susceptible groups, diagnosis using omics, imaging, clinical, and sensor data, patient detection within electronic health record (EHR), i.e., phenotyping, treatment response assessment, monitoring disease course, determining prognosis, novel drug discovery, and enhancing basic science research. They can also aid in risk assessment for incidence of comorbidities, e.g., cardiovascular diseases, in patients with RA. However, the proposed models may vary significantly in their performance and reliability. Despite the promising results achieved by AI models in enhancing early diagnosis and management of patients with RA, they are not fully ready to be incorporated into clinical practice. Future investigations are required to ensure development of reliable and generalizable algorithms while they carefully look for any potential source of bias or misconduct. We showed that a growing body of evidence supports the potential role of AI in revolutionizing screening, diagnosis, and management of patients with RA. However, multiple obstacles hinder clinical applications of AI models. Incorporating the machine and/or deep learning algorithms into real-world settings would be a key step in the progress of AI in medicine.

Using anti-malondialdehyde-modified peptide adduct autoantibodies in serum of taiwanese women to diagnose primary Sjogren's syndrome

BACKGROUND

Sjogren's syndrome (SS) is a systemic autoimmune disease featured with a dry mouth and dry eyes. Several autoantibodies, including anti-SSA, anti-SSB, antinuclear antibodies can be detected in patients with SS. Oxidation-specific epitopes (OSEs) can be formed from malondialdehyde (MDA)-modified protein adducts and trigger chronic inflammation. In this study, our purposes were used serum levels of anti-MDA-modified peptide adducts autoantibodies to evaluate predictive performance by machine learning algorithms in primary Sjögren's syndrome (pSS) and assess the association between pSS and healthy controls.

METHODS

Three novel MDA-modified peptide adducts, including immunoglobulin (Ig) gamma heavy chain 1 (IGHG1)^102-131, complement factor H (CFAH)^1045-1062_, and Ig heavy constant alpha 1 (IGHA1)^307-327 were identified and validated. Serum levels of protein, MDA-modified protein adducts, MDA, and autoantibodies recognizing unmodified peptides and MDA-modified peptide adducts were measured. Statistically significance in correlations and odds ratios (ORs) were estimated.

RESULTS

The random forest classifier utilized autoantibodies combination composed of IgM anti-IGHG1^102-131, IgM anti-IGHG1^102-131 MDA and IgM anti-IGHA1^307-327 achieved predictive performance as an accuracy of 88.0%, a sensitivity of 93.7%, and a specificity of 84.4% which may be as potential diagnostic biomarkers to differentiate patients with pSS from rheumatoid arthritis (RA), and secondary SS in RA and HCs.

CONCLUSIONS

Our findings imply that low levels of IgA anti-IGHG1^102-131 MDA (OR = 2.646), IgA anti-IGHG1^102-131 (OR = 2.408), IgA anti-CFAH^1045-1062 (OR = 2.571), and IgA anti-IGHA1^307-327 (OR = 2.905) may denote developing risks of pSS, respectively.

Machine Learning in Prediction of Bladder Cancer on Clinical Laboratory Data

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.

Using Anti-Malondialdehyde Modified Peptide Autoantibodies to Import Machine Learning for Predicting Coronary Artery Stenosis in Taiwanese Patients with Coronary Artery Disease

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-IGKC^76-99 MDA and IgM anti-A1AT^284-298 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.

Clinical Assay for the Early Detection of Colorectal Cancer Using Mass Spectrometric Wheat Germ Agglutinin Multiple Reaction Monitoring

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.

Abstract

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 PF4^54–62, ITIH4^429–438, and APOE^198–207 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 PF4^54–62, ITIH4^429–438, and APOE^198–207 levels in combination may serve as highly effective early diagnostic biomarkers for patients with CRC.