Upper Normal Serum Creatinine Concentrations as a Predictor for Chronic Kidney Disease: Analysis of 14 Years' Korean Genome and Epidemiology Study (KoGES)

Using Machine Learning and Silver Nanoparticle-Based Surface-Enhanced Raman Spectroscopy for Classification of Cardiovascular Disease Biomarkers

Characterizing complex biofluids using surface-enhanced Raman spectroscopy (SERS) coupled with machine learning (ML) has been proposed as a powerful tool for point-of-care detection of clinical disease. ML is well-suited to categorizing otherwise uninterpretable, patient-derived SERS spectra that contain a multitude of low concentration, disease-specific molecular biomarkers among a dense spectral background of biological molecules. However, ML can generate false, non-generalizable models when data sets used for model training are inadequate. It is thus critical to determine how different SERS experimental methodologies and workflow parameters can potentially impact ML disease classification of clinical samples. In this study, a label-free, broadband, Ag nanoparticle-based SERS platform was coupled with ML to assess simulated clinical samples for cardiovascular disease (CVD), containing randomized combinations of five key CVD biomarkers at clinically relevant concentrations in serum. Raman spectra obtained at 532, 633, and 785 nm from up to 300 unique samples were classified into physiological and pathological categories using two standard ML models. Label-free SERS and ML could correctly classify randomized CVD samples with high accuracies of up to 90.0% at 532 nm using as few as 200 training samples. Spectra obtained at 532 nm produced the highest accuracies with no significant increase achieved using multiwavelength SERS. Sample preparation and measurement methodologies (e.g., different SERS substrate lots, sample volumes, sample sizes, and known variations in randomization and experimental handling) were shown to strongly influence the ML classification and could artificially increase classification accuracies by as much as 27%. This detailed investigation into the proper application of ML techniques for CVD classification can lead to improved data set acquisition required for the SERS community, such that ML on labeled and robust SERS data sets can be practically applied for future point-of-care testing in patients.

Recent Advances in Epigenetics of Age-Related Kidney Diseases

Renal aging has attracted increasing attention in today’s aging society, as elderly people with advanced age are more susceptible to various kidney disorders such as acute kidney injury (AKI) and chronic kidney disease (CKD). There is no clear-cut universal mechanism for identifying age-related kidney diseases, and therefore, they pose a considerable medical and public health challenge. Epigenetics refers to the study of heritable modifications in the regulation of gene expression that do not require changes in the underlying genomic DNA sequence. A variety of epigenetic modifiers such as histone deacetylases (HDAC) inhibitors and DNA methyltransferase (DNMT) inhibitors have been proposed as potential biomarkers and therapeutic targets in numerous fields including cardiovascular diseases, immune system disease, nervous system diseases, and neoplasms. Accumulating evidence in recent years indicates that epigenetic modifications have been implicated in renal aging. However, no previous systematic review has been performed to systematically generalize the relationship between epigenetics and age-related kidney diseases. In this review, we aim to summarize the recent advances in epigenetic mechanisms of age-related kidney diseases as well as discuss the application of epigenetic modifiers as potential biomarkers and therapeutic targets in the field of age-related kidney diseases. In summary, the main types of epigenetic processes including DNA methylation, histone modifications, non-coding RNA (ncRNA) modulation have all been implicated in the progression of age-related kidney diseases, and therapeutic targeting of these processes will yield novel therapeutic strategies for the prevention and/or treatment of age-related kidney diseases.

A soft voting ensemble classifier for early prediction and diagnosis of occurrences of major adverse cardiovascular events for STEMI and NSTEMI during 2-year follow-up in patients with acute coronary syndrome

OBJECTIVE

Some researchers have studied about early prediction and diagnosis of major adverse cardiovascular events (MACE), but their accuracies were not high. Therefore, this paper proposes a soft voting ensemble classifier (SVE) using machine learning (ML) algorithms.

METHODS

We used the Korea Acute Myocardial Infarction Registry dataset and selected 11,189 subjects among 13,104 with the 2-year follow-up. It was subdivided into two groups (ST-segment elevation myocardial infarction (STEMI), non ST-segment elevation myocardial infarction NSTEMI), and then subdivided into training (70%) and test dataset (30%). Third, we selected the ranges of hyper-parameters to find the best prediction model from random forest (RF), extra tree (ET), gradient boosting machine (GBM), and SVE. We generated each ML-based model with the best hyper-parameters, evaluated by 5-fold stratified cross-validation, and then verified by test dataset. Lastly, we compared the performance in the area under the ROC curve (AUC), accuracy, precision, recall, and F-score.

RESULTS

The accuracies for RF, ET, GBM, and SVE were (88.85%, 88.94%, 87.84%, 90.93%) for complete dataset, (84.81%, 85.00%, 83.70%, 89.07%) STEMI, (88.81%, 88.05%, 91.23%, 91.38%) NSTEMI. The AUC values in RF were (98.96%, 98.15%, 98.81%), ET (99.54%, 99.02%, 99.00%), GBM (98.92%, 99.33%, 99.41%), and SVE (99.61%, 99.49%, 99.42%) for complete dataset, STEMI, and NSTEMI, respectively. Consequently, the accuracy and AUC in SVE outperformed other ML models.

CONCLUSIONS

The performance of our SVE was significantly higher than other machine learning models (RF, ET, GBM) and its major prognostic factors were different. This paper will lead to the development of early risk prediction and diagnosis tool of MACE in ACS patients.

Causal Pathways from Body Components and Regional Fat to Extensive Metabolic Phenotypes: A Mendelian Randomization Study

OBJECTIVE

The aim of this study was to explore the causal effects and pathways from body components to extensive metabolic phenotypes.

METHODS

Summarized data including 24 metabolic phenotypes from 10 consortiums were used to perform univariate, multivariable, and bidirectional Mendelian randomization analysis based on the network design.

RESULTS

For metabolically related biomarkers, a 1-SD increase in body fat mass (BFM) was robustly associated with increased fasting insulin, systolic blood pressure, diastolic blood pressure, and urate and decreased high-density lipoprotein cholesterol levels. For metabolically related diseases, the odds ratios and 95% CIs of a 1-SD increase in BFM were 1.76 (1.37 to 2.25) for type 2 diabetes mellitus (T2DM), 1.11 (1.09 to 1.13) for hypertension, 1.40 (1.25 to 1.57) for coronary artery disease, 1.41 (1.25 to 1.59) for myocardial infarction, 1.25 (1.12 to 1.40) for ischemic stroke, and 1.62 (1.02 to 2.57) for gout. The effects of body fat on diseases were mediated by extensive intermediate biomarkers, including blood pressure, lipids, glycemic traits, and urate. Regional fats had a similar effect with body fat in both absolute and relative scales, whereas fat-free components increased only the risk of T2DM 1.73 (1.11 to 2.68) and chronic kidney disease 1.51 (1.11 to 2.06).

CONCLUSIONS

Several potential pathways were found and confirmed the tremendous benefits of fat-lowering measures, including lowering of various regional fats. Future policies or interventions should focus more on the role of body fat.

Oxidative stress and the antioxidant system in salivary glands of rats with experimental chronic kidney disease

OBJECTIVE

This study aims to analyze the presence of oxidative stress and activity of the antioxidant system in the parotid and submandibular salivary glands of rats with Chronic Kidney Disease (CKD).

DESIGN

Sixteen male wistar rats were divided into two groups (n = 8, each): control rats and rats with CKD. CKD was induced by 5/6 nephrectomy. Blood urea nitrogen and serum creatinine clearance were quantified. Malondialdehyde, superoxide dismutase, glutathione peroxidase, glutathione reductase, catalase, total antioxidant status, ascorbic acid, α-tocopherol, superoxide anion, and hydrogen peroxide concentrations were assessed.

RESULTS

In CKD rats, blood urea nitrogen, serum creatinine, and proteinuria concentrations were increased, while creatinine clearance was reduced. In the submandibular gland, superoxide anion concentration was increased significantly (p < 0.05). Hydrogen peroxide and superoxide anion concentrations were reduced in the parotid gland. CKD rats presented increased malondialdehyde concentration, total antioxidant status, superoxide dismutase, and glutathione reductase activities only in the parotid gland (p < 0.05).

CONCLUSION

Oxidative stress and changes in the antioxidant system were found in the parotid and submandibular salivary glands in an experimental model of CKD induced by 5/6 nephrectomy.