Effectiveness of the ALT/AST ratio for predicting insulin resistance in a Korean population: A large-scale, cross-sectional cohort study.

Insulin resistance is a common pathophysiology in patients with type 2 diabetes mellitus, cardiovascular disease, and non-alcoholic fatty liver disease. Thus, screening for the risk of insulin resistance is important to prevent disease progression. We evaluated the alanine aminotransferase/aspartate aminotransferase (ALT/AST) ratio to predict insulin resistance in the general population, regardless of comorbidities. Datasets from the 2015, 2019, and 2020 Korea National Health and Nutrition Examination Surveys were used, and the following four indices were implemented to indicate insulin resistance: fasting serum glucose, insulin, homeostatic model assessment for insulin resistance (HOMA-IR), and ß-cell function. We analyzed the degree of association between the liver enzyme profile and insulin resistance indices using Pearson's correlation coefficient and determined the associations using linear or logistic regression analysis. Accordingly, ALT levels in both sexes were positively and consistently correlated with the four aforementioned insulin resistance indices in stratification analyses based on diabetes, dyslipidemia, alcohol consumption, and obesity status. In multivariate linear regression, when comparing with ALT levels, the ALT/AST ratio exhibited superior predictive performance for fasting serum glucose and HOMA-ß in Korean men and improved outcomes for all insulin resistance indices in Korean women. In this analysis that included a large community-based population, the ALT/AST ratio was a more useful predictive marker than the HOMA-IR. Regarding the predicted presence or absence of insulin resistance, the ALT/AST ratio could better predict HOMA-IR than the ALT level alone in Koreans. A simple, precise marker that represents the ALT/AST ratio could be a practical method to screen for insulin resistance in the general population, regardless of diabetes mellitus, alcohol intake, and sex.

Development of a formula for estimated glomerular filtration rate in pregnant women from physiological hyperfiltration of serum creatinine.

Increased body fluids during pregnancy complicates the application of estimated glomerular filtration rate (eGFR) formulas that are based on body surface area. Furthermore, gestational renal dysfunction cannot be identified if the serum creatinine (SCr) concentration is within the non-pregnant reference interval (RI) despite inadequate pregnancy-related renal hyperfiltration. 1484 SCr measurements from 957 healthy pregnant women were collected. The average SCr value of gestational week (GW) 0-3 was the representative SCr value of non-pregnant status. While the distribution of SCr measurements varied across GWs, it was transformed into a normal distribution using the bootstrap resampling method. A polynomial linear regression method was applied to achieve a continuous and smooth transformation of values. The normally distributed SCr values of each GW were compared to the non-pregnant status, leading to the calculation of SCr hyperfiltration. The final equation, (2 - SCr (µmol/L) / 55.25) × 103.1 × 55.25/(56.7 - 0.223 × GW - 0.113 × GW2 + 0.00545 × GW3 - 0.0000653 × GW4), and reference intervals for both SCr and eGFR for each GW were obtained. These RIs and novel equations can be effectively used to monitor renal dysfunction in pregnant women.

Predictive cut-off values for the triglyceride-to-high-density lipoprotein cholesterol ratio to predict metabolic syndrome in the middle-aged Korean population.

BACKGROUND AND AIMS: The triglyceride-to-high density lipoprotein cholesterol (TG/HDL) ratio is associated with insulin resistance related diseases, including metabolic syndrome (MetS). However, specific TG/HDL values that can predict MetS have not been well identified. In this study, we analyzed both cross-sectional and longitudinal data from two national Korean datasets to obtain TG/HDL cut-off values that can identify MetS and predict its occurrence. METHODS AND RESULTS: To distinguish the presence and occurrence of MetS, the cut-off values were determined using the maximum F-score calculated through a logistic regression analysis. To predict new-onset MetS within 10 years, Cox proportional hazard models were used to consider the time of occurrence. The TG/HDL cut-off values of 3.97, 3.24, and 3.24 were optimal for identifying current MetS and predicting new-onset MetS within 10 years and five years, respectively, in Korean men. In Korean women, the optimal values for each task were 3.18, 2.38, and 2.26, respectively. CONCLUSIONS: We suggest the TG/HDL ratio as a potential candidate predictor for MetS. Therefore, we anticipate that future studies will apply individual lipid levels as well as their combinatory values to establish models that predict the prevalence and occurrence of MetS, diabetes, and cardiovascular disease.

Comparative Analysis of Biological Signatures between Freshly Preserved and Cryo-Preserved Bone Marrow Mesenchymal Stem Cells.

Mesenchymal stem cells (MSCs) can differentiate into multiple connective tissue lineages, including osteoblasts, chondrocytes, and adipocytes. MSCs secrete paracrine molecules that are associated with immunomodulation, anti-fibrotic effects, and angiogenesis. Due to their orchestrative potential, MSCs have been therapeutically applied for several diseases. An important aspect of this process is the delivery of high-quality MSCs to patients at the right time, and cryo-biology and cryo-preservation facilitate the advancement of the logistics thereof. This study aimed to compare the biological signatures between freshly preserved and cryo-preserved MSCs by using big data sourced from the Pharmicell database. From 2011 to 2022, data on approximately 2300 stem cell manufacturing cases were collected. The dataset included approximately 60 variables, including viability, population doubling time (PDT), immunophenotype, and soluble paracrine molecules. In the dataset, 671 cases with no missing data were able to receive approval from an Institutional Review Board and were analyzed. Among the 60 features included in the final dataset, 20 were selected by experts and abstracted into two features by using a principal component analysis. Circular clustering did not introduce any differences between the two MSC preservation methods. This pattern was also observed when using viability, cluster of differentiation (CD) markers, and paracrine molecular indices as inputs for unsupervised analysis. The individual average PDT and cell viability at most passages did not differ according to the preservation method. Most immunophenotypes (except for the CD14 marker) and paracrine molecules did not exhibit different mean levels or concentrations between the frozen and unfrozen MSC groups. Collectively, the biochemical signatures of the cryo-preserved and unfrozen bone marrow MSCs were comparable.

Prediction Model for Pre-Eclampsia Using Gestational-Age-Specific Serum Creatinine Distribution.

Pre-eclampsia (PE) is a pregnancy-related disease, causing significant threats to both mothers and babies. Numerous studies have identified the association between PE and renal dysfunction. However, in clinical practice, kidney problems in pregnant women are often overlooked due to physiologic adaptations during pregnancy, including renal hyperfiltration. Recent studies have reported serum creatinine (SCr) level distribution based on gestational age (GA) and demonstrated that deviations from the expected patterns can predict adverse pregnancy outcomes, including PE. This study aimed to establish a PE prediction model using expert knowledge and by considering renal physiologic adaptation during pregnancy. This retrospective study included pregnant women who delivered at the Wonju Severance Christian Hospital. Input variables, such as age, gestational weeks, chronic diseases, and SCr levels, were used to establish the PE prediction model. By integrating SCr, GA, GA-specific SCr distribution, and quartile groups of GA-specific SCr (GAQ) were made. To provide generalized performance, a random sampling method was used. As a result, GAQ improved the predictive performance for any cases of PE and triple cases, including PE, preterm birth, and fetal growth restriction. We propose a prediction model for PE consolidating readily available clinical blood test information and pregnancy-related renal physiologic adaptations.

Classification Model for Epileptic Seizure Using Simple Postictal Laboratory Indices.

Distinguishing syncope from epileptic seizures in patients with sudden loss of consciousness is important. Various blood tests have been used to indicate epileptic seizures in patients with impaired consciousness. This retrospective study aimed to predict the diagnosis of epilepsy in patients with transient loss of consciousness using the initial blood test results. A seizure classification model was constructed using logistic regression, and predictors were selected from a cohort of 260 patients using domain knowledge and statistical methods. The study defined the diagnosis of seizures and syncope based on the consistency of the diagnosis made by an emergency medicine specialist at the first visit to the emergency room and the diagnosis made by an epileptologist or cardiologist at the first outpatient visit using the International Classification of Diseases 10th revision (ICD-10) code. Univariate analysis showed higher levels of white blood cells, red blood cells, hemoglobin, hematocrit, delta neutrophil index, creatinine kinase, and ammonia levels in the seizure group. The ammonia level had the highest correlation with the diagnosis of epileptic seizures in the prediction model. Therefore, it is recommended to be included in the first examination at the emergency room.

Association between urinary albumin creatinine ratio and cardiovascular disease.

INTRODUCTION: The association between microalbuminuria and cardiovascular disease (CVD) is accumulating in various patient populations. However, when stratified by sex, the relationship between microalbuminuria and CVD remains unclear. METHOD: We obtained data from the 2011-2014 and 2019-2020 Korea National Health and Nutrition Examination Survey (KNHANES). Microalbuminuria was measured based on spot urine albumin-creatinine ratio (UACR). The Framingham risk score (FRS) model was implemented to evaluate the CVD risk. Linear and logistic regression models were used to identify the associations of microalbuminuria status with cardiometabolic predictors and CVD status determined by the FRS score. RESULTS: Among 19,340 representative Korean participants, the (UACR) in Korean women and men with history of CVD was higher than in those without history of CVD. Among patients without history of CVD, multivariate regression analysis showed that a high UACR was related to older age, lower high-density lipoprotein cholesterol level, higher total cholesterol level, higher systolic blood pressure, higher prevalence of current smoking, higher prevalence of diabetes, and higher anti-hypertensive medication use in both women and men. The UACR showed a positive linear correlation with the Framingham risk score in both women and men. CONCLUSION: The presence of microalbuminuria was significantly associated with the cardiometabolic risk factors and the increased risk of CVD evaluated by FRS model in both women and men in a nationally representative sample of Korea.

Comparative analysis of the relationship between four hepatic steatosis indices and muscle mass.

Several studies have attempted to validate the relationship between hepatic steatosis and sarcopenia. The crucial limitation is to establish the status of hepatic steatosis by costly or invasive methods. Therefore, several models predicting non-alcoholic fatty liver disease (NAFLD) have been developed but have exhibited heterogeneous results. In this study, we aimed to review and compare four representative models and analyze their relationship with the risk of low muscle mass. Korea National Health and Nutrition Examination Surveys from 2008 to 2011 were used to confirm our hypothesis. Dual-energy X-ray absorptiometry was used to measure the amount of skeletal muscle mass. We used four hepatic steatosis indices: hepatic steatosis index (HSI), Framingham steatosis index (FSI), liver fat score (LFS), and fatty liver index (FLI). Multivariate linear and logistic regressions were used to reveal the relationship between NAFLD and low skeletal muscle index (LSMI). Pairs of FSI-FLI and HSI-FLI exhibited the best and second-best correlations among all possible pairs. The four hepatic steatosis models were associated with increased risk for LSMI. After removing the body mass index effect, HSI and FLI remained robust predictors for LSMI. NAFLD was a significant and potent risk factor for low skeletal muscle.

Quantitative ultrasound for non-invasive evaluation of subclinical rejection in renal transplantation.

OBJECTIVES: This study aimed to investigate the predictive efficacy of shear-wave elastography, superb microvascular imaging (SMI), and CEUS for allograft rejection in kidney transplants without graft dysfunction. METHODS: From January 2021 to November 2021, 72 consecutive patients who underwent both allograft biopsy and ultrasound were evaluated. Blood test results were obtained within a week of the ultrasound examinations, which were performed before the protocol biopsy. Resistive index (RI), tissue viscoelasticity, vascular index, and quantitative CEUS parameters were measured. Patients were divided based on biopsy results into the rejection and non-rejection groups. RESULTS: Among the 72 patients, 21 patients had pathological characteristics of acute rejection. RI of allograft was significantly higher in the rejection group (p = 0.007), compared to the non-rejection group. There were no significant between-group differences in vascular indices of SMI, mean elasticity, and mean viscosity. Meanwhile, among the parameters obtained by the time-intensity curve on CEUS, the cortical and medullary ratios of average contrast signal intensity, peak enhancement, wash-in area AUC, wash-in perfusion index, wash-out AUC, and wash-in and wash-out AUC were significantly different between the two groups (p < 0.05). In the receiver operating characteristic curve analysis for predicting allograft rejection, the AUC was 0.853 for the combination of six CEUS parameters, RI, and blood urea nitrogen. CONCLUSIONS: Among non-invasive quantitative ultrasound measurements, CEUS parameters are the most useful for diagnosing subclinical allograft rejection. Furthermore, the combination of CEUS parameters, RI, and blood urea nitrogen may be helpful for the early detection of renal allograft rejection. KEY POINTS: • Among non-invasive quantitative ultrasound measurements, CEUS parameters are the most useful for the diagnosis of subclinical allograft rejection. • On CEUS, the C/M ratios of MeanLin, PE, WiAUC, WiPI, WoAUC, and WiWoAUC are significantly lower in the rejection group; the combination of these showed reliable predictive performance for rejection. • The combination of CEUS parameters, RI, and BUN has a high predictive capability for subclinical allograft rejection.

Identification of Cardiovascular Disease-Related Genes Based on the Co-Expression Network Analysis of Genome-Wide Blood Transcriptome.

Inference of co-expression network and identification of disease-related modules and gene sets can help us understand disease-related molecular pathophysiology. We aimed to identify a cardiovascular disease (CVD)-related transcriptomic signature, specifically, in peripheral blood tissue, based on differential expression (DE) and differential co-expression (DcoE) analyses. Publicly available blood sample datasets for coronary artery disease (CAD) and acute coronary syndrome (ACS) statuses were integrated to establish a co-expression network. A weighted gene co-expression network analysis was used to construct modules that include genes with highly correlated expression values. The DE criterion is a linear regression with module eigengenes for module-specific genes calculated from principal component analysis and disease status as the dependent and independent variables, respectively. The DcoE criterion is a paired t-test for intramodular connectivity between disease and matched control statuses. A total of 21 and 23 modules were established from CAD status- and ACS-related datasets, respectively, of which six modules per disease status (i.e., obstructive CAD and ACS) were selected based on the DE and DcoE criteria. For each module, gene-gene interactions with extremely high correlation coefficients were individually selected under the two conditions. Genes displaying a significant change in the number of edges (gene-gene interaction) were selected. A total of 6, 10, and 7 genes in each of the three modules were identified as potential CAD status-related genes, and 14 and 8 genes in each of the two modules were selected as ACS-related genes. Our study identified gene sets and genes that were dysregulated in CVD blood samples. These findings may contribute to the understanding of CVD pathophysiology.

Classification Model for Diabetic Foot, Necrotizing Fasciitis, and Osteomyelitis.

Diabetic foot ulcers (DFUs) and their life-threatening complications, such as necrotizing fasciitis (NF) and osteomyelitis (OM), increase the healthcare cost, morbidity and mortality in patients with diabetes mellitus. While the early recognition of these complications could improve the clinical outcome of diabetic patients, it is not straightforward to achieve in the usual clinical settings. In this study, we proposed a classification model for diabetic foot, NF and OM. To select features for the classification model, multidisciplinary teams were organized and data were collected based on a literature search and automatic platform. A dataset of 1581 patients (728 diabetic foot, 76 NF, and 777 OM) was divided into training and validation datasets at a ratio of 7:3 to be analyzed. The final prediction models based on training dataset exhibited areas under the receiver operating curve (AUC) of the 0.80 and 0.73 for NF model and OM model, respectively, in validation sets. In conclusion, our classification models for NF and OM showed remarkable discriminatory power and easy applicability in patients with DFU.

COVID-19 and related social distancing measures induce significant metabolic complications without prominent weight gain in Korean adults.

Background: This study using multi-center health examination data from Korean adults was conducted to confirm changes in weight, and their related cardiometabolic parameters, before and after strengthening of social distancing regulations. Methods: A retrospective cohort study was conducted using health check-up data from 13 university hospitals. The study period was from January 2018 to July 2020. To examine the effect of systematic social distancing measures, participants who underwent a health check-up (Visit 3) between July 2020 and July 2021 (during full scale social distancing), and had undergone two previous health check-ups (Visits 1 and 2) between January 2018 and June 2020 (before social distancing), were selected. In total, data from 7,875 participants were analyzed. Linear mixed-effect models were used to calculate estimates of anthropometric indices and metabolic markers measured on Visits 2 and 3, compared with measurements from Visit 1. Results: There were no significant differences in body weight, body mass index, waist circumference, and body composition on Visit 3 than on Visits 1 and 2. However, the odds of metabolic syndrome and its components, including hypertension, high glucose, diabetes, hypercholesterolemia, hypertriglyceridemia, hyper-non-high-density lipoprotein cholesterolemia, and dyslipidemia were significantly higher on Visit 3 than on Visits 1 and 2. The increase in metabolic complications was marked, particularly in relatively young adults who visited health check-up centers located in the capital area. Conclusion: Metabolic syndrome and its components were significantly worse after high level social distancing, although there were no significant increases in anthropometric indices and body fat levels. Healthcare providers need to prevent and manage worsening of metabolic parameters in subpopulations prone to be more sedentary and eat unhealthy food during the COVID-19 pandemic and associated social distancing measures.

Fatty Liver Change in Korean Adults in a Systematic Social Distancing System Amid the COVID-19 Pandemic: A Multicenter Analysis.

In response to the COVID-19 pandemic, the Korean government implemented policies including the systematic social distancing (SSD) system which started on 28 June 2020. The present study investigated the development and aggravation of fatty liver measured using ultrasonography during the transition period (from pre-SSD to SSD) compared to the fatty liver changes during the pre-SSD period. Changes in fatty liver and liver enzymes were assessed in different groups stratified by alcohol consumption. Our retrospective cohort analysis included 5668 participants who underwent health checkups at 13 university hospitals during the SSD period and two or more checkups before the SSD period. Fatty liver developed and aggravated more in the transition period (13.6% development and 12.0% aggravation) than in the pre-SSD period (10.8% development and 10.1% aggravation) in the alcohol consumption group. This finding was more prominent in women than in men. Abnormal alanine transaminase levels were more often developed in the transition period than in the pre-SSD period, especially in men (11.1% vs. 8.6% in each period). In conclusion, the SSD system may contribute to fatty liver changes in individuals who regularly consume alcohol. Further research of the post-pandemic period is needed to assess long-term changes in fatty liver disease.

Association between Stroke and Abdominal Obesity in the Middle-Aged and Elderly Korean Population: KNHANES Data from 2011-2019.

Obesity and overweight status are primary risk factors for stroke. A relative small number of studies has analyzed the association of abdominal obesity, a crucial indicator for insulin resistance with stroke, compared to general obesity. We aimed to reveal 31,490 records from the Korea National Health and Nutrition Examination Survey (KNHANES). Logistic regression was used to identify the association of abdominal obesity with the risk of stroke. For the multivariate model, covariates were determined based on the cardio-cerebro vascular prediction models. In the sex-specific multivariate logistic regression analysis (including age, antihypertensive drug, diabetes, current smoking, and systolic blood pressure as confounders), the elevated waist circumference (WC) in women was significantly associated with the increased risk for stroke. In case of the categorized form of WC, we discerned the non-linear relationships between WC and the stroke status. The sex-specific associations between the abdominal obesity and stroke status were shown and their relationship pattern exhibited non-linear relationships.

Identification of the robust predictor for sepsis based on clustering analysis.

Sepsis is a life-threatening disorder with high incidence and mortality rate. However, the early detection of sepsis is challenging due to lack of specific marker and various etiology. This study aimed to identify robust risk factors for sepsis via cluster analysis. The integrative task of the automatic platform (i.e., electronic medical record) and the expert domain was performed to compile clinical and medical information for 2,490 sepsis patients and 16,916 health check-up participants. The subjects were categorized into 3 and 4 groups based on seven clinical and laboratory markers (Age, WBC, NLR, Hb, PLT, DNI, and MPXI) by K-means clustering. Logistic regression model was performed for all subjects including healthy control and sepsis patients, and cluster-specific cases, separately, to identify sepsis-related features. White blood cell (WBC), well-known parameter for sepsis, exhibited the insignificant association with the sepsis status in old age clusters (K3C3 and K4C3). Besides, NLR and DNI were the robust predictors in all subjects as well as three or four cluster-specific subjects including K3C3 or K4C3. We implemented the cluster-analysis for real-world hospital data to identify the robust predictors for sepsis, which could contribute to screen likely overlooked and potential sepsis patients (e.g., sepsis patients without WBC count elevation).

Identification of Disease-Related Genes That Are Common between Alzheimer's and Cardiovascular Disease Using Blood Genome-Wide Transcriptome Analysis.

Accumulating evidence has suggested a shared pathophysiology between Alzheimer's disease (AD) and cardiovascular disease (CVD). Based on genome-wide transcriptomes, specifically those of blood samples, we identify the shared disease-related signatures between AD and CVD. In addition to gene expressions in blood, the following prior knowledge were utilized to identify several candidate disease-related gene (DRG) sets: protein-protein interactions, transcription factors, disease-gene relationship databases, and single nucleotide polymorphisms. We selected the respective DRG sets for AD and CVD that show a high accuracy for disease prediction in bulk and single-cell gene expression datasets. Then, gene regulatory networks (GRNs) were constructed from each of the AD and CVD DRG sets to identify the upstream regulating genes. Using the GRNs, we identified two common upstream genes (GPBP1 and SETDB2) between the AD and CVD GRNs. In summary, this study has identified the potential AD- and CVD-related genes and common hub genes between these sets, which may help to elucidate the shared mechanisms between these two diseases.

Shared Blood Transcriptomic Signatures between Alzheimer's Disease and Diabetes Mellitus.

Alzheimer's disease (AD) and diabetes mellitus (DM) are known to have a shared molecular mechanism. We aimed to identify shared blood transcriptomic signatures between AD and DM. Blood expression datasets for each disease were combined and a co-expression network was used to construct modules consisting of genes with similar expression patterns. For each module, a gene regulatory network based on gene expression and protein-protein interactions was established to identify hub genes. We selected one module, where COPS4, PSMA6, GTF2B, GTF2F2, and SSB were identified as dysregulated transcription factors that were common between AD and DM. These five genes were also differentially co-expressed in disease-related tissues, such as the brain in AD and the pancreas in DM. Our study identified gene modules that were dysregulated in both AD and DM blood samples, which may contribute to reveal common pathophysiology between two diseases.

Prediction of Alzheimer's disease using blood gene expression data.

Identification of AD (Alzheimer's disease)-related genes obtained from blood samples is crucial for early AD diagnosis. We used three public datasets, ADNI, AddNeuroMed1 (ANM1), and ANM2, for this study. Five feature selection methods and five classifiers were used to curate AD-related genes and discriminate AD patients, respectively. In the internal validation (five-fold cross-validation within each dataset), the best average values of the area under the curve (AUC) were 0.657, 0.874, and 0.804 for ADNI, ANMI, and ANM2, respectively. In the external validation (training and test sets from different datasets), the best AUCs were 0.697 (training: ADNI to testing: ANM1), 0.764 (ADNI to ANM2), 0.619 (ANM1 to ADNI), 0.79 (ANM1 to ANM2), 0.655 (ANM2 to ADNI), and 0.859 (ANM2 to ANM1), respectively. These results suggest that although the classification performance of ADNI is relatively lower than that of ANM1 and ANM2, classifiers trained using blood gene expression can be used to classify AD for other data sets. In addition, pathway analysis showed that AD-related genes were enriched with inflammation, mitochondria, and Wnt signaling pathways. Our study suggests that blood gene expression data are useful in predicting the AD classification.

Deep neural network for estimating low density lipoprotein cholesterol.

BACKGROUND: LDL cholesterol (LDL-C) has been mainly estimated using the Friedewald equation, and other equations have recently been developed to complement the Friedewald equation. The present study aims to employ a deep neural network (DNN) to improve LDL-C estimation. METHODS: We used two independent datasets obtained from the Korean National Health and Nutrition Examination Survey and the Wonju Severance Christian Hospital as training and test datasets, respectively. We used the training dataset to construct the DNN architecture, which takes three input values of total cholesterol, HDL cholesterol, and triglyceride, and estimates LDL-C as the output. The model consists of six hidden layers, and each hidden layer has 30 nodes. The performance of the DNN model constructed by the training dataset was measured using the test dataset. RESULTS: In fivefold cross-validation using the training dataset, the DNN model showed the lowest mean and median squared errors compared to the Friedewald equation and Novel method. For the independent test dataset, our DNN model outperformed other existing methods on the basis of mean and median squared errors. CONCLUSIONS: The DNN model provided the most accurate estimation of LDL-C compared to other existing methods including the Friedewald and Novel methods.

Korean public and hospital data for estimating LDL-cholesterol.

The data is composed of 14,812 subjects, and was obtained from the Korean National Health and Nutritional Examination Survey (KNHANES) from 2009 to 2015. The KNHANES data is publicly available at https://knhanes.cdc.go.kr/knhanes/eng/index.do. By using random annotated ID, all subjects can be anonymous. The dataset consisting of 4520 participants was obtained from Wonju Severance Christian Hospital (WSCH) in South Korea. To protect the patient׳s personal information, we removed ID and gender of patients. Detail information of the data presented in the present article is available in the research article "Deep neural network for estimating low density lipoprotein cholesterol" (Lee et al., 2018).