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.

Construction of Asbestos Slate Deep-Learning Training-Data Model Based on Drone Images.

The detection of asbestos roof slate by drone is necessary to avoid the safety risks and costs associated with visual inspection. Moreover, the use of deep-learning models increases the speed as well as reduces the cost of analyzing the images provided by the drone. In this study, we developed a comprehensive learning model using supervised and unsupervised classification techniques for the accurate classification of roof slate. We ensured the accuracy of our model using a low altitude of 100 m, which led to a ground sampling distance of 3 cm/pixel. Furthermore, we ensured that the model was comprehensive by including images captured under a variety of light and meteorological conditions and from a variety of angles. After applying the two classification methods to develop the learning dataset and employing the as-developed model for classification, 12 images were misclassified out of 475. Visual inspection and an adjustment of the classification system were performed, and the model was updated to precisely classify all 475 images. These results show that supervised and unsupervised classification can be used together to improve the accuracy of a deep-learning model for the detection of asbestos roof slate.

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.

Localization of Cracks in Concrete Structures Using an Unmanned Aerial Vehicle.

Active research on crack detection technology for structures based on unmanned aerial vehicles (UAVs) has attracted considerable attention. Most of the existing research on localization of cracks using UAVs mounted the Global Positioning System (GPS)/Inertial Measurement Unit (IMU) on the UAVs to obtain location information. When such absolute position information is used, several studies confirmed that positioning errors of the UAVs were reflected and were in the order of a few meters. To address these limitations, in this study, without using the absolute position information, localization of cracks was defined using relative position between objects in UAV-captured images to significantly reduce the error level. Through aerial photography, a total of 97 images were acquired. Using the point cloud technique, image stitching, and homography matrix algorithm, 5 cracks and 3 reference objects were defined. Importantly, the comparative analysis of estimated relative position values and ground truth values through field measurement revealed that errors in the range 24-84 mm and 8-48 mm were obtained on the x- and y-directions, respectively. Also, RMSE errors of 37.95-91.24 mm were confirmed. In the future, the proposed methodology can be utilized for supplementing and improving the conventional methods for visual inspection of infrastructures and facilities.

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.

Gestational age-specific serum creatinine can predict adverse pregnancy outcomes.

Serum creatinine level (SCr) typically decreases during pregnancy due to physiologic glomerular hyperfiltration. Therefore, the clinical practice of estimated glomerular filtration rate (eGFR) based on SCr concentrations might be inapplicable to pregnant women with kidney disease since it does not take into account of the pregnancy-related biological changes. We integrated the Wonju Severance Christian Hospital (WSCH)-based findings and prior knowledge from big data to reveal the relationship between the abnormal but hidden SCr level and adverse pregnancy outcomes. We analyzed 4004 pregnant women who visited in WSCH. Adverse pregnancy outcomes included preterm birth, preeclampsia, fetal growth retardation, and intrauterine fetal demise. We categorized the pregnant women into four groups based on the gestational age (GA)-unadjusted raw distribution (Q1-4raw), and then GA-specific (Q1-4adj) SCr distribution. Linear regression analysis revealed that Q1-4adj groups had better predictive outcomes than the Q1-4raw groups. In logistic regression model, the Q1-4adj groups exhibited a robust non-linear U-shaped relationship with the risk of adverse pregnancy outcomes, compared to the Q1-4raw groups. The integrative analysis on SCr with respect to GA-specific distribution could be used to screen out pregnant women with a normal SCr coupled with a decreased renal function.

A Deep Neural Network for Estimating Low-Density Lipoprotein Cholesterol From Electronic Health Records: Real-Time Routine Clinical Application.

BACKGROUND: Previously, we constructed a deep neural network (DNN) model to estimate low-density lipoprotein cholesterol (LDL-C). OBJECTIVE: To routinely provide estimated LDL-C levels, we applied the aforementioned DNN model to an electronic health record (EHR) system in real time (deep LDL-EHR). METHODS: The Korea National Health and Nutrition Examination Survey and the Wonju Severance Christian Hospital (WSCH) datasets were used as training and testing datasets, respectively. We measured our proposed model's performance by using 5 indices, including bias, root mean-square error, P10-P30, concordance, and correlation coefficient. For transfer learning (TL), we pretrained the DNN model using a training dataset and fine-tuned it using 30% of the testing dataset. RESULTS: Based on 5 accuracy criteria, deep LDL-EHR generated inaccurate results compared with other methods for LDL-C estimation. By comparing the training and testing datasets, we found an overfitting problem. We then revised the DNN model using the TL algorithms and randomly selected subdata from the WSCH dataset. Therefore, the revised model (DNN+TL) exhibited the best performance among all methods. CONCLUSIONS: Our DNN+TL is expected to be suitable for routine real-time clinical application for LDL-C estimation in a clinical laboratory.

Clinical Application of Confidence Interval for Monitoring Changes in Tumor Markers to Determine the Responsiveness to Cancer Treatment.

OBJECTIVE: Tumor markers are used to monitor disease progression and determine the responsiveness to cancer treatment. However, there are no standardized criteria for monitoring serial tumor marker measurements. Herein, we have developed a monitoring system for interpreting changes in tumor markers using overlapping 95% confidence intervals (CIs). METHODS: Two-year data, including 117,289 results for 11 tumor markers in our laboratory, were analyzed. CI ranges for each tumor marker were set based on biological variation, and data were analyzed for each patient assessed at health check-ups and clinics, individually and overall. RESULTS: The 95th percentile cut-offs for each tumor marker were much higher in the clinic group than in the health check-up group. In decreasing order, the percentages of results with no overlap in 95% CIs were thyroglobulin antigen, 14.9%; protein induced by vitamin K absence-II (PIVKA), 11.9%; and prostate-specific antigen, 9.8%. After correction using the reference interval, the percentages decreased to less than 5%, except for PIVKA (10.9%). CONCLUSION: We suggest that our monitoring system can serve as a criterion for the auto-verification of tumor markers. Further studies are required to validate and demonstrate this concept in real clinical situations using actual clinical data reflecting disease progression in cancer patients and responsiveness to cancer treatment.

Clinical Application of Overlapping Confidence Intervals for Monitoring Changes in Serial Clinical Chemistry Test Results.

BACKGROUND: Interpretation of changes in serial laboratory results is necessary for both clinicians and laboratories; however, setting decision limits is not easy. Although the reference change value (RCV) has been widely used for auto-verification, it has limitations in clinical settings. We introduce the concept of overlapping confidence intervals (CIs) to determine whether the changes are statistically significant in clinical chemistry laboratory test results. METHODS: In total, 1,202,096 paired results for 33 analytes routinely tested in our clinical chemistry laboratory were analyzed. The distributions of delta% absolute values and cut-off values for certain percentiles were calculated. The CIs for each analyte were set based on biological variation, and data were analyzed at various confidence levels. Additionally, we analyzed the data using RCVs and compared their clinical utility. RESULTS: Most analytes had low indexes of individuality with large inter-individual variability. The 97.5th percentile cut-offs for each analyte were much larger than conventional RCVs. The percentages of results exceeding RCV95% and RCV99% corresponded to those with no overlap at the 83.4% and 93.2% confidence levels, respectively. CONCLUSIONS: The use of overlapping CIs in serial clinical chemistry test results can overcome the limitations of existing RCVs and replace them, especially for analytes with large intra-individual variation.

Development of an integrated reporting system for verifying hemolysis, icterus, and lipemia in clinical chemistry results.

BACKGROUND: Hemolysis, icterus, and lipemia (HIL) cause preanalytical interference and vary unpredictably with different analytical equipments and measurement methods. We developed an integrated reporting system for verifying HIL status in order to identify the extent of interference by HIL on clinical chemistry results. METHODS: HIL interference data from 30 chemical analytes were provided by the manufacturers and were used to generate a table of clinically relevant interference values that indicated the extent of bias at specific index values (alert index values). The HIL results generated by the Vista 1500 system (Siemens Healthcare Diagnostics, USA), Advia 2400 system (Siemens Healthcare Diagnostics), and Modular DPE system (Roche Diagnostics, Switzerland) were analyzed and displayed on physicians' personal computers. RESULTS: Analytes 11 and 29 among the 30 chemical analytes were affected by interference due to hemolysis, when measured using the Vista and Modular systems, respectively. The hemolysis alert indices for the Vista and Modular systems were 0.1-25.8% and 0.1-64.7%, respectively. The alert indices for icterus and lipemia were <1.4% and 0.7% in the Vista system and 0.7% and 1.0% in the Modular system, respectively. CONCLUSIONS: The HIL alert index values for chemical analytes varied depending on the chemistry analyzer. This integrated HIL reporting system provides an effective screening tool for verifying specimen quality with regard to HIL and simplifies the laboratory workflow.

Biphasic positive effect of formononetin on metabolic activity of human normal and osteoarthritic subchondral osteoblasts.

Osteoarthritis is a multifactorial disease characterized by loss of articular cartilage and subchondral plate thickening. Therefore, biochemical analysis of the underlying bone tissue has provided important information for treatment of osteoarthritis. In this study, we determined the potential role of formononetin, a phytoestrogen isolated from Astragalus membranaceus to alter the expression of metabolic markers and cytokine production of human normal osteoblasts (Obs) and osteoarthritis subchondral osteoblasts (OA Obs). Human OA Obs and normal Obs were cultured for 3days, 7days or 14days in the present medium only or were treated with various doses of formononetin. Cells were analyzed for viability by WST-8 assay, alkaline phosphatase (ALP) activity, osteogenic markers (osteocalcin (OCN) and type I collagen (Col I)) and cytokines (interleukin-6 (IL-6), vascular endothelial growth factor (VEGF), bone morphogenic protein-2 (BMP-2)). The level of IL-6, VEGF, BMP-2, OCN and Col I was increased in OA Obs compared with normal Obs. Formononetin dose-dependently decreased ALP, IL-6, VEGF, BMP-2, OCN and Col I in OA Obs, while markedly increased ALP, VEGF, BMP-2, OCN and Col I in normal Obs. Interestingly, formononetin markedly increased the expression of VEGF and BMP-2 for 3days of culture and significantly increased OCN and Col I at 14days in human normal Obs. The remodeling effect of formononetin on osteogenic markers and cytokines of inflammatory mediators was more striking in OA Obs as well. Taken together, these results could suggest that formononetin has biphasic positive effects on normal Obs and OA Obs by modifying their biological synthetic capacities.