Cardiovascular Event Rates in Statin-Treated Korean Patients with Cardiovascular Disease: Estimates from a Real-World Population Using Electronic Medical Record Data.

PURPOSE: To estimate the risk of recurrent cardiovascular events in a real-world population of very high-risk Korean patients with prior myocardial infarction (MI), ischemic stroke (IS), or symptomatic peripheral artery disease (sPAD), similar to the Further cardiovascular OUtcomes Research with proprotein convertase subtilisin-kexin type 9 Inhibition in subjects with Elevated Risk (FOURIER) trial population. METHODS: This retrospective study used the Asan Medical Center Heart Registry database built on electronic medical records (EMR) from 2000 to 2016. Patients with a history of clinically evident atherosclerotic cardiovascular disease (ASCVD) with multiple risk factors were followed up for 3 years. The primary endpoint was a composite of MI, stroke, hospitalization for unstable angina, coronary revascularization, and all-cause mortality. RESULTS: Among 15,820 patients, the 3-year cumulative incidence of the composite primary endpoint was 15.3% and the 3-year incidence rate was 5.7 (95% CI 5.5-5.9) per 100 person-years. At individual endpoints, the rates of deaths, MI, and IS were 0.4 (0.3-0.4), 0.9 (0.8-0.9), and 0.8 (0.7-0.9), respectively. The risk of the primary endpoint did not differ significantly between recipients of different intensities of statin therapy. Low-density lipoprotein cholesterol (LDL-C) goals were only achieved in 24.4% of patients during the first year of follow-up. CONCLUSION: By analyzing EMR data representing routine practice in Korea, we found that patients with very high-risk ASCVD were at substantial risk of further cardiovascular events in 3 years. Given the observed risk of recurrent events with suboptimal lipid management by statin, additional treatment to control LDL-C might be necessary to reduce the burden of further cardiovascular events for very high-risk ASCVD patients.

Electronic Medical Record-Based Machine Learning Approach to Predict the Risk of 30-Day Adverse Cardiac Events After Invasive Coronary Treatment: Machine Learning Model Development and Validation.

BACKGROUND: Although there is a growing interest in prediction models based on electronic medical records (EMRs) to identify patients at risk of adverse cardiac events following invasive coronary treatment, robust models fully utilizing EMR data are limited. OBJECTIVE: We aimed to develop and validate machine learning (ML) models by using diverse fields of EMR to predict the risk of 30-day adverse cardiac events after percutaneous intervention or bypass surgery. METHODS: EMR data of 5,184,565 records of 16,793 patients at a quaternary hospital between 2006 and 2016 were categorized into static basic (eg, demographics), dynamic time-series (eg, laboratory values), and cardiac-specific data (eg, coronary angiography). The data were randomly split into training, tuning, and testing sets in a ratio of 3:1:1. Each model was evaluated with 5-fold cross-validation and with an external EMR-based cohort at a tertiary hospital. Logistic regression (LR), random forest (RF), gradient boosting machine (GBM), and feedforward neural network (FNN) algorithms were applied. The primary outcome was 30-day mortality following invasive treatment. RESULTS: GBM showed the best performance with area under the receiver operating characteristic curve (AUROC) of 0.99; RF had a similar AUROC of 0.98. AUROCs of FNN and LR were 0.96 and 0.93, respectively. GBM had the highest area under the precision-recall curve (AUPRC) of 0.80, and the AUPRCs of RF, LR, and FNN were 0.73, 0.68, and 0.63, respectively. All models showed low Brier scores of <0.1 as well as highly fitted calibration plots, indicating a good fit of the ML-based models. On external validation, the GBM model demonstrated maximal performance with an AUROC of 0.90, while FNN had an AUROC of 0.85. The AUROCs of LR and RF were slightly lower at 0.80 and 0.79, respectively. The AUPRCs of GBM, LR, and FNN were similar at 0.47, 0.43, and 0.41, respectively, while that of RF was lower at 0.33. Among the categories in the GBM model, time-series dynamic data demonstrated a high AUROC of >0.95, contributing majorly to the excellent results. CONCLUSIONS: Exploiting the diverse fields of the EMR data set, the ML-based 30-day adverse cardiac event prediction models demonstrated outstanding results, and the applied framework could be generalized for various health care prediction models.

CardioNet: a manually curated database for artificial intelligence-based research on cardiovascular diseases.

BACKGROUND: Cardiovascular diseases (CVDs) are difficult to diagnose early and have risk factors that are easy to overlook. Early prediction and personalization of treatment through the use of artificial intelligence (AI) may help clinicians and patients manage CVDs more effectively. However, to apply AI approaches to CVDs data, it is necessary to establish and curate a specialized database based on electronic health records (EHRs) and include pre-processed unstructured data. METHODS: To build a suitable database (CardioNet) for CVDs that can utilize AI technology, contributing to the overall care of patients with CVDs. First, we collected the anonymized records of 748,474 patients who had visited the Asan Medical Center (AMC) or Ulsan University Hospital (UUH) because of CVDs. Second, we set clinically plausible criteria to remove errors and duplication. Third, we integrated unstructured data such as readings of medical examinations with structured data sourced from EHRs to create the CardioNet. We subsequently performed natural language processing to structuralize the significant variables associated with CVDs because most results of the principal CVD-related medical examinations are free-text readings. Additionally, to ensure interoperability for convergent multi-center research, we standardized the data using several codes that correspond to the common data model. Finally, we created the descriptive table (i.e., dictionary of the CardioNet) to simplify access and utilization of data for clinicians and engineers and continuously validated the data to ensure reliability. RESULTS: CardioNet is a comprehensive database that can serve as a training set for AI models and assist in all aspects of clinical management of CVDs. It comprises information extracted from EHRs and results of readings of CVD-related digital tests. It consists of 27 tables, a code-master table, and a descriptive table. CONCLUSIONS: CardioNet database specialized in CVDs was established, with continuing data collection. We are actively supporting multi-center research, which may require further data processing, depending on the subject of the study. CardioNet will serve as the fundamental database for future CVD-related research projects.

Medical resource utilization patterns and mortality rates according to age among critically ill patients admitted to a medical intensive care unit.

There is ongoing controversy about how to address the growing demand for intensive care for critically ill elderly patients. We investigated resource utilization patterns and mortality rates according to age among critically ill patients.We retrospectively analyzed the medical records of patients admitted to a medical intensive care unit (ICU) in a tertiary referral teaching hospital between July 2006 and June 2015. Patients were categorized into non-elderly (age <65 years, n = 4140), young-elderly (age 65-74 years, n = 2306), and old-elderly (age ≥75 years, n = 1508) groups.Among 7954 admissions, the mean age was 61.5 years, and 5061 (63.6%) were of male patients. The proportion of comorbidities increased with age (64.6% in the non-elderly vs 81.4% in the young-elderly vs 82.8% in the old-elderly, P < .001 and P for trend <.001), whereas the baseline Sequential Organ Failure Assessment (SOFA) score decreased with age (8.1 in the non-elderly vs 7.2 in the young-elderly vs 7.2 in the old-elderly, P < .001, R = -.092 and P for trend <.001). Utilization rates of mechanical ventilation (48.6% in the non-elderly vs 48.3% in the young-elderly vs 45.5% in the old-elderly, P = .11) and renal replacement therapy (27.5% in the non-elderly vs 25.5% in the young-elderly vs 24.8% in the old-elderly, P = .069) were comparable between the age groups. The 28-day ICU mortality rates were lower in the young-elderly and the old-elderly groups than in the non-elderly group (35.6% in the non-elderly vs 34.2% in the young-elderly, P = .011; and vs 32.6% in the old-elderly, P = .002).A substantial number of critically ill elderly patients used medical resources as non-elderly patients and showed favorable clinical outcomes. Our results support that underlying medical conditions rather than age per se need to be considered for determining intensive care.

Is Blockchain Technology Suitable for Managing Personal Health Records? Mixed-Methods Study to Test Feasibility.

BACKGROUND: There are many perspectives on the advantages of introducing blockchain in the medical field, but there are no published feasibility studies regarding the storage, propagation, and management of personal health records (PHRs) using blockchain technology. OBJECTIVE: The purpose of this study was to investigate the usefulness of blockchains in the medical field in relation to transactions with and propagation of PHRs in a private blockchain. METHODS: We constructed a private blockchain network using Ethereum version 1.8.4 and conducted verification using the de-identified PHRs of 300 patients. The private blockchain network consisted of one hospital node and 300 patient nodes. In order to verify the effectiveness of blockchain-based PHR management, PHRs at a time were loaded in a transaction between the hospital and patient nodes and propagated to the whole network. We obtained and analyzed the time and gas required for data transaction and propagation on the blockchain network. For reproducibility, these processes were repeated 100 times. RESULTS: Of 300 patient records, 74 (24.7%) were not loaded in the private blockchain due to the data block size of the transaction block. The remaining 226 individual health records were classified into groups A (80 patients with outpatient visit data less than 1 year old), B (84 patients with outpatient data from between 1 and 3 years before data collection), and C (62 patients with outpatient data 3 to 5 years old). With respect to mean transaction time in the blockchain, C (128.7 seconds) had the shortest time, followed by A (132.2 seconds) and then B (159.0 seconds). The mean propagation times for groups A, B, and C were 1494.2 seconds, 2138.9 seconds, and 4111.4 seconds, respectively; mean file sizes were 5.6 KB, 18.6 KB, and 45.38 KB, respectively. The mean gas consumption values were 1,900,767; 4,224,341; and 4,112,784 for groups A, B, and C, respectively. CONCLUSIONS: This study confirms that it is possible to exchange PHR data in a private blockchain network. However, to develop a blockchain-based PHR platform that can be used in practice, many improvements are required, including reductions in data size, improved personal information protection, and reduced operating costs.

Automated detection of vulnerable plaque in intravascular ultrasound images.

Acute coronary syndrome (ACS) is a syndrome caused by a decrease in blood flow in the coronary arteries. The ACS is usually related to coronary thrombosis and is primarily caused by plaque rupture followed by plaque erosion and calcified nodule. Thin-cap fibroatheroma (TCFA) is known to be the most similar lesion morphologically to a plaque rupture. In this paper, we propose methods to classify TCFA using various machine learning classifiers including feed-forward neural network (FNN), K-nearest neighbor (KNN), random forest (RF), and convolutional neural network (CNN) to figure out a classifier that shows optimal TCFA classification accuracy. In addition, we suggest pixel range-based feature extraction method to extract the ratio of pixels in the different region of interests to reflect the physician's TCFA discrimination criteria. Our feature extraction method examines the pixel distribution of the intravascular ultrasound (IVUS) image at a given ROI, which allows us to extract general characteristics of the IVUS image while simultaneously reflecting the different properties of the vessel's substances such as necrotic core and calcified nodule depending on the brightness of the pixel. A total of 12,325 IVUS images were labeled with corresponding optical coherence tomography (OCT) images to train and evaluate the classifiers. We achieved 0.859, 0.848, 0.844, and 0.911 area under the ROC curve (AUC) in the order of using FNN, KNN, RF, and CNN classifiers. As a result, the CNN classifier performed best and the top 10 features of the feature-based classifiers (FNN, KNN, RF) were found to be similar to the physician's TCFA diagnostic criteria. Graphical Abstract AUC result of proposed classifiers.

Lithium Dendrite Suppression with UV-Curable Polysilsesquioxane Separator Binders.

For the first time, an inorganic-organic hybrid polymer binder was used for the coating of hybrid composites on separators to enhance thermal stability and to prevent formation of lithium dendrite in lithium metal batteries. The fabricated hybrid-composite-coated separators exhibited minimal thermal shrinkage compared with the previous composite separators (<5% change in dimension), maintenance of porosity (Gurley number ∼400 s/100 cm(3)), and high ionic conductivity (0.82 mS/cm). Lithium metal battery cell examinations with our hybrid-composite-coated separators revealed excellent C-rate and cyclability performance due to the prevention of lithium dendrite growth on the lithium anode even after 200 cycles under 0.2-5C (charge-discharge) conditions. The mechanism for lithium dendrite prevention was attributed to exceptional nanoscale surface mechanical properties of the hybrid composite coating layer compared with the lithium metal anode, as the elastic modulus of the hybrid-composite-coated separator far exceeded those of both the lithium metal anode and the required threshold for lithium metal dendrite prevention.

Nanoscale magnetism control via surface and exchange anisotropy for optimized ferrimagnetic hysteresis.

With the aim of controlling nanoscale magnetism, we demonstrate an approach encompassing concepts of surface and exchange anisotropy while reflecting size, shape, and structural hybridization of nanoparticles. We visualize that cube has higher magnetization value than sphere with highest coercivity at 60 nm. Its hybridization into core-shell (CS) structure brings about a 14-fold increase in the coercivity with an exceptional energy conversion of magnetic field into thermal energy of 10600 W/g, the largest reported to date. Such capability of the CS-cube is highly effective for drug resistant cancer cell treatment.