• Journal of Cardiovascular Imaging
• /
• v.31 no.3
• /
• pp.135-141
• /
• 2023

BACKGROUND: Global longitudinal strain (GLS) is an accurate and reproducible parameter of left ventricular (LV) systolic function which has shown meaningful prognostic value. Fast, user-friendly, and accurate tools are required for its widespread implementation. We aim to compare a novel web-based tool with two established algorithms for strain analysis and test its reproducibility. METHODS: Thirty echocardiographic datasets with focused LV acquisitions were analyzed using three different semi-automated endocardial GLS algorithms by two readers. Analyses were repeated by one reader for the purpose of intra-observer variability. CAAS Qardia (Pie Medical Imaging) was compared with 2DCPA and AutoLV (TomTec). RESULTS: Mean GLS values were -15.0 ± 3.5% from Qardia, -15.3 ± 4.0% from 2DCPA, and -15.2 ± 3.8% from AutoLV. Mean GLS between Qardia and 2DCPA were not statistically different (p = 0.359), with a bias of -0.3%, limits of agreement (LOA) of 3.7%, and an intraclass correlation coefficient (ICC) of 0.88. Mean GLS between Qardia and AutoLV were not statistically different (p = 0.637), with a bias of -0.2%, LOA of 3.4%, and an ICC of 0.89. The coefficient of variation (CV) for intra-observer variability was 4.4% for Qardia, 8.4% 2DCPA, and 7.7% AutoLV. The CV for inter-observer variability was 4.5%, 8.1%, and 8.0%, respectively. CONCLUSIONS: In echocardiographic datasets of good image quality analyzed at an independent core laboratory using a standardized annotation method, a novel web-based tool for GLS analysis showed consistent results when compared with two algorithms of an established platform. Moreover, inter- and intra-observer reproducibility results were excellent.

• Korean Circulation Journal
• /
• v.53 no.10
• /
• pp.677-689
• /
• 2023

Background and Objectives: There is limited evidence regarding machine-learning prediction for the recurrence of atrial fibrillation (AF) after electrical cardioversion (ECV). This study aimed to predict the recurrence of AF after ECV using machine learning of clinical features and electrocardiograms (ECGs) in persistent AF patients. Methods: We analyzed patients who underwent successful ECV for persistent AF. Machine learning was designed to predict patients with 1-month recurrence. Individual 12-lead ECGs were collected before and after ECV. Various clinical features were collected and trained the extreme gradient boost (XGBoost)-based model. Ten-fold cross-validation was used to evaluate the performance of the model. The performance was compared to the C-statistics of the selected clinical features. Results: Among 718 patients (mean age 63.5±9.3 years, men 78.8%), AF recurred in 435 (60.6%) patients after 1 month. With the XGBoost-based model, the areas under the receiver operating characteristic curves (AUROCs) were 0.57, 0.60, and 0.63 if the model was trained by clinical features, ECGs, and both (the final model), respectively. For the final model, the sensitivity, specificity, and F1-score were 84.7%, 28.2%, and 0.73, respectively. Although the AF duration showed the best predictive performance (AUROC, 0.58) among the clinical features, it was significantly lower than that of the final machine-learning model (p<0.001). Additional training of extended monitoring data of 15-minute single-lead ECG and photoplethysmography in available patients (n=261) did not significantly improve the model's performance. Conclusions: Machine learning showed modest performance in predicting AF recurrence after ECV in persistent AF patients, warranting further validation studies.

• Korean Journal of Clinical Laboratory Science
• /
• v.46 no.2
• /
• pp.64-67
• /
• 2014

Vancomycin-resistant Enterococci (VRE) are a leading cause of a nosocomial infection. While seven glycopeptide resistance genotypes have been found in Enterococci, vanA and vanB are the most common resistance genotypes. Aims of this study were to detect antibiotic susceptibilities of 23 Enterococcus spp, which broke out in a university hospital by the disk diffusion test, to investigate specific genes of vanA and vanB by conventional and real-time PCR. PCR for vanA and vanB was performed on 23 Enterococci, all 23 were positive for vanA type. This study reports the validation of a simple and rapid VRE detection method that can be easily incorporated into the daily routine of a clinical laboratory. Early detection of VRE strains, including those with susceptibility to Vancomycin, is of paramount clinical importance, as it allows a rapid initiation of strict infection control practices as well as a therapeutic guidance for a confirmed infection. The real-time PCR method is a rapid technique to detect vanA in Enterococci. It is simple and reliable for the rapid characterization of VRE.

• Korean Journal of Radiology
• /
• v.23 no.8
• /
• pp.811-820
• /
• 2022

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.334-343
• /
• 2021

Objective: We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms. Materials and Methods: We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score. Results: The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all). Conclusion: Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

• Journal of Korean Academy of Nursing
• /
• v.48 no.4
• /
• pp.419-431
• /
• 2018

Purpose: The purpose of this study was to develop and establish the psychometric properties of a clinical nursing competency evaluation tool to be utilized by clinical preceptors. Methods: The initial items were identified through in-depth literature review and field interviews based on a hybrid model. Content validation of the items was evaluated through three rounds of content validity testing. Participants were 34 clinical preceptors and 443 nursing students participating in clinical practice. Data were analyzed using exploratory and confirmatory factor analysis, convergence and discriminant validity, internal consistency and inter-rater reliability. Results: The final scale consisted of 23 items and four factors, fundamental nursing skills performance, critical thinking skills based on the nursing process, basic nursing knowledge, and professional attitude; these factor explained 69.7% of the total variance. The analysis with multi-trait/multi-item matrix correlation coefficients yielded 100.0% and 95.7 % convergence and discriminant validity, respectively. Cronbach's alpha for the total items was .95. The four subscale model tested by confirmatory factor analysis was satisfactory. Inter-rater reliability ranged from .912 to .967. Conclusion: This scale was found to be a reliable and valid instrument that clinical preceptors can apply for evaluating the clinical nursing competency of nursing students in clinical settings.

• Journal of Korean Academy of Nursing Administration
• /
• v.19 no.4
• /
• pp.501-512
• /
• 2013

Purpose: This study was done to develop a nursing competency scale according to a clinical ladder system for intensive care nurses. Methods: Index of content validation was done by 20 clinical experts and 80 nurses in Intensive Care Units (ICU). Results: The process and results of study are as follows. First, 12 nursing competencies were used in the establishment of the clinical ladder system (Jang, 2000). Second, the first draft of the competency lists was developed. It was based on the clinical nurses' behavioral indicators of nursing competency by Jang (2000), and was modified and supplemented through various literature reviews including competency standards for specialist intensive care nurses in Australia and consultation with 2 clinical nurses with over 10 years experience in the ICU. Third, the draft was examined by 20 clinical experts for content validity. Finally, the final draft was analysed using clinical validity where 20 nurses in each ladder participated. The final number of items was fixed at 309. Conclusion: The tool represents expected nursing competency of nurses working in ICU. Intensive care nurses can recognize their strengths and weaknesses, and identify directions for their professional growth by analysing results of their competency evaluation using this tool.

• Korean Journal of Radiology
• /
• v.24 no.1
• /
• pp.51-61
• /
• 2023

Objective: To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET-derived parameters in derived parameters and an appropriate combination of machine learning methods in patients with OPSCC. Materials and Methods: This retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwent ¹⁸F-FDG PET-computed tomography (CT) between January 2012 and February 2020. Patients were randomly assigned to training and internal validation sets in a 7:3 ratio. An external test set of 19 patients (16 male; mean age, 65.3 years) was recruited sequentially from two other tertiary hospitals. Model 1 used only PET parameters, Model 2 used only clinical features, and Model 3 used both PET and clinical parameters. Multiple feature transforms, feature selection, oversampling, and training models are all investigated. The external test set was used to test the three models that performed best in the internal validation set. The values for area under the receiver operating characteristic curve (AUC) were compared between models. Results: In the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48, p = 0.047) and Model 2 using clinical parameters alone (AUC = 0.52, p = 0.142) in predicting HPV status. Conclusion: Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from ¹⁸F-FDG PET/CT and clinical parameters in OPSCC, which exhibited higher performance than the models using either PET or clinical parameters alone.

• Journal of Korean Academy of Nursing Administration
• /
• v.9 no.3
• /
• pp.481-494
• /
• 2003

Purpose: This study was to develop nursing competencies, sub-competencies and behavior indicators according to the clinical ladder of emergency nurses. Method: index of content validation was used by 21 clinical experts. Results: This study had three phases to develop nursing competencies, sub-competencies and behavior indicators. In first phase: 12 nursing competencies and 33 sub-competencies were developed through the literature review on nursing competency and emergency nurses' job description. The content of 12 competencies and 33 sub-competencies were reviewed by 3 nursing professors. The 12 competencies and 33 sub-competencies were followed: clinical judgement and measures(6 sub-competencies), processing ability of ward works(2 sub-competencies), flexibility(2 sub-competencies), resources management(2 sub-competencies), confidence(3 sub-competencies), cooperation(2 sub-competencies), professional development power(2 sub-competencies), patient service orientation(3 sub-competencies), inclination toward ethical value(5 sub-competencies), influence power(2 sub-competencies), developing others(2 sub-competencies), self control(2 sub-competencies). In second phase, 132 behavior indicators were developed according to nurse clinical ladder: novice, advanced novice, competent, proficient. In Third phase, content validity was examined on 132 behavior indicators by 21 clinical experts. 126 among 132 indicators had over 70% agreement among experts and 6 indicators under 70% were revised. Conclusion: nursing competencies, sub competencies and behavior indicators can be used nurses' clinical performance as well as establishing proper directions for professional growth related to reward system.

• Journal of Korean Academy of Nursing Administration
• /
• v.8 no.4
• /
• pp.535-549
• /
• 2002

Purpose : The purpose of this study was to develop a core competency evaluation tool of the preceptors training new graduate nurses and to determine the validity of the developed instrument. Method : This study was conducted in 2 phases. In phase I, preceptor's core competency list was developed through literature review, focus group interview, and review by nursing directors and nurse managers. In phase II, 60 preceptors were evaluated with the developed instrument and categorized into excellent, good & poor core competency groups. For validation of the instrument, new graduates' clinical performance improvement and satisfaction with preceptor were compared between excellent and poor group. Result : The data were analyzed by SPSS P.C and the results were as follows. 1) Preceptor's core competencies were classified into three domains; Role model(10 items), Socialization facilitator(8 items), and Educator(16 items), and each item had four point system of "strongly agree" to "strongly disagree". Cronbach'${\alpha}$ of the instrument was.9416. 2) Comparison of clinical performance improvement and satisfaction with preceptor of the new graduates trained by excellent and poor preceptors revealed that new graduates' clinical performance improvement(p=.015) and satisfaction with the preceptor(p=.005) were significantly higher in the excellent core competency preceptor group than the poor core competency preceptor group. Conclusion : The validity of the preceptor's core competency evaluation tool developed in this study was confirmed. Therefore, this tool can be effectively utilized for education and evaluation of new graduates' preceptors in clinical settings.