Background and Objectives: Although various cardiac parameters on echocardiography have clinical importance, their measurement by conventional manual methods is time-consuming and subject to variability. We evaluated the feasibility, accuracy, and predictive value of an artificial intelligence (AI)-based automated system for echocardiographic analysis in patients with ST-segment elevation myocardial infarction (STEMI). Methods: The AI-based system was developed using a nationwide echocardiographic dataset from five tertiary hospitals, and automatically identified views, then segmented and tracked the left ventricle (LV) and left atrium (LA) to produce volume and strain values. Both conventional manual measurements and AI-based fully automated measurements of the LV ejection fraction and global longitudinal strain, and LA volume index and reservoir strain were performed in 632 patients with STEMI. Results: The AI-based system accurately identified necessary views (overall accuracy, 98.5%) and successfully measured LV and LA volumes and strains in all cases in which conventional methods were applicable. Inter-method analysis showed strong correlations between measurement methods, with Pearson coefficients ranging 0.81–0.92 and intraclass correlation coefficients ranging 0.74–0.90. For the prediction of clinical outcomes (composite of all-cause death, re-hospitalization due to heart failure, ventricular arrhythmia, and recurrent myocardial infarction), AI-derived measurements showed predictive value independent of clinical risk factors, comparable to those from conventional manual measurements. Conclusions Our fully automated AI-based approach for LV and LA analysis on echocardiography is feasible and provides accurate measurements, comparable to conventional methods, in patients with STEMI, offering a promising solution for comprehensive echocardiographic analysis, reduced workloads, and improved patient care.

Background and Objectives: Although various cardiac parameters on echocardiography have clinical importance, their measurement by conventional manual methods is time-consuming and subject to variability. We evaluated the feasibility, accuracy, and predictive value of an artificial intelligence (AI)-based automated system for echocardiographic analysis in patients with ST-segment elevation myocardial infarction (STEMI). Methods: The AI-based system was developed using a nationwide echocardiographic dataset from five tertiary hospitals, and automatically identified views, then segmented and tracked the left ventricle (LV) and left atrium (LA) to produce volume and strain values. Both conventional manual measurements and AI-based fully automated measurements of the LV ejection fraction and global longitudinal strain, and LA volume index and reservoir strain were performed in 632 patients with STEMI. Results: The AI-based system accurately identified necessary views (overall accuracy, 98.5%) and successfully measured LV and LA volumes and strains in all cases in which conventional methods were applicable. Inter-method analysis showed strong correlations between measurement methods, with Pearson coefficients ranging 0.81–0.92 and intraclass correlation coefficients ranging 0.74–0.90. For the prediction of clinical outcomes (composite of all-cause death, re-hospitalization due to heart failure, ventricular arrhythmia, and recurrent myocardial infarction), AI-derived measurements showed predictive value independent of clinical risk factors, comparable to those from conventional manual measurements. Conclusions Our fully automated AI-based approach for LV and LA analysis on echocardiography is feasible and provides accurate measurements, comparable to conventional methods, in patients with STEMI, offering a promising solution for comprehensive echocardiographic analysis, reduced workloads, and improved patient care.

Background and Objectives: Although various cardiac parameters on echocardiography have clinical importance, their measurement by conventional manual methods is time-consuming and subject to variability. We evaluated the feasibility, accuracy, and predictive value of an artificial intelligence (AI)-based automated system for echocardiographic analysis in patients with ST-segment elevation myocardial infarction (STEMI). Methods: The AI-based system was developed using a nationwide echocardiographic dataset from five tertiary hospitals, and automatically identified views, then segmented and tracked the left ventricle (LV) and left atrium (LA) to produce volume and strain values. Both conventional manual measurements and AI-based fully automated measurements of the LV ejection fraction and global longitudinal strain, and LA volume index and reservoir strain were performed in 632 patients with STEMI. Results: The AI-based system accurately identified necessary views (overall accuracy, 98.5%) and successfully measured LV and LA volumes and strains in all cases in which conventional methods were applicable. Inter-method analysis showed strong correlations between measurement methods, with Pearson coefficients ranging 0.81–0.92 and intraclass correlation coefficients ranging 0.74–0.90. For the prediction of clinical outcomes (composite of all-cause death, re-hospitalization due to heart failure, ventricular arrhythmia, and recurrent myocardial infarction), AI-derived measurements showed predictive value independent of clinical risk factors, comparable to those from conventional manual measurements. Conclusions Our fully automated AI-based approach for LV and LA analysis on echocardiography is feasible and provides accurate measurements, comparable to conventional methods, in patients with STEMI, offering a promising solution for comprehensive echocardiographic analysis, reduced workloads, and improved patient care.

Background and Objectives: Although various cardiac parameters on echocardiography have clinical importance, their measurement by conventional manual methods is time-consuming and subject to variability. We evaluated the feasibility, accuracy, and predictive value of an artificial intelligence (AI)-based automated system for echocardiographic analysis in patients with ST-segment elevation myocardial infarction (STEMI). Methods: The AI-based system was developed using a nationwide echocardiographic dataset from five tertiary hospitals, and automatically identified views, then segmented and tracked the left ventricle (LV) and left atrium (LA) to produce volume and strain values. Both conventional manual measurements and AI-based fully automated measurements of the LV ejection fraction and global longitudinal strain, and LA volume index and reservoir strain were performed in 632 patients with STEMI. Results: The AI-based system accurately identified necessary views (overall accuracy, 98.5%) and successfully measured LV and LA volumes and strains in all cases in which conventional methods were applicable. Inter-method analysis showed strong correlations between measurement methods, with Pearson coefficients ranging 0.81–0.92 and intraclass correlation coefficients ranging 0.74–0.90. For the prediction of clinical outcomes (composite of all-cause death, re-hospitalization due to heart failure, ventricular arrhythmia, and recurrent myocardial infarction), AI-derived measurements showed predictive value independent of clinical risk factors, comparable to those from conventional manual measurements. Conclusions Our fully automated AI-based approach for LV and LA analysis on echocardiography is feasible and provides accurate measurements, comparable to conventional methods, in patients with STEMI, offering a promising solution for comprehensive echocardiographic analysis, reduced workloads, and improved patient care.

Purpose: There is increasing interest in the use of ultrasound for endoscopic and percutaneous procedures. Access can be achieved without radiation exposure under ultrasound guidance. Our aim was to develop a porcine-based training model for ultrasound-guided percutaneous renal access that could also be personalized to a specific patient. Materials and Methods: The Institutional Animal Care and Use Committee of Severance Hospital approved the study protocol. An anesthetized pig was placed in the dorsal lithotomy position. For the nephrostomy puncture, a Chiba biopsy needle with an echo tip was used under ultrasound guidance. Eight residents and three consultants in urology participated. Puncture time was defined as the nephrostomy time to confirm the flow of irrigation via the needle. After training, satisfaction survey results for clinical usability and procedural difficulty were evaluated. Results: The 5-point Likert scale satisfaction survey for clinical usability and procedural difficulty found mean results of 4.64 and 4.09 points, respectively. There were no differences between residents and consultants for either variable. For all participants combined, there was a significant difference for nephrostomy time between the first and second trials (278.8±70.6 s vs. 244.5±47.0 s;p=0.007). The between-trial difference was greater for residents (291.5±71.2 s vs. 259.1±41.9 s; p=0.039). The difference for the consultant was not significant (245.0±69.4 s vs. 205.7±42.5 s; p=0.250). Conclusions We developed a porcine-based ultrasound-guided nephrostomy puncture training model. Satisfaction survey results indicated high clinical usability and procedural difficulty. For nephrostomy time, the model was more effective for urology residents than for consultants.

Purpose: In men with metastatic castration-resistant prostate cancer (mCRPC), new bone lesions are sometimes not properly categorized through a confirmatory bone scan, and clinical significance of the test itself remains unclear. This study aimed to demonstrate the performance rate of confirmatory bone scans in a real-world setting and their prognostic impact in enzalutamide-treated mCRPC. Materials and Methods: Patients who received oral enzalutamide for mCRPC during 2014-2017 at 14 tertiary centers in Korea were included. Patients lacking imaging assessment data or insufficient drug exposure were excluded. The primary outcome was overall survival (OS). Secondary outcomes included performance rate of confirmatory bone scans in a real-world setting. Kaplan-Meier analysis and multivariate Cox regression analysis were performed. Results: Overall, 520 patients with mCRPC were enrolled (240 [26.2%] chemotherapy-naïve and 280 [53.2%] after chemotherapy). Among 352 responders, 92 patients (26.1%) showed new bone lesions in their early bone scan. Confirmatory bone scan was performed in 41 patients (44.6%), and it was associated with prolonged OS in the entire population (median, 30.9 vs. 19.7 months; p < 0.001), as well as in the chemotherapy-naïve (median, 47.2 vs. 20.5 months; p=0.011) and post-chemotherapy sub-groups (median, 25.5 vs. 18.0 months; p=0.006). Multivariate Cox regression showed that confirmatory bone scan performance was an independent prognostic factor for OS (hazard ratio 0.35, 95% confidence interval, 0.18 to 0.69; p=0.002). Conclusion Confirmatory bone scan performance was associated with prolonged OS. Thus, the premature discontinuation of enzalutamide without confirmatory bone scans should be discouraged.

Viral load and the duration of viral shedding of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are important determinants of the transmission of coronavirus disease 2019.In this study, we examined the effects of viral doses on the lung and spleen of K18-hACE2 transgenic mice by temporal histological and transcriptional analyses. Approximately, 1×105 plaque-forming units (PFU) of SARS-CoV-2 induced strong host responses in the lungs from 2 days post inoculation (dpi) which did not recover until the mice died, whereas responses to the virus were obvious at 5 days, recovering to the basal state by 14 dpi at 1×102 PFU. Further, flow cytometry showed that number of CD8+ T cells continuously increased in 1×102 PFU-virusinfected lungs from 2 dpi, but not in 1×105 PFU-virus-infected lungs. In spleens, responses to the virus were prominent from 2 dpi, and number of B cells was significantly decreased at 1×105PFU; however, 1×102 PFU of virus induced very weak responses from 2 dpi which recovered by 10 dpi. Although the defense responses returned to normal and the mice survived, lung histology showed evidence of fibrosis, suggesting sequelae of SARS-CoV-2 infection. Our findings indicate that specific effectors of the immune response in the lung and spleen were either increased or depleted in response to doses of SARS-CoV-2. This study demonstrated that the response of local and systemic immune effectors to a viral infection varies with viral dose, which either exacerbates the severity of the infection or accelerates its elimination.

Purpose: Results of initial endoscopic biopsy of gastric lesions often differ from those of the final pathological diagnosis. We evaluated whether an artificial intelligence-based gastric lesion detection and diagnostic system, ENdoscopy as AI-powered Device Computer Aided Diagnosis for Gastroscopy (ENAD CAD-G), could reduce this discrepancy. Materials and Methods: We retrospectively collected 24,948 endoscopic images of early gastric cancers (EGCs), dysplasia, and benign lesions from 9,892 patients who underwent esophagogastroduodenoscopy between 2011 and 2021. The diagnostic performance of ENAD CAD-G was evaluated using the following real-world datasets: patients referred from community clinics with initial biopsy results of atypia (n=154), participants who underwent endoscopic resection for neoplasms (Internal video set, n=140), and participants who underwent endoscopy for screening or suspicion of gastric neoplasm referred from community clinics (External video set, n=296). Results: ENAD CAD-G classified the referred gastric lesions of atypia into EGC (accuracy, 82.47%; 95% confidence interval [CI], 76.46%–88.47%), dysplasia (88.31%; 83.24%– 93.39%), and benign lesions (83.12%; 77.20%–89.03%). In the Internal video set, ENAD CAD-G identified dysplasia and EGC with diagnostic accuracies of 88.57% (95% CI, 83.30%– 93.84%) and 91.43% (86.79%–96.07%), respectively, compared with an accuracy of 60.71% (52.62%–68.80%) for the initial biopsy results (P<0.001). In the External video set, ENAD CAD-G classified EGC, dysplasia, and benign lesions with diagnostic accuracies of 87.50% (83.73%–91.27%), 90.54% (87.21%–93.87%), and 88.85% (85.27%–92.44%), respectively. Conclusions ENAD CAD-G is superior to initial biopsy for the detection and diagnosis of gastric lesions that require endoscopic resection. ENAD CAD-G can assist community endoscopists in identifying gastric lesions that require endoscopic resection.

Previously, we reported the concept of a cloud-based telemedicine platform for patients with intracerebral hemorrhage (ICH) at local emergency rooms in rural and medically underserved areas in Gangwon state by combining artificial intelligence and remote consultation with a neurosurgeon. Developing a telemedicine ICH treatment protocol exclusively for doctors with less ICH expertise working in emergency rooms should be part of establishing this system. Difficulties arise in providing appropriate early treatment for ICH in rural and underserved areas before the patient is transferred to a nearby hub hospital with stroke specialists. This has been an unmet medical need for decade. The available reporting ICH guidelines are realistically possible in university hospitals with a well-equipped infrastructure. However, it is very difficult for doctors inexperienced with ICH treatment to appropriately select and deliver ICH treatment based on the guidelines. To address these issues, we developed an ICH telemedicine protocol. Neurosurgeons from four university hospitals in Gangwon state first wrote the guidelines, and professors with extensive ICH expertise across the country revised them. Guidelines and recommendations for ICH management were described as simply as possible to allow more doctors to use them easily. We hope that our effort in developing the telemedicine protocols will ultimately improve the quality of ICH treatment in local emergency rooms in rural and underserved areas in Gangwon state.