Publications by authors named "Yong-Hyeon Cho"
Article Synopsis
- * The device achieves a high on/off ratio of 1273 by changing the conduction process from thermal injection to Fowler-Nordheim tunneling due to the modulation of energy barriers.
- * It shows promise for applications in neuromorphic computing, maintaining a read margin of 10% in integrated arrays exceeding 7k, and demonstrates over 92% accuracy in image recognition while confirming reliable self-rectifying behavior.
Hafnia-based ferroelectrics and their semiconductor applications are reviewed, focusing on next-generation dynamic random-access-memory (DRAM) and Flash. The challenges of achieving high endurance and high write/read speed and the optimal material properties to achieve them are discussed. In DRAM applications, the trade-off between remanent polarization (), endurance, and operation speed is highlighted, focusing on reducing the critical material property (coercive field).
View Article and Find Full Text PDFPurpose: Although renal failure is a major healthcare burden globally and the cornerstone for preventing its irreversible progression is an early diagnosis, an adequate and noninvasive tool to screen renal impairment (RI) reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance.
Methods: This retrospective cohort study included two hospitals.
Deep-learning model for screening sepsis using electrocardiography.
Scand J Trauma Resusc Emerg Med
October 2021
Article Synopsis
- - A deep learning model (DLM) was developed to screen for sepsis using electrocardiography (ECG) data from over 46,000 patients, with robust validation efforts involving multiple hospitals and ECG recordings.
- - The DLM demonstrated strong accuracy, achieving an area under the curve (AUC) of up to 0.901 for detecting sepsis and 0.906 for septic shock using 12-lead ECGs, indicating its potential effectiveness in clinical settings.
- - Results highlighted that specific ECG features, like the QRS complex and T waves, were critical for identifying sepsis, and the model was also able to predict in-hospital mortality in infected patients with a notable AUC of
Article Synopsis
- Early detection and intervention of arrhythmia is vital for effective treatment and reducing complications, prompting the development of an explainable deep learning model (XDM) for classification.
- Utilizing a large dataset of 86,802 electrocardiograms (ECGs), the XDM was validated against external data from 36,961 ECGs to ensure its accuracy and explainability.
- The XDM demonstrated high performance with area under the curve (AUC) scores of 0.976 and 0.966 during internal and external validation, respectively, indicating it could classify arrhythmias effectively while providing explanations for its classifications, enhancing its usefulness in clinical settings.
Artificial intelligence for detecting electrolyte imbalance using electrocardiography.
Ann Noninvasive Electrocardiol
May 2021
Introduction: The detection and monitoring of electrolyte imbalance is essential for appropriate management of many metabolic diseases; however, there is no tool that detects such imbalances reliably and noninvasively. In this study, we developed a deep learning model (DLM) using electrocardiography (ECG) for detecting electrolyte imbalance and validated its performance in a multicenter study.
Methods And Results: This retrospective cohort study included two hospitals: 92,140 patients who underwent a laboratory electrolyte examination and an ECG within 30 min were included in this study.
Aims: Paroxysmal supraventricular tachycardia (PSVT) is not detected owing to its paroxysmal nature, but it is associated with the risk of cardiovascular disease and worsens the patient quality of life. A deep learning model (DLM) was developed and validated to identify patients with PSVT during normal sinus rhythm in this multicentre retrospective study.
Methods And Results: This study included 12 955 patients with normal sinus rhythm, confirmed by a cardiologist.