Sunghoon Joo

Dr. Sunghoon Joo

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 July 2020 in ACS Omega
Verified
Journal Article
Closed access
SJSunghoon Joo
Sunghoon Joo
MKMin Soo Kim
Min Soo Kim
JYJaeho Yang
Jaeho Yang
JPJeahyun Park
Jeahyun Park

8 January 2025 in Biomedical Engineering Letters
Verified
Journal Article
Closed access
PDF file
JLJeonghwa Lim
Jeonghwa Lim
YLYeha Lee
Yeha Lee
WJWonseuk Jang
Wonseuk Jang
SJSunghoon Joo
Sunghoon Joo


4 June 2018 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
SJSunghoon Joo
Sunghoon Joo
YNYoonkey Nam
Yoonkey Nam
$Objective$: The use of microelectrode array (MEA) recordings is a very effective neurophysiological method, because it is able to continuously and noninvasively obtain the spatiotemporal information of electrical activity from many neurons constituting a neural network. Very recently, studies have been published that the measurement of a low-frequency component of electrical activity as an indicator of diverse activity of cultured neurons using MEAs. Although the occurrence of low-frequency activities has electrophysiological information that does not include the information from fast spikes, however, there is no in $vitro$ experimental model suitable for measuring the low-frequency activities (‘slow-waves’) for further study. $Methods$: The neural clusters consisting of dozens of neurons were placed directly on each electrode of an MEA, from which fast spikes and slow-waves were measured. $Results$: We obtained sufficient data on the early development patterns of the slow-waves and the spikes measured from the many independent neural clusters, confirming that the slow-waves first occurred before the emergence of spikes in the neural clusters. We also showed that changes in the occurrence frequency of the slow-waves for synaptic blockers were measured from a large number of independent cultures. $Conclusion$: Microsized neural cluster arrays, which can be combined with conventional MEAs, are suitable for multiple simultaneous recording the slow-waves. $Significance$: Our technology provides a simple but useful method to study the generation of a low-frequency component of the electrical activity in cultured neural networks that are not yet well known, as well as to expand the use of conventional MEAs.

13 October 2025 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
JKJu Youn Kim
Ju Youn Kim
KKKyung Geun Kim
Kyung Geun Kim
SJSunghoon Joo
Sunghoon Joo
MCMineok Chang
Mineok Chang
JKJuwon Kim
Juwon Kim
SPSeung-Jung Park
Seung-Jung Park
Background: Deep learning (DL) models using Holter-ECG may enhance risk stratification after heart failure (HF) or myocardial infarction (MI). Objective: To evaluate the prognostic performance of a Holter-based DL model for predicting major adverse cardiac events (MACE), compared with conventional noninvasive markers. Methods: In the K-REDEFINE study, 1108 patients with acute MI or HF underwent 24 h Holter monitoring. A DL model was trained using raw Holter-ECG data and tested for predicting a composite of cardiac death and ventricular arrhythmias. Its performance was compared with heart rate turbulence (HRT), T-wave alternans (TWA), and ejection fraction (EF). Results: During follow-up, 56 adjudicated cardiac deaths (1.18%/yr) and 21 ventricular arrhythmias (0.44%/yr) occurred. The DL model showed an area under the receiver operating characteristic curve (AUROC) of 0.74 (95% CI, 0.70–0.77) for the composite outcome, improving to 0.77 (0.74–0.81) when combined with EF. In comparison, HRT and TWA showed lower AUROCs of 0.62 and 0.55, respectively. For cardiac death alone, the AUROC reached 0.79, further improving to 0.82 with EF. Model-derived risk stratification revealed a seven-fold increase in cardiac death risk in the high-risk group compared to the low-risk group (HR 7.47, 95% CI 2.24–24.96, p < 0.001). This stratification remained particularly effective in patients with EF > 40%. Conclusions: A DL algorithm trained on single-lead Holter-ECG data effectively predicted cardiac death and ventricular arrhythmia. Its performance surpassed conventional markers and was further enhanced when integrated with EF, supporting its potential for noninvasive, scalable risk stratification.

19 March 2024 in arXiv
Verified
Preprint
Open access
PDF file
YNYeongyeon Na
Yeongyeon Na
MPMinje Park
Minje Park
YTYunwon Tae
Yunwon Tae
SJSunghoon Joo
Sunghoon Joo
Electrocardiograms (ECG) are widely employed as a diagnostic tool for monitoring electrical signals originating from a heart. Recent machine learning research efforts have focused on the application of screening various diseases using ECG signals. However, adapting to the application of screening disease is challenging in that labeled ECG data are limited. Achieving general representation through self-supervised learning (SSL) is a well-known approach to overcome the scarcity of labeled data; however, a naive application of SSL to ECG data, without considering the spatial-temporal relationships inherent in ECG signals, may yield suboptimal results. In this paper, we introduce ST-MEM (Spatio-Temporal Masked Electrocardiogram Modeling), designed to learn spatio-temporal features by reconstructing masked 12-lead ECG data. ST-MEM outperforms other SSL baseline methods in various experimental settings for arrhythmia classification tasks. Moreover, we demonstrate that ST-MEM is adaptable to various lead combinations. Through quantitative and qualitative analysis, we show a spatio-temporal relationship within ECG data. Our code is available at https://github.com/bakqui/ST-MEM.