Yonsei University · Medicine
Professor Dukyong Yoon's research lab specializes in leveraging electronic health records (EHRs) and biosignal data for pharmacovigilance and clinical decision support. The lab focuses on developing advanced machine learning and deep learning methods to detect adverse drug reactions, improve ECG signal analysis, and extract meaningful features from unlabeled biomedical data. Key research directions include postmarketing drug safety surveillance, noise detection in ECGs, and unsupervised feature learning for ECG interpretation using variational autoencoders. The lab also actively contributes to international health data networks by transforming EHRs into standardized clinical data models for research use.
Figures are computed from collected data and may differ slightly.
The risk of QT prolongation was increased when patients, particularly the elderly aged 60-79 years, were exposed to azithromycin. Therefore, clinicians should pay exercise caution using azithromycin or consider using other antibiotics, such as amoxicillin, instead of azithromycin.
We successfully converted our EHRs to a CDM and were able to participate as a data partner in an international DRN. Converting local records in this manner will provide various opportunities for researchers and data holders.
Electronic health records (EHRs) are expected to be a good source of data for pharmacovigilance. However, current quantitative methods are not applicable to EHR data. We propose a novel quantitative postmarketing surveillance algorithm, the Comparison of Laboratory Extreme Abnormality Ratio (CLEAR), for detecting adverse drug reaction (ADR) signals from EHR data. The methodology involves calculating the odds ratio of laboratory abnormalities between a specific drug-exposed group and a matched un
Objectives: Biosignal data captured by patient monitoring systems could provide key evidence for detecting or predicting critical clinical events; however, noise in these data hinders their use. Because deep learning algorithms can extract features without human annotation, this study hypothesized that they could be used to screen unacceptable electrocardiograms (ECGs) that include noise. To test that, a deep learning-based model for unacceptable ECG screening was developed, and its screening re
Improved performance of ML models indicated that applying our model to EHR data is feasible and promising for detecting more accurate and comprehensive ADR signals.
Most existing electrocardiogram (ECG) feature extraction methods rely on rule-based approaches. It is difficult to manually define all ECG features. We propose an unsupervised feature learning method using a convolutional variational autoencoder (CVAE) that can extract ECG features with unlabeled data. We used 596,000 ECG samples from 1,278 patients archived in biosignal databases from intensive care units to train the CVAE. Three external datasets were used for feature validation using two appr
Although concern regarding the increased risk for new-onset diabetes mellitus (NODM) after statin treatment has been raised, there has been a lack of evidence in real-world clinical practice, particularly in East Asians. We investigated whether statin use is associated with risk for NODM in Koreans. We conducted a retrospective cohort study using the clinical research database from electronic health records. The study cohort consisted of 8265 statin-exposed and 33,060 matched nonexposed patients
Biosignals such as electrocardiogram or photoplethysmogram are widely used for determining and monitoring the medical condition of patients. It was recently discovered that more information could be gathered from biosignals by applying artificial intelligence (AI). At present, one of the most impactful advancements in AI is deep learning. Deep learning-based models can extract important features from raw data without feature engineering by humans, provided the amount of data is sufficient. This
Our deep learning-based imputation model performed better than the other methods when imputing missing values in actigraphy data.
The Electrocardiogram Vigilance with Electronic data Warehouse II (ECG-ViEW II) is a large, single-center database comprising numeric parameter data of the surface electrocardiograms of all patients who underwent testing from 1 June 1994 to 31 July 2013. The electrocardiographic data include the test date, clinical department, RR interval, PR interval, QRS duration, QT interval, QTc interval, P axis, QRS axis, and T axis. These data are connected with patient age, sex, ethnicity, comorbidities,
Our system collects biosignal data from different systems in a unified format. The data collected by the system can be used to develop algorithms or applications without the need to consider the source of the data.
T-wave-based features were not correlated with serum potassium level, and their use in real clinical practice is currently limited.
Open papers in the app to read, cite, and organize with AI.
