Yerin Heo

Yerin Heo

Auto-generated profile, based on publicly available information

Yerin Heo

Department of Health Administration, College of Nursing and Health, Kongju National University, Gongju-si, Republic of Korea

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
1 January 2025 in Journal of Korean Medical Science
Verified
Journal Article
Open access
PDF file
JYJieun Yun
Jieun Yun
YCYoungs Chang
Youngs Chang
MJMinsol Jo
Minsol Jo
YHYerin Heo
Yerin Heo
DKDong-Sook Kim
Dong-Sook Kim
Yun J, et al. J Korean Med Sci. 2024 Nov;40:e16. https://doi.org/10.3346/jkms.2025.40.e16

28 February 2026 in Journal of Health Informatics and Statistics
Verified
Journal Article
Open access
PDF file
MJMinsol Jo
Minsol Jo
YHYerin Heo
Yerin Heo
DKDong-Sook Kim
Dong-Sook Kim
ISInmyung Song
Inmyung Song
This study examines performance evaluation cases of gastroenteritis surveillance systems and trends in diagnostic methods abroad to derive implicationsfor improving Korea’s domestic surveillance systems. Several studies in the United States, Canada, and Australia have assessed surveillance system performance,primarily focusing on sensitivity and timeliness. The United States operates multiple surveillance systems led by the Centers for Disease Controland Prevention, utilizing diverse data sources for the early detection of infectious diseases. Additionally, diagnostic methods for bacterial entericinfections are evolving, with more laboratories adopting culture-independent diagnostic tests, thereby improving sensitivity and timeliness. Similarly,Korea operates Korea PulseNet, a system comparable to that in the United States, based on a culture-based surveillance framework. However, the adoptionof non-culture diagnostic methods remains limited, and the heavy reliance on report-based surveillance restricts rapid response capabilities. To enhancesurveillance, a multi-layered system integrating various data sources, such as emergency department visit records and telemedicine data, should beestablished. Furthermore, introducing culture-independent diagnostic tests can improve pathogen detection speed and the timeliness of the surveillancesystem. Strengthening sensitivity and timeliness is essential for effective surveillance evaluation, and the findings of this study may help enhanceearly detection and response systems for infectious diseases.

3 October 2026 in JMIR Preprints
Verified
Preprint
Open access
SLSeung-Bo Lee
Seung-Bo Lee
ISInmyung Song
Inmyung Song
YHYerin Heo
Yerin Heo
DKDong-Sook Kim
Dong-Sook Kim
BACKGROUND Pharmaceutical supply disruptions can compromise treatment continuity and increase health-system burden, yet national surveillance is largely reactive. Conventional next-month status prediction can also be misleading when instability is persistent, because a model may mainly identify products that are already unstable rather than newly emerging events. OBJECTIVE To develop and internally validate a machine learning model for predicting new-onset pharmaceutical supply-demand instability one month ahead among products that were stable at the time of prediction. METHODS We analyzed a national monthly panel from the Republic of Korea (July 2018 to March 2023; 3,245 products; 150,128 product-months). Supply-demand instability was defined using a prespecified operational threshold of the supply-demand instability ratio (SR ≥0.20). The primary outcome was transition from stable to unstable status one month later among at-risk product-months. Thirty-five backward-looking features were derived from supply, use, and distribution-flow series. Ten machine learning algorithms were compared, and a 10-feature random forest was retained as a parsimonious reference model. Internal validation included product-grouped cross-validation and nested product-grouped and time-ordered temporal schemes, with calibration and risk-enrichment characteristics also assessed. RESULTS Instability occurred in 15.0% of product-months, but 74% of instability months with an observed preceding month were continuations of an existing unstable state. New onset occurred in 4.58% of at-risk months. The 10-feature random forest achieved an AUPRC of 0.245 ± 0.019 and an AUROC of 0.844 ± 0.013, compared with 0.182 and 0.774 for logistic regression. In nested internal validation of the modeling pipeline, AUPRC and AUROC were 0.288 ± 0.022 and 0.873 ± 0.008 under product-grouped validation and 0.261 ± 0.020 and 0.855 ± 0.010 under the time-ordered temporal scheme. Expected calibration error was ≤0.003. Approximately half of onsets in each outer test fold were concentrated in its top 10% of predicted risk. Feature-group ablation indicated that performance did not depend on instability-ratio autocorrelation. CONCLUSIONS Routine national pharmaceutical monitoring data supported internally validated prediction of newly emerging supply-demand instability when the prediction task was restricted to currently stable products. The results support further evaluation of risk ranking as a decision-support approach for pharmaceutical surveillance. Direct validation against regulator-reported shortages, strictly month-aligned temporal evaluation, and prospective assessment are required before operational use. CLINICALTRIAL N/A

17 September 2026 in BMC Public Health
Verified
Journal Article
Open access
PDF file
YHYerin Heo
Yerin Heo
ISInmyung Song
Inmyung Song
MJMinsol Jo
Minsol Jo
YWYeon-Hee Woo
Yeon-Hee Woo
DKDong-Sook Kim
Dong-Sook Kim
Bacterial gastrointestinal infections in Korea are monitored through a sentinel surveillance system whose reporting patterns may differ from claims-based h

26 August 2026 in JMIR Public Health and Surveillance
Verified
Journal Article
Open access
ISInmyung Song
Inmyung Song
YHYerin Heo
Yerin Heo
MJMinsol Jo
Minsol Jo
JPJung-Yeon Park
Jung-Yeon Park
SRSukhyun Ryu
Sukhyun Ryu
DKDong-Sook Kim
Dong-Sook Kim
Background: Bacterial gastroenteritis remains a substantial public health burden. South Korea has operated an electronic sentinel surveillance system (SSS) since 2000; in 2023, a total of 211 sentinel hospitals conducted surveillance for 11 notifiable types of bacterial gastroenteritis. The system has not undergone a comprehensive evaluation. Objective: This study evaluated the SSS’s operational performance and reporting completeness, assessed the population-based geographic allocation of sentinel sites, and explored concordance between SSS reports and National Health Insurance (NHI) claim records. Methods: We conducted a mixed methods evaluation using a 2024 survey of staff at the 211 sentinel hospitals, an interview with the Korea Disease Control and Prevention Agency (KDCA) operator, KDCA operational reporting records, nationwide NHI claim records, and regional population statistics. The primary evaluation year was 2023; 2021 was a nonconsecutive descriptive comparator because these were the 2 complete annual extracts available in the analytic dataset. We calculated delayed reporting, submission completeness, and on-time completeness. Exploratory Pearson correlations compared paired weekly all-pathogen totals (52 weeks per year), annual surveillance target, and diagnosis code category counts within each age group (11 paired categories), and actual vs population-proportional sentinel allocations across 17 regions. Results: Of 211 sentinel hospitals, 180 (85.3%) responded. In total, 90% (162/180) rated reporting as simple or adequate; responses on goal awareness and overall satisfaction were predominantly neutral. The delayed reporting proportion was 2.4% (255/10,652) in 2021 and 1.1% (122/10,972) in 2023; submission completeness was 99.9% (10,652/10,660) and 100% (10,972/10,972), respectively; and on-time completeness was 97.5% (10,397/10,660) and 98.9% (10,850/10,972), respectively. The exploratory weekly SSS-NHI correlation was 0.899 in 2021 and 0.937 in 2023. Age-stratified annual cross-category correlations ranged from 0.665 to 0.969 in 2021 and from 0.939 to 0.983 in 2023. Correlations between actual and population-proportional sentinel allocations were 0.946 in 2021 and 0.951 in 2023. Conclusions: The SSS demonstrated favorable operational performance, with low reporting delay and near-complete submission. The claim comparison showed strong ecological comovement but cannot establish sensitivity or diagnostic equivalence because the data sources use different case definitions and counting units. Priorities are clearer communication of operational goals, standardized operator training, and future validation using patient- or episode-level data linked to laboratory results.

23 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
YHYerin Heo
Yerin Heo
ECEunseon Choi
Eunseon Choi
DKDong-Sook Kim
Dong-Sook Kim
BackgroundBacterial gastrointestinal infections remain an important public health concern, but their claims-based temporal patterns may differ substantially across pathogens. We examined whether pathogen-specific temporal structure in administrative claims data could inform surveillance interpretation for bacterial gastrointestinal infections in South Korea.MethodsThis retrospective ecological time-series study used nationwide South Korean health insurance claims data from 2014 to 2023 to construct monthly region-level claims-based occurrence series for 11 bacterial gastrointestinal pathogens across 17 administrative regions. Temporal structure was summarized by claims-based occurrence level, variability, and seasonal concentration. Forecast stability and surveillance interpretation were assessed using SARIMAX, CatBoost, and a seasonal naive baseline, with predictor sets including prior claims-based occurrence and climate variables. Robustness was evaluated using alternative lag specifications and temporal train-test splits. Results Claims-based temporal structure varied markedly across pathogens. Salmonella spp. and Campylobacter spp. showed the highest mean monthly claims-based occurrence and relatively lower variability, whereas Bacillus cereus, enteroinvasive Escherichia coli (EIEC), and Listeria monocytogenes showed mean monthly occurrence below 1 and greater instability. Pathogens with higher occurrence and clearer seasonal concentration generally showed more interpretable forecast performance, whereas sparse pathogens showed low absolute errors but unstable percentage-based error measures. Recent claims-based occurrence was the most consistently informative predictor, whereas climate variables contributed selectively across pathogens.ConclusionsPathogen-specific claims-based temporal structure was associated with differences in forecast stability and surveillance interpretation. Routine forecasting appeared more interpretable for pathogens with higher occurrence and clearer seasonal concentration, whereas sparse and unstable patterns were more difficult to interpret using routine point forecasting alone and may warrant supplementary interpretive approaches. These findings suggest that administrative surveillance signals for bacterial gastrointestinal pathogens may benefit from interpretation that is more attentive to pathogen-specific temporal structure.