Sohyeon Jeon

Sohyeon Jeon

Auto-generated profile, based on publicly available information

Sohyeon Jeon

Interdisciplinary Program of Medical Informatics, College of Medicine, Seoul National University

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 July 2025 in Computers in Biology and Medicine
Verified
Journal Article
Open access
SJSohyeon Jeon
Sohyeon Jeon
HKHong-Gee Kim
Hong-Gee Kim
Large language models (LLMs) hold transformative potential for clinical decision-making in the rapidly advancing field of AI in medicine. This study evaluates how Chain-of-Thought (CoT) prompting techniques affect medical reasoning performance with consideration for clinical applicability. Five LLMs (GPT-4o-mini, GPT-3.5-turbo, o1-mini, Gemini-1.5-Flash, Gemini-1.0-pro) were assessed via API access using CoT prompting methods exhibiting distinct cognitive characteristics. Evaluations included clinical datasets and non-clinical datasets. An iterative QA system was constructed to ensure consistent and reproducible results. o1-mini achieved the highest performance with 88.4 % accuracy in EHRNoteQA using MIMIC-IV discharge summaries. Traditional CoT consistently provided stable results across clinical datasets, while Interactive CoT showed variability - underperforming in complex medical reasoning tasks like MedMCQA (61.7 %) but performing well in clinical notes (83.5 % in EHRNoteQA). Statistical analysis revealed no significant differences between prompting methods across datasets (p > .05), though effect size analysis showed notable variations in method effectiveness. Complex prompting techniques do not significantly enhance performance compared to simpler approaches. Dataset characteristics and model architecture have greater impact, suggesting simpler CoT methods may be more effective for clinical applications.

21 July 2025 in medRxiv
Verified
Preprint
Open access
PDF file
SJSohyeon Jeon
Sohyeon Jeon
Background: Electronic Health Records face a fundamental challenge: the semantic gap between relational data storage and clinical reasoning patterns. Traditional databases struggle with complex healthcare queries requiring multiple joins and temporal analysis, creating performance bottlenecks that limit real-time clinical applications. Methods: We developed a Neo4j-based framework integrating MIMIC-IV clinical data (1,504 patients, 4,967 admissions) with SNOMED CT medical ontology through ICD-10-CM mappings. The implementation created a unified graph comprising 625,708 nodes and 2,189,093 relationships, with systematic preservation of temporal and semantic connections. Results: Performance analysis demonstrated substantial improvements over PostgreSQL across five query types, with Neo4j showing 5.4x to 48.4x faster execution times. The framework successfully enabled three clinical applications: ventilator-associated pneumonia temporal analysis (revealing 47.79% pneumonia rates among ventilated ICU stays), hypertension semantic network mapping through multi-level SNOMED-CT relationships, and Medicare Part D quality measure monitoring. Notably, the system identified that 96.7% of eligible diabetic patients lacked statin prescriptions, demonstrating practical utility for healthcare quality improvement initiatives. Conclusion: This graph-based approach provides a robust foundation for next-generation clinical decision support systems by bridging the gap between fragmented clinical data and integrated patient-centric analysis. The framework’s demonstrated performance advantages and practical applications in quality measure monitoring establish its potential for addressing real-world healthcare challenges while supporting the transition toward more effective, evidence-based patient care.

20 April 2026 in The Lancet Regional Health - Americas
Verified
Journal Article
Open access
GSGustavo Cruz Suarez
Gustavo Cruz Suarez
DHDaniela Hincapié-Ayala
Daniela Hincapié-Ayala
FOFelipe Ocampo Osorio
Felipe Ocampo Osorio
MGMaría Camila Gómez-Ayala
María Camila Gómez-Ayala
SASergio Alzate-Ricaurte
Sergio Alzate-Ricaurte
LCLeo Anthony Celi
Leo Anthony Celi
Evidence-based medicine (EBM) integrates clinical expertise, patient values, and best available research evidence, yet classical trial-based approaches struggle to accommodate the scale, heterogeneity, and structural constraints of contemporary health systems. The rapid expansion of biomedical data is positioning artificial intelligence (AI) as an extension of evidence generation rather than a replacement for epidemiologic reasoning. This state-of-the-art Review examines how AI is beginning to reshape the methodological and ethical foundations of EBM through multimodal data integration, target trial emulation, and simulation-based modelling, while emphasizing that predictive performance does not ensure causal validity or clinical benefit. Implementation depends on rigorous epidemiologic design, integration within clinical informatics systems, and effective human–machine collaboration. In the Americas, fragmented health systems and uneven digital infrastructures constrain representativeness and equitable deployment. AI will not transform EBM on its own; its constructive role requires governance reform, transparent validation, and structural change to prevent the reinforcement of existing inequities.

11 August 2025 in medRxiv
Verified
Preprint
Open access
PDF file
SJSohyeon Jeon
Sohyeon Jeon
Effective clinical decision-making in critical care depends on interpreting complex, high-dimensional patient data. However, many advanced AI models function as uninterpretable “black boxes,” limiting their trustworthiness and scientific value. This study introduces NETWISE, a geometric and topological framework designed not for mere prediction, but for building a validated patient similarity network to serve as a scientific discovery engine. We demonstrate the framework’s utility using acute cholangitis, a life-threatening emergency, as a case study. Analyzing 1,372 patients from the MIMIC-IV database, NETWISE constructs a heterogeneous graph to learn a robust patient manifold. The resulting model achieved high predictive accuracy (AUC-ROC of 82.5%) while offering multiple layers of interpretability. The framework’s potential for discovery was demonstrated through two complementary analyses: SHAP identified clinically coherent predictors, while discrete clustering autonomously generated 13 data-driven patient subgroups, presenting them as testable hypotheses for future clinical investigation. Crucially, topological analysis confirmed the network’s immense structural complexity (β1 = 63,187). This study’s primary contribution is a transparent, validated, and network-based methodological framework capable of generating new, data-driven clinical hypotheses from complex EHR data.