ELEric W. Lee

Eric W. Lee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Eric W. Lee has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Comparing machine and deep learning models for pediatric anxiety classification using structured EHRs and area-based measures of health data

    by Eric W. Lee, Sanghyun Choo, Dakotah Maguire, Abhishek Shivanna, Daniel Santel, Surbhi Bhatnagar, Ian Goethert, Kelly Patterson, Jay Gholap, Heidi A. Hanson, et al.

    Objective: This retrospective, case-control study with internal validation evaluates the performance of machine learning (ML) and deep learning (DL) models in classifying pediatric patients at risk for anxiety disorders using structured electronic health records (EHRs) and area-based measures of health (ABMH). The aim is to enable proactive care by monitoring potential anxiety onset across developmental stages. Methods: We trained a series of ML models (Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors, XGBoost) and DL models (LSTM, GRU, RETAIN, Dipole) using structured EHR data from 30-day windows prior to diagnosis. Two datasets were used per age group: one with structured EHR data only, and another including both EHR and ABMH data. ML models were trained using short-term cross-sectional features, while DL models leveraged full longitudinal patient histories. Performance was assessed using AUROC, AUPRC, PPV, NPV, F1 score, and accuracy. Due to differences in input scope, model performance reflects both algorithmic and temporal design differences and is not intended as a direct comparison between ML and DL. Results: ML models offered strong baseline performance, with XGBoost achieving AUROC scores of 0.817 (EHR) and 0.816 (EHR+ABMH) for 8-year-olds. Adding ABMH features did not significantly improve performance. DL models, particularly RETAIN and Dipole, achieved the highest AUROC values (e.g., Dipole: 0.853 with EHR, 0.857 with EHR+ABMH for 8-year-olds), outperforming other DL and ML models within their respective design constraints. Conclusion: Both ML and DL models successfully identified likely anxiety onset using structured EHR data. DL models using longitudinal data achieved the highest performance, while XGBoost provided a robust ML baseline. The minimal impact of ABMH features highlights integration challenges, and performance variation across ages emphasizes the need for age-stratified modeling approaches.

  • Open Access

    Comparing Machine and Deep Learning Models for Pediatric Anxiety Classification using Structured EHRs and Area-based Measures of Health Data

    by Eric W. Lee, Sanghyun Choo, Dakotah Maguire, Abhishek Shivanna, Daniel Santel, Surbhi Bhatnagar, Ian Goethert, Kelly Patterson, Jay Gholap, Heidi A. Hanson, et al.

    Objective: This study investigates the performance of various machine learning (ML) and deep learning (DL) models to classify pediatric patients at risk of anxiety disorders using electronic health records (EHRs). By leveraging EHR data and including Area-based measures of health (ABMH) data, this approach aims to enable proactive care by monitoring potential anxiety onset comprehensively across various age groups. Methods: In this study, we trained a series of ML and DL models to classify youth at risk of developing anxiety disorders. ML models (Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors, XGBoost) and DL models (LSTM, GRU, RETAIN, Dipole) were trained using structured EHR data from 30-day periods before anxiety diagnoses. Two datasets per age group were used: one with structured EHR data only and another with incorporating both structured EHR and ABMH data. Model performance was assessed using accuracy, the AUROC, AUPRC, PPV, NPV, and F1 scores. Results: The ML models provided a solid performance baseline, with XGBoost showing strong baseline performance across age groups, with AUROC scores of 0.817 (structured EHR) and 0.816 (structured EHR + ABMH). Between DL models, RETAIN and Dipole performed the best. For example, RETAIN achieved AUROC scores of 0.851 (structured EHR) and 0.853 (structured + ABMH), while Dipole scored 0.853 and 0.857, respectively, for 8-year-olds. These results underscore the viability of both ML and DL models for the early detection of pediatric anxiety disorders. Conclusion: This study comprehensively investigated ML and DL models for diagnosing pediatric anxiety. We demonstrated that ML and DL models can effectively monitor probable anxiety onset within an EHR system and also with the ABMH data. We discovered that model performance varied with age, indicating the need for personalized model development per age group for effective clinical predictive analytics.

  • Open Access

    HypMix: Hyperbolic Representation Learning for Graphs with Mixed Hierarchical and Non-hierarchical Structures

    by Eric W. Lee, Bo Xiong, Carl Yang, Joyce C. Ho

    Heterogeneous networks contain multiple types of nodes and links, with some link types encapsulating hierarchical structure over entities. Hierarchical relationships can codify information such as subcategories or one entity being subsumed by another and are often used for organizing conceptual knowledge into a tree-structured graph. Hyperbolic embedding models learn node representations in a hyperbolic space suitable for preserving the hierarchical structure. Unfortunately, current hyperbolic embedding models only implicitly capture the hierarchical structure, failing to distinguish between node types, and they only assume a single tree. In practice, many networks contain a mixture of hierarchical and non-hierarchical structures, and the hierarchical relations may be represented as multiple trees with complex structures, such as sharing certain entities. In this work, we propose a new hyperbolic representation learning model that can handle complex hierarchical structures and also learn the representation of both hierarchical and non-hierarchic structures. We evaluate our model on several datasets, including identifying relevant articles for a systematic review, which is an essential tool for evidence-driven medicine and node classification.


  • Open Access

    PGB: A PubMed Graph Benchmark for Heterogeneous Network Representation Learning

    by Eric W. Lee, Joyce C. Ho

    There has been rapid growth in biomedical literature, yet capturing the heterogeneity of the bibliographic information of these articles remains relatively understudied. Graph neural networks have gained popularity, however, they may not fully capture the information available in the PubMed database, a biomedical literature repository containing over 33 million articles. We introduce PubMed Graph Benchmark (PGB), a new benchmark dataset for evaluating heterogeneous graph representations. PGB is one of the largest heterogeneous networks to date and aggregates the rich metadata into a unified source including abstract, authors, citations, keywords, and the associated keyword hierarchy. The benchmark contains an evaluation task of 21 systematic review topics, an essential knowledge translation tool.


  • Open Access

    PGB: A PubMed Graph Benchmark for Heterogeneous Network Representation Learning

    by Eric W Lee, Joyce C Ho

    There has been rapid growth in biomedical literature, yet capturing the heterogeneity of the bibliographic information of these articles remains relatively understudied. Although graph mining research via heterogeneous graph neural networks has taken center stage, it remains unclear whether these approaches capture the heterogeneity of the PubMed database, a vast digital repository containing over 33 million articles. We introduce PubMed Graph Benchmark (PGB), a new benchmark dataset for evaluating heterogeneous graph embeddings for biomedical literature. The benchmark contains rich metadata including abstract, authors, citations, MeSH terms, MeSH hierarchy, and some other information. The benchmark contains three different evaluation tasks encompassing systematic reviews, node classification, and node clustering. In PGB, we aggregate the metadata associated with the biomedical articles from PubMed into a unified source and make the benchmark publicly available for any future works.

  • GASP: Graph-Based Approximate Sequential Pattern Mining for Electronic Health Records

    by Wenqin Dong, Eric W. Lee, Vicki Stover Hertzberg, Roy L. Simpson, Joyce C. Ho

    Sequential pattern mining can be used to extract meaningful sequences from electronic health records. However, conventional sequential pattern mining algorithms that discover all frequent sequential patterns can incur a high computational and be susceptible to noise in the observations . Approximate sequential pattern mining techniques have been introduced to address these shortcomings yet, existing approximate methods fail to reflect the true frequent sequential patterns or only target single-item event sequences. Multi-item event sequences are prominent in healthcare as a patient can have multiple interventions for a single visit. To alleviate these issues, we propose GASP, a graph-based approximate sequential pattern mining, that discovers frequent patterns for multi-item event sequences. Our approach compresses the sequential information into a concise graph structure which has computational benefits. The empirical results on two healthcare datasets suggest that GASP outperforms existing approximate models by improving recoverability and extracts better predictive patterns. Keywords Sequential pattern mining Healthcare data


  • Open Access

    MMiDaS-AE

    by Eric W. Lee, Byron C. Wallace, Karla I. Galaviz, Joyce C. Ho

    Systematic review (SR) is an essential process to identify, evaluate, and summarize the findings of all relevant individual studies concerning health-related questions. However, conducting a SR is labor-intensive, as identifying relevant studies is a daunting process that entails multiple researchers screening thousands of articles for relevance. In this paper, we propose MMiDaS-AE, a Multi-modal Missing Data aware Stacked Autoencoder, for semi-automating screening for SRs. We use a multi-modal view that exploits three representations, of: 1) documents, 2) topics, and 3) citation networks. Documents that contain similar words will be nearby in the document embedding space. Models can also exploit the relationship between documents and the associated SR MeSH terms to capture article relevancy. Finally, related works will likely share the same citations, and thus closely related articles would, intuitively, be trained to be close to each other in the embedding space. However, using all three learned representations as features directly result in an unwieldy number of parameters. Thus, motivated by recent work on multi-modal auto-encoders, we adopt a multi-modal stacked autoencoder that can learn a shared representation encoding all three representations in a compressed space. However, in practice one or more of these modalities may be missing for an article (e.g., if we cannot recover citation information). Therefore, we propose to learn to impute the shared representation even when specific inputs are missing. We find this new model significantly improves performance on a dataset consisting of 15 SRs compared to existing approaches.