RYRichard Yang

Richard Yang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Richard Yang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A retrieval-augmented generation large language model framework for accurate dementia identification from electronic health records

    by Liqin Wang, Baoren Liu, Richard Yang, Ya-Wen Chuang, Hossein Estiri, Shawn Murphy, Li Zhou, Gad A. Marshall

    Objective: Accurate and scalable dementia phenotyping from electronic health records (EHRs) is foundational for population-level research, risk prediction, and learning health system interventions. Traditional rule- and keyword-based approaches are limited by inconsistent documentation and inability to capture clinical nuance. We aim to develop and evaluate a framework that leverages large language models (LLMs) with retrieval-augmented generation (RAG) to overcome these limitations and improve dementia identification from real-world EHR data. Methods: Using EHR data from the Mass General Brigham health system, we first assembled a cohort of adults with potential dementia based on diagnosis codes, problem lists, dementia-related medications, and free-text note mentions. A subset of candidate cases underwent detailed manual chart review to assign gold-standard dementia status. With this labeled sample, we implemented and compared three approaches for dementia ascertainment: (1) a rule-based classifier leveraging structured EHR data, (2) large language models (LLMs) applied to keyword-filtered clinical note excerpts, and (3) a RAG-based LLM framework that integrates retrieved, context-rich note snippets. Within each approach, we evaluated multiple configurations of embedding models, retrieval methods, LLMs, structured-data inclusion, and prompts to identify the best-performing classifier. Performance was assessed using standard classification metrics, including sensitivity, specificity, positive predictive value (PPV), and F1 score, and supplemented by qualitative error analyses to characterize common sources of false positives and false negatives across methods. Results: The RAG-based classifier achieved the highest performance (F1=0.933, sensitivity=91.1%, PPV=95.5%) compared to rule-based (F1=0.823, sensitivity=81.1%, PPV=83.5%) and keyword-filtered LLM (F1=0.903, sensitivity=91.7%, PPV=88.6%). Including ICD codes alongside free text in the RAG-based LLM pipeline significantly reduced the PPV and modestly decreased F-1 score. Error analysis revealed that structured-code dependence contributed to false positives, whereas unrecognized contextual cues in notes drove false negatives. Conclusion: A RAG-based LLM pipeline without structured ICD codes improved dementia ascertainment from EHR data compared with ICD-based rules and keyword-based filtering. This approach can enhance dementia case identification and support patient care, predictive modeling and risk analysis.


  • Open Access

    Assessing Risk Factors for Cognitive Decline Using Electronic Health Records: A Scoping Review

    by Liqin Wang, Richard Yang, Ziqin Sha, Anna Maria Kuraszkiewicz, Conrad Leonik, Li Zhou, Gad Asher Marshall

    Background: Electronic health records (EHR) provide rich, diverse, longitudinal real-world data, offering valuable opportunities to study antecedent risk factors for cognitive decline. However, the extent to which such records have been utilized to understand the risk factors of cognitive decline remains unclear. Methods: We conducted a systematic review following PRISMA guidelines. We retrieved relevant articles published between January 1, 2010, and April 30, 2023, from PubMed, Web of Science, and CINAHL. Inclusion criteria were studies utilizing EHR to study risk factors for cognitive decline, including subjective cognitive decline, mild cognitive impairment, and dementia. Each article was screened by at least two reviewers. Data elements were manually extracted based on a predefined schema. The studied risk factors were reported. Results: Of 1,593 articles identified, 80 research articles were selected. Seventy (87.5%) were retrospective cohort studies, 53 (66.3%) used datasets with greater than 10,000 patients, and 69 (86.3%) used EHR datasets from the United States or United Kingdom. Furthermore, 39 (48.8%) targeted medical conditions, 23 (28.8%) related to medical interventions, and 14 (17.5%) related to lifestyle, socioeconomic status, and environmental factors. The majority of studied medical conditions were associated with an elevated risk of cognitive decline, whereas medical interventions addressing these conditions often reduced the risk. Conclusion: EHRs have significantly advanced our understanding of medical conditions, interventions, lifestyle, socioeconomic status, and environmental factors related to the risk of cognitive decline. Highlights: Electronic health records are increasingly analyzed to discern dementia risk factors. Eighty articles have been published and most of them were retrospective cohort studies. Most risk factors addressed were related to medical conditions and interventions. A few articles studied lifestyle, socioeconomic status, and environmental factors.