JAJaerong Ahn

Jaerong Ahn

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jaerong Ahn has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    REFINE: Closing the Loop Between Large Language Models and Symbolic Rules in Clinical NLP

    by Nan Wang, Alexandra Kakadiaris, Chenyu Li, Rongrong Wang, Jaerong Ahn, Yashan Wang, Sunyang Fu

    Symbolic clinical natural language processing (NLP) systems remain widely used for extracting clinical concepts from electronic health record (EHR) narratives, but maintaining rule resources requires extensive manual error analysis and rule refinement. This study investigates whether large language models (LLMs) can assist in identifying extraction errors and generating candidate rules to improve symbolic clinical NLP systems. Using error reports derived from a multi-site evaluation of a previously validated symbolic model for cognitive and neuropsychiatric-related clinical concepts, we developed a human-in-the-loop framework, REFINE. The framework first uses LLMs to classify extraction errors and generate explanatory reasoning, which can then be incorporated into prompts for rule generation. Three LLMs (GPT-5.2, GPT-4o, GPT-4o-mini) were evaluated under four prompting conditions. LLM-generated rule sets improved performance compared with the baseline NLP-CAM system, increasing F1-score from 0.37 to 0.58. These findings suggest that LLMs can support scalable rule refinement for symbolic clinical NLP systems.

  • MedADL: high-throughput information extraction of functional status from electronic health records to advance frailty assessment in older adults

    by Sunyang Fu, Zhiyi Yue, Jennyly T Nguyen, Huipeng Liu, Jaerong Ahn, Vanessa Ramirez, Jude Des Bordes, Hongfang Liu, Min Ji Kwak, Nahid J Rianon

    Background: Functional status is essential for assessing frailty and planning care in older adults but is often under-documented in the structured fields of electronic health records. Manual chart review can capture functional status information but is labor-intensive and time-consuming. In this study, we developed and validated a scalable natural language processing (NLP) model to extract functional status information from unstructured electronic health record (EHR) notes. Methods: This retrospective cohort study included 110 older adults seen at a geriatric osteoporosis clinic. A large language model–augmented symbolic NLP pipeline (MedADL) was developed to extract activities of daily living (ADL) and instrumental activities of daily living (IADL) impairments from 13 182 clinical notes and derive the Cumulative Functional Burden Index (CFBI), validated against grip strength, walking speed, balance score, and frailty status using ordinal logistic regression with 10-fold cross-validation. Results: The NLP model demonstrated moderate to strong performance across 16 ADL and IADL categories, with an average precision of 0.868, sensitivity of 0.828, specificity of 0.937, and F1 score of 0.816. CFBI was significantly associated with frailty status (odds ratio [OR] = 0.799, reciprocal OR = 1.25, p = .049, AUC (Area Under the Curve) = 0.66), indicating that each additional functional deficit was associated with approximately 25% higher odds of being classified in a less robust frailty category. CFBI was correlated with walking speed (r = 0.43, p < .001), balance (r = −0.42, p < .001), grip strength (r = −0.24, p = .019), and fall history (r = 0.21, p = .040). Conclusion: MedADL demonstrated moderate-to-strong performance across 16 bADL and iADL categories, and the derived CFBI was significantly associated with frailty status and correlated with 4 objective physical performance measures. Future studies will prospectively evaluate long-term outcomes and integrate the model into the EHR to enable real-time clinical decision support.

  • Open Access

    A Self-Explainable Dynamic Risk Monitoring Framework for Predicting Alzheimer’s Disease and Related Dementias

    by Xiaoyang Ruan, Shuyu Lu, Sunyang Fu, Jaerong Ahn, Fang Chen, Rui Li, Andrew Wen, Liwei Wang, Ezenwa Onyema, Victoria Tang, et al.

    Background Alzheimer’s Disease and Related Dementias (ADRD) affect millions worldwide and can begin over a decade before symptoms appear. ADRD are generally irreversible once clinical symptoms appear, making early prediction and intervention critical. While neuroimaging improves prediction, its availability restricts use at the population level. Electronic Health Record (EHR) data offers a scalable alternative, but existing models often overlook three key challenges: irregular clinical encounters, severe data sparsity, and the need for interpretability. To address these gaps, we propose GRU-D-RETAIN, a temporal deep learning architecture combines GRU-D’s strength in parameterized missing imputation with RETAIN’s explainable attention mechanism, enabling real-time risk monitoring at arbitrary clinical encounters with meaningful interpretations. Methods We identified 15,172 ADRD cases (age>=50) and 145,443 gender and date of birth matched controls from 6M patients in the University of Texas (UT) Physician EHR system. EHR were retrieved for each individual up to 10 years before ADRD diagnosis, and a random follow-up initiation date was assigned to simulate a real-world 10-year follow-up practice. Competing models including GRU-D-RETAIN, GRU-D, LSTM, Logit static, and Logit dynamic were trained on 6-fold cross-validation chunks and applied to the held-out to estimate performance. Results The scarcity of EHR records beyond 10 years before ADRD diagnosis precludes the development of valid predictive models beyond this timeframe. At the 10- year mark, only diagnoses of hypertension and hyperlipidemia exceeded 1% among ADRD cases. After randoming follow-up initiation date, GRU-D-RETAIN exhibited performance closely matching that of GRU-D across the entire follow-up period, both showing improved accuracy as follow-up time increases. Without applying data availability cut-off, both models achieved AUROC of 0.6 and 0.7 at 2-year and 8-year follow-up, respectively, significantly outperforming competing models. Data availability plays a more critical role than follow-up length in determining prediction performance. For example, 1 year of follow-up with 15% data availability yields comparable performance (AUROC of 0.75 and average precision of 0.5) to 7.5 years of follow-up with 10% data availability. For individual ADRD cases, GRU-D-RETAIN offered overall consistent explanations across training folds. However, certain folds produced different explanations at both the timestep and feature levels, despite yielding similar risk predictions. Conclusion We demonstrate that EHR data can support dynamic ADRD risk monitoring up to 10 years before diagnosis, though model utility depends highly on data completeness. GRU-D-RETAIN enables real-time risk monitoring with explainable attention weights at both timestep and feature levels, aiding clinicians in interpreting the output and identifying high-risk patients as well as potential key risk factors at individual level. This framework is broadly applicable to other conditions expecting irregular clinical encounters and requiring dynamic and interpretable risk assessment.