arXiv subjects

Licong Cui

Publications and source records attributed to Licong Cui.

8 recordsLinked to original sources

arXiv2026

Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study

The reliance on unstructured free text for documenting clinical trial protocols creates a significant barrier to automated reasoning, cohort discovery, and trial simulation. The lack of formal structure obscures critical temporal phenotypes, such as dynamic eligibility criteria and event timing constraints. Although Temporal Ensemble Logic (TEL) offers an expressive framework for modeling these elements, manual encoding remains a prohibitive bottleneck. We introduce the CT-TEL workflow: a scalable pipeline leveraging Large Language Models (LLMs) to translate narrative clinical protocols into TEL formulas. We applied CT-TEL to generate logical models for 23 real-world trials from ClinicalTrials.gov. We evaluated translation fidelity via a back-translation approach, using LLMs to convert TEL formulas back into natural language and measuring semantic similarity against source texts. The resulting semantic retention suggests that LLMs may offer a pathway for mapping informal protocols to computable logic, providing preliminary evidence toward scalable clinical trial emulation within the emerging "Symbolic Biomedicine" paradigm championed by the corresponding author.

cs.LO↗

arXiv2026

Ensemble Logic for Symbolic Representation of Sleep Medicine Guidelines

The American Academy of Sleep Medicine (AASM) Manual is the clinical standard for polysomnography (PSG) scoring, but its narrative rules can admit multiple reasonable interpretations, contributing to inter-scorer variability and implementation differences across studies and software systems. We present a formal framework for translating sleep-scoring rules into Rational Ensemble Logic (QEL), a dense-time (i.e., a continuous, rational-valued timeline rather than discrete steps) formalism that combines first-order quantification with metric temporal operators. Using an extraction-and-compilation procedure, we identified 18 unique atomic propositions and derived 12 final specifications corresponding to clinically scoreable AASM events. Back-translation of QEL specifications into clinician-facing language retained high semantic fidelity to the original scoring narratives (embedding cosine similarity: 79.3, 95% CI: 79.0--79.7) despite low lexical overlap (ROUGE-L: 18.3, 95 CI: 17.6--18.9). Formalization also clarifies latent ambiguities, including implicit physiological latencies and overlapping exclusions. This framework yields executable, rigorous rule specifications for computational phenotyping, more consistent implementation across datasets, and standardized open-source PSG analysis. This work is a part of the "Symbolic Biomedicine" program championed by the corresponding author.

cs.LO↗

arXiv2026

A Logic-based Temporal Cohort Discovery Engine: Algorithms, Indices, and Experimental Results on the National Sleep Research Resource

Large sleep-study repositories contain rich time-stamped physiological annotations, but cohort discovery is still commonly implemented as ad hoc scripts or scalar-index filters. We present a logic-based temporal cohort discovery engine that brings formal semantics, model checking, specialized indexing, and empirical evaluation into a unified biomedical informatics framework. We adopt Rational Ensemble Logic (QEL) as a dense-time formal foundation for sleep-data querying and represent each annotated polysomnogram as a Biomedical Event Structure Temporal Model (BEST), a finite mapping from event labels to non-overlapping rational interval ensembles. Cohort discovery is formulated as model checking of QEL formulas over BEST databases. We organize common sleep-research requirements into three reusable temporal query patterns: single-event retrieval, dual-event temporal pattern matching, and event data extraction. The prototype cohort discovery engine was implemented in Python with in-memory and MongoDB-backed execution modes and evaluated on synthetic interval datasets containing up to 90 million intervals and on real-world National Sleep Research Resource annotations from the Cleveland Children's Sleep and Health Study (CCSHS) containing 515 subjects, 202,587 intervals, 23 event labels. 2DFC constructs indexes in linear space and linear build time, reducing build time at 90 million intervals from 11,549 s with RTFC and 23,902 seconds with 2DRT to 3,655 seconds. On CCSHS, cohort-selection queries executed at sub-second latency at native scale and under 45 seconds at 1,000 times scale. This work is a part of the Symbolic Biomedicine program championed by the corresponding author.

cs.DB↗

arXiv2025

AD-CDO: A Lightweight Ontology for Representing Eligibility Criteria in Alzheimer's Disease Clinical Trials

Objective This study introduces the Alzheimer's Disease Common Data Element Ontology for Clinical Trials (AD-CDO), a lightweight, semantically enriched ontology designed to represent and standardize key eligibility criteria concepts in Alzheimer's disease (AD) clinical trials. Materials and Methods We extracted high-frequency concepts from more than 1,500 AD clinical trials on ClinicalTrials.gov and organized them into seven semantic categories: Disease, Medication, Diagnostic Test, Procedure, Social Determinants of Health, Rating Criteria, and Fertility. Each concept was annotated with standard biomedical vocabularies, including the UMLS, OMOP Standardized Vocabularies, DrugBank, NDC, and NLM VSAC value sets. To balance coverage and manageability, we applied the Jenks Natural Breaks method to identify an optimal set of representative concepts. Results The optimized AD-CDO achieved over 63% coverage of extracted trial concepts while maintaining interpretability and compactness. The ontology effectively captured the most frequent and clinically meaningful entities used in AD eligibility criteria. We demonstrated AD-CDO's practical utility through two use cases: (a) an ontology-driven trial simulation system for formal modeling and virtual execution of clinical trials, and (b) an entity normalization task mapping raw clinical text to ontology-aligned terms, enabling consistency and integration with EHR data. Discussion AD-CDO bridges the gap between broad biomedical ontologies and task-specific trial modeling needs. It supports multiple downstream applications, including phenotyping algorithm development, cohort identification, and structured data integration. Conclusion By harmonizing essential eligibility entities and aligning them with standardized vocabularies, AD-CDO provides a versatile foundation for ontology-driven AD clinical trial research.

cs.CL↗

arXiv2024

CDEMapper: Enhancing NIH Common Data Element Normalization using Large Language Models

Common Data Elements (CDEs) standardize data collection and sharing across studies, enhancing data interoperability and improving research reproducibility. However, implementing CDEs presents challenges due to the broad range and variety of data elements. This study aims to develop an effective and efficient mapping tool to bridge the gap between local data elements and National Institutes of Health (NIH) CDEs. We propose CDEMapper, a large language model (LLM) powered mapping tool designed to assist in mapping local data elements to NIH CDEs. CDEMapper has three core modules: (1) CDE indexing and embeddings. NIH CDEs were indexed and embedded to support semantic search; (2) CDE recommendations. The tool combines Elasticsearch (BM25 similarity methods) with state of the art GPT services to recommend candidate CDEs and their permissible values; and (3) Human review. Users review and select the NIH CDEs and values that best match their data elements and value sets. We evaluate the tool recommendation accuracy against manually annotated mapping results. CDEMapper offers a publicly available, LLM-powered, and intuitive user interface that consolidates essential and advanced mapping services into a streamlined pipeline. It provides a step by step, quality assured mapping workflow designed with a user-centered approach. The evaluation results demonstrated that augmenting BM25 with GPT embeddings and a ranker consistently enhances CDEMapper mapping accuracy in three different mapping settings across four evaluation datasets. This work opens up the potential of using LLMs to assist with CDE recommendation and human curation when aligning local data elements with NIH CDEs. Additionally, this effort enhances clinical research data interoperability and helps researchers better understand the gaps between local data elements and NIH CDEs.

cs.IR↗

arXiv2024

A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients

Generating discharge summaries is a crucial yet time-consuming task in clinical practice, essential for conveying pertinent patient information and facilitating continuity of care. Recent advancements in large language models (LLMs) have significantly enhanced their capability in understanding and summarizing complex medical texts. This research aims to explore how LLMs can alleviate the burden of manual summarization, streamline workflow efficiencies, and support informed decision-making in healthcare settings. Clinical notes from a cohort of 1,099 lung cancer patients were utilized, with a subset of 50 patients for testing purposes, and 102 patients used for model fine-tuning. This study evaluates the performance of multiple LLMs, including GPT-3.5, GPT-4, GPT-4o, and LLaMA 3 8b, in generating discharge summaries. Evaluation metrics included token-level analysis (BLEU, ROUGE-1, ROUGE-2, ROUGE-L) and semantic similarity scores between model-generated summaries and physician-written gold standards. LLaMA 3 8b was further tested on clinical notes of varying lengths to examine the stability of its performance. The study found notable variations in summarization capabilities among LLMs. GPT-4o and fine-tuned LLaMA 3 demonstrated superior token-level evaluation metrics, while LLaMA 3 consistently produced concise summaries across different input lengths. Semantic similarity scores indicated GPT-4o and LLaMA 3 as leading models in capturing clinical relevance. This study contributes insights into the efficacy of LLMs for generating discharge summaries, highlighting LLaMA 3's robust performance in maintaining clarity and relevance across varying clinical contexts. These findings underscore the potential of automated summarization tools to enhance documentation precision and efficiency, ultimately improving patient care and operational capability in healthcare settings.

cs.CL↗

arXiv2023

Application of an ontology for model cards to generate computable artifacts for linking machine learning information from biomedical research

Model card reports provide a transparent description of machine learning models which includes information about their evaluation, limitations, intended use, etc. Federal health agencies have expressed an interest in model cards report for research studies using machine-learning based AI. Previously, we have developed an ontology model for model card reports to structure and formalize these reports. In this paper, we demonstrate a Java-based library (OWL API, FaCT++) that leverages our ontology to publish computable model card reports. We discuss future directions and other use cases that highlight applicability and feasibility of ontology-driven systems to support FAIR challenges.

cs.DL↗

arXiv2019

Discriminative Sleep Patterns of Alzheimer's Disease via Tensor Factorization

Sleep change is commonly reported in Alzheimer's disease (AD) patients and their brain wave studies show decrease in dreaming and non-dreaming stages. Although sleep disturbance is generally considered as a consequence of AD, it might also be a risk factor of AD as new biological evidence shows. Leveraging National Sleep Research Resource (NSRR), we built a unique cohort of 83 cases and 331 controls with clinical variables and EEG signals. Supervised tensor factorization method was applied for this temporal dataset to extract discriminative sleep patterns. Among the 30 patterns extracted, we identified 5 significant patterns (4 patterns for AD likely and 1 pattern for normal ones) and their visual patterns provide interesting linkage to sleep with repeated wakefulness, insomnia, epileptic seizure, and etc. This study is preliminary but findings are interesting, which is a first step to provide quantifiable evidences to measure sleep as a risk factor of AD.

q-bio.NC↗