AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science最新文献_第2页

ChartOCR: A Longitudinal OCR System Using a Unified Periodontal Assessment Form. ChartOCR：使用统一牙周评估表的纵向OCR系统。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Yunseo Moon, Minh Do Ngoc Luong, Seungjun Chong, Seung-Hee Ryu, Hye-Jin Hyun, Hyun-Jae Cho, Hyunggu Jung

{"title":"ChartOCR: A Longitudinal OCR System Using a Unified Periodontal Assessment Form.","authors":"Yunseo Moon, Minh Do Ngoc Luong, Seungjun Chong, Seung-Hee Ryu, Hye-Jin Hyun, Hyun-Jae Cho, Hyunggu Jung","doi":"","DOIUrl":"","url":null,"abstract":"Periodontitis generates substantial clinical data, yet periodontal and PI charts remain predominantly paper-based, which limits reuse for clinical analysis and decision support. We present ChartOCR, a system that digitizes unified periodontal-plaque forms using template-based alignment, coordinate-based region-of-interest extraction, a fine-tuned TrOCR model, and SHA-256. ChartOCR supports common handwriting conventions and provides an interactive interface with real-time result streaming, in-place correction, and CSV export. We evaluated the system on 30 scanned handwritten charts. Periodontal charts achieved a mean accuracy and mAP of 0.987, while PI charts reached 0.942 accuracy and 0.884 mAP. Most digits performed well, although PPV was lower for higher plaque scores. On a MacBook Pro (M3 Pro), the average processing time per chart was approximately 70 seconds. These results demonstrate that our approach enables accurate, efficient digitization of handwritten dental charts and provides a scalable foundation for periodontal informatics research.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"323-332"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274332/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Identifying Digital Health Technology Engagement and Frustration Phenotypes in Patients with Multiple Chronic Conditions: Evidences from a Nationally Representative Cross-Sectional Study. 识别多种慢性疾病患者的数字健康技术参与和挫折表型：来自全国代表性横断面研究的证据

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Haoxin Chen, Jiancheng Ye

{"title":"Identifying Digital Health Technology Engagement and Frustration Phenotypes in Patients with Multiple Chronic Conditions: Evidences from a Nationally Representative Cross-Sectional Study.","authors":"Haoxin Chen, Jiancheng Ye","doi":"","DOIUrl":"","url":null,"abstract":"This cross-sectional study analyzed nationally representative data from the Health Information National Trends Survey (HINTS 7, 2024) to examine patterns of digital health technology (DHT) use and the associations among multimorbidity, DHT adoption, and user-reported frustration (N=3,753). Adults with multimorbidity used more DHT types on average (mean=3.9 vs. 3.6, p<0.001) yet reported significantly higher frustration (61.2% vs. 54.1%, p<0.001) compared to those with a single chronic condition. Multivariable regression identified higher income and education were associated with reduced frustration, and greater DHT engagement independently predicted lower frustration (OR=0.78, 95% CI: 0.71-0.87). Phenotypic analysis revealed a high-risk subgroup of multimorbid, low DHT users with older age and lower socioeconomic status (SES), exhibiting the highest frustration prevalence (60.3%). These findings underscore the need for targeted digital literacy support and user-centered design to alleviate digital health burden in complex chronic disease populations.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"97-106"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274273/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

REACT (Real-world Emulated Clinical Trials): A Framework for Drug Repurposing Applied to Osteoporotic Fractures. REACT（真实世界模拟临床试验）：用于骨质疏松性骨折的药物再利用框架。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Jianing Liu, Seungyeon Lee, Xianhui Chen, Soledad A Fernández, Qing Wu, Ping Zhang

{"title":"REACT (Real-world Emulated Clinical Trials): A Framework for Drug Repurposing Applied to Osteoporotic Fractures.","authors":"Jianing Liu, Seungyeon Lee, Xianhui Chen, Soledad A Fernández, Qing Wu, Ping Zhang","doi":"","DOIUrl":"","url":null,"abstract":"Osteoporotic fractures remain common despite available therapies, highlighting the need for new, safe, and affordable treatment options. Advances in real-world data and causal inference have enabled target trial emulation, with prior frameworks demonstrating drug repurposing using observational data. However, no large-scale trial emulation framework has been applied to systematic drug repurposing for osteoporotic fracture prevention. To address this gap, we developed REACT (Real-world Emulated Clinical Trials), a scalable framework that operationalizes established target trial principles into an automated, comparator-robust pipeline for high-throughput drug screening. Applied to fracture prevention in older adults with osteoporosis, REACT screened 1,222 drugs and identified 18 with statistically significant associations, including 11 with protective effects and 7 with risk-increasing effects. The convergence of these findings with biological and prior observational evidence underscores REACT's ability to surface clinically meaningful patterns and its potential as a generalizable platform for accelerating real-world drug discovery and safety surveillance.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"267-276"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing an LLM-Based Clinical Data Querying System Using Metadata Enrichment and Task Decomposition. 基于元数据充实和任务分解的临床数据查询系统优化

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Weixin Liu, Bowen Qu, Pratheek Mallya, Jingyuan Wu, Kathie Thomas, Jennifer L Hall, Juan Zhao, Zhijun Yin

{"title":"Optimizing an LLM-Based Clinical Data Querying System Using Metadata Enrichment and Task Decomposition.","authors":"Weixin Liu, Bowen Qu, Pratheek Mallya, Jingyuan Wu, Kathie Thomas, Jennifer L Hall, Juan Zhao, Zhijun Yin","doi":"","DOIUrl":"","url":null,"abstract":"Accessing complex clinical registries traditionally requires SQL programming expertise, limiting data accessibility for non-technical researchers. In this paper, we designed and evaluated whether a text-to-SQL solution based on large language models (LLMs) could enable natural language querying of a real-world clinical registry under strict privacy and security constraints. Using self-hosted, open-source LLMs, we developed a multi-layered optimization framework incorporating metadata enrichment, query decomposition, hybrid retrieval, and SQL self-correction. We assessed its performance across 600 queries spanning one-, two-, and three-field complexity using execution-based validation. Accuracy was improved from 88.0% to 94.5% for one-field queries and from 10.0% to 82.0% for three-field queries. Real-world testing by data scientists revealed domain-specific challenges related to coded variables, clinical ambiguity, and multi-step reasoning. We summarize key technical and operational lessons learned and discuss implications for safe, scalable deployment of LLM-assisted analytic tools in clinical registry environments.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"277-286"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274305/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating RAG and Non-RAG Pipelines for Concept Discovery in Environmental Health Ontologies. 评价环境健康本体中概念发现的RAG和非RAG管道。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Naren Khatwani, Navya Martin Kollapally, Lijing Wang, James Geller

{"title":"Evaluating RAG and Non-RAG Pipelines for Concept Discovery in Environmental Health Ontologies.","authors":"Naren Khatwani, Navya Martin Kollapally, Lijing Wang, James Geller","doi":"","DOIUrl":"","url":null,"abstract":"The expansion of biomedical ontologies with relevant, high utility concepts remains a significant challenge in biomedical knowledge representation, particularly for rapidly evolving fields like Environmental Determinants of Health (EnDOH). In this work, we evaluate the effectiveness of using LLMs in support of ontology expansion, comparing Retrieval-Augmented Generation (RAG) with non-RAG concept extraction from the medical literature. Candidate concepts were generated across 15 targeted topics using category-specific prompts. The quality of candidate concepts was assessed through semantic similarity to existing EnDOH concepts and sub-hierarchies. This design enables both a comparative analysis of RAG versus non-RAG concept extraction approaches and the identification of topic-level concept alignment with the ontology. Our results quantify the comparative strengths and weaknesses of RAG vs non-RAG concept extraction and offer a replicable methodology for effectively extracting potentially useful candidate concepts from the literature for the purpose of inclusion in biomedical ontologies.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"229-238"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274364/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Trends in Telemedicine at a Cancer Center: Analyzing Sustained Use. 癌症中心远程医疗的趋势：分析持续使用。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Fernanda C G Polubriaginof, Allison Lipitz-Snyderman, Susan Chimonas, Jennifer Prey Dawson, Gilad Kuperman

{"title":"Trends in Telemedicine at a Cancer Center: Analyzing Sustained Use.","authors":"Fernanda C G Polubriaginof, Allison Lipitz-Snyderman, Susan Chimonas, Jennifer Prey Dawson, Gilad Kuperman","doi":"","DOIUrl":"","url":null,"abstract":"Telemedicine at a comprehensive cancer center evolved in the late-COVID-19 steady-state period. We retrospectively analyzed 3,761,467 ambulatory visits (2021-2024); 1,104,526 (29.4%) were telemedicine. Telemedicine's share declined from 33.1% in 2021 to 25.8% in 2024. Medicine services decreased from 35.7% to 28.4%, while Surgery rose from 13.5% to 15.1%. Adoption varied by service: Clinical Genetics (96.1%), Hematology (89.3%), Endocrinology (74.8%), and Infectious Disease (68.2%) remained high; Dermatology (4.9%) and Dental Surgery (0.1%) were low. Among surgical specialties, Hepatopancreatobiliary Surgery reached 41.6% (+14.4 points vs 2021). These findings indicate a durable hybrid care model, with sustained telemedicine in consultation-heavy services and limited use where examinations or procedures predominate. Factors influencing sustained use may include clinical appropriateness, and patient and clinician preferences. Results can inform digital health strategy, space planning, and policy decisions as national telehealth flexibilities evolve.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"363-370"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274306/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Large Language Models and Primary Care: A Scoping Review. 大型语言模型与初级保健：范围综述。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Julio M F Zhang, Mariana Leite, Carolina Baptista Dos Santos, Felipe Dirceu Dantas Leite Pessôa, Wen-Jan Tuan

引用次数: 0

Exploring the Utility of MALDI-TOF Mass Spectrometry and Antimicrobial Resistance in Hospital Outbreak Detection. 探索MALDI-TOF质谱法和抗菌药物耐药性在医院暴发检测中的应用。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Chang Liu, Jieshi Chen, Alexander J Sundermann, Kathleen Shutt, Marissa P Griffith, Lora Lee Pless, Lee H Harrison, Artur W Dubrawski

引用次数: 0

Logit Fingerprinting: A Novel, Accuracy-Independent Method for Validating Large Language Model Stability in High-Stakes Clinical Applications. 罗吉特指纹识别：一种新颖的、与准确性无关的方法，用于验证高风险临床应用中的大型语言模型稳定性。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

W Vaiden Logan, V K Cody Bumgardner

{"title":"Logit Fingerprinting: A Novel, Accuracy-Independent Method for Validating Large Language Model Stability in High-Stakes Clinical Applications.","authors":"W Vaiden Logan, V K Cody Bumgardner","doi":"","DOIUrl":"","url":null,"abstract":"The integration of Large Language Models (LLMs) into clinical settings requires quality assurance mechanisms capable of detecting the hidden effects of model compression and architectural instability. Conventional accuracy metrics often fail to capture the behavioral volatility introduced by quantization, distillation, and sparse architectures. We propose the \"Single-Token Forced-Choice Logit Probe,\" a method that generates a \"behavioral fingerprint\" of a model by analyzing its decision-making stability on a domain-specific (MedQA) benchmark. Validated on 11 local model families, our approach achieved 100% accuracy in distinguishing full-precision models from quantized variants. Furthermore, a longitudinal audit of commercial APIs revealed a distinct \"Stability Gap\": distilled \"Nano\" models exhibited nearly double the decision instability (2.82% vs. 1.58% Flip Rate) of their standard counterparts. Forensic classification identified the underlying compression techniques (Q8 vs. FP8), while analysis suggests the inherent non-determinism stems from Sparse Mixture-of-Experts (SMoE) routing. We conclude that Flip Rate is a critical safety metric and that distilled and quantized models require rigorous stability auditing before clinical deployment.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"287-292"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274300/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating NLP Approaches to Extract Drug Indications. 评价NLP方法提取药物适应症。

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science Pub Date : 2026-06-01 eCollection Date: 2026-01-01

Indra Neil Sarkar

{"title":"Evaluating NLP Approaches to Extract Drug Indications.","authors":"Indra Neil Sarkar","doi":"","DOIUrl":"","url":null,"abstract":"Reliable drug-indication knowledge is essential for clinical decision support and pharmacovigilance, yet manual curation is labor-intensive and difficult to scale. This study evaluated nine natural language processing approaches to extract therapeutic indications from FDA Structured Product Labels, benchmarking against 1,838 manually curated indication statements from twenty commonly prescribed medications. Methods included dictionary-based matching (QuickUMLS), a biomedical-pretrained transformer (PubMedBERT), and seven large language models spanning general-purpose and medical domain-specialized architectures. General-purpose LLMs achieved the highest performance, with Gemma2 attaining the best F1-Score (0.568) despite being the smallest model (2B parameters). Contrary to expectations, biomedical-specialized LLMs underperformed general-purpose counterparts, while dictionary-based matching yielded excessive false positives (F1 = 0.106). Performance differed markedly by drug, with narrow indication profiles yielding near-perfect accuracy and broader or symptom-adjacent indications proving consistently challenging. These findings establish a benchmark for LLM-based indication extraction and highlight opportunities for hybrid pipelines that balance high recall with precision-oriented validation.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"390-399"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274338/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0