AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science最新文献

Opioid Overdose Death Prediction with Graph Neural Networks. 基于图神经网络的阿片类药物过量死亡预测。

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

Xianhui Chen, Zishan Gu, John Myers, Joanne Kim, Changchang Yin, Naleef Fareed, Neena Thomas, Soledad Ferna Ndez, Ping Zhang

{"title":"Opioid Overdose Death Prediction with Graph Neural Networks.","authors":"Xianhui Chen, Zishan Gu, John Myers, Joanne Kim, Changchang Yin, Naleef Fareed, Neena Thomas, Soledad Ferna Ndez, Ping Zhang","doi":"","DOIUrl":"","url":null,"abstract":"The opioid crisis has severely impacted Ohio, with overdose death rates surpassing national averages and disproportionately affecting rural and Appalachian regions. Accurately predicting county-level opioid overdose (OD) deaths is critical for timely intervention but remains challenging due to the wide differences in opioid OD deaths between large and small counties. We propose a Spatial-Temporal Graph Neural Network (ST-GNN) framework that integrates graph neural networks (GNNs) to capture spatial relationships between counties and Long Short-Term Memory (LSTM) networks to model temporal dynamics. Using quarterly OD death data from Q1 2017 to Q2 2023 for 88 Ohio counties, we incorporate a nine-dimensional dynamic feature set, including naloxone administration events and high-risk opioid prescribing, along with a static Social Determinants of Health (SDoH) index. Compared to traditional statistical models and temporal deep learning baselines, our ST-GNN demonstrates superior performance, particularly in larger counties, while a classification-based strategy improves predictions for small counties, leading to more stable and reliable results. Our findings emphasize the need for spatial-temporal modeling and customized training to enhance public health decision-making in addressing the opioid crisis.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"87-96"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274302/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280188","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

MSCA-Net: Multi-Modal Cell Segmentation for Spatial Transcriptomics. MSCA-Net：空间转录组学的多模态细胞分割。

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

Jiong Chen, Chentianye Xu, Huasheng Yu, Kevin Shen, Anna Carroll, Nathan Wu, Miguel Francisco Mercado, Jingxuan Bao, Shu Yang, Duy Duong-Tran, Sumita Garai, Mingyao Li, Wenqin Luo, Min Xu, Li Shen

{"title":"MSCA-Net: Multi-Modal Cell Segmentation for Spatial Transcriptomics.","authors":"Jiong Chen, Chentianye Xu, Huasheng Yu, Kevin Shen, Anna Carroll, Nathan Wu, Miguel Francisco Mercado, Jingxuan Bao, Shu Yang, Duy Duong-Tran, Sumita Garai, Mingyao Li, Wenqin Luo, Min Xu, Li Shen","doi":"","DOIUrl":"","url":null,"abstract":"Single-cell spatial transcriptomics has advanced spatial resolution from several cells per spot to hundreds of transcripts per cell, enabling a more comprehensive understanding of cellular interaction and local tissue organization. However, such high-resolution imaging introduces significant computational challenges, particularly in accurately segmenting cellular boundaries. Existing segmentation methods typically rely on a single modality, such as cellular imaging or transcript profiling, and thus fail to leverage the complementary information between modalities. Here we propose MSCA-Net, a Multi-Scale Convolutional Attention U-Net framework that integrates H&E staining images with selected transcriptomic features to achieve accurate cell boundary extraction. We evaluate MSCA-Net on dorsal root ganglia (DRG) neurons and demonstrate that it consistently outperforms state-of-the-art competing methods. Our study also shows that the reconstructed spatial transcriptomic slice can reproduce the downstream analysis consistent with prior knowledge, providing reliable and valuable insights for biological discovery.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"77-86"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274350/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280174","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

Title: Multimodal Fusion of Clinical and Imaging Data for Early Prediction of Massive Transfusion in Trauma. 题目：多模态融合临床和影像资料早期预测创伤大量输血。

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

Michael R Kolesnikov, Phillip D Jenkins, Vishnu Mohan, Laszlo Kiraly, Karen Eden, Steven Bedrick

{"title":"Title: Multimodal Fusion of Clinical and Imaging Data for Early Prediction of Massive Transfusion in Trauma.","authors":"Michael R Kolesnikov, Phillip D Jenkins, Vishnu Mohan, Laszlo Kiraly, Karen Eden, Steven Bedrick","doi":"","DOIUrl":"","url":null,"abstract":"Massive transfusion (MT) prediction in trauma remains limited by scoring systems with suboptimal discrimination and generalizability. We developed a multimodal joint fusion model integrating structured electronic health record (EHR) data with admission chest X-rays to support early MT risk stratification. From 33,824 trauma patients (2014-2024), 10,090 met inclusion criteria, including 226 MT cases (2.24%). Structured presentation variables were modeled using a multilayer perceptron, while imaging features were extracted using a pretrained DenseNet-121; intermediate feature fusion enabled end-to-end learning. Class imbalance was addressed with SMOTE for structured data and geometric augmentation for imaging. On the held-out validation set, the fusion model achieved an AUC of 0.669. At the selected threshold, sensitivity was 0.72 and specificity 0.84. Grad-CAM visualizations demonstrated attention over clinically relevant thoracoabdominal regions. Despite limited positive predictive value due to low event prevalence, these findings demonstrate feasibility of workflow-aligned multimodal MT prediction using routinely available data, warranting prospective multi-center validation.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"239-248"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274277/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148279949","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

Robust FDR Control for Neuroimaging-based Classification via Knockoffs. 基于仿制品的神经成像分类鲁棒FDR控制。

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

Sumita Garai, Hongzhuo Chen, Frederick Xu, Duy Duong-Tran, Pratik Chaudhari, Christos Davatzikos, Brielin C Brown, Li Shen

{"title":"Robust FDR Control for Neuroimaging-based Classification via Knockoffs.","authors":"Sumita Garai, Hongzhuo Chen, Frederick Xu, Duy Duong-Tran, Pratik Chaudhari, Christos Davatzikos, Brielin C Brown, Li Shen","doi":"","DOIUrl":"","url":null,"abstract":"Machine learning for medical image analysis has received unprecedented attention and success in the recent years. Yet, ensuring the reliability of discovered features for neuroimaging-based classification remains a challenge. In this study, we demonstrate the knockoff framework, a robust statistical approach that guarantees a theoretical bound on the False Discovery Rate (FDR), even under complex feature dependencies and model mis-specification. Unlike the Benjamini-Hochberg (BH) procedure, which assumes feature independence, knockoffs provide precise and provable FDR control for any feature correlation structure. We evaluate multiple knockoff construction methods on synthetic data for binary classification, observing near-perfect detection of true features and valid FDR control. We then apply the knockoff filter to fMRI data from the Human Connectome Project (HCP) to identify brain regions that contribute to an imaging-based classification model. The regions identified by the knockoff filter are found to be stable and reproducible across test-retest scans, indicating that they capture consistent task-related neural activation.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"137-146"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274285/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280157","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

A Novel Approach to Zero-Shot Drug-Drug Interaction Prediction Enabled by EHR-Augmented Knowledge Graphs. 基于ehr增强知识图谱的零起点药物-药物相互作用预测新方法。

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

Srijith Chinthalapudi, Sandeep K Mallipattu, Alisa Yurovsky, Tengfei Ma

{"title":"A Novel Approach to Zero-Shot Drug-Drug Interaction Prediction Enabled by EHR-Augmented Knowledge Graphs.","authors":"Srijith Chinthalapudi, Sandeep K Mallipattu, Alisa Yurovsky, Tengfei Ma","doi":"","DOIUrl":"","url":null,"abstract":"With more and more prescription drugs being administered, screening for adverse drug-drug interactions (DDIs) is now a major pharmacovigilance challenge. Electronic Health Record (EHR)-based statistical methods produce noisy predictions with high false positive rates due to confounding factors. Knowledge Graph (KG)-based machine learning methods, while more accurate, cannot predict interactions for drugs absent from the original graph, lacking zero-shot capability. We present a novel approach that augments large-scale but incomplete biomedical KGs with statistically noisy but comprehensive real-world edges derived from EHRs. We hypothesize that the EHR-derived associations act as bridges connecting unseen drugs to the pharmacological knowledge in KGs, thus enabling zero-shot capability. To rigorously test this, we designed a KG-embedding experiment that isolates drugs during training while preserving their interactions for testing. Results quantitatively demonstrate that our approach specifically enables effective zero-shot DDI prediction.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"107-116"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274378/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280114","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 Linkage Approaches for Address-Level Socioenvironmental Exposure Assessment. 评价地址级社会环境暴露评估的联系方法。

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

Carson S Hartlage, Erika Rasnick Manning, Cole Brokamp

{"title":"Evaluating Linkage Approaches for Address-Level Socioenvironmental Exposure Assessment.","authors":"Carson S Hartlage, Erika Rasnick Manning, Cole Brokamp","doi":"","DOIUrl":"","url":null,"abstract":"Accurate linkage of addresses to parcel-level data is essential for hyperlocal environmental exposure assessment, yet the performance of methods, including their impact on exposure misclassification and bias, remains poorly characterized. Using a gold standard match of 853,255 National Address Database records to authoritative datasets from Hamilton and Franklin Counties, Ohio, we evaluated address tag fuzzy matching and geocoding-based (geomatching) approaches on accuracy of linked parcel identifier and parcel market total value and usage type. Address tag fuzzy matching achieved 100% agreement; address point geomatching performed moderately well (65.1% - 76.1%), and street range geomatching performed poorly (7.2% - 59.2%). Poorer agreement was more common in neighborhoods with higher address densities and more community material deprivation, highlighting potential for differential misclassification of exposure assessment. These findings emphasize a need for precise, scalable, and standardized linkage approaches to support valid address- and parcel-level exposure assessment in clinical and population health research.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"183-192"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274357/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280209","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

Development of a Pilot Artificial Intelligence Education Curriculum for Hospital Staff. 医院员工人工智能教育试点课程的开发。

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

Brian Lefchak, Uzoma Abakporo, Gagandeep Anand, Justin Gaines, Christopher Adams, Ryan Jelinek

{"title":"Development of a Pilot Artificial Intelligence Education Curriculum for Hospital Staff.","authors":"Brian Lefchak, Uzoma Abakporo, Gagandeep Anand, Justin Gaines, Christopher Adams, Ryan Jelinek","doi":"","DOIUrl":"","url":null,"abstract":"Artificial intelligence (AI) is rapidly advancing, yet many healthcare staff lack foundational knowledge, risking inefficient or unsafe use. To address this, we developed an internal voluntary AI Primer pilot curriculum for all staff, including non-clinicians, within a safety-net health system. The micro-learning program included six modules featuring creative AI-generated content to enhance engagement. In its first three months, 80 staff voluntarily enrolled, generating over 500 views. Participants completing an optional post-course survey (n = 7) scored highly on post-course assessments (86-100%), found the content relevant, and felt it addressed AI safety (85%). Most appreciated the design, and nearly one-third enrolled out of curiosity about AI in healthcare. Our pilot's findings contribute to a nascent body of literature and demonstrate that a multimodal education/entertainment approach can promote AI literacy across a diverse range of hospital roles in a scalable manner. Future efforts may incorporate clinical examples and strategies to expand participation.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"249-256"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274320/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280193","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

Enhancing Inter-institutional AI Research Collaboration Across Multidisciplinary Teams to Increase the National AI Workforce in Healthcare. 加强跨多学科团队的机构间人工智能研究合作，以增加医疗保健领域的国家人工智能劳动力。

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

Toufeeq Ahmed Syed, Sarah Popal, D'Laney Kernan, Deevakar Rogith, Zulfiia Ditto, Paul Warhurst, Jay Johnson, Jamboor K Vishwanatha

{"title":"Enhancing Inter-institutional AI Research Collaboration Across Multidisciplinary Teams to Increase the National AI Workforce in Healthcare.","authors":"Toufeeq Ahmed Syed, Sarah Popal, D'Laney Kernan, Deevakar Rogith, Zulfiia Ditto, Paul Warhurst, Jay Johnson, Jamboor K Vishwanatha","doi":"","DOIUrl":"","url":null,"abstract":"Inter-institutional team collaboration is critical for impactful multidisciplinary AI research in healthcare. The goal of our project (AIM-AHEAD Connect) is to increase multidisciplinary collaborations by connecting AI/ML experts and healthcare researchers, trainees and professionals to enhance research and improve health for all Americans. As of February 2026, AIM-AHEAD Connect has over 10,100 AI/ML and healthcare experts from across 2,400 institutions, has made more than 7,800 connections and facilitated 194 collaborative online groups. We conducted a unique study to understand collaboration, and analyzed profile, connection, and platform engagement metrics to determine if AI experts and healthcare researchers with more inter-institutional connections are more successful in obtaining research and training funding. By creating this bridge to foster collaborations between AI/ML experts and healthcare professionals, this project has created a unique space to enhance healthcare outcomes for all.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"448-457"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274375/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280191","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

Leadership, Informatics Expertise, and Resources: Determinants of Institutional Data Sharing in the National Clinical Cohort Collaborative (N3C). 领导力、信息学专业知识和资源：国家临床队列协作（N3C）中机构数据共享的决定因素。

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

Carly M Rose, William S Bush, Mark F Beno, Scott M Williams, Jonathan L Haines, Dana C Crawford

{"title":"Leadership, Informatics Expertise, and Resources: Determinants of Institutional Data Sharing in the National Clinical Cohort Collaborative (N3C).","authors":"Carly M Rose, William S Bush, Mark F Beno, Scott M Williams, Jonathan L Haines, Dana C Crawford","doi":"","DOIUrl":"","url":null,"abstract":"The National Clinical Cohort Collaborative (N3C), initially developed in response to the SARS-CoV-2/COVID-19 pandemic, is one of the largest centralized, individual-level clinical data repositories available for research in the US. Some institutions do not share data with N3C. We accessed public data to derive institutional variables representative of leadership, informatics expertise, and resources, potentially addressable factors we hypothesized were associated with N3C clinical data sharing. N3C data sharing institutions were more likely to have active NCATS funding, have affiliated departments, centers, or institutes of biomedical informatics, and active Fellows of the American College of Medical Informatics faculty compared with institutions that did not share data with N3C. While we identified institutional characteristics associated with N3C data sharing, there are likely other characteristics associated with institutional data sharing decisions. Understanding factors that motivate or deter institutional data sharing for research is key to addressing barriers and making more data open.","PeriodicalId":72181,"journal":{"name":"AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science","volume":"2026 ","pages":"381-389"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13274281/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148280217","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

Machine Learning Based County Level Phenotypes Related to Diabetes Prevalence. 基于机器学习的县域表型与糖尿病患病率相关

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

Md Fitrat Hossain, Fadia T Shaya

引用次数: 0