IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics最新文献

{"title":"Quantifying the Uncertainty and Risk Contributions of Activities of Daily Living Features in Dementia Prediction.","authors":"Souvik Bag, Eunji Jeon, Muskan Garg, Xingyi Liu, Maria Vassilaki, Ronald C Petersen, Jennifer St Sauver, Sunghwan Sohn","doi":"10.1109/ichi69079.2026.00046","DOIUrl":"10.1109/ichi69079.2026.00046","url":null,"abstract":"<p><p>Activities of daily living (ADL) features contain important prognostic signals for future dementia and improve prediction model performance. However, assessing their contributions to predictive performance alone is insufficient to demonstrate how consistently and reliably individual ADL features contribute to dementia progression. To develop trustworthy and clinically actionable predictions using ADL features, it is crucial to quantify the prediction uncertainty associated with these features. This study introduces an uncertainty-aware framework combining credibility scores to quantify the uncertainty of the prediction model. Then, we measure the SHapley Additive exPlanations-based contributions of five-year impairment in each ADL to the predicted risk and model uncertainty. To address age-specific ADL patterns, we analyzed the contributions across different age groups. Our finding demonstrates that ADL impairments driving <i>prediction probability</i> are not necessarily those that drive <i>prediction reliability</i>. In particular, we categorize the ADL features into four sections namely \"red flags\", \"golden signals\", \"noisy predictors\" and \"safety signals\" for each group, based on their contribution (positive/negative) in dementia prediction and uncertainty quantification. This approach moves dementia detection beyond opaque probability scores toward a transparent and credible workflow for clinical application.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"291-296"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13474598/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148760264","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}

{"title":"Improving Survival Prediction of Head and Neck Cancer Patients by Modeling Long-term Symptom Burden.","authors":"Yaohua Wang, Eric A Anyimadu, Clifton David Fuller, Amy Catherine Moreno, Xinhua Zhang, G Elisabeta Marai, Guadalupe Canahuate","doi":"10.1109/ichi69079.2026.00054","DOIUrl":"10.1109/ichi69079.2026.00054","url":null,"abstract":"<p><p>Accurate survival prediction in head and neck cancer (HNC) is essential for effective treatment planning and management. Patient-reported outcomes (PROs) provide a complementary source of prognostic information by capturing longitudinal symptom trajectories that reflect patients' health status and treatment response, but their integration into survival modeling remains challenging due to missing data and limited availability at the desired decision points. We propose an end-to-end approach that models longitudinal symptom trajectories using a bidirectional long short-term memory (Bi-LSTM) network to forecast late symptom burden from baseline PROs. Predicted symptom trajectories are summarized into cluster-level average symptom burden scores, which are standardized and incorporated as continuous covariates into a Cox proportional hazards model alongside clinical features. The proposed approach improves test-set prognostic discrimination, increasing the concordance index from 0.802 to 0.842. These results demonstrate that forecasting longitudinal PRO dynamics and representing symptom burden as continuous, data-driven measures can enhance personalized survival prediction in HNC.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"357-366"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13470404/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148762820","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}

{"title":"Pseudocode Generation from Clinical Protocol Flowchart using Large Vision-Language Models.","authors":"Le Zhou, Xiao Luo, Chinmay Chandra, Zhan Zhang","doi":"10.1109/ichi69079.2026.00113","DOIUrl":"10.1109/ichi69079.2026.00113","url":null,"abstract":"<p><p>A key component of developing clinical decision support systems (CDSS) involves translating clinical protocols into executable code linking to the backend Electronic Health Record (EHR) systems - a challenging, time-consuming, and error-prone task, particularly for flowchart-based protocols with complex logic and role-specific actions. This study investigates the potential of large vision-language models (LVLMs) to automate pseudocode generation from clinical protocols as an initial step in this process. Using emergency medical services (EMS) as a case study, we evaluated state-of-the-art LVLMs and finetuned two LVLMs for generating pseudocode that can support the development of CDSS for future EHR database integration. The results indicate that model finetuning leads to a substantial performance improvement of at least 15% in terms of BLEU or CodeBLEU for pseudocode generation and up to 20% in terms of F1 for medical terminology extraction. Although these models show promise, challenges remain in the interpretation of complex protocols with conditional assessments tied to specific roles of care providers. The Pass@1 evaluation results show that human expert evaluation is necessary to assess both the semantic and logical correctness of code generation.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"903-912"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13474615/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148760310","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}

{"title":"Patient Portal Use Among Older Adults: A Systematic Review and Meta-Analysis.","authors":"Nina Sakhnini, Debaleena Chattopadhyay","doi":"10.1109/ichi69079.2026.00092","DOIUrl":"10.1109/ichi69079.2026.00092","url":null,"abstract":"<p><p>Patient portals are digital tools for managing health information. As healthcare shifts toward digital-centered delivery, portals increasingly shape how older adults access information and participate in their care. Yet, it remains unclear how older adults use these systems and what factors shape sustained engagement. We conducted a systematic review and meta-analysis of studies published between 2005 and 2025 to examine portal use among older adults. From 1,487 unique records, 52 studies were included in the systematic review and 18 in the meta-analysis. While prevalence varied significantly across diverse study contexts (<i>I</i> ² ≥ 97.6%), pooled estimates suggest that approximately 55% (95% CI: 0.28-0.79) of older adults had ever used a portal and 48% (95% CI: 0.31-0.67) were continuing users. Publication year significantly moderated ever use, indicating increasing uptake over time (<i>OR/year</i> = 1.39), but was not significantly associated with continued use.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"719-728"},"PeriodicalIF":0.0,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13475054/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148762195","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}

{"title":"Promise and Caution: Mapping Opportunities for AI Decision Support in Emergency Medical Services.","authors":"Zhan Zhang, Vanessa Fechi Agbugba, Enze Bai, Sian Billings, Xiao Luo, Kathleen Adelgais","doi":"10.1109/ichi69079.2026.00086","DOIUrl":"10.1109/ichi69079.2026.00086","url":null,"abstract":"<p><p>Designing AI-enabled decision support for fast-paced medical teams remains underexplored. We use Emergency Medical Services (EMS) as a critical use case to examine where AI can, and should not, support time-critical decision-making. We conducted participatory design workshops and formative user evaluations with EMS providers to elicit, prototype, and critique candidate AI application areas for EMS work. Providers identified several promising uses of AI: (1) AI-enabled information retrieval to accelerate access to protocols and medication references; (2) speech-based documentation support to reduce charting burden and generate draft records during care; (3) AI-generated patient \"snapshots\" that summarize relevant history from prior encounters; and (4) AI-based medication recognition to identify home medications and surface key safety information. In contrast, participants were cautious about clinical reasoning support that could be interpreted as diagnostic assertions, ambient \"always-on\" monitoring to flag errors or workflow deviations, and voice-based exchanges with AI in front of patients. Across various concepts, providers emphasized key factors critical for AI adoption in EMS, including seamless workflow fit, robustness to noisy environments, transparency, appropriate trust calibration, and the preservation of professional autonomy. We conclude with design implications for responsibly advancing the use of AI technology for EMS decision support.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"661-670"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13480403/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802494","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}

{"title":"Identify Patients at Risk of HIV Using a Clinical Large Language Model from Electronic Health Records.","authors":"Yiyang Liu, Ziyi Chen, Pogul Suman, Hwayoung Cho, Mattia Prosperi, Yonghui Wu","doi":"10.1109/ichi69079.2026.00031","DOIUrl":"10.1109/ichi69079.2026.00031","url":null,"abstract":"<p><p>This study developed a large language model (LLM)-based solution to identify people at HIV risk using electronic health records. We transformed structured EHR data, including demographics, diagnoses, and medications, into narrative descriptions ordered by visit date and applied GatorTron, a widely used clinical LLM trained on 82 billion words of de-identified clinical text. We compared GatorTron with traditional machine learning models, including LASSO and XGBoost. We identified a cohort with 54,265 individuals, where only 3,342 (6%) had new HIV diagnoses. Our LLM solution, based on GatorTron, achieved excellent performance, reaching an F1 score of 53.5% and an AUC of 0.88, comparable to traditional machine learning approaches. Subgroup analysis showed that, across age, sex, and race/ethnicity groups, both LLM and traditional models achieved AUCs above 0.82. Interpretability analyses showed broadly consistent patterns across LLM models and traditional machine learning models.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"159-166"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13502286/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148815158","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}

{"title":"Comparing LLM and Fine-Tuned Model Performance on NVDRS Circumstance Extraction with Varying Prompt Complexity.","authors":"Geoffrey Martin, Xuan Zhong Feng, Yifan Peng","doi":"10.1109/ichi69079.2026.00020","DOIUrl":"10.1109/ichi69079.2026.00020","url":null,"abstract":"<p><p>Suicide is a leading cause of death in the United States, and understanding the circumstances that precede it requires extracting structured information from death investigation narratives. Many of these circumstances require semantic inference beyond simple keyword matching. We develop a \"Complexity Score\" algorithm that analyzes coding manual structure to predict when detailed prompts with full coding guidelines improve over name-only prompts. We then construct a hybrid approach that selects a prompt strategy per circumstance. We evaluate large language models (LLMs) against fine-tuned RoBERTa on 25 inferentially complex circumstances from the National Violent Death Reporting System (NVDRS). We found that LLMs substantially outperform on low-prevalence circumstances where training data is insufficient. We further demonstrate that our framework generalizes across frontier LLMs, with GPT-5.2, Gemini 2.5 Pro and Llama-3 70B showing consistent performance patterns. These findings support a hybrid architecture where LLMs handle rare, inferentially complex circumstances while fine-tuned models handle common ones.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"67-72"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13492185/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802504","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}

{"title":"Using reasoning LLMs to extract SDOH events from clinical notes.","authors":"Ertan Dogan, Kunyu Yu, Yifan Peng","doi":"10.1109/ichi69079.2026.00022","DOIUrl":"10.1109/ichi69079.2026.00022","url":null,"abstract":"<p><p>Social Determinants of Health (SDOH) refer to environmental, behavioral, and social conditions that influence how individuals live, work, and age. SDOH have a significant impact on personal health outcomes, and their systematic identification and management can yield substantial improvements in patient care. However, SDOH information is predominantly captured in unstructured clinical notes within electronic health records, which limits its direct use as machine-readable entities. To address this issue, researchers have employed Natural Language Processing (NLP) techniques using pre-trained BERT-based models, demonstrating promising performance but requiring sophisticated implementation and extensive computational resources. In this study, we investigated prompt engineering strategies for extracting structured SDOH events utilizing LLMs with advanced reasoning capabilities. Our method consisted of four modules: 1) developing concise and descriptive prompts integrated with established guidelines, 2) applying few-shot learning with carefully curated examples, 3) using a self-consistency mechanism to ensure robust outputs, and 4) post-processing for quality control. Our approach achieved a micro-F1 score of 0.866, demonstrating competitive performance compared to the leading models. The results demonstrated that LLMs with reasoning capabilities are effective solutions for SDOH event extraction, offering both implementation simplicity and strong performance.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"83-92"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13501414/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148815147","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}

{"title":"Interpretable Alzheimer's Diagnosis via Multimodal Fusion of Regional Brain Experts.","authors":"Farica Zhuang, Shu Yang, Dinara Aliyeva, Zixuan Wen, Duy Duong-Tran, Christos Davatzikos, Tianlong Chen, Song Wang, Li Shen","doi":"10.1109/ichi69079.2026.00049","DOIUrl":"10.1109/ichi69079.2026.00049","url":null,"abstract":"<p><p>Accurate and early diagnosis of Alzheimer's disease (AD) is critical for effective intervention and requires integrating complementary information from multimodal neuroimaging data. However, conventional fusion approaches often rely on simple concatenation of features, which cannot adaptively balance the contributions of biomarkers such as amyloid PET and MRI across brain regions. In this work, we propose MREF-AD, a Multimodal Regional Expert Fusion model for AD diagnosis. It is a Mixture-of-Experts (MoE) framework that models mesoscopic brain regions within each modality as independent experts and employs a gating network to learn subject-specific fusion weights. Utilizing tabular neuroimaging and demographic information from the Alzheimer's Disease Neuroimaging Initiative (ADNI), MREF-AD achieves competitive performance over strong classic and deep baselines while providing interpretable, modality- and region-level insight into how structural and molecular imaging jointly contribute to AD diagnosis. The source code is available at https://github.com/PennShenLab/mref-ad.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"311-320"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13480405/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802524","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}

{"title":"From Routine Imaging to Risk Stratification: Multimodal Vision-Language Survival Modeling for Pancreatic Cancer.","authors":"David Le, Ramon Luis Correa Medero, Amara Tariq, Vedant Joshi, Zhemin Zhang, Fnu Murlidhar, Hexin Dong, Yifan Peng, George Shih, Zhen Wang, Rahul Pannala, Motoyo Yano, Imon Banerjee","doi":"10.1109/ichi69079.2026.00071","DOIUrl":"10.1109/ichi69079.2026.00071","url":null,"abstract":"<p><p>Pancreatic ductal adenocarcinoma (PDAC) is frequently diagnosed in advanced stages, substantially limiting opportunities for early intervention. In this work, we present a multimodal survival modeling framework for prediagnostic PDAC risk stratification using routinely acquired clinical data, including abdominal computed tomography (CT) imaging, radiology reports, and structured electronic health record (EHR) variables. Our first contribution is a unified multimodal framework that integrates heterogeneous clinical data sources for prediagnostic risk modeling. Second, to address the sparsity and heterogeneity of EHR data, we introduce text-based encoding of clinical variables, while volumetric variability in CT imaging is mitigated through automated pancreas detection and standardized subvolume selection. Third, we integrate a vision-language foundation model (VLM) with a survival modeling objective based on negative log-likelihood to estimate cancer-free survival. Model performance was evaluated on internal and external validation cohorts using the concordance index (C-index). Across cohorts, multimodal fusion generally outperformed unimodal approaches. Vision-language models demonstrated strong and consistent discriminative performance, while feature-engineered models achieved competitive performance, particularly on external validation. Overall, multimodal integration provided the most robust performance, highlighting the complementary value of combining imaging, text, and structured clinical data. Finally, to address interpretability challenges associated with VLM-based modalities, we conducted systematic ablation studies using modality-specific occlusion and noise perturbation to quantify the contribution of image and text features. These results support the feasibility of opportunistic PDAC risk stratification from routinely collected multimodal clinical data and underscore the potential of multimodal representation learning for early risk identification.</p>","PeriodicalId":73284,"journal":{"name":"IEEE International Conference on Healthcare Informatics. IEEE International Conference on Healthcare Informatics","volume":"2026 ","pages":"515-524"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13497519/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802488","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}