Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing最新文献_第3页

Trust, Reproducibility, and Progress: The Roles of Independent Blind Prediction and Assessment and Benchmarking in Computational Biology. 信任、可重复性和进步：独立盲预测、评估和基准测试在计算生物学中的作用。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0065

Gaia Andreoletti, Serghei Mangul, Predrag Radivojac, Steven E Brenner

引用次数: 0

DeepDiff-SHAP: Interpretable deep learning for subgroup-specific causal hypothesis generation using conditional SHAP. deepff -SHAP：使用条件SHAP生成子组特定因果假设的可解释深度学习。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0052

Aditya Sriram, Soyeon Kim, Joseph A Carcillo, Hyun Jung Park

{"title":"DeepDiff-SHAP: Interpretable deep learning for subgroup-specific causal hypothesis generation using conditional SHAP.","authors":"Aditya Sriram, Soyeon Kim, Joseph A Carcillo, Hyun Jung Park","doi":"10.1142/9789819824755_0052","DOIUrl":"10.1142/9789819824755_0052","url":null,"abstract":"Precision medicine aims to tailor healthcare strategies to individual differences in genetic, clinical, and environmental factors. However, identifying subgroup-specific causal relationships in complex biomedical data remains a major challenge, especially when standard causal inference methods average over population heterogeneity. We introduce DeepDiff-SHAP, a novel framework that combines regression-based and deep learning-based differential causal inference to detect changes in causal relationships across patient subgroups. DeepDiff-SHAP integrates conditional SHapley Additive exPlanations (SHAP) to estimate conditional dependencies and perform nonlinear differential causal inference in a principled, interpretable manner. Applying DeepDiff-SHAP to two population-scale datasets, the CDC Diabetes Health Indicators Dataset and a UK Biobank sepsis cohort stratified by hypertension status, we identified clinically meaningful and subgroupspecific causal changes in relationships between features across the datasets including age, general health, alkaline phosphatase, and cholesterol. Our results reinforce the idea that deep learning enhances sensitivity to complex interaction patterns overlooked by linear models, providing new biological insights into disease progression and comorbidity-specific risk mechanisms. DeepDiff-SHAP offers a scalable and interpretable solution to uncover individualized causal pathways, advancing the goal of truly personalized medicine.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"722-737"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13159393/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310683","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

Integrating Imaging-Derived Clinical Endotypes with Plasma Proteomics and External Polygenic Risk Scores Enhances Coronary Microvascular Disease Risk Prediction. 将影像学衍生的临床内窥镜与血浆蛋白质组学和外部多基因风险评分相结合可提高冠状动脉微血管疾病的风险预测。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0045

Rasika Venkatesh, Tess Cherlin, Penn Medicine BioBank, Marylyn D Ritchie, Marie A Guerraty, Shefali S Verma

{"title":"Integrating Imaging-Derived Clinical Endotypes with Plasma Proteomics and External Polygenic Risk Scores Enhances Coronary Microvascular Disease Risk Prediction.","authors":"Rasika Venkatesh, Tess Cherlin, Penn Medicine BioBank, Marylyn D Ritchie, Marie A Guerraty, Shefali S Verma","doi":"10.1142/9789819824755_0045","DOIUrl":"10.1142/9789819824755_0045","url":null,"abstract":"Coronary microvascular disease (CMVD) is an underdiagnosed but significant contributor to the burden of ischemic heart disease, characterized by angina and myocardial infarction. The development of risk prediction models such as polygenic risk scores (PRS) for CMVD has been limited by a lack of large-scale genome-wide association studies (GWAS). However, there is significant overlap between CMVD and enrollment criteria for coronary artery disease (CAD) GWAS. In this study, we developed CMVD PRS models by selecting variants identified in a CMVD GWAS and applying weights from an external CAD GWAS, using CMVD-associated loci as proxies for the genetic risk. We integrated plasma proteomics, clinical measures from perfusion PET imaging, and PRS to evaluate their contributions to CMVD risk prediction in comprehensive machine and deep learning models. We then developed a novel unsupervised endotyping framework for CMVD from perfusion PET-derived myocardial blood flow data, revealing distinct patient subgroups beyond traditional case-control definitions. This imaging-based stratification substantially improved classification performance alongside plasma proteomics and PRS, achieving AUROCs between 0.65 and 0.73 per class, significantly outperforming binary classifiers and existing clinical models, highlighting the potential of this stratification approach to enable more precise and personalized diagnosis by capturing the underlying heterogeneity of CMVD. This work represents the first application of imaging-based endotyping and the integration of genetic and proteomic data for CMVD risk prediction, establishing a framework for multimodal modeling in complex diseases.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"612-628"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12952676/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310798","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

MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries. MedFactEval和MedAgentBrief：生成和评估事实性临床总结的框架和工作流程。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0027

Françcois Grolleau, Emily Alsentzer, Timothy Keyes, Philip Chung, Akshay Swaminathan, Asad Aali, Jason Hom, Tridu Huynh, Thomas Lew, April Liang, Weihan Chu, Natasha Steele, Christina Lin, Jingkun Yang, Kameron Black, Stephen Ma, Fateme N Haredasht, Nigam H Shah, Kevin Schulman, Jonathan H Chen

{"title":"MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries.","authors":"Françcois Grolleau, Emily Alsentzer, Timothy Keyes, Philip Chung, Akshay Swaminathan, Asad Aali, Jason Hom, Tridu Huynh, Thomas Lew, April Liang, Weihan Chu, Natasha Steele, Christina Lin, Jingkun Yang, Kameron Black, Stephen Ma, Fateme N Haredasht, Nigam H Shah, Kevin Schulman, Jonathan H Chen","doi":"10.1142/9789819824755_0027","DOIUrl":"10.1142/9789819824755_0027","url":null,"abstract":"Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with two complementary contributions. First, we introduce MedFactEval, a framework for scalable, fact-grounded evaluation where clinicians define high-salience key facts and an \"LLM Jury\"-a multi-LLM majority vote-assesses their inclusion in generated summaries. Second, we present MedAgentBrief, a model-agnostic, multi-step workflow designed to generate high-quality, factual discharge summaries. To validate our evaluation framework, we established a gold-standard reference using a seven-physician majority vote on clinician-defined key facts from inpatient cases. The MedFactEval LLM Jury achieved almost perfect agreement with this panel (Cohen's κ = 81%), a performance statistically non-inferior to that of a single human expert (κ = 67%, P < 0.001). Our work provides both a robust evaluation framework (MedFactEval) and a high-performing generation workflow (MedAgentBrief), offering a comprehensive approach to advance the responsible deployment of generative AI in clinical workflows.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"388-399"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13182771/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310855","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

Building Fair and Trustworthy Biomedical AI: A Tool for Identifying Key Decision Points. 构建公平可信的生物医学人工智能：识别关键决策点的工具。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0042

Nicole Foti, Janet K Shim, Caitlin McMahon, Sandra Soo-Jin Lee

{"title":"Building Fair and Trustworthy Biomedical AI: A Tool for Identifying Key Decision Points.","authors":"Nicole Foti, Janet K Shim, Caitlin McMahon, Sandra Soo-Jin Lee","doi":"10.1142/9789819824755_0042","DOIUrl":"10.1142/9789819824755_0042","url":null,"abstract":"Recent advancements in artificial intelligence (AI) have transformed biomedicine, offering tools for improved diagnostics, drug discovery, and patient care. Yet these innovations raise pressing ethical concerns, including bias, inequitable outcomes, and privacy risks, which highlight the need for deliberate attention to fairness, trust, and trustworthiness in AI development. In this paper, we argue that ethical responsibility should be embedded at both institutional and individual levels, and that multi-stakeholder engagement, especially with underrepresented groups, is essential to ensure AI tools meet diverse needs. Building on a framework originally developed for precision medicine research, we present an adapted decision-mapping tool-the Trustworthy AI Decision Map-that can anchor and structure dialogue about the ethical implications of specific AI tools. The map identifies key decision points across the AI life cycle that impact fairness and trustworthiness and facilitates dialogue among stakeholders. In making these decisions visible, the map seeks to enable teams to anticipate downstream consequences, integrate multiple perspectives, and support institutional accountability. We illustrate its potential through a case involving the deployment of AI in rural healthcare settings. Moving forward, we suggest that empirical testing with stakeholders is needed to validate and refine the map's utility in biomedical AI contexts to promote fair and trustworthy AI practices.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"580-595"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models. dreasonknee：推进医学视觉语言模型中的接地推理。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0008

Sraavya Sambara, Sung Eun Kim, Xiaoman Zhang, Luyang Luo, Shreya Johri, Mohammed Baharoon, Du Hyun Ro, Pranav Rajpurkar

{"title":"3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models.","authors":"Sraavya Sambara, Sung Eun Kim, Xiaoman Zhang, Luyang Luo, Shreya Johri, Mohammed Baharoon, Du Hyun Ro, Pranav Rajpurkar","doi":"10.1142/9789819824755_0008","DOIUrl":"10.1142/9789819824755_0008","url":null,"abstract":"Current Vision-Language Models (VLMs) struggle to ground anatomical regions in 3D medical images and reason about them in a step-by-step manner-a key requirement of realworld diagnostic assessment. This ability is essential for aligning model outputs with the diagnostic workflows clinicians use in practice, enabling trustworthy clinician-AI collaboration. Existing 3D datasets provide localization labels, but none support this \"grounded reasoning\" ability. To address this gap, we introduce 3DReasonKnee, the first 3D grounded reasoning dataset for medical images, which provides 494k high-quality quintuples derived from 7,970 3D knee MRI volumes. Each quintuple includes: (1) the 3D MRI volume, (2) a diagnostic question targeting a specific anatomical region (3) a 3D bounding box localizing the relevant anatomical structures, (4) clinician-generated diagnostic reasoning steps that explicitly detail the 3D reasoning process, and (5) structured severity assessments for the relevant anatomical region. The meticulous creation and validation of 3DReasonKnee, involving over 450 hours of expert clinician time for manually segmenting MRIs and generating reasoning chains, ensures its superior quality and clinical relevance. We establish ReasonKnee-Bench to evaluate localization and diagnostic accuracy, providing novel insight into VLM ability to perform grounding and severity assessment across diverse anatomical regions and diagnostic inquiries. We benchmark five state-of-the-art VLMs, providing baseline performance for ReasonKnee-Bench. By providing this unique resource of expertannotated 3D reasoning pathways, 3DReasonKnee serves as a repository of orthopedic surgeons' diagnostic expertise and offers a vital testbed for advancing multimodal medical AI systems towards 3D, clinically aligned, localized decision-making capabilities. The dataset can be found in HuggingFace: rajpurkarlab/3DReasonKnee.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"99-113"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Session Introduction: Fairness and Bias in Biomedical AI/ML: Defining Goals and Putting Them Into Practice. 会议介绍：生物医学AI/ML中的公平与偏见：确定目标并付诸实践。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0037

Nicole Martinez-Martin, Abdoul Jalil Djiberou Mahamadou, Madelena Ng, Mildred K Cho

引用次数: 0

Large language models identify causal genes in complex trait GWAS. 大型语言模型识别复杂性状GWAS的因果基因。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0034

Suyash S Shringarpure, Wei Wang, Sotiris Karagounis, Xin Wang, Anna C Reisetter, Adam Auton, Aly A Khan

引用次数: 0

Speaker Role Identification in Clinical Conversations. 临床会话中的说话人角色识别。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0011

Andrew Zolensky, Kuk Jin Jang, Janice Sabin, Andrea Hartzler, Basam Alasaly, Sriharsha Mopidevi, Mark Liberman, Kevin Johnson

{"title":"Speaker Role Identification in Clinical Conversations.","authors":"Andrew Zolensky, Kuk Jin Jang, Janice Sabin, Andrea Hartzler, Basam Alasaly, Sriharsha Mopidevi, Mark Liberman, Kevin Johnson","doi":"10.1142/9789819824755_0011","DOIUrl":"10.1142/9789819824755_0011","url":null,"abstract":"Patient-clinician communication research is crucial for understanding interaction dynamics and for predicting outcomes that are associated with clinical discourse. Traditionally, interaction analysis is conducted manually because of challenges such as Speaker Role Identification (SRI), which must reliably differentiate between doctors, medical assistants, patients, and other caregivers in the same room. Although automatic speech recognition with diarization can efficiently create a transcript with separate labels for each speaker, these systems are not able to assign roles to each person in the interaction. Previous SRI studies in task-oriented scenarios have directly predicted roles using linguistic features, bypassing diarization. However, to our knowledge nobody has investigated SRI in clinical settings. We explored whether Large Language Models (LLMs) such as BERT could accurately identify speaker roles in clinical transcripts, with and without diarization. We used veridical turn segmentation and diarization identifiers, fine-tuning each model at varying levels of identifier corruption to assess impact on performance. Our results demonstrate that BERT achieves high performance with linguistic signals alone (82% accuracy/82% F1-score), while incorporating accurate diarization identifiers further enhances accuracy (95%/95%). We conclude that fine-tuned LLMs are effective tools for SRI in clinical settings.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"144-157"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12952674/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310724","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

Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs. 原型学习从心电图中创建精细的可解释数字表型。

Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Pub Date : 2026-01-01 DOI: 10.1142/9789819824755_0049

Sahil Sethi, David Chen, Michael C Burkhart, Nipun Bhandari, Bashar Ramadan, Brett Beaulieu-Jones

{"title":"Prototype Learning to Create Refined Interpretable Digital Phenotypes from ECGs.","authors":"Sahil Sethi, David Chen, Michael C Burkhart, Nipun Bhandari, Bashar Ramadan, Brett Beaulieu-Jones","doi":"10.1142/9789819824755_0049","DOIUrl":"10.1142/9789819824755_0049","url":null,"abstract":"Prototype-based neural networks offer interpretable predictions by comparing inputs to learned, representative signal patterns anchored in training data. While such models have shown promise in the classification of physiological data, it remains unclear whether their prototypes capture an underlying structure that aligns with broader clinical phenotypes.We use a prototype-based deep learning model trained for multi-label ECG classification using the PTB-XL dataset. Then without modification we performed inference on the MIMIC-IV clinical database. We assess whether individual prototypes, trained solely for classification, are associated with hospital discharge diagnoses in the form of phecodes in this external population. Individual prototypes demonstrate significantly stronger and more specific associations with clinical outcomes compared to the classifier's class predictions, NLP-extracted concepts, or broader prototype classes across all phecode categories. Prototype classes with mixed significance patterns exhibit significantly greater intra-class distances (p < 0.0001), indicating the model learned to differentiate clinically meaningful variations within diagnostic categories. The prototypes achieve strong predictive performance across diverse conditions, with AUCs ranging as high as 0.89 for atrial fibrillation to 0.91 for heart failure, while also showing substantial signal for non-cardiac conditions such as sepsis and renal disease. These findings suggest that prototype-based models can support interpretable digital phenotyping from physiologic time-series data, providing transferable intermediate phenotypes that capture clinically meaningful physiologic signatures beyond their original training objectives.","PeriodicalId":34954,"journal":{"name":"Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing","volume":"31 ","pages":"679-693"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12952667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147310782","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