Journal of Biomedical Informatics最新文献_第4页

Mamba-enhanced disease semantic knowledge graph for interpretable automatic ICD coding 用于可解释的自动ICD编码的mamba增强疾病语义知识图。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2026-01-01 Epub Date: 2025-12-22 DOI: 10.1016/j.jbi.2025.104973

Pengli Lu , Chao Dong , Jingjin Xue , Fentang Gao

Automatic ICD coding refers to the process of using artificial intelligence methods to automatically extract information related to diseases, symptoms, diagnoses, treatments, and other relevant details from electronic health records, and convert it into codes that comply with the International Classification of Diseases (ICD) standard. Automatic ICD coding technology has been gradually improved with the advancement of deep learning, but in practical deployment, it still faces challenges such as inconsistent semantics, ambiguous labels, and limited interpretability. To address these issues, we propose a novel automatic ICD coding framework MKHCNet (Mamba-Knowledge-HPLA-ContraNorm Network) which integrates unstructured clinical knowledge representation, long-range dependency modeling, and contrastive normalization techniques to enhance coding performance. Specifically, we construct a disease semantic knowledge graph to enrich ICD label representations, employ the Mamba network to capture cross-domain dependencies, apply the ContraNorm module to enhance label separability, and propose the Hierarchical Position Label Attention (HPLA) mechanism to achieve fine-grained, attention-based interpretability. Finally, with the purpose of capturing complex nonlinear relationships more effectively and better adapting to complex patterns in EHR data, FastKAN acts as a classifier and utilizes radial basis function (RBF) for feature transformation. We conducted systematic experiments on the benchmark datasets MIMIC-FULL and MIMIC-50. The experimental results show that MKHCNet improves MaAUC and P

@

8 by 2.1% and 0.3% on MIMIC-FULL respectively compared with the best existing mainstream model. Furthermore, case studies demonstrate that the model is able to effectively identify complex semantic cues and provide strong clinical interpretability.

ICD自动编码是指利用人工智能方法，从电子健康记录中自动提取与疾病、症状、诊断、治疗等相关细节信息，并将其转换为符合国际疾病分类（ICD）标准的代码的过程。随着深度学习的推进，自动ICD编码技术逐渐得到完善，但在实际部署中，仍然面临语义不一致、标签模糊、可解释性有限等挑战。为了解决这些问题，我们提出了一种新的ICD自动编码框架MKHCNet (mamba - knowledge - hpla - contransform Network)，该框架集成了非结构化临床知识表示、远程依赖建模和对比归一化技术来提高编码性能。具体而言，我们构建了疾病语义知识图来丰富ICD标签表示，使用Mamba网络捕获跨领域依赖关系，应用contransform模块增强标签可分离性，并提出了分层位置标签注意（HPLA）机制来实现细粒度的、基于注意的可解释性。最后，为了更有效地捕捉复杂的非线性关系，更好地适应电子病历数据中的复杂模式，FastKAN作为分类器，利用径向基函数（RBF）进行特征转换。我们在基准数据集MIMIC- full和MIMIC 50上进行了系统的实验。实验结果表明，与现有最佳主流模型相比，MKHCNet在MIMIC-FULL上的MaAUC和MaF分别提高了2.2%和0.9%。此外，案例研究表明，该模型能够有效识别复杂的语义线索，并提供强大的临床可解释性。

{"title":"Mamba-enhanced disease semantic knowledge graph for interpretable automatic ICD coding","authors":"Pengli Lu , Chao Dong , Jingjin Xue , Fentang Gao","doi":"10.1016/j.jbi.2025.104973","DOIUrl":"10.1016/j.jbi.2025.104973","url":null,"abstract":"<div><div>Automatic ICD coding refers to the process of using artificial intelligence methods to automatically extract information related to diseases, symptoms, diagnoses, treatments, and other relevant details from electronic health records, and convert it into codes that comply with the International Classification of Diseases (ICD) standard. Automatic ICD coding technology has been gradually improved with the advancement of deep learning, but in practical deployment, it still faces challenges such as inconsistent semantics, ambiguous labels, and limited interpretability. To address these issues, we propose a novel automatic ICD coding framework <strong>MKHCNet</strong> (<strong>M</strong>amba-<strong>K</strong>nowledge-<strong>H</strong>PLA-<strong>C</strong>ontraNorm <strong>Net</strong>work) which integrates unstructured clinical knowledge representation, long-range dependency modeling, and contrastive normalization techniques to enhance coding performance. Specifically, we construct a disease semantic knowledge graph to enrich ICD label representations, employ the Mamba network to capture cross-domain dependencies, apply the ContraNorm module to enhance label separability, and propose the Hierarchical Position Label Attention (HPLA) mechanism to achieve fine-grained, attention-based interpretability. Finally, with the purpose of capturing complex nonlinear relationships more effectively and better adapting to complex patterns in EHR data, FastKAN acts as a classifier and utilizes radial basis function (RBF) for feature transformation. We conducted systematic experiments on the benchmark datasets MIMIC-FULL and MIMIC-50. The experimental results show that MKHCNet improves MaAUC and P<span><math><mi>@</mi></math></span>8 by 2.1% and 0.3% on MIMIC-FULL respectively compared with the best existing mainstream model. Furthermore, case studies demonstrate that the model is able to effectively identify complex semantic cues and provide strong clinical interpretability.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"173 ","pages":"Article 104973"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145827758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CausalGenDiff: Generative causal diffusion bridges scRNA-seq and spatial transcriptomics CausalGenDiff：生成因果扩散连接scRNA-seq和空间转录组学。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2026-01-01 Epub Date: 2025-12-05 DOI: 10.1016/j.jbi.2025.104966

Rabeya Tus Sadia , Md Atik Ahamed , Qiang Cheng

Understanding gene expression within a spatial context requires the effective integration of single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST) data. However, existing approaches often perform suboptimally, with structural similarity typically falling below 60%. We identify the neglect of causal gene relationships as a major limiting factor. To address this, we propose CausalGenDiff, a model that integrates diffusion and autoregressive processes to exploit these underlying causal dependencies. Our approach extends the Causal Attention Transformer originally designed for image generation to handle high-dimensional gene expression data, enabling the capture of gene regulatory mechanisms without relying on predefined relationships. We further incorporate VAE-based pretraining and fine-tuning strategies to enhance performance, supported by thorough ablation studies. Evaluated on 10 tissue datasets, our method consistently outperforms state-of-the-art baselines across four standard metrics, achieving improvements of 5%–32% in Pearson correlation and structural similarity, thereby contributing to both technical advancement and biological insight.

理解空间背景下的基因表达需要单细胞RNA测序（scRNA-seq）和空间转录组学（ST）数据的有效整合。然而，现有的方法往往表现不佳，结构相似性通常低于60%。我们认为忽视因果基因关系是一个主要的限制因素。为了解决这个问题，我们提出了CausalGenDiff，一个集成了扩散和自回归过程的模型，以利用这些潜在的因果关系。我们的方法扩展了最初设计用于图像生成的因果注意转换器，以处理高维基因表达数据，从而能够在不依赖预定义关系的情况下捕获基因调控机制。我们进一步结合基于vae的预训练和微调策略，在彻底消融研究的支持下提高性能。通过对10个组织数据集的评估，我们的方法在四个标准指标上始终优于最先进的基线，在Pearson相关性和结构相似性方面实现了5%-32%的改进，从而为技术进步和生物学洞察力做出了贡献。

{"title":"CausalGenDiff: Generative causal diffusion bridges scRNA-seq and spatial transcriptomics","authors":"Rabeya Tus Sadia , Md Atik Ahamed , Qiang Cheng","doi":"10.1016/j.jbi.2025.104966","DOIUrl":"10.1016/j.jbi.2025.104966","url":null,"abstract":"<div><div>Understanding gene expression within a spatial context requires the effective integration of single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics (ST) data. However, existing approaches often perform suboptimally, with structural similarity typically falling below 60%. We identify the neglect of causal gene relationships as a major limiting factor. To address this, we propose CausalGenDiff, a model that integrates diffusion and autoregressive processes to exploit these underlying causal dependencies. Our approach extends the Causal Attention Transformer originally designed for image generation to handle high-dimensional gene expression data, enabling the capture of gene regulatory mechanisms without relying on predefined relationships. We further incorporate VAE-based pretraining and fine-tuning strategies to enhance performance, supported by thorough ablation studies. Evaluated on 10 tissue datasets, our method consistently outperforms state-of-the-art baselines across four standard metrics, achieving improvements of 5%–32% in Pearson correlation and structural similarity, thereby contributing to both technical advancement and biological insight.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"173 ","pages":"Article 104966"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145700219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Graph-spa: A Spatiotemporal Graph Neural Network based framework for ARDS prediction and interpretability Graph-spa：基于时空图神经网络的ARDS预测和可解释性框架。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2026-01-01 Epub Date: 2025-12-10 DOI: 10.1016/j.jbi.2025.104969

Shashank Yadav , Molly Douglas , Jarrod Mosier , Vignesh Subbian

Objective:

Traditional deep learning models for multivariate time-series data often fall short in capturing long-range temporal dependencies critical for early prediction of the onset of acute respiratory distress syndrome (ARDS). To address this gap, we introduce Graph-spa, a dynamic Spatiotemporal Graph Neural Network (STGNN) based framework that not only improves ARDS prediction by modeling evolving interactions among clinical variables but also enhances interpretability through model-agnostic feature attribution.

Methods:

Graph-spa at its core integrates temporal convolution layers with an STGNN model that dynamically updates the adjacency structure, capturing both local and non-local temporal dependencies across three datasets (HiRID, MIMIC-IV, and eICU). We benchmarked our model against four traditional deep learning models (GRU, LSTM, TCN, Transformer) and an STGNN baseline. To complement the prediction framework, we applied mask-based interpretability approaches to generate feature-time attribution scores. These scores guide a subsequent co-occurrence analysis that identifies clusters of sustained feature activations in the 12-h window preceding ARDS onset.

Results:

Our experiments demonstrate that Graph-spa consistently outperforms the baseline models in both internal and external validations. On the AUC F1–MCC metric, chosen for this imbalanced classification task, Graph-spa achieves 50.02% vs 45.61% on HiRID, 48.52% vs 46.88% on MIMIC-IV, and 46.64% vs 45.41% on eICU-CRD compared with the STGNN baseline. Graph-spa also outperforms recurrent, convolutional, and attention-based models evaluated under identical settings (Wilcoxon signed-rank; Holm-adjusted p-values

<

0.05). The dynamic adjacency enhancement allows the model to capture complex, evolving feature interactions, as evidenced by more diversified connectivity patterns compared to the baseline. In addition, interpretability analysis reveals that sustained abnormalities in potassium levels, along with declining Glasgow Coma Scale scores, form a critical composite risk profile that may serve as an early indicator of ARDS.

Conclusion:

Graph-spa advances dynamic clinical event prediction and also offers significant promise for early detection of organ failure in acute care settings by illustrating an end-to-end approach covering spatiotemporal modeling, interpretability, and discovery of sub-clinical signatures. Because its core modules, dynamic spatiotemporal graph construction, mask-based attribution, and co-occurrence mining, are model-agnostic, the framework can easily be extrapolated to any dynamic classification or regression task in the ICU. The code is available at https://github.com/vsubbian/Graph-spa.

目的：用于多变量时间序列数据的传统深度学习模型在捕获长期时间依赖性方面往往存在不足，这对早期预测急性呼吸窘迫综合征（ARDS）的发作至关重要。为了解决这一差距，我们引入了Graph-spa，这是一个基于动态时空图神经网络（STGNN）的框架，它不仅通过模拟临床变量之间不断变化的相互作用来改善ARDS预测，而且通过模型无关的特征归因提高了可解释性。方法：Graph-spa的核心是将时间卷积层与动态更新邻接结构的STGNN模型集成在一起，捕获三个数据集（HiRID、MIMIC-IV和eICU）的局部和非局部时间依赖性。我们将模型与四种传统深度学习模型（GRU、LSTM、TCN、Transformer）和STGNN基线进行了基准测试。为了补充预测框架，我们应用基于掩码的可解释性方法来生成特征时间归因分数。这些评分指导随后的共发生分析，以确定在ARDS发病前12小时窗口内持续特征激活的集群。结果：我们的实验表明，Graph-spa在内部和外部验证中始终优于基线模型。与STGNN基线相比，在为这种不平衡分类任务选择的AUC F1-MCC指标上，Graph-spa在HiRID上达到50.02%对45.61%，在MIMIC-IV上达到48.52%对46.88%，在eICU-CRD上达到46.64%对45.41%。在相同的设置下，Graph-spa也优于循环、卷积和基于注意力的模型（Wilcoxon符号秩；holm调整的p值< 0.05）。动态邻接增强允许模型捕捉复杂的、不断变化的特征交互，与基线相比，更多样化的连接模式证明了这一点。此外，可解释性分析显示，钾水平的持续异常，以及格拉斯哥昏迷量表评分的下降，形成了一个关键的综合风险特征，可以作为ARDS的早期指标。结论：Graph-spa推进了动态临床事件预测，并通过展示涵盖时空建模、可解释性和亚临床特征发现的端到端方法，为急性护理环境中器官衰竭的早期检测提供了重大希望。由于其核心模块动态时空图构建、基于掩码的属性和共现挖掘是模型不可知的，因此该框架可以很容易地外推到ICU中的任何动态分类或回归任务。代码可在https://github.com/vsubbian/Graph-spa上获得。

{"title":"Graph-spa: A Spatiotemporal Graph Neural Network based framework for ARDS prediction and interpretability","authors":"Shashank Yadav , Molly Douglas , Jarrod Mosier , Vignesh Subbian","doi":"10.1016/j.jbi.2025.104969","DOIUrl":"10.1016/j.jbi.2025.104969","url":null,"abstract":"<div><h3>Objective:</h3><div>Traditional deep learning models for multivariate time-series data often fall short in capturing long-range temporal dependencies critical for early prediction of the onset of acute respiratory distress syndrome (ARDS). To address this gap, we introduce <em>Graph-spa</em>, a dynamic Spatiotemporal Graph Neural Network (STGNN) based framework that not only improves ARDS prediction by modeling evolving interactions among clinical variables but also enhances interpretability through model-agnostic feature attribution.</div></div><div><h3>Methods:</h3><div>Graph-spa at its core integrates temporal convolution layers with an STGNN model that dynamically updates the adjacency structure, capturing both local and non-local temporal dependencies across three datasets (HiRID, MIMIC-IV, and eICU). We benchmarked our model against four traditional deep learning models (GRU, LSTM, TCN, Transformer) and an STGNN baseline. To complement the prediction framework, we applied mask-based interpretability approaches to generate feature-time attribution scores. These scores guide a subsequent co-occurrence analysis that identifies clusters of sustained feature activations in the 12-h window preceding ARDS onset.</div></div><div><h3>Results:</h3><div>Our experiments demonstrate that Graph-spa consistently outperforms the baseline models in both internal and external validations. On the AUC F1–MCC metric, chosen for this imbalanced classification task, Graph-spa achieves 50.02% vs 45.61% on HiRID, 48.52% vs 46.88% on MIMIC-IV, and 46.64% vs 45.41% on eICU-CRD compared with the STGNN baseline. Graph-spa also outperforms recurrent, convolutional, and attention-based models evaluated under identical settings (Wilcoxon signed-rank; Holm-adjusted p-values <span><math><mo><</mo></math></span> 0.05). The dynamic adjacency enhancement allows the model to capture complex, evolving feature interactions, as evidenced by more diversified connectivity patterns compared to the baseline. In addition, interpretability analysis reveals that sustained abnormalities in potassium levels, along with declining Glasgow Coma Scale scores, form a critical composite risk profile that may serve as an early indicator of ARDS.</div></div><div><h3>Conclusion:</h3><div>Graph-spa advances dynamic clinical event prediction and also offers significant promise for early detection of organ failure in acute care settings by illustrating an end-to-end approach covering spatiotemporal modeling, interpretability, and discovery of sub-clinical signatures. Because its core modules, dynamic spatiotemporal graph construction, mask-based attribution, and co-occurrence mining, are model-agnostic, the framework can easily be extrapolated to any dynamic classification or regression task in the ICU. The code is available at <span><span>https://github.com/vsubbian/Graph-spa</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"173 ","pages":"Article 104969"},"PeriodicalIF":4.5,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145742755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reviewer Acknowledgement 2025. 审稿人致谢2025。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2025-12-25 DOI: 10.1016/j.jbi.2025.104974

引用次数: 0

A method for characterizing disease progression from acute kidney injury to chronic kidney disease 一种表征从急性肾损伤到慢性肾病的疾病进展的方法。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2025-12-01 Epub Date: 2025-11-12 DOI: 10.1016/j.jbi.2025.104956

Yilu Fang , Jordan G. Nestor , Casey N. Ta , Jerard Z. Kneifati-Hayek , Chunhua Weng

Objective

Patients with acute kidney injury (AKI) are at high risk of developing chronic kidney disease (CKD), but identifying those at greatest risk remains challenging. We used electronic health record (EHR) data to dynamically track AKI patients’ clinical evolution and characterize AKI-to-CKD progression.

Methods

Post-AKI clinical states were identified by clustering patient vectors derived from longitudinal medical codes and creatinine measurements. Transition probabilities between states and progression to CKD were estimated using multi-state modeling. After identifying common post-AKI trajectories, CKD risk factors in AKI subpopulations were identified through survival analysis.

Results

Of 20,699 patients with AKI at admission, 3,491 (17 %) developed CKD. We identified fifteen distinct post-AKI states, each with different probabilities of CKD development. Most patients (75 %, n = 15,607) remained in a single state or made only one transition during the study period. Both established (e.g., AKI severity, diabetes, hypertension, heart failure, liver disease) and novel CKD risk factors, with their impact varying across these clinical states.

Conclusion

This study demonstrates a data-driven approach for identifying high-risk AKI patients, supporting the development of decision-support tools for early CKD detection and intervention.

目的：急性肾损伤（AKI）患者发展为慢性肾脏疾病（CKD）的风险很高，但识别那些风险最大的患者仍然具有挑战性。我们使用电子健康记录（EHR）数据来动态跟踪AKI患者的临床演变并表征AKI到ckd的进展。方法：通过纵向医学编码和肌酐测量得出的聚类患者载体来识别aki后的临床状态。使用多状态模型估计状态之间的转移概率和CKD的进展。在确定了AKI后常见的发展轨迹后，通过生存分析确定了AKI亚群中CKD的危险因素。结果：入院时患有AKI的20,699例患者中，3,491例（17% %）发展为CKD。我们确定了15种不同的aki后状态，每种状态都有不同的CKD发展概率。大多数患者（75% %,n = 15,607）在研究期间保持单一状态或仅进行一次转换。既有（如AKI严重程度、糖尿病、高血压、心力衰竭、肝脏疾病）和新的CKD危险因素，其影响在这些临床状态中各不相同。结论：本研究展示了一种数据驱动的方法来识别高风险AKI患者，支持早期CKD检测和干预决策支持工具的开发。

{"title":"A method for characterizing disease progression from acute kidney injury to chronic kidney disease","authors":"Yilu Fang , Jordan G. Nestor , Casey N. Ta , Jerard Z. Kneifati-Hayek , Chunhua Weng","doi":"10.1016/j.jbi.2025.104956","DOIUrl":"10.1016/j.jbi.2025.104956","url":null,"abstract":"<div><h3>Objective</h3><div>Patients with acute kidney injury (AKI) are at high risk of developing chronic kidney disease (CKD), but identifying those at greatest risk remains challenging. We used electronic health record (EHR) data to dynamically track AKI patients’ clinical evolution and characterize AKI-to-CKD progression.</div></div><div><h3>Methods</h3><div>Post-AKI clinical states were identified by clustering patient vectors derived from longitudinal medical codes and creatinine measurements. Transition probabilities between states and progression to CKD were estimated using multi-state modeling. After identifying common post-AKI trajectories, CKD risk factors in AKI subpopulations were identified through survival analysis.</div></div><div><h3>Results</h3><div>Of 20,699 patients with AKI at admission, 3,491 (17 %) developed CKD. We identified fifteen distinct post-AKI states, each with different probabilities of CKD development. Most patients (75 %, n = 15,607) remained in a single state or made only one transition during the study period. Both established (e.g., AKI severity, diabetes, hypertension, heart failure, liver disease) and novel CKD risk factors, with their impact varying across these clinical states.</div></div><div><h3>Conclusion</h3><div>This study demonstrates a data-driven approach for identifying high-risk AKI patients, supporting the development of decision-support tools for early CKD detection and intervention.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"172 ","pages":"Article 104956"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145523424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A joint learning framework for analyzing data from national geriatric centralized networks: A new toolbox deciphering real-world complexity 用于分析国家老年集中网络数据的联合学习框架：一个破译现实世界复杂性的新工具箱。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2025-12-01 Epub Date: 2025-11-11 DOI: 10.1016/j.jbi.2025.104954

Biyi Shen , Yilin Zhang , Thomas G. Travison , Michelle Shardell , Rozalina G. McCoy , Takumi Saegusa , Jason Falvey , Chixiang Chen

Objective:

We propose JLNet, along with a companion R software package, as a systematic joint learning framework for analyzing data from national geriatric centralized networks, such as Medicare Claims. JLNet addresses key challenges in real-world, large-scale healthcare datasets, including hospital-level clustering and heterogeneity, patient-level variability from high-dimensional covariates, and losses to follow-up, while promoting easy implementation to ultimately support decision-making.

Methods:

JLNet proceeds in three steps: (1) fit a dynamic propensity score model to handle patient loss to follow-up; (2) fit a projection-based regularized regression to identify predictive patient-level features while adjusting for hospital-level confounding; and (3) perform hospital-level clustering using transformed residuals, enabling downstream analyses without sharing raw data. We applied JLNet to Medicare claims data to study post-fracture recovery among older adults with Alzheimer’s disease and related dementias (ADRD) following a hip fracture (2010–2018), and evaluated its performance via numerical experiments.

Results:

JLNet identified clinically meaningful patient-level variables (e.g., age, weight loss, peripheral vascular disease, etc.) and distinct hospital clusters associated with variation in post-discharge recovery, measured by days at home, among patients with ADRD. Numerical experiments showed that JLNet outperformed existing approaches in variable selection and hospital clustering in the setting involving high-dimensional covariates and unmeasured hospital-level confounding.

Discussion and conclusion:

JLNet is a scalable, interpretable framework for analyzing centralized health data. It enhances identification of high-risk subcohorts and hospital clusters, supporting more precise resource allocation and personalized care strategies for high-risk older adults. Findings also inform the design of tailored interventions in real-world settings.

目的：我们提出JLNet，以及配套的R软件包，作为一个系统的联合学习框架，用于分析来自国家老年集中网络的数据，如医疗保险索赔。JLNet解决了现实世界中大规模医疗保健数据集中的关键挑战，包括医院级聚类和异质性、来自高维协变量的患者级可变性以及随访损失，同时促进易于实施，最终支持决策。方法：JLNet分三步进行：(1)拟合动态倾向评分模型，处理患者失访问题；(2)拟合基于预测的正则化回归，以识别预测性患者水平特征，同时调整医院水平的混杂因素；(3)使用转换后的残差进行医院级聚类，在不共享原始数据的情况下进行下游分析。我们将JLNet应用于医疗保险索赔数据，研究2010-2018年髋部骨折后老年阿尔茨海默病及相关痴呆（ADRD）患者骨折后的康复情况，并通过数值实验评估其性能。结果：JLNet确定了有临床意义的患者水平变量（如年龄、体重减轻、周围血管疾病等），以及与ADRD患者出院后恢复变化相关的不同医院集群，以在家天数衡量。数值实验表明，在涉及高维协变量和未测量的医院水平混杂的情况下，JLNet在变量选择和医院聚类方面优于现有方法。讨论和结论：JLNet是一个可扩展的、可解释的框架，用于分析集中的健康数据。它增强了对高风险亚群和医院群的识别，支持对高风险老年人更精确的资源分配和个性化护理策略。研究结果还为在现实环境中设计量身定制的干预措施提供了信息。

{"title":"A joint learning framework for analyzing data from national geriatric centralized networks: A new toolbox deciphering real-world complexity","authors":"Biyi Shen , Yilin Zhang , Thomas G. Travison , Michelle Shardell , Rozalina G. McCoy , Takumi Saegusa , Jason Falvey , Chixiang Chen","doi":"10.1016/j.jbi.2025.104954","DOIUrl":"10.1016/j.jbi.2025.104954","url":null,"abstract":"<div><h3>Objective:</h3><div>We propose JLNet, along with a companion R software package, as a systematic joint learning framework for analyzing data from national geriatric centralized networks, such as Medicare Claims. JLNet addresses key challenges in real-world, large-scale healthcare datasets, including hospital-level clustering and heterogeneity, patient-level variability from high-dimensional covariates, and losses to follow-up, while promoting easy implementation to ultimately support decision-making.</div></div><div><h3>Methods:</h3><div>JLNet proceeds in three steps: (1) fit a dynamic propensity score model to handle patient loss to follow-up; (2) fit a projection-based regularized regression to identify predictive patient-level features while adjusting for hospital-level confounding; and (3) perform hospital-level clustering using transformed residuals, enabling downstream analyses without sharing raw data. We applied JLNet to Medicare claims data to study post-fracture recovery among older adults with Alzheimer’s disease and related dementias (ADRD) following a hip fracture (2010–2018), and evaluated its performance via numerical experiments.</div></div><div><h3>Results:</h3><div>JLNet identified clinically meaningful patient-level variables (e.g., age, weight loss, peripheral vascular disease, etc.) and distinct hospital clusters associated with variation in post-discharge recovery, measured by days at home, among patients with ADRD. Numerical experiments showed that JLNet outperformed existing approaches in variable selection and hospital clustering in the setting involving high-dimensional covariates and unmeasured hospital-level confounding.</div></div><div><h3>Discussion and conclusion:</h3><div>JLNet is a scalable, interpretable framework for analyzing centralized health data. It enhances identification of high-risk subcohorts and hospital clusters, supporting more precise resource allocation and personalized care strategies for high-risk older adults. Findings also inform the design of tailored interventions in real-world settings.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"172 ","pages":"Article 104954"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145513020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Vision-language model-based semantic-guided imaging biomarker for lung nodule malignancy prediction 基于视觉语言模型的语义引导的肺结节恶性肿瘤预测成像生物标志物

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2025-12-01 Epub Date: 2025-10-27 DOI: 10.1016/j.jbi.2025.104947

Luoting Zhuang , Seyed Mohammad Hossein Tabatabaei , Ramin Salehi-Rad , Linh M. Tran , Denise R. Aberle , Ashley E. Prosper , William Hsu

Objective:

Machine learning models have utilized semantic features, deep features, or both to assess lung nodule malignancy. However, their reliance on manual annotation during inference, limited interpretability, and sensitivity to imaging variations hinder their application in real-world clinical settings. Thus, this research aims to integrate semantic features derived from radiologists’ assessments of nodules, guiding the model to learn clinically relevant, robust, and explainable imaging features for predicting lung cancer.

Methods:

We obtained 938 low-dose CT scans from the National Lung Screening Trial (NLST) with 1,261 nodules and semantic features. Additionally, the Lung Image Database Consortium dataset contains 1,018 CT scans, with 2,625 lesions annotated for nodule characteristics. Three external datasets were obtained from UCLA Health, the LUNGx Challenge, and the Duke Lung Cancer Screening. For imaging input, we obtained 2D nodule slices in nine directions from

50 \times 50 \times 50 mm

nodule crop. We converted structured semantic features into sentences using Gemini. We fine-tuned a pretrained Contrastive Language-Image Pretraining (CLIP) model with a parameter-efficient fine-tuning approach to align imaging and semantic text features and predict the one-year lung cancer diagnosis.

Results:

Our model outperformed the state-of-the-art (SOTA) models in the NLST test set with an AUROC of 0.901 and AUPRC of 0.776. It also showed robust results in external datasets. Using CLIP, we also obtained predictions on semantic features through zero-shot inference, such as nodule margin (AUROC: 0.807), nodule consistency (0.812), and pleural attachment (0.840).

Conclusion:

By incorporating semantic features into the vision-language model, our approach surpasses the SOTA models in predicting lung cancer from CT scans collected from diverse clinical settings. It provides explainable outputs, aiding clinicians in comprehending the underlying meaning of model predictions. The code is available at https://github.com/luotingzhuang/CLIP_nodule.

目的：机器学习模型利用语义特征、深度特征或两者同时使用来评估肺结节恶性肿瘤。然而，它们在推理过程中依赖于手动注释，有限的可解释性和对成像变化的敏感性阻碍了它们在现实世界临床环境中的应用。因此，本研究旨在整合来自放射科医生对结节评估的语义特征，指导模型学习临床相关的、稳健的、可解释的影像学特征，以预测肺癌。方法：我们从国家肺筛查试验（NLST）中获得938个低剂量CT扫描，其中有1261个结节和语义特征。此外，肺图像数据库联盟数据集包含1,018个CT扫描，其中2,625个病变注释了结节特征。从加州大学洛杉矶分校健康中心、LUNGx挑战和杜克大学肺癌筛查获得了三个外部数据集。作为成像输入，我们从50×50×50mm结节作物中获得了9个方向的二维结节切片。我们使用Gemini将结构化语义特征转换为句子。我们对预训练的对比语言-图像预训练（CLIP）模型进行了微调，采用参数有效的微调方法来对齐成像和语义文本特征，并预测一年的肺癌诊断。结果：我们的模型在NLST测试集上的AUROC为0.901，AUPRC为0.776，优于最先进（SOTA）模型。它还在外部数据集中显示了稳健的结果。使用CLIP，我们还通过零射推理获得了语义特征的预测，如结节边缘（AUROC: 0.807）、结节一致性（0.812）和胸膜附着（0.840）。结论：通过将语义特征整合到视觉语言模型中，我们的方法在从不同临床环境收集的CT扫描中预测肺癌方面优于SOTA模型。它提供了可解释的输出，帮助临床医生理解模型预测的潜在含义。代码可在https://github.com/luotingzhuang/CLIP_nodule上获得。

{"title":"Vision-language model-based semantic-guided imaging biomarker for lung nodule malignancy prediction","authors":"Luoting Zhuang , Seyed Mohammad Hossein Tabatabaei , Ramin Salehi-Rad , Linh M. Tran , Denise R. Aberle , Ashley E. Prosper , William Hsu","doi":"10.1016/j.jbi.2025.104947","DOIUrl":"10.1016/j.jbi.2025.104947","url":null,"abstract":"<div><h3>Objective:</h3><div>Machine learning models have utilized semantic features, deep features, or both to assess lung nodule malignancy. However, their reliance on manual annotation during inference, limited interpretability, and sensitivity to imaging variations hinder their application in real-world clinical settings. Thus, this research aims to integrate semantic features derived from radiologists’ assessments of nodules, guiding the model to learn clinically relevant, robust, and explainable imaging features for predicting lung cancer.</div></div><div><h3>Methods:</h3><div>We obtained 938 low-dose CT scans from the National Lung Screening Trial (NLST) with 1,261 nodules and semantic features. Additionally, the Lung Image Database Consortium dataset contains 1,018 CT scans, with 2,625 lesions annotated for nodule characteristics. Three external datasets were obtained from UCLA Health, the LUNGx Challenge, and the Duke Lung Cancer Screening. For imaging input, we obtained 2D nodule slices in nine directions from <span><math><mrow><mn>50</mn><mo>×</mo><mn>50</mn><mo>×</mo><mn>50</mn><mspace></mspace><mi>mm</mi></mrow></math></span> nodule crop. We converted structured semantic features into sentences using Gemini. We fine-tuned a pretrained Contrastive Language-Image Pretraining (CLIP) model with a parameter-efficient fine-tuning approach to align imaging and semantic text features and predict the one-year lung cancer diagnosis.</div></div><div><h3>Results:</h3><div>Our model outperformed the state-of-the-art (SOTA) models in the NLST test set with an AUROC of 0.901 and AUPRC of 0.776. It also showed robust results in external datasets. Using CLIP, we also obtained predictions on semantic features through zero-shot inference, such as nodule margin (AUROC: 0.807), nodule consistency (0.812), and pleural attachment (0.840).</div></div><div><h3>Conclusion:</h3><div>By incorporating semantic features into the vision-language model, our approach surpasses the SOTA models in predicting lung cancer from CT scans collected from diverse clinical settings. It provides explainable outputs, aiding clinicians in comprehending the underlying meaning of model predictions. The code is available at <span><span>https://github.com/luotingzhuang/CLIP_nodule</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"172 ","pages":"Article 104947"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145398392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-scale cancer driver gene prediction by flexible data selection and network topology guidance 基于灵活数据选择和网络拓扑引导的多尺度癌症驱动基因预测。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2025-12-01 Epub Date: 2025-11-21 DOI: 10.1016/j.jbi.2025.104961

Jian Liu , Yingzan Ren , Guodong Xiao , Ponian Li , Chuanqi Sun , Jiaxin Chen , Fubin Ma , Rui Gao , Jia Mi , Haiyan Cong , Mingyi Wang , Yusen Zhang

Objective

Efficient and comprehensive prioritization of cancer driver genes across individual patients, cancer cohorts, and pan–cancer is crucial for advancing cancer diagnosis and treatment. The existing methods are effective, but they seem to have reached a plateau in accuracy enhancement and lack broad–scale joint analysis, flexibility in adapting to cancer and interpretability.

Methods

Here, we introduce GenMorw, a heterogeneous network framework that discovers a novel association score between patients and their mutated genes, enabling the estimation of the likelihood of the mutated genes acting as drivers in patients. GenMorw flexibly integrates or fully utilize collected mutation, gene/miRNA expression, methylation data and PPI networks to classify patient groups based on data–specific characteristics and identify potential drivers at the individual, cancer and pan–cancer levels.

Results

GenMorw outperforms existing algorithms with an average cohort AUC improvement of 17.66% and higher overall accuracy by a cumulative ranking strategy in patient–gene heterogeneous networks. Except for AUC evaluation, other various comparative strategies consistently demonstrate the superior performance of GenMorw across multiple cancers, outperforming other algorithms. Some uniquely predicted genes, such as ANK3, CENPF, and COL7A1, which are absent from standard databases and not identified by other methods, were validated as highly cancer–related through literature review and survival analysis. Based on GenMorw–derived heterogeneous networks, the strongly connected components and cliques, which are extracted from them, capture most of the predicted or known driver genes to help predict driver genes.

Conclusion

We conclude that GenMorw, with its novel gene–patient score mechanism, offers a significant advance in cancer driver gene discovery by capturing both population-wide and patient-specific network signals, thereby improving predictive power and enabling deeper insights into cancer heterogeneity.

目的：在个体患者、癌症群体和泛癌症中高效、全面地确定癌症驱动基因的优先级对于推进癌症的诊断和治疗至关重要。现有的方法是有效的，但它们似乎在准确性提高方面已经达到了一个平台，缺乏广泛的联合分析，适应癌症的灵活性和可解释性。方法：在这里，我们引入了GenMorw，这是一个异构网络框架，它发现了患者与其突变基因之间的一种新的关联评分，从而能够估计突变基因在患者中作为驱动因素的可能性。GenMorw灵活整合或充分利用收集到的突变、基因/miRNA表达、甲基化数据和PPI网络，根据数据特异性特征对患者群体进行分类，并在个体、癌症和泛癌症水平上识别潜在的驱动因素。结果：GenMorw优于现有算法，在患者-基因异质性网络中，通过累积排序策略，平均队列AUC提高了17.66%，总体准确率更高。除AUC评估外，其他各种比较策略一致显示GenMorw在多种癌症中的优越性能，优于其他算法。一些独特的预测基因，如ANK3、CENPF和COL7A1，没有在标准数据库中，也没有通过其他方法识别，通过文献回顾和生存分析被证实为与癌症高度相关。基于genmorw衍生的异构网络，从中提取的强连接成分和派系捕获了大多数预测或已知的驱动基因，以帮助预测驱动基因。结论：我们得出的结论是，GenMorw通过其新颖的基因-患者评分机制，通过捕获人群范围和患者特异性网络信号，在癌症驱动基因发现方面取得了重大进展，从而提高了预测能力，并能够更深入地了解癌症异质性。

{"title":"Multi-scale cancer driver gene prediction by flexible data selection and network topology guidance","authors":"Jian Liu , Yingzan Ren , Guodong Xiao , Ponian Li , Chuanqi Sun , Jiaxin Chen , Fubin Ma , Rui Gao , Jia Mi , Haiyan Cong , Mingyi Wang , Yusen Zhang","doi":"10.1016/j.jbi.2025.104961","DOIUrl":"10.1016/j.jbi.2025.104961","url":null,"abstract":"<div><h3>Objective</h3><div>Efficient and comprehensive prioritization of cancer driver genes across individual patients, cancer cohorts, and pan–cancer is crucial for advancing cancer diagnosis and treatment. The existing methods are effective, but they seem to have reached a plateau in accuracy enhancement and lack broad–scale joint analysis, flexibility in adapting to cancer and interpretability.</div></div><div><h3>Methods</h3><div>Here, we introduce GenMorw, a heterogeneous network framework that discovers a novel association score between patients and their mutated genes, enabling the estimation of the likelihood of the mutated genes acting as drivers in patients. GenMorw flexibly integrates or fully utilize collected mutation, gene/miRNA expression, methylation data and PPI networks to classify patient groups based on data–specific characteristics and identify potential drivers at the individual, cancer and pan–cancer levels.</div></div><div><h3>Results</h3><div>GenMorw outperforms existing algorithms with an average cohort AUC improvement of 17.66% and higher overall accuracy by a cumulative ranking strategy in patient–gene heterogeneous networks. Except for AUC evaluation, other various comparative strategies consistently demonstrate the superior performance of GenMorw across multiple cancers, outperforming other algorithms. Some uniquely predicted genes, such as ANK3, CENPF, and COL7A1, which are absent from standard databases and not identified by other methods, were validated as highly cancer–related through literature review and survival analysis. Based on GenMorw–derived heterogeneous networks, the strongly connected components and cliques, which are extracted from them, capture most of the predicted or known driver genes to help predict driver genes.</div></div><div><h3>Conclusion</h3><div>We conclude that GenMorw, with its novel gene–patient score mechanism, offers a significant advance in cancer driver gene discovery by capturing both population-wide and patient-specific network signals, thereby improving predictive power and enabling deeper insights into cancer heterogeneity.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"172 ","pages":"Article 104961"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145587610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrigendum to “Drug repositioning with metapath guidance and adaptive negative sampling enhancement” [J. Biomed. Inform. 171 (2025) 104916] “药物再定位与路径引导和自适应负采样增强”[J]。生物医学。通报。171(2025)104916]。

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2025-12-01 Epub Date: 2025-11-18 DOI: 10.1016/j.jbi.2025.104953

Yaozheng Zhou , Xingyu Shi , Lingfeng Wang , Jin Xu , Demin Li , Congzhou Chen

引用次数: 0

Study on multimodal spatially-constrained contrastive learning for knee osteoarthritis severity grading 多模态空间约束对比学习在膝关节骨关节炎严重程度分级中的应用研究

IF 4.5 2区医学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Journal of Biomedical Informatics

Pub Date : 2025-12-01 Epub Date: 2025-11-25 DOI: 10.1016/j.jbi.2025.104962

YuHao Wu , Zhijie Xiang , Yuzhe Tan , Jiayue Hu , Desheng Chen , Jing Zhao , Haicheng Wei

To address the limitations of single-modal feature coverage and class distribution imbalance in knee osteoarthritis (KOA) classification, this study proposes a Multimodal Spatial-constraint Contrastive Learning (MSCL) model. First, dynamic and static plantar pressure data and human keypoint trajectories are synchronously acquired. The model first feeds dynamic plantar pressure and keypoint data into a multimodal spatial–temporal fusion branch, where graph convolutional networks and Transformers extract spatial–temporal representations of human keypoints and dynamic pressure patterns respectively, followed by Cross Attention fusion. Subsequently, static plantar pressure is processed through a pyramid CNN architecture to generate coarse-grained spatial constraint vectors, which serve as anatomical priors to regularize the fused representations. Finally, a contrastive learning framework is integrated to establish explicit mapping between the enhanced representations and Kellgren–Lawrence (KL) grading system, enabling precise KOA severity stratification. Experimental results demonstrate that the MSCL model achieves 0.94 macro-average accuracy in KL grading, with 7% improvement in F1-scores for imbalanced categories with limited samples. This work establishes a novel paradigm for accurate KOA assessment through multimodal gait analysis.

针对膝关节骨关节炎（KOA）分类中单模态特征覆盖和类别分布不平衡的局限性，本研究提出了一个多模态空间约束对比学习（MSCL）模型。首先，同步获取动态、静态足底压力数据和人体关键点轨迹；该模型首先将动态足底压力和关键点数据输入到多模态时空融合分支中，其中图卷积网络和transformer分别提取人体关键点和动态压力模式的时空表示，然后进行交叉注意融合。随后，通过金字塔CNN架构对静态足底压力进行处理，生成粗粒度空间约束向量，作为正则化融合表征的解剖先验。最后，集成了一个对比学习框架，在增强表征和Kellgren-Lawrence （KL）分级系统之间建立显式映射，从而实现精确的KOA严重程度分层。实验结果表明，MSCL模型在KL分级中达到了0.94的宏观平均准确率，在有限样本的不平衡类别中f1分数提高了7%。本研究为通过多模态步态分析准确评估KOA建立了一个新的范式。

{"title":"Study on multimodal spatially-constrained contrastive learning for knee osteoarthritis severity grading","authors":"YuHao Wu , Zhijie Xiang , Yuzhe Tan , Jiayue Hu , Desheng Chen , Jing Zhao , Haicheng Wei","doi":"10.1016/j.jbi.2025.104962","DOIUrl":"10.1016/j.jbi.2025.104962","url":null,"abstract":"<div><div>To address the limitations of single-modal feature coverage and class distribution imbalance in knee osteoarthritis (KOA) classification, this study proposes a Multimodal Spatial-constraint Contrastive Learning (MSCL) model. First, dynamic and static plantar pressure data and human keypoint trajectories are synchronously acquired. The model first feeds dynamic plantar pressure and keypoint data into a multimodal spatial–temporal fusion branch, where graph convolutional networks and Transformers extract spatial–temporal representations of human keypoints and dynamic pressure patterns respectively, followed by Cross Attention fusion. Subsequently, static plantar pressure is processed through a pyramid CNN architecture to generate coarse-grained spatial constraint vectors, which serve as anatomical priors to regularize the fused representations. Finally, a contrastive learning framework is integrated to establish explicit mapping between the enhanced representations and Kellgren–Lawrence (KL) grading system, enabling precise KOA severity stratification. Experimental results demonstrate that the MSCL model achieves 0.94 macro-average accuracy in KL grading, with 7% improvement in F1-scores for imbalanced categories with limited samples. This work establishes a novel paradigm for accurate KOA assessment through multimodal gait analysis.</div></div>","PeriodicalId":15263,"journal":{"name":"Journal of Biomedical Informatics","volume":"172 ","pages":"Article 104962"},"PeriodicalIF":4.5,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145615386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0