首页 > 最新文献

Computers in biology and medicine最新文献

英文 中文
Modeling for dynamical aspects of smoking abuse with e-cigarette users: Threshold dynamics and optimal control strategies 电子烟使用者吸烟滥用的动态方面建模:阈值动力学和最优控制策略
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-28 DOI: 10.1016/j.compbiomed.2026.111457
Abdullah , Ghaus ur Rahman , Faira Kanwal Janjua , Ravi P. Agarwal , J.F. Gómez-Aguilar
Smoking is one of the leading causes of mortality and morbidity around the globe, and e-cigarette use introduces new challenges to public health concerns. Understanding the connection between traditional smoking, e-cigarette adoption, and cessation dynamics is critical for developing effective tobacco-related harm reduction initiatives. In this paper, we present a compartmental mathematical model that captures the transitions between nonsmokers, smokers, e-cigarette users, and quitters while explicitly integrating relapse and cessation behaviors. In the paradigm, e-cigarettes serve as a harm-reduction transition for current smokers, from which users can either quit entirely or return to smoking. The model is analyzed using threshold dynamics to determine the conditions under which smoking behavior persists or declines in a population, and stability analysis is employed to characterize equilibrium states and identify crucial parameters that influence long-term outcomes. Building on this paradigm, we formulate an optimal-control problem by linking control functions to intervention-sensitive processes such as the transition from smoking to e-cigarette usage, the cessation rate among e-cigarette users, and the relapse rate from vaping to smoking. Following harm-reduction principles, the framework prioritizes reducing explosive smoking while discouraging consistent vaping, provided that doing so does not increase smoking prevalence. This paradigm enables researchers to investigate how policy-relevant levers may alter the trajectory of tobacco use over time; however, the report does not compare specific treatments. The model can be extended with numerical simulations that compare the efficacy of interventions like awareness campaigns, taxation, and cessation programs. Such simulations might also include cost-effectiveness studies to determine how limited public health resources could be best allocated across various initiatives. The proposed paradigm provides a theoretical foundation for embedding public health interventions into the dynamics of smoking and e-cigarette use, allowing policymakers and academics to explore how different strategies affect long-term prevalence and reduction outcomes. The graphs illustrate the difference between uncontrolled baseline dynamics and the implementation of an effective management method, demonstrating how interventions can accelerate smoking prevalence reductions. The findings provide a theoretical basis for evaluating how interventions can influence the trajectories of tobacco/vaping use, without claiming to have identified a single “most effective” policy. Future developments could include comparative simulations and cost-effectiveness assessments to help inform targeted decisions related to public health.
吸烟是全球死亡和发病的主要原因之一,电子烟的使用给公共卫生问题带来了新的挑战。了解传统吸烟、电子烟采用和戒烟动态之间的联系,对于制定有效的减少烟草相关危害举措至关重要。在本文中,我们提出了一个分区数学模型,该模型捕捉了非吸烟者、吸烟者、电子烟使用者和戒烟者之间的过渡,同时明确地整合了复发和戒烟行为。在这种模式下,电子烟是当前吸烟者减少危害的过渡,用户可以完全戒烟,也可以重新吸烟。使用阈值动力学来分析模型,以确定吸烟行为在人群中持续或减少的条件,并使用稳定性分析来表征平衡状态并确定影响长期结果的关键参数。在此范式的基础上,我们通过将控制功能与干预敏感过程(如从吸烟到使用电子烟的过渡、电子烟用户的戒烟率以及从吸电子烟到吸烟的复发率)联系起来,制定了一个最优控制问题。根据减少危害的原则,该框架优先减少爆炸性吸烟,同时不鼓励持续吸电子烟,前提是这样做不会增加吸烟率。这一范式使研究人员能够调查政策相关杠杆如何随着时间的推移改变烟草使用的轨迹;然而,该报告没有比较具体的治疗方法。该模型可以通过数值模拟进行扩展,以比较宣传运动、税收和戒烟计划等干预措施的效果。这种模拟还可能包括成本效益研究,以确定如何在各种举措之间最好地分配有限的公共卫生资源。所提出的范式为将公共卫生干预措施纳入吸烟和电子烟使用的动态提供了理论基础,使政策制定者和学者能够探索不同策略如何影响长期流行和减少结果。这些图表说明了不受控制的基线动态与有效管理方法的实施之间的差异,展示了干预措施如何能够加速降低吸烟率。这些发现为评估干预措施如何影响烟草/电子烟使用轨迹提供了理论基础,但没有声称已经确定了单一的“最有效”政策。未来的发展可包括比较模拟和成本效益评估,以帮助为与公共卫生有关的有针对性的决策提供信息。
{"title":"Modeling for dynamical aspects of smoking abuse with e-cigarette users: Threshold dynamics and optimal control strategies","authors":"Abdullah ,&nbsp;Ghaus ur Rahman ,&nbsp;Faira Kanwal Janjua ,&nbsp;Ravi P. Agarwal ,&nbsp;J.F. Gómez-Aguilar","doi":"10.1016/j.compbiomed.2026.111457","DOIUrl":"10.1016/j.compbiomed.2026.111457","url":null,"abstract":"<div><div>Smoking is one of the leading causes of mortality and morbidity around the globe, and e-cigarette use introduces new challenges to public health concerns. Understanding the connection between traditional smoking, e-cigarette adoption, and cessation dynamics is critical for developing effective tobacco-related harm reduction initiatives. In this paper, we present a compartmental mathematical model that captures the transitions between nonsmokers, smokers, e-cigarette users, and quitters while explicitly integrating relapse and cessation behaviors. In the paradigm, e-cigarettes serve as a harm-reduction transition for current smokers, from which users can either quit entirely or return to smoking. The model is analyzed using threshold dynamics to determine the conditions under which smoking behavior persists or declines in a population, and stability analysis is employed to characterize equilibrium states and identify crucial parameters that influence long-term outcomes. Building on this paradigm, we formulate an optimal-control problem by linking control functions to intervention-sensitive processes such as the transition from smoking to e-cigarette usage, the cessation rate among e-cigarette users, and the relapse rate from vaping to smoking. Following harm-reduction principles, the framework prioritizes reducing explosive smoking while discouraging consistent vaping, provided that doing so does not increase smoking prevalence. This paradigm enables researchers to investigate how policy-relevant levers may alter the trajectory of tobacco use over time; however, the report does not compare specific treatments. The model can be extended with numerical simulations that compare the efficacy of interventions like awareness campaigns, taxation, and cessation programs. Such simulations might also include cost-effectiveness studies to determine how limited public health resources could be best allocated across various initiatives. The proposed paradigm provides a theoretical foundation for embedding public health interventions into the dynamics of smoking and e-cigarette use, allowing policymakers and academics to explore how different strategies affect long-term prevalence and reduction outcomes. The graphs illustrate the difference between uncontrolled baseline dynamics and the implementation of an effective management method, demonstrating how interventions can accelerate smoking prevalence reductions. The findings provide a theoretical basis for evaluating how interventions can influence the trajectories of tobacco/vaping use, without claiming to have identified a single “most effective” policy. Future developments could include comparative simulations and cost-effectiveness assessments to help inform targeted decisions related to public health.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111457"},"PeriodicalIF":6.3,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075230","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
Dementia severity index: A threshold-based approach to classifying dementia levels using resting state EEG 痴呆严重程度指数:一种基于阈值的方法来分类痴呆水平使用静息状态脑电图
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-27 DOI: 10.1016/j.compbiomed.2026.111505
Shivani Ranjan , Robin Badal , Pramod Yadav , Lalan Kumar

Background

Alzheimer’s Disease (AD) and FrontoTemporal Dementia (FTD) are dementia conditions that often overlap clinically, leading to misdiagnoses. Traditional questionnaires are subjective and time-intensive, while neuroimaging is costly and less accessible. EEG-based methods offer a cost-effective alternative but primarily focus on spectral and source analyses, with a limited exploration into quantitative range identification for differentiating dementia states.

Methods

This study presents a threshold-based approach to dementia-level classification using resting-state EEG. In particular, an algorithm is presented for threshold computation followed by Dementia Severity Index (DSI) formulation. Two potential biomarkers for cognitive decline that capture band-specific alterations are explored. These biomarkers form the basis of the DSI, categorizing individuals into AD, FTD, or Healthy Control (HC). The classification performance of the proposed DSI is evaluated comprehensively using multiple machine learning classifiers and subject validation strategies.

Results

The proposed DSI-based approach achieves classification accuracies of 81.62% using kNN. The approach reliability is validated across three diverse EEG datasets and through threshold variation analysis. Furthermore, the relationship between EEG features and cognitive performance is analyzed using Spearman’s correlation. A significant correlation of 0.79 and 0.62 is obtained between predicted and actual MMSE.

Conclusion

The proposed DSI effectively differentiates AD, FTD, and HC, providing a robust threshold-based framework for dementia assessment. It enhances interpretability by assigning quantitative values to dementia states and reduces subjective reliance. This study offers a potential EEG-based biomarker suitable for clinical settings, offering minimal stress to patients during assessments.
阿尔茨海默病(AD)和额颞叶痴呆(FTD)是临床上经常重叠的痴呆疾病,导致误诊。传统的问卷调查是主观的、耗时的,而神经成像既昂贵又不易获得。基于脑电图的方法提供了一种具有成本效益的替代方法,但主要侧重于光谱和源分析,对区分痴呆状态的定量范围识别的探索有限。方法提出了一种基于阈值的静息状态脑电图痴呆水平分类方法。特别是,提出了一种阈值计算算法,然后制定痴呆严重程度指数(DSI)。探索了两个潜在的认知衰退生物标志物,它们可以捕获特定波段的改变。这些生物标志物构成了DSI的基础,将个体分为AD、FTD或健康控制(HC)。使用多个机器学习分类器和主题验证策略对所提出的DSI的分类性能进行了综合评估。结果基于dsi的kNN分类准确率达到81.62%。通过三种不同的EEG数据集和阈值变异分析验证了该方法的可靠性。在此基础上,利用Spearman相关分析了脑电特征与认知能力的关系。预测MMSE与实际MMSE的相关系数分别为0.79和0.62。结论提出的DSI可有效区分AD、FTD和HC,为痴呆评估提供了一个稳健的基于阈值的框架。它通过为痴呆状态分配定量值来增强可解释性,并减少主观依赖。这项研究提供了一种潜在的适合临床环境的基于脑电图的生物标志物,在评估过程中为患者提供最小的压力。
{"title":"Dementia severity index: A threshold-based approach to classifying dementia levels using resting state EEG","authors":"Shivani Ranjan ,&nbsp;Robin Badal ,&nbsp;Pramod Yadav ,&nbsp;Lalan Kumar","doi":"10.1016/j.compbiomed.2026.111505","DOIUrl":"10.1016/j.compbiomed.2026.111505","url":null,"abstract":"<div><h3>Background</h3><div>Alzheimer’s Disease (AD) and FrontoTemporal Dementia (FTD) are dementia conditions that often overlap clinically, leading to misdiagnoses. Traditional questionnaires are subjective and time-intensive, while neuroimaging is costly and less accessible. EEG-based methods offer a cost-effective alternative but primarily focus on spectral and source analyses, with a limited exploration into quantitative range identification for differentiating dementia states.</div></div><div><h3>Methods</h3><div>This study presents a threshold-based approach to dementia-level classification using resting-state EEG. In particular, an algorithm is presented for threshold computation followed by Dementia Severity Index (DSI) formulation. Two potential biomarkers for cognitive decline that capture band-specific alterations are explored. These biomarkers form the basis of the DSI, categorizing individuals into AD, FTD, or Healthy Control (HC). The classification performance of the proposed DSI is evaluated comprehensively using multiple machine learning classifiers and subject validation strategies.</div></div><div><h3>Results</h3><div>The proposed DSI-based approach achieves classification accuracies of 81.62% using kNN. The approach reliability is validated across three diverse EEG datasets and through threshold variation analysis. Furthermore, the relationship between EEG features and cognitive performance is analyzed using Spearman’s correlation. A significant correlation of 0.79 and 0.62 is obtained between predicted and actual MMSE.</div></div><div><h3>Conclusion</h3><div>The proposed DSI effectively differentiates AD, FTD, and HC, providing a robust threshold-based framework for dementia assessment. It enhances interpretability by assigning quantitative values to dementia states and reduces subjective reliance. This study offers a potential EEG-based biomarker suitable for clinical settings, offering minimal stress to patients during assessments.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111505"},"PeriodicalIF":6.3,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075229","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
Gender-based data bias and model fairness evaluation in benchmarked open-access disease prediction datasets 基准开放获取疾病预测数据集中基于性别的数据偏差和模型公平性评估
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-27 DOI: 10.1016/j.compbiomed.2026.111503
Shahadat Uddin , Huan Liang , Haolan Guo
The widespread use of open-access datasets for validating machine learning (ML) models has raised critical concerns about data bias and model fairness, particularly in relation to gender. This study systematically investigates gender-based data bias in disease prediction datasets and evaluates the fairness of ML algorithms trained on them. A total of 74 datasets were selected from Kaggle and the UCI Machine Learning Repository, based on the inclusion of gender as a feature and classification labels. Data bias was quantified using Earth Mover's Distance to measure disparities in class-wise gender distributions, with statistical significance assessed via bootstrapping. Fairness was evaluated across seven ML algorithms (Decision Tree, Random Forest, Logistic Regression, Artificial Neural Networks, Support Vector Machine, K-Nearest Neighbours, and Naïve Bayes) using k-fold cross-validation and statistical tests. Two fairness definitions, Equalised Odds and Treatment Equality, were applied. Results showed that 35 datasets exhibited gender-based data bias, disproportionately affecting females. Heart disease datasets had the highest prevalence of data bias, while the lung cancer and mental health datasets were found to be bias-free. Fairness outcomes varied significantly across algorithms, with Decision Tree showing the fewest issues and Logistic Regression the most. Bias-free datasets consistently produced fewer fairness concerns, with statistically significant differences (p < 0.01) across all algorithm groups. These findings highlight the importance of addressing gender-based data bias and selecting appropriate algorithms to improve fairness in ML applications. The study highlights the importance of addressing gender-based data bias in enhancing model fairness. It contributes to the development of equitable AI systems, thereby supporting data-driven decision-making in healthcare.
广泛使用开放获取数据集来验证机器学习(ML)模型,引发了对数据偏差和模型公平性的严重担忧,特别是在性别方面。本研究系统地调查了疾病预测数据集中基于性别的数据偏差,并评估了在这些数据集上训练的ML算法的公平性。基于性别作为特征和分类标签,从Kaggle和UCI机器学习存储库中总共选择了74个数据集。使用Earth Mover's Distance来量化数据偏差,以衡量班级性别分布的差异,并通过自举评估统计显著性。通过k-fold交叉验证和统计检验,评估了七种机器学习算法(决策树、随机森林、逻辑回归、人工神经网络、支持向量机、k近邻和Naïve贝叶斯)的公平性。采用了两个公平定义,即均等赔率和待遇平等。结果显示,35个数据集存在基于性别的数据偏差,对女性的影响不成比例。心脏病数据集的数据偏倚发生率最高,而肺癌和心理健康数据集则没有偏倚。不同算法的公平性结果差异很大,决策树显示的问题最少,逻辑回归显示的问题最多。无偏差数据集始终产生较少的公平性问题,在所有算法组中具有统计学显著差异(p < 0.01)。这些发现强调了解决基于性别的数据偏见和选择适当算法以提高机器学习应用公平性的重要性。该研究强调了解决基于性别的数据偏见在提高模型公平性方面的重要性。它有助于开发公平的人工智能系统,从而支持医疗保健领域的数据驱动决策。
{"title":"Gender-based data bias and model fairness evaluation in benchmarked open-access disease prediction datasets","authors":"Shahadat Uddin ,&nbsp;Huan Liang ,&nbsp;Haolan Guo","doi":"10.1016/j.compbiomed.2026.111503","DOIUrl":"10.1016/j.compbiomed.2026.111503","url":null,"abstract":"<div><div>The widespread use of open-access datasets for validating machine learning (ML) models has raised critical concerns about data bias and model fairness, particularly in relation to gender. This study systematically investigates gender-based data bias in disease prediction datasets and evaluates the fairness of ML algorithms trained on them. A total of 74 datasets were selected from Kaggle and the UCI Machine Learning Repository, based on the inclusion of gender as a feature and classification labels. Data bias was quantified using Earth Mover's Distance to measure disparities in class-wise gender distributions, with statistical significance assessed via bootstrapping. Fairness was evaluated across seven ML algorithms (Decision Tree, Random Forest, Logistic Regression, Artificial Neural Networks, Support Vector Machine, K-Nearest Neighbours, and Naïve Bayes) using k-fold cross-validation and statistical tests. Two fairness definitions, Equalised Odds and Treatment Equality, were applied. Results showed that 35 datasets exhibited gender-based data bias, disproportionately affecting females. Heart disease datasets had the highest prevalence of data bias, while the lung cancer and mental health datasets were found to be bias-free. Fairness outcomes varied significantly across algorithms, with Decision Tree showing the fewest issues and Logistic Regression the most. Bias-free datasets consistently produced fewer fairness concerns, with statistically significant differences (p &lt; 0.01) across all algorithm groups. These findings highlight the importance of addressing gender-based data bias and selecting appropriate algorithms to improve fairness in ML applications. The study highlights the importance of addressing gender-based data bias in enhancing model fairness. It contributes to the development of equitable AI systems, thereby supporting data-driven decision-making in healthcare.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111503"},"PeriodicalIF":6.3,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075228","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
Peptide-nanoparticle platforms for antisense therapeutics: A coarse-grained modeling approach to brain delivery 用于反义治疗的肽-纳米粒子平台:脑传递的粗粒度建模方法。
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-25 DOI: 10.1016/j.compbiomed.2026.111479
Burcu Yesildag Uner , Alper Demir , Pingkun Zhou , Ekim Z. Taskiran , Tsjerk Wassenaar
Traumatic brain injury (TBI) is a leading cause of long-term neurological deficits, often resulting in complex, unresolved molecular and cellular dysfunctions. Among these, gene–circuit disruptions—particularly those affecting neuroinflammation, oxidative stress, and mitochondrial dynamics—have emerged as critical mediators of post-traumatic neuropathology. In this study, we utilized artificial intelligence (AI)-driven proteomics and RNA sequence integration to map altered signaling pathways following TBI. Computational predictions identified specific gene–circuit nodes susceptible to therapeutic intervention, including redox-sensitive mitochondrial regulators and genes involved in the neuroimmune interface. Importantly, although our analyses are derived from rodent models, the conserved signaling pathways and regulatory circuits identified here provide a translational window with strong relevance to human TBI pathophysiology, thereby bridging preclinical findings with potential therapeutic application. Based on these insights, we designed a suite of responsive nanoparticle formulations optimized in silico for targeted delivery to dysregulated brain regions. These carriers incorporated ligands targeting disrupted circuits and incorporated redox-sensitive release mechanisms. Our platform demonstrates the feasibility of a closed-loop, data-guided strategy that integrates AI-based gene network profiling with rational nanocarrier design. This approach provides a scalable framework for precision neurotherapeutics, particularly for complex disorders such as TBI where conventional monotherapies have proven inadequate.
创伤性脑损伤(TBI)是长期神经功能障碍的主要原因,通常导致复杂的、未解决的分子和细胞功能障碍。其中,基因回路紊乱——尤其是那些影响神经炎症、氧化应激和线粒体动力学的紊乱——已经成为创伤后神经病理学的重要媒介。在这项研究中,我们利用人工智能(AI)驱动的蛋白质组学和RNA序列整合来绘制TBI后改变的信号通路。计算预测确定了易受治疗干预影响的特定基因回路节点,包括氧化还原敏感的线粒体调节因子和参与神经免疫界面的基因。重要的是,尽管我们的分析来自啮齿类动物模型,但这里确定的保守信号通路和调控回路提供了一个与人类TBI病理生理学密切相关的翻译窗口,从而将临床前研究结果与潜在的治疗应用联系起来。基于这些见解,我们设计了一套反应灵敏的纳米颗粒配方,用于定向递送到失调的大脑区域。这些载体结合了靶向破坏电路的配体,并结合了氧化还原敏感释放机制。我们的平台证明了一种闭环、数据引导策略的可行性,该策略将基于人工智能的基因网络分析与合理的纳米载体设计相结合。这种方法为精确的神经治疗提供了一个可扩展的框架,特别是对于复杂的疾病,如创伤性脑损伤,传统的单一疗法已被证明是不够的。
{"title":"Peptide-nanoparticle platforms for antisense therapeutics: A coarse-grained modeling approach to brain delivery","authors":"Burcu Yesildag Uner ,&nbsp;Alper Demir ,&nbsp;Pingkun Zhou ,&nbsp;Ekim Z. Taskiran ,&nbsp;Tsjerk Wassenaar","doi":"10.1016/j.compbiomed.2026.111479","DOIUrl":"10.1016/j.compbiomed.2026.111479","url":null,"abstract":"<div><div>Traumatic brain injury (TBI) is a leading cause of long-term neurological deficits, often resulting in complex, unresolved molecular and cellular dysfunctions. Among these, gene–circuit disruptions—particularly those affecting neuroinflammation, oxidative stress, and mitochondrial dynamics—have emerged as critical mediators of post-traumatic neuropathology. In this study, we utilized artificial intelligence (AI)-driven proteomics and RNA sequence integration to map altered signaling pathways following TBI. Computational predictions identified specific gene–circuit nodes susceptible to therapeutic intervention, including redox-sensitive mitochondrial regulators and genes involved in the neuroimmune interface. Importantly, although our analyses are derived from rodent models, the conserved signaling pathways and regulatory circuits identified here provide a translational window with strong relevance to human TBI pathophysiology, thereby bridging preclinical findings with potential therapeutic application. Based on these insights, we designed a suite of responsive nanoparticle formulations optimized in silico for targeted delivery to dysregulated brain regions. These carriers incorporated ligands targeting disrupted circuits and incorporated redox-sensitive release mechanisms. Our platform demonstrates the feasibility of a closed-loop, data-guided strategy that integrates AI-based gene network profiling with rational nanocarrier design. This approach provides a scalable framework for precision neurotherapeutics, particularly for complex disorders such as TBI where conventional monotherapies have proven inadequate.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111479"},"PeriodicalIF":6.3,"publicationDate":"2026-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146046221","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
Reconstructing in-vitro and in-vivo signals and parameters in networks of elastic vessels using physics-informed neural networks 利用物理信息神经网络重建弹性血管网络中的体外和体内信号和参数
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-22 DOI: 10.1016/j.compbiomed.2026.111472
J. Orera, J. Mairal, L. Sánchez-Fuster, J. Murillo
The reconstruction of waveforms and hidden parameters is crucial for the physical modeling of steady and transient flows in networks of elastic vessels (arteries), where many mechanical properties are not directly measurable. This work investigates the potential of Physics-Informed Neural Networks (PINNs) to address the challenge of reconstructing pressure and flow signals and inferring parameters from experimental data. We incorporate the zero-dimensional (0D) system of coupled differential equations that describe flow in elastic vessels into the neural network, which we call 0D-PINN. We evaluate our methodology with several test cases representing different dynamical systems, including an experimental mock arterial network with 37 silicone vessels replicating the human arterial system, as well as a clinical case based on in-vivo MRI data from a healthy adult’s thoracic aorta. It is shown that coupling 0D models with Physics-Informed Neural Networks (PINNs) enables the recovery of parameters and waveforms from experimental in-vitro or in-vivo data.
波形和隐藏参数的重建对于弹性血管(动脉)网络中稳态和瞬态流动的物理建模至关重要,其中许多力学特性无法直接测量。本研究探讨了物理信息神经网络(pinn)的潜力,以解决重建压力和流量信号以及从实验数据推断参数的挑战。我们将描述弹性血管流动的零维耦合微分方程系统纳入神经网络,我们称之为0D- pinn。我们用几个代表不同动力系统的测试案例来评估我们的方法,包括一个由37个硅胶血管复制人类动脉系统的实验性模拟动脉网络,以及一个基于健康成人胸主动脉活体MRI数据的临床病例。研究表明,将0D模型与物理信息神经网络(pinn)耦合,可以从实验的体外或体内数据中恢复参数和波形。
{"title":"Reconstructing in-vitro and in-vivo signals and parameters in networks of elastic vessels using physics-informed neural networks","authors":"J. Orera,&nbsp;J. Mairal,&nbsp;L. Sánchez-Fuster,&nbsp;J. Murillo","doi":"10.1016/j.compbiomed.2026.111472","DOIUrl":"10.1016/j.compbiomed.2026.111472","url":null,"abstract":"<div><div>The reconstruction of waveforms and hidden parameters is crucial for the physical modeling of steady and transient flows in networks of elastic vessels (arteries), where many mechanical properties are not directly measurable. This work investigates the potential of Physics-Informed Neural Networks (PINNs) to address the challenge of reconstructing pressure and flow signals and inferring parameters from experimental data. We incorporate the zero-dimensional (0D) system of coupled differential equations that describe flow in elastic vessels into the neural network, which we call 0D-PINN. We evaluate our methodology with several test cases representing different dynamical systems, including an experimental mock arterial network with 37 silicone vessels replicating the human arterial system, as well as a clinical case based on in-vivo MRI data from a healthy adult’s thoracic aorta. It is shown that coupling 0D models with Physics-Informed Neural Networks (PINNs) enables the recovery of parameters and waveforms from experimental in-vitro or in-vivo data.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111472"},"PeriodicalIF":6.3,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036224","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 neural network-guided identification and biological evaluation of potential AKT1 inhibitors for triple-negative breast cancer 图神经网络引导下三阴性乳腺癌潜在AKT1抑制剂的鉴定和生物学评价
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-22 DOI: 10.1016/j.compbiomed.2026.111481
Ravishankar Jaiswal , Girdhar Bhati , Santosh Shukla , Shakil Ahmed , Mohammad Imran Siddiqi
Triple-negative breast cancer (TNBC) presents a significant therapeutic challenge due to its aggressive behavior and lack of targeted therapies. The PI3K/AKT/mTOR signaling pathway, particularly AKT1, is frequently dysregulated in TNBC, driving disease progression. Despite extensive research, many clinically evaluated AKT1 inhibitors have encountered challenges related to both efficacy and tolerability, highlighting the need for novel therapeutics. Here, we employed graph neural networks (GNNs) for molecular graph-based prediction of potential AKT1 inhibitors. Six GNN architectures, including attention-based (AttentiveFP, GATv2Conv, TransformerConv) and non-attention-based (GCNConv, GINConv, GraphSAGE) models were trained and benchmarked against traditional machine learning (ML) methods using random and scaffold-based data splits. To enhance predictive relevance and model generalizability, we integrated phenotypic screening data from breast cancer (BC) cell lines alongside AKT1 bioassay data to capture broader pathway effects. Screening the Maybridge chemical library, we identified 9 novel scaffold compounds through consensus hit selection, molecular docking, and novelty filtration. Enzymatic validation confirmed 4 early-stage AKT1 inhibitors with low-micromolar potency (IC50 down to 2.5 μM). Explainable AI analyses using Integrated Gradients and Captum saliency maps highlighted key structural features driving AKT1 inhibition, providing interpretable structure-activity relationship (SAR) insights. Scaffold diversity analysis further confirmed that the validated hits occupy chemical space distinct from known AKT1 inhibitors. Overall, this study presents an interpretable AI-driven discovery framework that identifies novel AKT1 inhibitor scaffolds and provides a validated starting point for hit-to-lead optimization in TNBC drug discovery.
三阴性乳腺癌(TNBC)由于其侵袭性行为和缺乏靶向治疗而提出了重大的治疗挑战。PI3K/AKT/mTOR信号通路,特别是AKT1,在TNBC中经常失调,导致疾病进展。尽管进行了广泛的研究,但许多临床评估的AKT1抑制剂在疗效和耐受性方面都遇到了挑战,这突出了对新治疗方法的需求。在这里,我们使用图神经网络(gnn)进行基于分子图的潜在AKT1抑制剂预测。六种GNN架构,包括基于注意力的(AttentiveFP, GATv2Conv, TransformerConv)和非基于注意力的(GCNConv, GINConv, GraphSAGE)模型,使用随机和基于脚手架的数据分割对传统机器学习(ML)方法进行了训练和基准测试。为了提高预测相关性和模型的普遍性,我们将乳腺癌(BC)细胞系的表型筛选数据与AKT1生物测定数据结合起来,以捕获更广泛的途径效应。筛选Maybridge化学文库,通过一致命中选择、分子对接和新颖性过滤,我们鉴定出9种新的支架化合物。酶法验证证实4种早期AKT1抑制剂具有低微摩尔效价(IC50低至2.5 μM)。使用集成梯度和Captum显著性图的可解释AI分析突出了驱动AKT1抑制的关键结构特征,提供了可解释的结构-活性关系(SAR)见解。支架多样性分析进一步证实,验证的hit占据了与已知AKT1抑制剂不同的化学空间。总的来说,本研究提出了一个可解释的人工智能驱动的发现框架,该框架确定了新的AKT1抑制剂支架,并为TNBC药物发现的hit- lead优化提供了一个有效的起点。
{"title":"Graph neural network-guided identification and biological evaluation of potential AKT1 inhibitors for triple-negative breast cancer","authors":"Ravishankar Jaiswal ,&nbsp;Girdhar Bhati ,&nbsp;Santosh Shukla ,&nbsp;Shakil Ahmed ,&nbsp;Mohammad Imran Siddiqi","doi":"10.1016/j.compbiomed.2026.111481","DOIUrl":"10.1016/j.compbiomed.2026.111481","url":null,"abstract":"<div><div>Triple-negative breast cancer (TNBC) presents a significant therapeutic challenge due to its aggressive behavior and lack of targeted therapies. The PI3K/AKT/mTOR signaling pathway, particularly AKT1, is frequently dysregulated in TNBC, driving disease progression. Despite extensive research, many clinically evaluated AKT1 inhibitors have encountered challenges related to both efficacy and tolerability, highlighting the need for novel therapeutics. Here, we employed graph neural networks (GNNs) for molecular graph-based prediction of potential AKT1 inhibitors. Six GNN architectures, including attention-based (AttentiveFP, GATv2Conv, TransformerConv) and non-attention-based (GCNConv, GINConv, GraphSAGE) models were trained and benchmarked against traditional machine learning (ML) methods using random and scaffold-based data splits. To enhance predictive relevance and model generalizability, we integrated phenotypic screening data from breast cancer (BC) cell lines alongside AKT1 bioassay data to capture broader pathway effects. Screening the Maybridge chemical library, we identified 9 novel scaffold compounds through consensus hit selection, molecular docking, and novelty filtration. Enzymatic validation confirmed 4 early-stage AKT1 inhibitors with low-micromolar potency (IC<sub>50</sub> down to 2.5 μM). Explainable AI analyses using Integrated Gradients and Captum saliency maps highlighted key structural features driving AKT1 inhibition, providing interpretable structure-activity relationship (SAR) insights. Scaffold diversity analysis further confirmed that the validated hits occupy chemical space distinct from known AKT1 inhibitors. Overall, this study presents an interpretable AI-driven discovery framework that identifies novel AKT1 inhibitor scaffolds and provides a validated starting point for hit-to-lead optimization in TNBC drug discovery.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111481"},"PeriodicalIF":6.3,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036157","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
HybridDeepSynergy: A hybrid deep learning model integrating CNN, LSTM, and attention mechanisms for cancer drug synergy prediction HybridDeepSynergy:一个集成CNN、LSTM和注意机制的混合深度学习模型,用于癌症药物协同作用预测。
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-21 DOI: 10.1016/j.compbiomed.2026.111471
Sajid Naveed , Mujtaba Husnain , Najah Alsubaie
A variety of AI-based approaches have been employed to analyze complex genomic datasets. Predicting the synergy of drug combinations is a critical step toward optimizing cancer treatment by identifying the most effective drug pairs. This study presents HybridDeepSynergy, a novel hybrid deep learning model that integrates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Transformer attention mechanisms to predict drug synergy across diverse drug combinations and cancer cell lines. The model is designed to enhance precision medicine and cancer treatment outcomes.
HybridDeepSynergy leverages CNNs to capture local feature interactions, LSTMs to model sequential dependencies, and attention mechanisms to extract long-range relationships within the data. The model was trained and evaluated on a comprehensive dataset containing numerous drug combinations, using five established synergy scoring models: Bliss Independence (BLISS), Zero Interaction Potency (ZIP), Loewe Additivity (LOEWE), Highest Single Agent (HSA), and General Synergy (S).
Our model demonstrated superior performance compared to existing approaches, achieving a lower Root Mean Squared Error (RMSE = 3.911) and Mean Absolute Error (MAE = 2.922), along with higher coefficients of determination (R2 = 0.953), Pearson correlation (0.917), and Spearman correlation (0.886). These results confirm its predictive efficiency and consistency across multiple synergy scoring models. Furthermore, the incorporation of attention mechanisms provides interpretability by highlighting significant features associated with drug resistance.
Future work will focus on incorporating additional cancer datasets, enhancing model predictive capabilities, and validating the approach in clinical settings to support personalized medicine. The findings suggest that HybridDeepSynergy has the potential to substantially improve treatment strategies for cancer and may be applicable to other disease contexts.
各种基于人工智能的方法已被用于分析复杂的基因组数据集。预测药物组合的协同作用是通过确定最有效的药物对来优化癌症治疗的关键一步。本研究提出了一种新型混合深度学习模型HybridDeepSynergy,该模型集成了卷积神经网络(cnn)、长短期记忆(LSTM)和变压器注意机制,用于预测不同药物组合和癌细胞系之间的药物协同作用。该模型旨在提高精准医疗和癌症治疗效果。HybridDeepSynergy利用cnn捕获局部特征交互,lstm建模顺序依赖关系,以及注意机制提取数据中的远程关系。该模型在包含多种药物组合的综合数据集上进行训练和评估,使用五种已建立的协同评分模型:Bliss Independence (Bliss)、Zero Interaction Potency (ZIP)、Loewe Additivity (Loewe)、Highest Single Agent (HSA)和General synergy (S)。与现有方法相比,我们的模型表现出更优越的性能,实现了更低的均方根误差(RMSE = 3.911)和平均绝对误差(MAE = 2.922),以及更高的决定系数(R2 = 0.953), Pearson相关性(0.917)和Spearman相关性(0.886)。这些结果证实了它在多个协同评分模型之间的预测效率和一致性。此外,通过强调与耐药性相关的重要特征,注意机制的结合提供了可解释性。未来的工作将集中于整合更多的癌症数据集,增强模型预测能力,并在临床环境中验证该方法,以支持个性化医疗。研究结果表明,HybridDeepSynergy具有显著改善癌症治疗策略的潜力,并可能适用于其他疾病。
{"title":"HybridDeepSynergy: A hybrid deep learning model integrating CNN, LSTM, and attention mechanisms for cancer drug synergy prediction","authors":"Sajid Naveed ,&nbsp;Mujtaba Husnain ,&nbsp;Najah Alsubaie","doi":"10.1016/j.compbiomed.2026.111471","DOIUrl":"10.1016/j.compbiomed.2026.111471","url":null,"abstract":"<div><div>A variety of AI-based approaches have been employed to analyze complex genomic datasets. Predicting the synergy of drug combinations is a critical step toward optimizing cancer treatment by identifying the most effective drug pairs. This study presents HybridDeepSynergy, a novel hybrid deep learning model that integrates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Transformer attention mechanisms to predict drug synergy across diverse drug combinations and cancer cell lines. The model is designed to enhance precision medicine and cancer treatment outcomes.</div><div>HybridDeepSynergy leverages CNNs to capture local feature interactions, LSTMs to model sequential dependencies, and attention mechanisms to extract long-range relationships within the data. The model was trained and evaluated on a comprehensive dataset containing numerous drug combinations, using five established synergy scoring models: Bliss Independence (BLISS), Zero Interaction Potency (ZIP), Loewe Additivity (LOEWE), Highest Single Agent (HSA), and General Synergy (S).</div><div>Our model demonstrated superior performance compared to existing approaches, achieving a lower Root Mean Squared Error (RMSE = 3.911) and Mean Absolute Error (MAE = 2.922), along with higher coefficients of determination (<span><math><msup><mi>R</mi><mn>2</mn></msup></math></span> = 0.953), Pearson correlation (0.917), and Spearman correlation (0.886). These results confirm its predictive efficiency and consistency across multiple synergy scoring models. Furthermore, the incorporation of attention mechanisms provides interpretability by highlighting significant features associated with drug resistance.</div><div>Future work will focus on incorporating additional cancer datasets, enhancing model predictive capabilities, and validating the approach in clinical settings to support personalized medicine. The findings suggest that HybridDeepSynergy has the potential to substantially improve treatment strategies for cancer and may be applicable to other disease contexts.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111471"},"PeriodicalIF":6.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146028663","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
MS-CoTF: Multi-scale chain-of-thought fusion for interpretable biological reasoning with large language models MS-CoTF:基于大型语言模型的可解释生物推理的多尺度思维链融合。
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-21 DOI: 10.1016/j.compbiomed.2026.111467
Zeyuan Song , Xiao-Cong Zhen
Large language models (LLMs) have demonstrated impressive proficiency in various science and engineering applications. However, due to the innate multi-scale property of biological systems, existing LLMs face severe limitations in capturing hierarchical relationships and context-dependent interactions across molecular, cellular, tissue, and systemic levels. These models often lack the architectural mechanisms needed to reason effectively across different biological scales, resulting in reduced accuracy and limited interpretability when applied to complex tasks. Here, we introduce a novel framework named multi-scale chain-of-thought fusion (MS-CoTF), which fuses reasoning at molecular, cellular, tissue, and system scales to enhance accuracy and interpretability when solving biological tasks. Through adaptive reasoning depth control, multi-scale integration, bi-directional flow and dynamic fusion strategies, our MS-CoTF model effectively processes queries of varying complexity, enabling scalable and interpretable reasoning across multiple biological levels. Ablation studies demonstrate that these components function synergistically to enhance model accuracy while simultaneously providing biologically meaningful insights. Furthermore, our MS-CoTF model consistently outperforms state-of-the-art reasoning models by 10–15% across three benchmark problems and two case studies in terms of accuracy, expert ratings, and the capacity to produce reasonable inference chains. Technically, MS-CoTF orchestrates a frozen biomedical LLM backbone with trainable cross-scale modules, employing a precise definition of per-step chain-of-thought (CoT) construction and linking. To ensure rigorous evaluation, we implement an explicit dataset splitting protocol (entity-disjoint and temporal) and utilize the Reasoning Coherence Score strictly as a post-hoc metric to ensure fair comparisons. We further validate the framework through extended baselines, including structure-conditioned and multimodal biomedical LLMs, alongside detailed human evaluation protocols and hallucination stress tests.
大型语言模型(llm)在各种科学和工程应用中表现出令人印象深刻的熟练程度。然而,由于生物系统固有的多尺度特性,现有的llm在捕获跨分子、细胞、组织和系统水平的层次关系和上下文依赖的相互作用方面面临严重的限制。这些模型通常缺乏跨不同生物尺度进行有效推理所需的体系结构机制,导致在应用于复杂任务时准确性降低,可解释性有限。在这里,我们介绍了一个名为多尺度思维链融合(MS-CoTF)的新框架,它融合了分子、细胞、组织和系统尺度的推理,以提高解决生物任务时的准确性和可解释性。通过自适应推理深度控制、多尺度集成、双向流和动态融合策略,我们的MS-CoTF模型有效地处理不同复杂性的查询,实现跨多个生物水平的可扩展和可解释推理。消融研究表明,这些成分协同作用,提高了模型的准确性,同时提供了生物学上有意义的见解。此外,我们的MS-CoTF模型在三个基准问题和两个案例研究中,在准确性、专家评级和产生合理推理链的能力方面,始终比最先进的推理模型高出10-15%。从技术上讲,MS-CoTF编排了一个冷冻的生物医学法学硕士主干,具有可训练的跨尺度模块,采用了每一步思维链(CoT)构建和链接的精确定义。为了确保严格的评估,我们实现了一个明确的数据集分割协议(实体不相交和时间),并严格利用推理一致性评分作为事后指标,以确保公平的比较。我们通过扩展基线进一步验证该框架,包括结构条件和多模态生物医学法学硕士,以及详细的人体评估协议和幻觉压力测试。
{"title":"MS-CoTF: Multi-scale chain-of-thought fusion for interpretable biological reasoning with large language models","authors":"Zeyuan Song ,&nbsp;Xiao-Cong Zhen","doi":"10.1016/j.compbiomed.2026.111467","DOIUrl":"10.1016/j.compbiomed.2026.111467","url":null,"abstract":"<div><div>Large language models (LLMs) have demonstrated impressive proficiency in various science and engineering applications. However, due to the innate multi-scale property of biological systems, existing LLMs face severe limitations in capturing hierarchical relationships and context-dependent interactions across molecular, cellular, tissue, and systemic levels. These models often lack the architectural mechanisms needed to reason effectively across different biological scales, resulting in reduced accuracy and limited interpretability when applied to complex tasks. Here, we introduce a novel framework named multi-scale chain-of-thought fusion (MS-CoTF), which fuses reasoning at molecular, cellular, tissue, and system scales to enhance accuracy and interpretability when solving biological tasks. Through adaptive reasoning depth control, multi-scale integration, bi-directional flow and dynamic fusion strategies, our MS-CoTF model effectively processes queries of varying complexity, enabling scalable and interpretable reasoning across multiple biological levels. Ablation studies demonstrate that these components function synergistically to enhance model accuracy while simultaneously providing biologically meaningful insights. Furthermore, our MS-CoTF model consistently outperforms state-of-the-art reasoning models by 10–15% across three benchmark problems and two case studies in terms of accuracy, expert ratings, and the capacity to produce reasonable inference chains. Technically, MS-CoTF orchestrates a frozen biomedical LLM backbone with trainable cross-scale modules, employing a precise definition of per-step chain-of-thought (CoT) construction and linking. To ensure rigorous evaluation, we implement an explicit dataset splitting protocol (entity-disjoint and temporal) and utilize the Reasoning Coherence Score strictly as a post-hoc metric to ensure fair comparisons. We further validate the framework through extended baselines, including structure-conditioned and multimodal biomedical LLMs, alongside detailed human evaluation protocols and hallucination stress tests.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111467"},"PeriodicalIF":6.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146028623","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 hybrid hierarchical transformer model for ECG classification and age prediction 一种用于心电分类和年龄预测的混合层次变压器模型。
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-21 DOI: 10.1016/j.compbiomed.2026.111462
Pedro Dutenhefner , Turi Rezende , José Geraldo Fernandes , Diogo Tuler , Gabriela M.M. Paixão , Gisele Pappa , Antønio Ribeiro , Wagner Meira Jr.
Electrocardiograms (ECGs) play a crucial role in cardiovascular healthcare, requiring effective analytical models. ECG analysis is inherently hierarchical, involving multiple temporal scales from individual waveforms to intervals within heartbeats, and finally to the distances between heartbeats. Convolutional Neural Networks (CNNs) have demonstrated strong performance in ECG classification tasks due to their inductive bias toward local connectivity and translation invariance. In other domains, Transformers have emerged as powerful models for capturing long-range dependencies. This paper introduces HiT-NeXt, a hybrid hierarchical model designed to capture both local morphological patterns and global temporal dependencies by combining CNNs with transformer blocks featuring restricted attention windows. The model incorporates ConvNeXt-based convolutional layers to extract local features and perform patch merging, enabling hierarchical representation learning. Transformer blocks are constrained with local attention windows and leverage relative contextual positional encoding to incorporate positional information effectively into embeddings, enhancing robustness to translations in ECG signal patterns. Experimental results demonstrate that HiT-NeXt outperforms state-of-the-art methods on tasks including ECG abnormality classification and cardiological age prediction, achieving superior performance compared to both existing models and cardiologist evaluations.2
心电图(ECGs)在心血管保健中起着至关重要的作用,需要有效的分析模型。ECG分析本质上是分层的,涉及从单个波形到心跳间隔的多个时间尺度,最后到心跳之间的距离。卷积神经网络(cnn)由于其对局部连通性和平移不变性的归纳偏见,在心电分类任务中表现出了很强的性能。在其他领域,变形金刚已经成为捕获远程依赖关系的强大模型。本文介绍了HiT-NeXt,这是一种混合层次模型,旨在通过将cnn与具有限制注意窗口的变形块相结合来捕获局部形态模式和全局时间依赖性。该模型结合了基于convnext的卷积层来提取局部特征并执行补丁合并,从而实现分层表示学习。变压器块受到局部注意窗口的约束,并利用相对上下文位置编码将位置信息有效地嵌入到嵌入中,增强了对心电信号模式转换的鲁棒性。实验结果表明,HiT-NeXt在ECG异常分类和心脏年龄预测等任务上优于最先进的方法,与现有模型和心脏病专家评估相比,都取得了更好的性能。
{"title":"A hybrid hierarchical transformer model for ECG classification and age prediction","authors":"Pedro Dutenhefner ,&nbsp;Turi Rezende ,&nbsp;José Geraldo Fernandes ,&nbsp;Diogo Tuler ,&nbsp;Gabriela M.M. Paixão ,&nbsp;Gisele Pappa ,&nbsp;Antønio Ribeiro ,&nbsp;Wagner Meira Jr.","doi":"10.1016/j.compbiomed.2026.111462","DOIUrl":"10.1016/j.compbiomed.2026.111462","url":null,"abstract":"<div><div>Electrocardiograms (ECGs) play a crucial role in cardiovascular healthcare, requiring effective analytical models. ECG analysis is inherently hierarchical, involving multiple temporal scales from individual waveforms to intervals within heartbeats, and finally to the distances between heartbeats. Convolutional Neural Networks (CNNs) have demonstrated strong performance in ECG classification tasks due to their inductive bias toward local connectivity and translation invariance. In other domains, Transformers have emerged as powerful models for capturing long-range dependencies. This paper introduces HiT-NeXt, a hybrid hierarchical model designed to capture both local morphological patterns and global temporal dependencies by combining CNNs with transformer blocks featuring restricted attention windows. The model incorporates ConvNeXt-based convolutional layers to extract local features and perform patch merging, enabling hierarchical representation learning. Transformer blocks are constrained with local attention windows and leverage relative contextual positional encoding to incorporate positional information effectively into embeddings, enhancing robustness to translations in ECG signal patterns. Experimental results demonstrate that HiT-NeXt outperforms state-of-the-art methods on tasks including ECG abnormality classification and cardiological age prediction, achieving superior performance compared to both existing models and cardiologist evaluations.<span><span><sup>2</sup></span></span></div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111462"},"PeriodicalIF":6.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146028640","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
Research on breast ultrasound images lesion localization and diagnosis based on knowledge-driven and data-driven methods 基于知识驱动和数据驱动方法的乳腺超声图像病灶定位与诊断研究。
IF 6.3 2区 医学 Q1 BIOLOGY Pub Date : 2026-01-20 DOI: 10.1016/j.compbiomed.2026.111465
Jianqiang Li , Lintao Song , Xiaoling Liu , Yiming Liu , Tianbao Ma , Jun Bai , Qing Zhao , Xi Xu
Breast cancer poses the most significant threat to women’s health, yet early detection through screening can markedly reduce mortality. Ultrasound imaging, with its affordability, non-invasiveness, and efficacy in dense breast tissue, has emerged as a crucial tool for early screening. Recent advancements in computer vision have spurred the development of computer-aided diagnostic systems that focus on the automated localization and diagnosis of breast lesions. However, challenges such as speckle noise, blurred boundaries, and low contrast in ultrasound images impede accurate lesion detection. This review examines recent studies on breast ultrasound lesion localization and diagnosis, emphasizing model feature construction. It provides an overview of the task, available datasets, and evaluation metrics, and outlines selection criteria through a comprehensive literature analysis. The review categorizes models into three groups: domain knowledge-driven, data-driven, and hybrid approaches. It also discusses current challenges and future directions, aiming to enhance the accuracy of breast lesion localization and diagnosis.
乳腺癌对妇女健康构成最严重的威胁,但通过筛查及早发现可显著降低死亡率。超声成像以其可负担性、非侵入性和对致密乳腺组织的有效性,已成为早期筛查的重要工具。计算机视觉的最新进展促进了计算机辅助诊断系统的发展,该系统专注于乳房病变的自动定位和诊断。然而,诸如斑点噪声、模糊边界和超声图像对比度低等挑战阻碍了准确的病变检测。本文综述了近年来乳腺超声病灶定位与诊断的研究进展,重点介绍了模型特征的构建。它提供了任务、可用数据集和评估指标的概述,并通过全面的文献分析概述了选择标准。该综述将模型分为三组:领域知识驱动、数据驱动和混合方法。讨论了当前面临的挑战和未来的发展方向,旨在提高乳腺病变定位和诊断的准确性。
{"title":"Research on breast ultrasound images lesion localization and diagnosis based on knowledge-driven and data-driven methods","authors":"Jianqiang Li ,&nbsp;Lintao Song ,&nbsp;Xiaoling Liu ,&nbsp;Yiming Liu ,&nbsp;Tianbao Ma ,&nbsp;Jun Bai ,&nbsp;Qing Zhao ,&nbsp;Xi Xu","doi":"10.1016/j.compbiomed.2026.111465","DOIUrl":"10.1016/j.compbiomed.2026.111465","url":null,"abstract":"<div><div>Breast cancer poses the most significant threat to women’s health, yet early detection through screening can markedly reduce mortality. Ultrasound imaging, with its affordability, non-invasiveness, and efficacy in dense breast tissue, has emerged as a crucial tool for early screening. Recent advancements in computer vision have spurred the development of computer-aided diagnostic systems that focus on the automated localization and diagnosis of breast lesions. However, challenges such as speckle noise, blurred boundaries, and low contrast in ultrasound images impede accurate lesion detection. This review examines recent studies on breast ultrasound lesion localization and diagnosis, emphasizing model feature construction. It provides an overview of the task, available datasets, and evaluation metrics, and outlines selection criteria through a comprehensive literature analysis. The review categorizes models into three groups: domain knowledge-driven, data-driven, and hybrid approaches. It also discusses current challenges and future directions, aiming to enhance the accuracy of breast lesion localization and diagnosis.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111465"},"PeriodicalIF":6.3,"publicationDate":"2026-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146017584","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
期刊
Computers in biology and medicine
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1