Smart Health最新文献_第4页

Editorial – Elsevier smart health special issue: Advancing ICT for health, accessibility, and wellbeing 社论-爱思唯尔智能健康特刊：推进ICT促进健康、可及性和福祉

Q2 Health Professions

Smart Health

Pub Date : 2025-04-23 DOI: 10.1016/j.smhl.2025.100580

Achilleas Achilleos , Edwige Pissaloux , George A. Papadopoulos , Ramiro Velazquez

引用次数: 0

Enhancing polyp detection in endoscopy with cross-channel self-attention fusion 跨通道自注意融合增强内镜息肉检测

Q2 Health Professions

Smart Health

Pub Date : 2025-04-17 DOI: 10.1016/j.smhl.2025.100578

Xiaolong Liang , Shuijiao Chen , Linfeng Shu , Dechun Wang , Qilei Chen , Yu Cao , Benyuan Liu , Honggang Zhang , Xiaowei Liu

Colorectal cancer (CRC) poses a significant global health challenge, ranking as a leading cause of cancer-related mortality. Colonoscopy, the most effective means of preventing CRC, is utilized for early detection and removal of precancerous growths. However, while there have been many efforts that utilize deep learning based approaches for automatic polyp detection, false positive rates in polyp detection during colonoscopy remain high due to the diverse characteristics of polyps and the presence of various artifacts. This paper introduces an innovative technique aimed at improving polyp detection accuracy in colonoscopy video frames. The proposed method introduces a novel framework incorporating a cross-channel self-attention fusion unit, aimed at enhancing polyp detection accuracy in endoscopic procedures. The integration of this unit proves to play an important role in refining prediction quality, resulting in more precise detection outcomes in complex medical imaging scenarios. To substantiate the effectiveness of our framework, we create an extensive private dataset comprising complete endoscopy videos, captured from diverse equipment from different manufacturers. This dataset represents realistic and intricate application scenarios, offering an authentic and effective foundation for both training and evaluating our framework. Thorough experiments and ablation studies are conducted to assess the performance of our proposed approach. The results demonstrate that our framework, featuring key technical innovations, significantly reduces false detections and achieves a higher recall rate. This underscores the remarkable effectiveness of our framework in upgrading polyp detection accuracy in real-world endoscopy procedures.

结直肠癌（CRC）是一项重大的全球健康挑战，是癌症相关死亡的主要原因。结肠镜检查是预防结直肠癌最有效的手段，用于早期发现和切除癌前病变。然而，尽管已经有许多利用基于深度学习的方法进行自动息肉检测的努力，但由于息肉的不同特征和各种伪影的存在，结肠镜检查期间息肉检测的假阳性率仍然很高。本文介绍了一种旨在提高结肠镜视频帧息肉检测精度的创新技术。提出的方法引入了一种新的框架，包括跨通道自关注融合单元，旨在提高内镜手术中息肉检测的准确性。事实证明，该单元的集成在提高预测质量方面发挥了重要作用，在复杂的医学成像场景中可以获得更精确的检测结果。为了证实我们框架的有效性，我们创建了一个广泛的私人数据集，包括从不同制造商的不同设备捕获的完整内窥镜视频。该数据集代表了真实而复杂的应用场景，为训练和评估我们的框架提供了真实而有效的基础。进行了彻底的实验和烧蚀研究来评估我们提出的方法的性能。结果表明，我们的框架以关键技术创新为特色，显著减少了误检，实现了更高的召回率。这强调了我们的框架在提高息肉检测准确性在现实世界的内窥镜检查程序显著的有效性。

{"title":"Enhancing polyp detection in endoscopy with cross-channel self-attention fusion","authors":"Xiaolong Liang , Shuijiao Chen , Linfeng Shu , Dechun Wang , Qilei Chen , Yu Cao , Benyuan Liu , Honggang Zhang , Xiaowei Liu","doi":"10.1016/j.smhl.2025.100578","DOIUrl":"10.1016/j.smhl.2025.100578","url":null,"abstract":"<div><div>Colorectal cancer (CRC) poses a significant global health challenge, ranking as a leading cause of cancer-related mortality. Colonoscopy, the most effective means of preventing CRC, is utilized for early detection and removal of precancerous growths. However, while there have been many efforts that utilize deep learning based approaches for automatic polyp detection, false positive rates in polyp detection during colonoscopy remain high due to the diverse characteristics of polyps and the presence of various artifacts. This paper introduces an innovative technique aimed at improving polyp detection accuracy in colonoscopy video frames. The proposed method introduces a novel framework incorporating a cross-channel self-attention fusion unit, aimed at enhancing polyp detection accuracy in endoscopic procedures. The integration of this unit proves to play an important role in refining prediction quality, resulting in more precise detection outcomes in complex medical imaging scenarios. To substantiate the effectiveness of our framework, we create an extensive private dataset comprising complete endoscopy videos, captured from diverse equipment from different manufacturers. This dataset represents realistic and intricate application scenarios, offering an authentic and effective foundation for both training and evaluating our framework. Thorough experiments and ablation studies are conducted to assess the performance of our proposed approach. The results demonstrate that our framework, featuring key technical innovations, significantly reduces false detections and achieves a higher recall rate. This underscores the remarkable effectiveness of our framework in upgrading polyp detection accuracy in real-world endoscopy procedures.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100578"},"PeriodicalIF":0.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Breath as a biomarker: A survey of contact and contactless applications and approaches in respiratory monitoring 呼吸作为一种生物标志物：在呼吸监测中的接触和非接触应用和方法的调查

Q2 Health Professions

Smart Health

Pub Date : 2025-04-16 DOI: 10.1016/j.smhl.2025.100579

Almustapha A. Wakili, Babajide J. Asaju, Woosub Jung

Breath analysis has emerged as a critical tool in health monitoring, offering insights into respiratory function, disease detection, and continuous health assessment. While traditional contact-based methods are reliable, they often pose challenges in comfort and practicality, particularly for long-term monitoring. This survey comprehensively examines contact-based and contactless approaches, emphasizing recent advances in machine learning and deep learning techniques applied to breath analysis. Contactless methods, including Wi-Fi Channel State Information and acoustic sensing, are analyzed for their ability to provide accurate, noninvasive respiratory monitoring.

We explore a broad range of applications, from single-user respiratory rate detection to multi-user scenarios, user identification, and respiratory disease detection. Furthermore, this survey details essential data preprocessing, feature extraction, and classification techniques, offering comparative insights into machine learning/deep learning models suited to each approach. Key challenges like dataset scarcity, multi-user interference, and data privacy are also discussed, along with emerging trends like Explainable AI, federated learning, transfer learning, and hybrid modeling. By synthesizing current methodologies and identifying open research directions, this survey offers a comprehensive framework to guide future innovations in breath analysis, bridging advanced technological capabilities with practical healthcare applications.

呼吸分析已成为健康监测的关键工具，提供了对呼吸功能，疾病检测和持续健康评估的见解。虽然传统的基于接触的方法是可靠的，但它们往往在舒适性和实用性方面存在挑战，特别是对于长期监测。这项调查全面考察了基于接触和非接触的方法，强调了机器学习和深度学习技术应用于呼吸分析的最新进展。非接触式方法，包括Wi-Fi通道状态信息和声学传感，分析了它们提供准确、无创呼吸监测的能力。我们探索了广泛的应用，从单用户呼吸频率检测到多用户场景，用户识别和呼吸疾病检测。此外，本调查详细介绍了基本的数据预处理、特征提取和分类技术，提供了适合每种方法的机器学习/深度学习模型的比较见解。会议还讨论了数据集稀缺性、多用户干扰和数据隐私等关键挑战，以及可解释人工智能、联邦学习、迁移学习和混合建模等新兴趋势。通过综合当前的方法和确定开放的研究方向，本调查提供了一个全面的框架来指导呼吸分析的未来创新，将先进的技术能力与实际的医疗保健应用相结合。

{"title":"Breath as a biomarker: A survey of contact and contactless applications and approaches in respiratory monitoring","authors":"Almustapha A. Wakili, Babajide J. Asaju, Woosub Jung","doi":"10.1016/j.smhl.2025.100579","DOIUrl":"10.1016/j.smhl.2025.100579","url":null,"abstract":"<div><div>Breath analysis has emerged as a critical tool in health monitoring, offering insights into respiratory function, disease detection, and continuous health assessment. While traditional contact-based methods are reliable, they often pose challenges in comfort and practicality, particularly for long-term monitoring. This survey comprehensively examines contact-based and contactless approaches, emphasizing recent advances in machine learning and deep learning techniques applied to breath analysis. Contactless methods, including Wi-Fi Channel State Information and acoustic sensing, are analyzed for their ability to provide accurate, noninvasive respiratory monitoring.</div><div>We explore a broad range of applications, from single-user respiratory rate detection to multi-user scenarios, user identification, and respiratory disease detection. Furthermore, this survey details essential data preprocessing, feature extraction, and classification techniques, offering comparative insights into machine learning/deep learning models suited to each approach. Key challenges like dataset scarcity, multi-user interference, and data privacy are also discussed, along with emerging trends like Explainable AI, federated learning, transfer learning, and hybrid modeling. By synthesizing current methodologies and identifying open research directions, this survey offers a comprehensive framework to guide future innovations in breath analysis, bridging advanced technological capabilities with practical healthcare applications.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100579"},"PeriodicalIF":0.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143863368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Thermal vision: Pioneering non-invasive temperature tracking in congested spaces 热视觉：在拥挤的空间开创性的非侵入性温度跟踪

Q2 Health Professions

Smart Health

Pub Date : 2025-04-03 DOI: 10.1016/j.smhl.2025.100576

Arijit Samal, Haroon R. Lone

Non-invasive temperature monitoring of individuals plays a crucial role in identifying and isolating symptomatic individuals. Temperature monitoring becomes particularly vital in settings characterized by close human proximity, often referred to as dense settings. However, existing research on non-invasive temperature estimation using thermal cameras has predominantly focused on sparse settings. Unfortunately, the risk of disease transmission is significantly higher in dense settings like movie theaters or classrooms. Consequently, there is an urgent need to develop robust temperature estimation methods tailored explicitly for dense settings.

Our study proposes a non-invasive temperature estimation system that combines a thermal camera with an edge device. Our system employs YOLO models for face detection and utilizes a regression framework for temperature estimation. We evaluated the system on a diverse dataset collected in dense and sparse settings. Our proposed face detection model achieves an impressive mAP score of over 94 in both in-dataset and cross-dataset evaluations. Furthermore, the regression framework demonstrates remarkable performance with a mean square error of 0.18 °C and an impressive

R^{2}

score of 0.96. Our experiments’ results highlight the developed system’s effectiveness, positioning it as a promising solution for continuous temperature monitoring in real-world applications. With this paper, we release our dataset and programming code publicly.

个体无创体温监测在识别和隔离有症状个体中起着至关重要的作用。温度监测在人类接近的环境中变得尤为重要，通常被称为密集环境。然而，现有的热像仪非侵入式温度估计研究主要集中在稀疏设置上。不幸的是，在电影院或教室等人口密集的环境中，疾病传播的风险要高得多。因此，迫切需要开发针对密集环境量身定制的鲁棒温度估计方法。本研究提出一种结合热像仪与边缘装置的非侵入式温度估计系统。我们的系统采用YOLO模型进行人脸检测，并利用回归框架进行温度估计。我们在密集和稀疏设置中收集的不同数据集上评估了系统。我们提出的人脸检测模型在数据集内和跨数据集评估中都取得了令人印象深刻的超过94分的mAP分数。此外，回归框架表现出显著的性能，均方误差为0.18°C， R2得分为0.96。我们的实验结果突出了开发系统的有效性，将其定位为实际应用中连续温度监测的有前途的解决方案。在本文中，我们公开发布了我们的数据集和编程代码。

{"title":"Thermal vision: Pioneering non-invasive temperature tracking in congested spaces","authors":"Arijit Samal, Haroon R. Lone","doi":"10.1016/j.smhl.2025.100576","DOIUrl":"10.1016/j.smhl.2025.100576","url":null,"abstract":"<div><div>Non-invasive temperature monitoring of individuals plays a crucial role in identifying and isolating symptomatic individuals. Temperature monitoring becomes particularly vital in settings characterized by close human proximity, often referred to as <em>dense settings</em>. However, existing research on non-invasive temperature estimation using thermal cameras has predominantly focused on <em>sparse settings</em>. Unfortunately, the risk of disease transmission is significantly higher in dense settings like movie theaters or classrooms. Consequently, there is an urgent need to develop robust temperature estimation methods tailored explicitly for dense settings.</div><div>Our study proposes a non-invasive temperature estimation system that combines a thermal camera with an edge device. Our system employs YOLO models for face detection and utilizes a regression framework for temperature estimation. We evaluated the system on a diverse dataset collected in dense and sparse settings. Our proposed face detection model achieves an impressive mAP score of over 94 in both in-dataset and cross-dataset evaluations. Furthermore, the regression framework demonstrates remarkable performance with a mean square error of 0.18 °C and an impressive <span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span> score of 0.96. Our experiments’ results highlight the developed system’s effectiveness, positioning it as a promising solution for continuous temperature monitoring in real-world applications. With this paper, we release our dataset and programming code publicly.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100576"},"PeriodicalIF":0.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Metamorphic Testing for Robustness and Fairness Evaluation of LLM-based Automated ICD Coding Applications 基于llm的自动化ICD编码应用鲁棒性和公平性评估的变质测试

Q2 Health Professions

Smart Health

Pub Date : 2025-04-02 DOI: 10.1016/j.smhl.2025.100564

Guna Sekaran Jaganathan, Indika Kahanda, Upulee Kanewala

Healthcare and medical domain-specific LLMs (BioMed LLMs), such as PubMedBERT and Med-PaLM, are developed and pre-trained on biomedical and clinical text to be used specifically in healthcare and medical applications. The recent popularity of these BioMed LLMs increased the use of LLMs in health and medical applications to perform various critical tasks, including ICD (International Classification of Diseases) coding. For such safety-critical applications, it is vital to focus not just on accuracy but also on other quality attributes such as robustness and fairness. Unfortunately, application developers rarely assess these attributes despite their importance in BioMed LLMs-based applications due to difficulties in defining the expected output. This study uses Metamorphic Testing (MT) to evaluate the robustness and fairness of the BioMed LLM-based automated ICD coding application. We defined several Metamorphic Relations (MRs) to evaluate these quality attributes systematically. Our results using the MIMIC-III dataset reveal several instances where the application performance is significantly impacted due to various simple manipulations that mimic common mistakes in the input clinical notes. Our findings highlight the necessity of rigorous testing for these metrics to ensure the reliable use of BioMed LLMs in healthcare and medical applications. Further, our research provides a comprehensive framework for such evaluations by leveraging MT, which is helpful to the application developers and contributes to developing more reliable and robust biomedical AI systems.

医疗保健和医疗领域特定的llm (BioMed llm)，如PubMedBERT和Med-PaLM，是针对专门用于医疗保健和医疗应用的生物医学和临床文本进行开发和预培训的。最近这些生物医学法学硕士的普及增加了法学硕士在健康和医疗应用中的使用，以执行各种关键任务，包括ICD（国际疾病分类）编码。对于这样的安全关键应用，不仅要关注准确性，还要关注其他质量属性，如鲁棒性和公平性，这一点至关重要。不幸的是，尽管这些属性在基于BioMed llms的应用程序中很重要，但由于难以定义预期输出，应用程序开发人员很少评估这些属性。本研究使用变形测试（MT）来评估BioMed基于llm的自动ICD编码应用程序的鲁棒性和公平性。我们定义了几个变质关系（MRs）来系统地评价这些质量属性。我们使用mimic - iii数据集的结果揭示了几个实例，其中应用程序性能由于模仿输入临床记录中的常见错误的各种简单操作而受到显著影响。我们的研究结果强调了对这些指标进行严格测试的必要性，以确保生物医学法学硕士在医疗保健和医学应用中的可靠使用。此外，我们的研究通过利用机器学习为这种评估提供了一个全面的框架，这有助于应用程序开发人员，并有助于开发更可靠和强大的生物医学人工智能系统。

{"title":"Metamorphic Testing for Robustness and Fairness Evaluation of LLM-based Automated ICD Coding Applications","authors":"Guna Sekaran Jaganathan, Indika Kahanda, Upulee Kanewala","doi":"10.1016/j.smhl.2025.100564","DOIUrl":"10.1016/j.smhl.2025.100564","url":null,"abstract":"<div><div>Healthcare and medical domain-specific LLMs (BioMed LLMs), such as PubMedBERT and Med-PaLM, are developed and pre-trained on biomedical and clinical text to be used specifically in healthcare and medical applications. The recent popularity of these BioMed LLMs increased the use of LLMs in health and medical applications to perform various critical tasks, including ICD (International Classification of Diseases) coding. For such safety-critical applications, it is vital to focus not just on accuracy but also on other quality attributes such as robustness and fairness. Unfortunately, application developers rarely assess these attributes despite their importance in BioMed LLMs-based applications due to difficulties in defining the expected output. This study uses Metamorphic Testing (MT) to evaluate the robustness and fairness of the BioMed LLM-based automated ICD coding application. We defined several Metamorphic Relations (MRs) to evaluate these quality attributes systematically. Our results using the MIMIC-III dataset reveal several instances where the application performance is significantly impacted due to various simple manipulations that mimic common mistakes in the input clinical notes. Our findings highlight the necessity of rigorous testing for these metrics to ensure the reliable use of BioMed LLMs in healthcare and medical applications. Further, our research provides a comprehensive framework for such evaluations by leveraging MT, which is helpful to the application developers and contributes to developing more reliable and robust biomedical AI systems.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100564"},"PeriodicalIF":0.0,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143777368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic fog computing for enhanced LLM execution in medical applications 在医疗应用中增强LLM执行的动态雾计算

Q2 Health Professions

Smart Health

Pub Date : 2025-04-02 DOI: 10.1016/j.smhl.2025.100577

Philipp Zagar , Vishnu Ravi , Lauren Aalami , Stephan Krusche , Oliver Aalami , Paul Schmiedmayer

The ability of large language models (LLMs) to process, interpret, and comprehend vast amounts of heterogeneous data presents a significant opportunity to enhance data-driven care delivery. However, the sensitive nature of protected health information (PHI) raises concerns about data privacy and trust in remote LLM platforms. Additionally, the cost of cloud-based artificial intelligence (AI) services remains a barrier to widespread adoption. To address these challenges, we propose shifting the LLM execution environment from centralized, opaque cloud providers to a decentralized and dynamic fog computing architecture. By running open-weight LLMs in more trusted environments, such as a user’s edge device or a fog layer within a local network, we aim to mitigate the privacy, trust, and financial concerns associated with cloud-based LLMs. We introduce SpeziLLM, an open-source framework designed to streamline LLM execution across multiple layers, facilitating seamless integration into digital health applications. To demonstrate its versatility, we showcase SpeziLLM across six digital health applications, highlighting its broad applicability in various healthcare settings.

大型语言模型（llm）处理、解释和理解大量异构数据的能力为增强数据驱动的医疗服务提供了重要机会。然而，受保护的健康信息（PHI）的敏感性引起了对远程LLM平台的数据隐私和信任的担忧。此外，基于云的人工智能（AI）服务的成本仍然是广泛采用的障碍。为了应对这些挑战，我们建议将LLM执行环境从集中的、不透明的云提供商转移到分散的、动态的雾计算架构。通过在更可信的环境中运行开放权重llm，例如用户的边缘设备或本地网络中的雾层，我们的目标是减轻与基于云的llm相关的隐私、信任和财务问题。我们推出了SpeziLLM，这是一个开源框架，旨在简化LLM跨多层的执行，促进无缝集成到数字健康应用程序中。为了展示其多功能性，我们在六个数字健康应用程序中展示了SpeziLLM，突出了其在各种医疗保健环境中的广泛适用性。

{"title":"Dynamic fog computing for enhanced LLM execution in medical applications","authors":"Philipp Zagar , Vishnu Ravi , Lauren Aalami , Stephan Krusche , Oliver Aalami , Paul Schmiedmayer","doi":"10.1016/j.smhl.2025.100577","DOIUrl":"10.1016/j.smhl.2025.100577","url":null,"abstract":"<div><div>The ability of large language models (LLMs) to process, interpret, and comprehend vast amounts of heterogeneous data presents a significant opportunity to enhance data-driven care delivery. However, the sensitive nature of protected health information (PHI) raises concerns about data privacy and trust in remote LLM platforms. Additionally, the cost of cloud-based artificial intelligence (AI) services remains a barrier to widespread adoption. To address these challenges, we propose shifting the LLM execution environment from centralized, opaque cloud providers to a decentralized and dynamic fog computing architecture. By running open-weight LLMs in more trusted environments, such as a user’s edge device or a fog layer within a local network, we aim to mitigate the privacy, trust, and financial concerns associated with cloud-based LLMs. We introduce <em>SpeziLLM</em>, an open-source framework designed to streamline LLM execution across multiple layers, facilitating seamless integration into digital health applications. To demonstrate its versatility, we showcase <em>SpeziLLM</em> across six digital health applications, highlighting its broad applicability in various healthcare settings.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100577"},"PeriodicalIF":0.0,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Heterogeneous sensing based indoor localization leveraging Bayesian prior estimation 基于贝叶斯先验估计的异质感知室内定位

Q2 Health Professions

Smart Health

Pub Date : 2025-03-28 DOI: 10.1016/j.smhl.2025.100559

Changming Li , Cong Shi , Yingying Chen , David Maluf , Jerome Henry

Indoor wireless localization is critical for enabling a wide range of mobile and IoT applications, such as elder monitoring, robot navigation, and augmented reality/virtual reality. Current wireless localization techniques rely on homogeneous sensing, utilizing single-modality signals like Bluetooth, WiFi, or mmWave, which are susceptible to in-channel interference, multipath distortions, and environmental variability (e.g., device position and furniture placement changes). In this paper, we design a heterogeneous sensing system that combines wireless signals of multiple modalities to enhance indoor localization accuracy. Through building a Bayesian-based framework, we statistically integrate location fingerprints from various sensing modalities to address the nonlinearities introduced by spatial and temporal fluctuations. Our approach is generalizable and can be applied to existing fingerprinting localization methods based on machine learning algorithms, such as K-nearest neighbors (KNN), support vector machines (SVM), and deep learning models, significantly enhancing the localization performance and robustness. Extensive real-world experiments demonstrate that our system reduces the average localization errors from 2.1 m to 1.23 m, even in the presence of complex environmental dynamics.

室内无线定位对于实现广泛的移动和物联网应用至关重要，例如老年人监控，机器人导航和增强现实/虚拟现实。当前的无线定位技术依赖于同质感应，利用蓝牙、WiFi或毫米波等单模态信号，这些信号容易受到信道内干扰、多径失真和环境可变性的影响（例如，设备位置和家具放置位置的变化）。为了提高室内定位精度，本文设计了一种结合多模态无线信号的异构传感系统。通过构建基于贝叶斯的框架，我们统计整合了来自不同传感方式的位置指纹，以解决空间和时间波动带来的非线性问题。我们的方法具有通用性，可以应用于现有的基于机器学习算法的指纹定位方法，如k近邻（KNN）、支持向量机（SVM）和深度学习模型，显著提高了定位性能和鲁棒性。大量的实际实验表明，即使在复杂的环境动态存在下，我们的系统也将平均定位误差从2.1 m降低到1.23 m。

{"title":"Heterogeneous sensing based indoor localization leveraging Bayesian prior estimation","authors":"Changming Li , Cong Shi , Yingying Chen , David Maluf , Jerome Henry","doi":"10.1016/j.smhl.2025.100559","DOIUrl":"10.1016/j.smhl.2025.100559","url":null,"abstract":"<div><div>Indoor wireless localization is critical for enabling a wide range of mobile and IoT applications, such as elder monitoring, robot navigation, and augmented reality/virtual reality. Current wireless localization techniques rely on homogeneous sensing, utilizing single-modality signals like Bluetooth, WiFi, or mmWave, which are susceptible to in-channel interference, multipath distortions, and environmental variability (e.g., device position and furniture placement changes). In this paper, we design a heterogeneous sensing system that combines wireless signals of multiple modalities to enhance indoor localization accuracy. Through building a Bayesian-based framework, we statistically integrate location fingerprints from various sensing modalities to address the nonlinearities introduced by spatial and temporal fluctuations. Our approach is generalizable and can be applied to existing fingerprinting localization methods based on machine learning algorithms, such as K-nearest neighbors (KNN), support vector machines (SVM), and deep learning models, significantly enhancing the localization performance and robustness. Extensive real-world experiments demonstrate that our system reduces the average localization errors from 2.1 m to 1.23 m, even in the presence of complex environmental dynamics.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100559"},"PeriodicalIF":0.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Objective anxiety level classification using unsupervised learning and multimodal physiological signals 目的利用无监督学习和多模态生理信号对焦虑水平进行分类

Q2 Health Professions

Smart Health

Pub Date : 2025-03-27 DOI: 10.1016/j.smhl.2025.100572

Maxine He , Jonathan Cerna , Roshni Mathew , Jiaqi Zhao , Jennifer Zhao , Ethan Espina , Jean L. Clore , Richard B. Sowers , Elizabeth T. Hsiao-Wecksler , Manuel E. Hernandez

Anxiety disorders are prevalent worldwide and can negatively impact physical and mental health. Thus, the timely detection of changes in anxiety levels is crucial for mental health management. This study used multimodal physiological features from wearable devices to classify anxiety levels across various conditions, normalized by individual baseline responses for personalized analysis. Gaussian Mixture Models clustered data into binary or ternary anxiety levels, interpreted by statistics of self-reported scores and physiological features. Clus ters showed modest alignment with State and Trait Inventory scores and physiological markers and demonstrated task-specific variability. Silhouette scores indicated moderate separation (0.40 for two clusters, 0.14 for three clusters). Binary and three-class classifications using unsupervised learning and leave-one-participant-out validation demonstrated effectiveness, with Support Vector Machine achieving highest accuracies (90.9% and 73.3%). This approach enables objective, personalized anxiety monitoring without relying on subjective labeling.

焦虑症在世界范围内普遍存在，并可能对身心健康产生负面影响。因此，及时发现焦虑水平的变化对心理健康管理至关重要。本研究使用来自可穿戴设备的多模态生理特征对不同情况下的焦虑水平进行分类，并通过个体基线反应进行标准化，以进行个性化分析。高斯混合模型将数据聚类为二元或三元焦虑水平，通过自我报告分数和生理特征的统计来解释。聚类与状态和特质量表得分和生理标记适度一致，并表现出特定任务的可变性。廓形评分显示中度分离（两组为0.40，三组为0.14）。使用无监督学习和留一个参与者验证的二分类和三类分类证明了有效性，支持向量机达到了最高的准确率（90.9%和73.3%）。这种方法可以实现客观、个性化的焦虑监测，而不依赖于主观标签。

{"title":"Objective anxiety level classification using unsupervised learning and multimodal physiological signals","authors":"Maxine He , Jonathan Cerna , Roshni Mathew , Jiaqi Zhao , Jennifer Zhao , Ethan Espina , Jean L. Clore , Richard B. Sowers , Elizabeth T. Hsiao-Wecksler , Manuel E. Hernandez","doi":"10.1016/j.smhl.2025.100572","DOIUrl":"10.1016/j.smhl.2025.100572","url":null,"abstract":"<div><div>Anxiety disorders are prevalent worldwide and can negatively impact physical and mental health. Thus, the timely detection of changes in anxiety levels is crucial for mental health management. This study used multimodal physiological features from wearable devices to classify anxiety levels across various conditions, normalized by individual baseline responses for personalized analysis. Gaussian Mixture Models clustered data into binary or ternary anxiety levels, interpreted by statistics of self-reported scores and physiological features. Clus ters showed modest alignment with State and Trait Inventory scores and physiological markers and demonstrated task-specific variability. Silhouette scores indicated moderate separation (0.40 for two clusters, 0.14 for three clusters). Binary and three-class classifications using unsupervised learning and leave-one-participant-out validation demonstrated effectiveness, with Support Vector Machine achieving highest accuracies (90.9% and 73.3%). This approach enables objective, personalized anxiety monitoring without relying on subjective labeling.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100572"},"PeriodicalIF":0.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143725637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intoxication detection from speech using representations learned from self-supervised pre-training 使用自监督预训练学习表征的语音中毒检测

Q2 Health Professions

Smart Health

Pub Date : 2025-03-27 DOI: 10.1016/j.smhl.2025.100562

Abigail Albuquerque, Samuel Chibuoyim Uche, Emmanuel Agu

Alcohol intoxication is one of the leading causes of death around the globe. Existing approaches to prevent Driving Under the Influence (DUI) are expensive, intrusive, or require external apparatus such as breathalyzers, which the drinker may not possess. Speech is a viable modality for detecting intoxication from changes in vocal patterns. Intoxicated speech is slower, has lower amplitude, and is more prone to errors at the sentence, word, and phonological levels than sober speech. However, intoxication detection from speech is challenging due to high inter- and intra-user variability and the confounding effects of other factors such as fatigue, which may also impair speech. This paper investigates Wav2Vec 2.0, a self-supervised neural network architecture, for intoxication classification from audio. Wav2Vec 2.0 is a Transformer-based model that has demonstrated remarkable performance in various speech-related tasks. It analyzes raw audio directly by applying a multi-head attention mechanism to latent audio representations and was pre-trained on the Librispeech, Libri-Light and EmoDB datasets. The proposed model achieved an unweighted average recall of 73.3%, outperforming state-of-the-art models, highlighting its potential for accurate DUI detection to prevent alcohol-related incidents.

酒精中毒是全球死亡的主要原因之一。现有的防止酒后驾驶的方法要么价格昂贵，要么具有侵入性，要么需要外部设备，比如酒精测试仪，而饮酒者可能没有这些设备。语音是通过声音模式的变化来检测中毒的一种可行的方式。醉酒时说话的速度较慢，幅度较低，并且比清醒时说话更容易在句子、单词和语音层面上出错。然而，由于使用者之间和内部的高度可变性以及疲劳等其他因素的混杂影响，从语音中检测中毒是具有挑战性的，这些因素也可能损害语音。本文研究了一种自监督神经网络结构——Wav2Vec 2.0，用于音频中毒分类。Wav2Vec 2.0是一个基于transformer的模型，在各种与语音相关的任务中表现出色。它通过对潜在音频表示应用多头注意机制直接分析原始音频，并在librisspeech， lib - light和EmoDB数据集上进行预训练。该模型实现了73.3%的非加权平均召回率，优于最先进的模型，突出了其准确检测DUI以防止酒精相关事故的潜力。

{"title":"Intoxication detection from speech using representations learned from self-supervised pre-training","authors":"Abigail Albuquerque, Samuel Chibuoyim Uche, Emmanuel Agu","doi":"10.1016/j.smhl.2025.100562","DOIUrl":"10.1016/j.smhl.2025.100562","url":null,"abstract":"<div><div>Alcohol intoxication is one of the leading causes of death around the globe. Existing approaches to prevent Driving Under the Influence (DUI) are expensive, intrusive, or require external apparatus such as breathalyzers, which the drinker may not possess. Speech is a viable modality for detecting intoxication from changes in vocal patterns. Intoxicated speech is slower, has lower amplitude, and is more prone to errors at the sentence, word, and phonological levels than sober speech. However, intoxication detection from speech is challenging due to high inter- and intra-user variability and the confounding effects of other factors such as fatigue, which may also impair speech. This paper investigates Wav2Vec 2.0, a self-supervised neural network architecture, for intoxication classification from audio. Wav2Vec 2.0 is a Transformer-based model that has demonstrated remarkable performance in various speech-related tasks. It analyzes raw audio directly by applying a multi-head attention mechanism to latent audio representations and was pre-trained on the Librispeech, Libri-Light and EmoDB datasets. The proposed model achieved an unweighted average recall of 73.3%, outperforming state-of-the-art models, highlighting its potential for accurate DUI detection to prevent alcohol-related incidents.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100562"},"PeriodicalIF":0.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143799304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ADHDSymTracker: Predicting ADHD Symptoms using Apple HealthKit Data ADHDSymTracker：使用Apple HealthKit数据预测ADHD症状

Q2 Health Professions

Smart Health

Pub Date : 2025-03-27 DOI: 10.1016/j.smhl.2025.100563

Shweta Ware , Allison Baun , Peiyi Wang , Caleb Kwakye , Sofia Dimotsi , Ethan Swift , Nikoloz Gvelesiani , Laura E. Knouse

Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent condition that impacts cognitive and behavioral functioning, posing significant challenges for individuals’ academic and daily lives, particularly among college students. The core symptoms are inattention, hyperactivity and impulsivity. Current diagnostic and symptom tracking methods, whether clinician-administered or self-reported, have several limitations, such as recall bias, high costs, and the necessity for manual intervention. This underscores the necessity for an objective, accurate, and cost-effective tool for ADHD diagnosis that requires minimal manual intervention. To address this issue, we propose a novel approach, ADHDSymTracker, which uses Apple HealthKit data to predict ADHD symptoms. We calculated behavioral features using data collected from 38 college-age students including some with ADHD and developed a suite of machine learning models for ADHD symptom prediction. Our results from ADHDSymTracker indicate that most symptoms can be predicted with reasonable accuracy, achieving an

F_{1}

score as high as 0.72, rendering it a promising solution for automatic and continuous ADHD monitoring.

注意缺陷多动障碍（ADHD）是一种影响认知和行为功能的普遍疾病，对个人的学习和日常生活构成了重大挑战，尤其是在大学生中。核心症状是注意力不集中、多动和冲动。目前的诊断和症状跟踪方法，无论是临床给药还是自我报告，都有一些局限性，如回忆偏差、高成本和人工干预的必要性。这强调了需要一种客观、准确、成本效益高的ADHD诊断工具，这种工具需要最少的人工干预。为了解决这个问题，我们提出了一种新的方法，ADHDSymTracker，它使用Apple HealthKit数据来预测ADHD症状。我们使用从38名大学生中收集的数据来计算行为特征，其中包括一些患有多动症的学生，并开发了一套用于多动症症状预测的机器学习模型。我们的ADHDSymTracker的结果表明，大多数症状都可以以合理的准确性预测，F1得分高达0.72，使其成为自动连续监测ADHD的有希望的解决方案。

{"title":"ADHDSymTracker: Predicting ADHD Symptoms using Apple HealthKit Data","authors":"Shweta Ware , Allison Baun , Peiyi Wang , Caleb Kwakye , Sofia Dimotsi , Ethan Swift , Nikoloz Gvelesiani , Laura E. Knouse","doi":"10.1016/j.smhl.2025.100563","DOIUrl":"10.1016/j.smhl.2025.100563","url":null,"abstract":"<div><div>Attention Deficit Hyperactivity Disorder (ADHD) is a prevalent condition that impacts cognitive and behavioral functioning, posing significant challenges for individuals’ academic and daily lives, particularly among college students. The core symptoms are inattention, hyperactivity and impulsivity. Current diagnostic and symptom tracking methods, whether clinician-administered or self-reported, have several limitations, such as recall bias, high costs, and the necessity for manual intervention. This underscores the necessity for an objective, accurate, and cost-effective tool for ADHD diagnosis that requires minimal manual intervention. To address this issue, we propose a novel approach, ADHDSymTracker, which uses Apple HealthKit data to predict ADHD symptoms. We calculated behavioral features using data collected from 38 college-age students including some with ADHD and developed a suite of machine learning models for ADHD symptom prediction. Our results from ADHDSymTracker indicate that most symptoms can be predicted with reasonable accuracy, achieving an <span><math><msub><mrow><mi>F</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span> score as high as 0.72, rendering it a promising solution for automatic and continuous ADHD monitoring.</div></div>","PeriodicalId":37151,"journal":{"name":"Smart Health","volume":"36 ","pages":"Article 100563"},"PeriodicalIF":0.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0