Pub Date : 2026-03-05DOI: 10.1109/JTEHM.2026.3671170
Giorgia Rita Di Ruggiero;Sarah Hösli;Christopher J. Bockisch;Julia Dlugaiczyk;Dominik Straumann;Carolina Beppi
Objective: The diagnostic work-up for vestibular pathologies involves a battery of tests designed to quantify the functioning of the otolith organs and semicircular canals. Clinical data from video head-impulse tests, vestibular-evoked myogenic potentials, subjective visual verticality, and caloric tests are usually collected. Our study applied regression analyses to predict the affected side of a patient group with vestibular schwannoma, learning from laboratory vestibular tests, to assess their relative predictive capacity in predicting the tumor side. Technology or Method: The dataset was pre-processed to handle missing values, outliers, and differences in the measurement scales. The mean asymmetry values and their direction (either negative = left-side asymmetry or positive = right-side asymmetry) were calculated. The classifiers’ ability to accurately predict the tumor side was evaluated. Finally, both logistic and multiple regression analyses were conducted. Results: The regression models’ binary output (i.e., right or left side affected) was compared to the true labels of the affected side given by magnetic resonance imaging to estimate the model’s accuracy. Linear regression analysis showed that caloric, cVEMP and RLLL reached AUCs >0.9; multiple regression revealed an AUC of 0.96 for caloric and cVEMP combined. Conclusion: Our study demonstrated that combining caloric and vestibular-evoked myogenic potential tests provides the most accurate identification of the vestibular schwannoma-affected side, achieving the highest predictive capacity. Furthermore, our findings align with previous studies revealing that the monocular video head-impulse test introduces a gain bias for all three semicircular canals that must be adjusted to correctly estimate semicircular canal function. Clinical and Impact—This study addresses the clinical challenge of finding the affected side in unilateral vestibular schwannoma patients by using machine learning to vestibular tests linking computational methods with clinical practice
{"title":"Regression-Based Analysis of Vestibular Laboratory Tests for the Prediction of Unilateral Vestibular Schwannoma","authors":"Giorgia Rita Di Ruggiero;Sarah Hösli;Christopher J. Bockisch;Julia Dlugaiczyk;Dominik Straumann;Carolina Beppi","doi":"10.1109/JTEHM.2026.3671170","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3671170","url":null,"abstract":"Objective: The diagnostic work-up for vestibular pathologies involves a battery of tests designed to quantify the functioning of the otolith organs and semicircular canals. Clinical data from video head-impulse tests, vestibular-evoked myogenic potentials, subjective visual verticality, and caloric tests are usually collected. Our study applied regression analyses to predict the affected side of a patient group with vestibular schwannoma, learning from laboratory vestibular tests, to assess their relative predictive capacity in predicting the tumor side. Technology or Method: The dataset was pre-processed to handle missing values, outliers, and differences in the measurement scales. The mean asymmetry values and their direction (either negative = left-side asymmetry or positive = right-side asymmetry) were calculated. The classifiers’ ability to accurately predict the tumor side was evaluated. Finally, both logistic and multiple regression analyses were conducted. Results: The regression models’ binary output (i.e., right or left side affected) was compared to the true labels of the affected side given by magnetic resonance imaging to estimate the model’s accuracy. Linear regression analysis showed that caloric, cVEMP and RLLL reached AUCs >0.9; multiple regression revealed an AUC of 0.96 for caloric and cVEMP combined. Conclusion: Our study demonstrated that combining caloric and vestibular-evoked myogenic potential tests provides the most accurate identification of the vestibular schwannoma-affected side, achieving the highest predictive capacity. Furthermore, our findings align with previous studies revealing that the monocular video head-impulse test introduces a gain bias for all three semicircular canals that must be adjusted to correctly estimate semicircular canal function. Clinical and Impact—This study addresses the clinical challenge of finding the affected side in unilateral vestibular schwannoma patients by using machine learning to vestibular tests linking computational methods with clinical practice","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"133-143"},"PeriodicalIF":4.4,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421970","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arrhythmia is a common cardiac condition that can precipitate severe complications without timely intervention. Among them, atrial fibrillation (AF) is the most common form. While continuous monitoring is essential for timely diagnosis, conventional approaches such as electrocardiogram (ECG) and wearable devices are constrained by their reliance on specialized medical expertise and patient discomfort from their contact nature. Existing contactless monitoring, primarily designed for healthy subjects, face significant challenges when analyzing reflections from AF patients due to disrupted spatial stability and temporal consistency caused by underlying irregular heart contractions. In this paper, we introduce mCardiacDx, a radar-driven contactless system that accurately analyzes these complex reflections and reconstructs heart pulse waveforms (HPWs) for AF monitoring and diagnosis. The key technical contributions of our work include a novel precise target localization (PTL) technique that accurately locates heart reflections despite spatial disruptions, an encoder-decoder model (HPR-Net) that effectively transforms these reflections into HPWs, addressing temporal inconsistencies, and a final analysis module for AF monitoring and diagnosis. Our evaluation on a dataset of 48 subjects (24 healthy, 24 with AF) in a seated, normal breathing, real-world setting shows that both mCardiacDx and the PTL technique significantly outperform the state-of-the-art approach in monitoring and diagnosing AF. Objective: To develop a contactless radar-driven system, mCardiacDx, that overcomes reflection disruption challenges in AF patients to accurately reconstruct interpretable heart pulse waveforms (HPWs) for monitoring and diagnosis.Methods and procedures: We introduce a PTL technique to locate heart reflections despite spatial disruptions, and an encoder-decoder model (HPR-Net) to robustly process reflections and reconstruct interpretable HPWs, addressing temporal inconsistencies. The HPWs are then processed by a final analysis module for AF monitoring and diagnosis. mCardiacDx is validated against a state-of-the-art approach (baseline) on a dataset of 48 subjects (24 healthy, 24 with AF) in a seated, normal breathing, real-world setting. This validation confirms the system’s robustness and generalizability to real-world seated scenarios variations in posture and environment.Results: mCardiacDx significantly outperforms the baseline in both monitoring and diagnosis. HPW fidelity (Dynamic time warping (DTW) score) for AF patients improves from 5.92 to 2.92. HR/RR interval median absolute percentage error (MedAPE) reduced (e.g., HR from 9.10 % to 2.94 %; RR interval from 8.42 % to 2.95 %). Our system achieves superior diagnostic performance with 0.93 accuracy, and 0.91 recall (sensitivity), significantly surpassing the baseline’s accuracy of 0.85 and recall of 0.75, while both maintain a specificity of 0.96.Conclusion: mCardiacDx is a robust, non-contact system for co
{"title":"mCardiacDx: Radar-Driven Contactless Monitoring and Diagnosis of Atrial Fibrillation","authors":"Arjun Kumar;Noppanat Wadlom;Jaeheon Kwak;Si-Hyuck Kang;Insik Shin","doi":"10.1109/JTEHM.2026.3670383","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3670383","url":null,"abstract":"Arrhythmia is a common cardiac condition that can precipitate severe complications without timely intervention. Among them, atrial fibrillation (AF) is the most common form. While continuous monitoring is essential for timely diagnosis, conventional approaches such as electrocardiogram (ECG) and wearable devices are constrained by their reliance on specialized medical expertise and patient discomfort from their contact nature. Existing contactless monitoring, primarily designed for healthy subjects, face significant challenges when analyzing reflections from AF patients due to disrupted spatial stability and temporal consistency caused by underlying irregular heart contractions. In this paper, we introduce mCardiacDx, a radar-driven contactless system that accurately analyzes these complex reflections and reconstructs heart pulse waveforms (HPWs) for AF monitoring and diagnosis. The key technical contributions of our work include a novel precise target localization (PTL) technique that accurately locates heart reflections despite spatial disruptions, an encoder-decoder model (HPR-Net) that effectively transforms these reflections into HPWs, addressing temporal inconsistencies, and a final analysis module for AF monitoring and diagnosis. Our evaluation on a dataset of 48 subjects (24 healthy, 24 with AF) in a seated, normal breathing, real-world setting shows that both mCardiacDx and the PTL technique significantly outperform the state-of-the-art approach in monitoring and diagnosing AF. Objective: To develop a contactless radar-driven system, mCardiacDx, that overcomes reflection disruption challenges in AF patients to accurately reconstruct interpretable heart pulse waveforms (HPWs) for monitoring and diagnosis.Methods and procedures: We introduce a PTL technique to locate heart reflections despite spatial disruptions, and an encoder-decoder model (HPR-Net) to robustly process reflections and reconstruct interpretable HPWs, addressing temporal inconsistencies. The HPWs are then processed by a final analysis module for AF monitoring and diagnosis. mCardiacDx is validated against a state-of-the-art approach (baseline) on a dataset of 48 subjects (24 healthy, 24 with AF) in a seated, normal breathing, real-world setting. This validation confirms the system’s robustness and generalizability to real-world seated scenarios variations in posture and environment.Results: mCardiacDx significantly outperforms the baseline in both monitoring and diagnosis. HPW fidelity (Dynamic time warping (DTW) score) for AF patients improves from 5.92 to 2.92. HR/RR interval median absolute percentage error (MedAPE) reduced (e.g., HR from 9.10 % to 2.94 %; RR interval from 8.42 % to 2.95 %). Our system achieves superior diagnostic performance with 0.93 accuracy, and 0.91 recall (sensitivity), significantly surpassing the baseline’s accuracy of 0.85 and recall of 0.75, while both maintain a specificity of 0.96.Conclusion: mCardiacDx is a robust, non-contact system for co","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"144-163"},"PeriodicalIF":4.4,"publicationDate":"2026-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11421399","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-27DOI: 10.1109/JTEHM.2026.3669059
Wonhee Lee;Seung-Ick Choi;Kyung Pyo Hong;Yu Joo Kang;Huiwoo Yang;Jin Young Park;Na Young Kim
Objective: Continuous monitoring of patients’ physical and psychological status using wearable sensors and Internet of Things platforms may enhance rehabilitation. We aimed to assess the feasibility of an Internet of Things-based smart hospital system integrating multi-source data to support individualized rehabilitation in patients with gait disturbances. Methods: We conducted a single-center feasibility study at Yongin Severance Hospital, Korea, including 15 inpatients with subacute central nervous system injuries (mean age, $60.9pm 16.7$ years). The system integrated smart insoles, smart bands, real-time location system data, and mobile application data into the electronic medical record. Gait parameters, including step count, walking distance, gait speed, stride length, and symmetry, were measured during self-exercise. The app collected self-reported scores on pain, anxiety, depression, appetite, sleep, and general condition. Compliance, patient satisfaction, and nurses’ qualitative feedback were analyzed descriptively. Results: Monitoring lasted $17.0pm 12.6$ days. Patients averaged 7,$323pm 5$ ,520 steps/day and walked 3,$910pm 3$ ,198 m/day; 87% showed reduced stride length and 27% had marked gait asymmetry. Application-based symptom monitoring enabled tailored interventions, including medication adjustments and referrals. Smart band data were sometimes incomplete owing to recording errors. Operational challenges included battery depletion, data transfer interruptions, and device registration errors. Overall satisfaction averaged 4.28/5; comfort rated the highest, durability the lowest. Nurses valued real-time condition detection and improved self-report honesty but noted increased workload. Conclusion: Implementing an Internet of Things-based system that integrates wearable and self-reported data into an electronic medical record is feasible in inpatient rehabilitation, facilitating individualized feedback and clinical decision-making while maintaining high patient adherence and satisfaction. Clinical Impact—This study shows the feasibility of an IoT-based smart hospital system integrating multisource data into EMRs, enabling personalized rehabilitation, improving clinical decision-making, and supporting scalable digital healthcare models.
{"title":"Promoting Rehabilitation Using a Multimodal Internet of Things-Based Patient Monitoring System in a Smart Hospital","authors":"Wonhee Lee;Seung-Ick Choi;Kyung Pyo Hong;Yu Joo Kang;Huiwoo Yang;Jin Young Park;Na Young Kim","doi":"10.1109/JTEHM.2026.3669059","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3669059","url":null,"abstract":"Objective: Continuous monitoring of patients’ physical and psychological status using wearable sensors and Internet of Things platforms may enhance rehabilitation. We aimed to assess the feasibility of an Internet of Things-based smart hospital system integrating multi-source data to support individualized rehabilitation in patients with gait disturbances. Methods: We conducted a single-center feasibility study at Yongin Severance Hospital, Korea, including 15 inpatients with subacute central nervous system injuries (mean age, <inline-formula> <tex-math>$60.9pm 16.7$ </tex-math></inline-formula> years). The system integrated smart insoles, smart bands, real-time location system data, and mobile application data into the electronic medical record. Gait parameters, including step count, walking distance, gait speed, stride length, and symmetry, were measured during self-exercise. The app collected self-reported scores on pain, anxiety, depression, appetite, sleep, and general condition. Compliance, patient satisfaction, and nurses’ qualitative feedback were analyzed descriptively. Results: Monitoring lasted <inline-formula> <tex-math>$17.0pm 12.6$ </tex-math></inline-formula> days. Patients averaged 7,<inline-formula> <tex-math>$323pm 5$ </tex-math></inline-formula>,520 steps/day and walked 3,<inline-formula> <tex-math>$910pm 3$ </tex-math></inline-formula>,198 m/day; 87% showed reduced stride length and 27% had marked gait asymmetry. Application-based symptom monitoring enabled tailored interventions, including medication adjustments and referrals. Smart band data were sometimes incomplete owing to recording errors. Operational challenges included battery depletion, data transfer interruptions, and device registration errors. Overall satisfaction averaged 4.28/5; comfort rated the highest, durability the lowest. Nurses valued real-time condition detection and improved self-report honesty but noted increased workload. Conclusion: Implementing an Internet of Things-based system that integrates wearable and self-reported data into an electronic medical record is feasible in inpatient rehabilitation, facilitating individualized feedback and clinical decision-making while maintaining high patient adherence and satisfaction. Clinical Impact—This study shows the feasibility of an IoT-based smart hospital system integrating multisource data into EMRs, enabling personalized rehabilitation, improving clinical decision-making, and supporting scalable digital healthcare models.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"113-122"},"PeriodicalIF":4.4,"publicationDate":"2026-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11417159","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440613","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-26DOI: 10.1109/JTEHM.2026.3668755
Zhibin Yang;Chuanyue Chen;Seedahmed S. Mahmoud;Xuerui Tan;Yequn Chen;Qiang Fang
Cardiovascular diseases are a leading global cause of death, but their accurate diagnosis remains challenging. While Large Language Models (LLMs) show promise in assisting disease diagnosis in general, their adoption in cardiology is hindered by three critical limitations: hallucination, inadequate domain-specific reasoning, and restricted knowledge coverage. To overcome these barriers, we developed Cardiology-Chat, an LLM-based system specifically tailored for cardiology. The system employs a three-step main reasoning framework: 1) parsing user queries with Llama 3.1 8B-instruct to extract key clinical information; 2) retrieving evidence from the knowledge base via Retrieval-augmented generation (RAG); and 3) generating diagnostic conclusions using the fine-tuned Llama model. Two critical components have been developed to support the system’s functionality. The first is a specialized cardiovascular vector knowledge base, constructed from multiple data sources to enhance the RAG subsystem. The second is a Chain-of-Thought–augmented dataset designed to strengthen the LLM’s in-depth reasoning capabilities. In addition, multiple LLMs were adopted to mitigate the possible “self-consistency” bias. Experiments on public cardiology QA and real clinical cases demonstrated significant performance improvements, achieving 0.796 accuracy and 0.807 F1 respectively.
{"title":"Cardiology-Chat: A Multi-LLMs Powered System for Cardiac Diagnostic Reasoning and Clinical Support","authors":"Zhibin Yang;Chuanyue Chen;Seedahmed S. Mahmoud;Xuerui Tan;Yequn Chen;Qiang Fang","doi":"10.1109/JTEHM.2026.3668755","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3668755","url":null,"abstract":"Cardiovascular diseases are a leading global cause of death, but their accurate diagnosis remains challenging. While Large Language Models (LLMs) show promise in assisting disease diagnosis in general, their adoption in cardiology is hindered by three critical limitations: hallucination, inadequate domain-specific reasoning, and restricted knowledge coverage. To overcome these barriers, we developed Cardiology-Chat, an LLM-based system specifically tailored for cardiology. The system employs a three-step main reasoning framework: 1) parsing user queries with Llama 3.1 8B-instruct to extract key clinical information; 2) retrieving evidence from the knowledge base via Retrieval-augmented generation (RAG); and 3) generating diagnostic conclusions using the fine-tuned Llama model. Two critical components have been developed to support the system’s functionality. The first is a specialized cardiovascular vector knowledge base, constructed from multiple data sources to enhance the RAG subsystem. The second is a Chain-of-Thought–augmented dataset designed to strengthen the LLM’s in-depth reasoning capabilities. In addition, multiple LLMs were adopted to mitigate the possible “self-consistency” bias. Experiments on public cardiology QA and real clinical cases demonstrated significant performance improvements, achieving 0.796 accuracy and 0.807 F1 respectively.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"123-132"},"PeriodicalIF":4.4,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11414432","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147440690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-25DOI: 10.1109/JTEHM.2026.3667847
Ye Joon Kim;Seung-Ick Choi;Huiwoo Yang;Wonhee Lee;Seongmin Hong;Na Young Kim
Objective: Gait disturbances in Parkinson’s disease (PD) indicate impaired motor automaticity, particularly under cognitively demanding conditions. Although spatiotemporal parameters are commonly used to assess dual-task cost (DTC), their sensitivity in PD is limited. This study aimed to characterize the plantar pressure alterations during dual-task walking using a sensor-based insole system and compare them with conventional gait metrics. Method: We performed an on-site validation of the insole-derived parameters against a 3D motion analysis system in healthy adults. Subsequently, we conducted a cross-sectional study comparing spatiotemporal parameters, plantar pressure metrics, and DTCs among healthy young adults, healthy older adults, and patients with early-stage PD (EPD). Participants completed 10-meter walking tests under both single- and dual-task (serial subtraction) conditions. Results: The insole-derived parameters showed significant agreement with the 3D motion analysis, with cadence and acceleration times demonstrating good validity. Under single-task conditions, patients with EPD exhibited slower velocity, shorter stride length, and greater gait variability than both control groups. Plantar pressure analysis revealed reduced peak pressures in the toe, medial forefoot, and heel regions in patients with EPD, with increased variability particularly in the heel region. Under dual-task conditions, spatiotemporal DTCs did not differ significantly between the groups. In contrast, plantar pressure metrics revealed distinct alterations in patients with EPD, with reduced heel loading and increased variability. Conclusion: These findings suggest that plantar pressure metrics provide additional sensitivity beyond conventional spatiotemporal parameters for detecting dual-task-related gait alterations in patients with PD, highlighting their potential utility in clinical assessments. Clinical Impact—Affordable, easy-to-use sensor-based insoles provide practical and sensitive gait metrics, enabling detection of subtle gait changes and helping bridge the gap between research-grade gait analysis and routine clinical practice.
{"title":"Insole-Derived Plantar Pressure Variability Reveals Dual-Task Gait Differences in Early-Stage Parkinson’s Disease","authors":"Ye Joon Kim;Seung-Ick Choi;Huiwoo Yang;Wonhee Lee;Seongmin Hong;Na Young Kim","doi":"10.1109/JTEHM.2026.3667847","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3667847","url":null,"abstract":"Objective: Gait disturbances in Parkinson’s disease (PD) indicate impaired motor automaticity, particularly under cognitively demanding conditions. Although spatiotemporal parameters are commonly used to assess dual-task cost (DTC), their sensitivity in PD is limited. This study aimed to characterize the plantar pressure alterations during dual-task walking using a sensor-based insole system and compare them with conventional gait metrics. Method: We performed an on-site validation of the insole-derived parameters against a 3D motion analysis system in healthy adults. Subsequently, we conducted a cross-sectional study comparing spatiotemporal parameters, plantar pressure metrics, and DTCs among healthy young adults, healthy older adults, and patients with early-stage PD (EPD). Participants completed 10-meter walking tests under both single- and dual-task (serial subtraction) conditions. Results: The insole-derived parameters showed significant agreement with the 3D motion analysis, with cadence and acceleration times demonstrating good validity. Under single-task conditions, patients with EPD exhibited slower velocity, shorter stride length, and greater gait variability than both control groups. Plantar pressure analysis revealed reduced peak pressures in the toe, medial forefoot, and heel regions in patients with EPD, with increased variability particularly in the heel region. Under dual-task conditions, spatiotemporal DTCs did not differ significantly between the groups. In contrast, plantar pressure metrics revealed distinct alterations in patients with EPD, with reduced heel loading and increased variability. Conclusion: These findings suggest that plantar pressure metrics provide additional sensitivity beyond conventional spatiotemporal parameters for detecting dual-task-related gait alterations in patients with PD, highlighting their potential utility in clinical assessments. Clinical Impact—Affordable, easy-to-use sensor-based insoles provide practical and sensitive gait metrics, enabling detection of subtle gait changes and helping bridge the gap between research-grade gait analysis and routine clinical practice.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"104-112"},"PeriodicalIF":4.4,"publicationDate":"2026-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11411780","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147362405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-11DOI: 10.1109/JTEHM.2026.3663967
Irfan Ullah;Tyler Ward;Tom Greig;Gillian Lake-Thompson;Meijing Liu;Lynn Reeves;Elaine Dennison;John Tudor;Kai Yang
Objectives: To develop and evaluate a wearable, garment-integrated transcutaneous electrical nerve stimulation (TENS) system for relieving osteoarthritis knee pain, emphasizing safety, usability, and readiness for home and clinical deployment.Methods: We designed an IEC 60601 compliant TENS system that embeds flexible electrodes into a close-fitting, machine-washable textile. A seven-day, home-based usability evaluation was conducted with 11 participants with osteoarthritis. Outcomes included self-reported pain (baseline vs. post-use) and usability metrics (ease of setup and comfort). The system received Medicines and Healthcare products Regulatory Agency (MHRA) and Health Research Authority (HRA) approvals for a subsequent clinical investigation.Results: Participants reported strong user acceptance, ease of use and comfort. Average pain decreased by 54.79% over the evaluation period, indicating a meaningful short-term analgesic benefit in a home setting. No serious adverse events were observed.Conclusion: Integrating electrodes into a wearable garment addresses key limitations of conventional adhesive-pad TENS, improving placement consistency, comfort, and ease of use while supporting safe operation under IEC 60601. These preliminary findings support the feasibility of garment-based TENS for osteoarthritis management at home and justify a follow-on clinical trial to rigorously quantify pain relief, functional outcomes, and user satisfaction in a larger cohort. Clinical Impact: The use of a washable TENS garment, compliant with IEC 60601, resulted in reduced osteoarthritis pain in a home setting. Its integration into home care is facilitated by an easy to use device with reusable textile electrodes
{"title":"A Wearable TENS Garment for Joint Pain Management: IEC 60601 Compliant Design and Preliminary Evaluation","authors":"Irfan Ullah;Tyler Ward;Tom Greig;Gillian Lake-Thompson;Meijing Liu;Lynn Reeves;Elaine Dennison;John Tudor;Kai Yang","doi":"10.1109/JTEHM.2026.3663967","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3663967","url":null,"abstract":"Objectives: To develop and evaluate a wearable, garment-integrated transcutaneous electrical nerve stimulation (TENS) system for relieving osteoarthritis knee pain, emphasizing safety, usability, and readiness for home and clinical deployment.Methods: We designed an IEC 60601 compliant TENS system that embeds flexible electrodes into a close-fitting, machine-washable textile. A seven-day, home-based usability evaluation was conducted with 11 participants with osteoarthritis. Outcomes included self-reported pain (baseline vs. post-use) and usability metrics (ease of setup and comfort). The system received Medicines and Healthcare products Regulatory Agency (MHRA) and Health Research Authority (HRA) approvals for a subsequent clinical investigation.Results: Participants reported strong user acceptance, ease of use and comfort. Average pain decreased by 54.79% over the evaluation period, indicating a meaningful short-term analgesic benefit in a home setting. No serious adverse events were observed.Conclusion: Integrating electrodes into a wearable garment addresses key limitations of conventional adhesive-pad TENS, improving placement consistency, comfort, and ease of use while supporting safe operation under IEC 60601. These preliminary findings support the feasibility of garment-based TENS for osteoarthritis management at home and justify a follow-on clinical trial to rigorously quantify pain relief, functional outcomes, and user satisfaction in a larger cohort. Clinical Impact: The use of a washable TENS garment, compliant with IEC 60601, resulted in reduced osteoarthritis pain in a home setting. Its integration into home care is facilitated by an easy to use device with reusable textile electrodes","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"91-103"},"PeriodicalIF":4.4,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11393507","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-30DOI: 10.1109/JTEHM.2026.3659651
Sofia Basha;Mohammad Khorasani;Nihal Abdurahiman;Jhasketan Padhan;Victor Baez;Abdulla Al-Ansari;Panagiotis Tsiamyrtzis;Aaron T. Becker;Nikhil V. Navkar
Objective: Flexible endoscopy is a valuable tool in diagnostic procedures, enabling examination of internal areas via natural orifices. An actuation system tends to improve the procedural outcomes by enabling controlled movements of the endoscope and offering a stable view of the operative field. A user interface is used to issue actuation commands to these systems. Thus, selection of an ideal user interface is vital to improve the ergonomics for the endoscopist and to ensure efficient endoscope navigation. The objective of this work is to perform an in-depth comparative analysis of various user interfaces to optimize endoscope maneuverability. Methods and Procedures: A custom-built actuation system was used to maneuver a flexible endoscope. The actuation system enabled translational and rotational movement of the endoscope’s shaft as well as supported left/right and up/down steering of the endoscope’s distal end. Four user interfaces (head-motion based device, eye-gaze based device, a stylus, and a joystick) working under three interaction modes (continuous, discrete, threshold) along with a clutching mechanism were used to issue commands to the actuation system. A user study was conducted to assess the effectiveness of the user interfaces for two scenarios: Scenario-A, which involved maneuvering the endoscope’s distal end to focus on a localized operative field, and Scenario-B, which required targeting polyps during the withdrawal phase of a simulated colonoscopy. Results: In Scenario-A, the head motion-based device and stylus, when used in continuous interaction mode, resulted in the shorter task duration and fewer clutches. The joystick, operating under threshold interaction mode, also demonstrated a reduced task duration. Additionally, the joystick led to fewer instances of the endoscope’s focus shifting outside the localized operative field. In Scenario-B, eye gaze-based device under discrete interaction mode took the longest duration for task completion. The continuous mode of the stylus took the shortest duration to target polyps, once visualized in the operating field. However, it also required the highest number of clutches compared to other user interface and interaction modes. Conclusion: The joystick consistently outperformed other interfaces across all interaction modes. Performance among the other user interfaces varied based on the parameters of the scenarios. Head motion-based and eye-based user interfaces enabled hands-free manipulation of the endoscope. This study establishes a benchmark for enhancing both user interfaces and interaction modes in actuated flexible endoscopy.
{"title":"Evaluation of User Interfaces for Actuated Control of Endoscopes During Flexible Endoscopy","authors":"Sofia Basha;Mohammad Khorasani;Nihal Abdurahiman;Jhasketan Padhan;Victor Baez;Abdulla Al-Ansari;Panagiotis Tsiamyrtzis;Aaron T. Becker;Nikhil V. Navkar","doi":"10.1109/JTEHM.2026.3659651","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3659651","url":null,"abstract":"Objective: Flexible endoscopy is a valuable tool in diagnostic procedures, enabling examination of internal areas via natural orifices. An actuation system tends to improve the procedural outcomes by enabling controlled movements of the endoscope and offering a stable view of the operative field. A user interface is used to issue actuation commands to these systems. Thus, selection of an ideal user interface is vital to improve the ergonomics for the endoscopist and to ensure efficient endoscope navigation. The objective of this work is to perform an in-depth comparative analysis of various user interfaces to optimize endoscope maneuverability. Methods and Procedures: A custom-built actuation system was used to maneuver a flexible endoscope. The actuation system enabled translational and rotational movement of the endoscope’s shaft as well as supported left/right and up/down steering of the endoscope’s distal end. Four user interfaces (head-motion based device, eye-gaze based device, a stylus, and a joystick) working under three interaction modes (continuous, discrete, threshold) along with a clutching mechanism were used to issue commands to the actuation system. A user study was conducted to assess the effectiveness of the user interfaces for two scenarios: Scenario-A, which involved maneuvering the endoscope’s distal end to focus on a localized operative field, and Scenario-B, which required targeting polyps during the withdrawal phase of a simulated colonoscopy. Results: In Scenario-A, the head motion-based device and stylus, when used in continuous interaction mode, resulted in the shorter task duration and fewer clutches. The joystick, operating under threshold interaction mode, also demonstrated a reduced task duration. Additionally, the joystick led to fewer instances of the endoscope’s focus shifting outside the localized operative field. In Scenario-B, eye gaze-based device under discrete interaction mode took the longest duration for task completion. The continuous mode of the stylus took the shortest duration to target polyps, once visualized in the operating field. However, it also required the highest number of clutches compared to other user interface and interaction modes. Conclusion: The joystick consistently outperformed other interfaces across all interaction modes. Performance among the other user interfaces varied based on the parameters of the scenarios. Head motion-based and eye-based user interfaces enabled hands-free manipulation of the endoscope. This study establishes a benchmark for enhancing both user interfaces and interaction modes in actuated flexible endoscopy.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"67-76"},"PeriodicalIF":4.4,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11368894","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: Detection of mild cognitive impairment (MCI), a precursor to dementia, is critical for timely intervention. Functional near-infrared spectroscopy (fNIRS) offers non-invasive, cost-effective, and motion-tolerant brain activity monitoring, but existing machine learning approaches for MCI classification using fNIRS face two limitations: 1) underutilization of complementary information between resting-state and task-state data, and 2) high feature dimensionality relative to small sample sizes, limiting model robustness and generalizability. We propose a spatio-temporal feature engineering framework addressing these gaps.Methods: Resting-state fNIRS signals are processed via independent component analysis to derive subject-specific spatial filters, which are then clustered into a universal population-level filter set. This filter set isolates spatial features from task-state signals. Then, temporal feature selection combines variance-based and advanced methods to further reduce dimensionality by identifying discriminative task-evoked time points relevant to MCI detection. The framework integrates fNIRS spatial filtering (resting-state) and temporal selection (task-state) critical for MCI detection.Results: Validated on 104 participants, this framework achieved a single-run best of 90.91% accuracy for cognitively normal vs. MCI classification, with 91.07% feature dimensionality reduction, suggest the potential for generalizable MCI detection and efficient model retraining for expanding clinical data. Feature analysis reveals (1) universal spatial filters linked to MCI biomarkers and (2) temporal weights highlighting critical decision time points during cognitive tasks.Conclusion: By resolving the integration gap between resting-state neurovascular patterns with task-evoked hemodynamic dynamics while reducing dimensionality, the framework achieves higher accuracy and interpretability, advancing fNIRS-based MCI detection.
{"title":"Enhanced fNIRS-Based MCI Detection via Resting-State and Task-State Integration With Spatial–Temporal Feature Reduction","authors":"Chutian Zhang;Hongjun Yang;Jiaxing Wang;Kexin Xiang;Jingyao Chen;Liang Peng;Chenyu Fan;Yi Wu;Zeng-Guang Hou","doi":"10.1109/JTEHM.2026.3659529","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3659529","url":null,"abstract":"Objective: Detection of mild cognitive impairment (MCI), a precursor to dementia, is critical for timely intervention. Functional near-infrared spectroscopy (fNIRS) offers non-invasive, cost-effective, and motion-tolerant brain activity monitoring, but existing machine learning approaches for MCI classification using fNIRS face two limitations: 1) underutilization of complementary information between resting-state and task-state data, and 2) high feature dimensionality relative to small sample sizes, limiting model robustness and generalizability. We propose a spatio-temporal feature engineering framework addressing these gaps.Methods: Resting-state fNIRS signals are processed via independent component analysis to derive subject-specific spatial filters, which are then clustered into a universal population-level filter set. This filter set isolates spatial features from task-state signals. Then, temporal feature selection combines variance-based and advanced methods to further reduce dimensionality by identifying discriminative task-evoked time points relevant to MCI detection. The framework integrates fNIRS spatial filtering (resting-state) and temporal selection (task-state) critical for MCI detection.Results: Validated on 104 participants, this framework achieved a single-run best of 90.91% accuracy for cognitively normal vs. MCI classification, with 91.07% feature dimensionality reduction, suggest the potential for generalizable MCI detection and efficient model retraining for expanding clinical data. Feature analysis reveals (1) universal spatial filters linked to MCI biomarkers and (2) temporal weights highlighting critical decision time points during cognitive tasks.Conclusion: By resolving the integration gap between resting-state neurovascular patterns with task-evoked hemodynamic dynamics while reducing dimensionality, the framework achieves higher accuracy and interpretability, advancing fNIRS-based MCI detection.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"77-90"},"PeriodicalIF":4.4,"publicationDate":"2026-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11368855","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146223693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-29DOI: 10.1109/JTEHM.2026.3659415
{"title":"2025 Index IEEE Journal of Translational Engineering in Health and Medicine Vol. 13","authors":"","doi":"10.1109/JTEHM.2026.3659415","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3659415","url":null,"abstract":"","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"573-588"},"PeriodicalIF":4.4,"publicationDate":"2026-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11368643","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1109/JTEHM.2026.3657639
Abel Torres;Luis Estrada-Petrocelli;Tim Raveling;Marieke L. Duiverman
Objective: Accurate detection of inspiratory onset and offset in the diaphragm electromyographic signal (EMGdi) is clinically relevant to assess patient-ventilator interaction in COPD patients undergoing non-invasive ventilation (NIV). Manual annotations are time-consuming and subject to inter-observer variability, highlighting the need for reliable automatic methods. Method: We developed a fully automatic algorithm to detect EMGdi activity cycles and their onset/offset timing in overnight NIV recordings. Four ECG suppression approaches were combined with root mean square (RMS) and fixed sample entropy (fSE) envelopes, and a novel bias correction strategy based on inspiratory-to-basal signal-to-noise ratio (I2BSNR) was introduced. Performance was compared with double-blind annotations from two independent experts. Results: In a cohort of 10 severe COPD patients (9212 annotated cycles), the best configuration (adaptive filtering with fSE exponential envelope) achieved F$1=0.96$ , with onset bias −28 ms (SD 270 ms) and offset bias + 120 ms (SD 292 ms). We show that fSE-based envelopes consistently outperform RMS in onset/offset detection, and that I2BSNR-based correction reduces systematic bias to within accepted clinical timing windows. Conclusions: The proposed method provides accurate and robust onset/offset detection of EMGdi during NIV in COPD patients. This enables reliable quantification of patient-ventilator asynchronies such as ineffective efforts and delayed cycling, offering direct clinical value for optimizing nightly ventilator settings in severe COPD. Clinical and Impact: Reliable detection of patient inspiratory activity offers a practical tool to guide real-time ventilator adjustments and reduce patient-ventilator asynchronies
目的：准确检测膈肌电图信号（EMGdi）的吸气起始和偏移量，对评估COPD无创通气（NIV）患者与呼吸机的相互作用具有临床意义。手动注释非常耗时，并且受观察者之间的可变性的影响，这突出了对可靠的自动方法的需求。方法：我们开发了一种全自动算法来检测EMGdi活动周期及其在夜间NIV记录中的发作/偏移时间。将四种ECG抑制方法与均方根（RMS）和固定样本熵（fSE）包络相结合，提出了一种基于激励-基信噪比（I2BSNR）的新型偏置校正策略。性能由两位独立专家的双盲注释进行比较。结果：在10例重度COPD患者（9212个带注周期）的队列中，最佳配置（fSE指数包络自适应滤波）达到F $1=0.96$，发病偏差为- 28 ms (SD 270 ms)，偏移偏差为+ 120 ms （SD 292 ms）。我们发现基于fse的包络在发病/偏移检测方面始终优于RMS，并且基于i2bsnr的校正将系统偏差减少到可接受的临床时间窗口内。结论：该方法提供了COPD患者NIV期间EMGdi的准确和可靠的起病/偏移检测。这可以可靠地量化患者与呼吸机的不同步，如无效的努力和延迟的循环，为优化严重COPD患者夜间呼吸机设置提供直接的临床价值。临床和影响：可靠的患者吸气活动检测为指导实时呼吸机调整和减少患者与呼吸机的不同步提供了实用的工具
{"title":"Automatic Detection of Onset and Offset of Respiratory Electromyographic Activity in Severe COPD Patients on Non-Invasive Mechanical Ventilation","authors":"Abel Torres;Luis Estrada-Petrocelli;Tim Raveling;Marieke L. Duiverman","doi":"10.1109/JTEHM.2026.3657639","DOIUrl":"https://doi.org/10.1109/JTEHM.2026.3657639","url":null,"abstract":"Objective: Accurate detection of inspiratory onset and offset in the diaphragm electromyographic signal (EMGdi) is clinically relevant to assess patient-ventilator interaction in COPD patients undergoing non-invasive ventilation (NIV). Manual annotations are time-consuming and subject to inter-observer variability, highlighting the need for reliable automatic methods. Method: We developed a fully automatic algorithm to detect EMGdi activity cycles and their onset/offset timing in overnight NIV recordings. Four ECG suppression approaches were combined with root mean square (RMS) and fixed sample entropy (fSE) envelopes, and a novel bias correction strategy based on inspiratory-to-basal signal-to-noise ratio (I2BSNR) was introduced. Performance was compared with double-blind annotations from two independent experts. Results: In a cohort of 10 severe COPD patients (9212 annotated cycles), the best configuration (adaptive filtering with fSE exponential envelope) achieved F<inline-formula> <tex-math>$1=0.96$ </tex-math></inline-formula>, with onset bias −28 ms (SD 270 ms) and offset bias + 120 ms (SD 292 ms). We show that fSE-based envelopes consistently outperform RMS in onset/offset detection, and that I2BSNR-based correction reduces systematic bias to within accepted clinical timing windows. Conclusions: The proposed method provides accurate and robust onset/offset detection of EMGdi during NIV in COPD patients. This enables reliable quantification of patient-ventilator asynchronies such as ineffective efforts and delayed cycling, offering direct clinical value for optimizing nightly ventilator settings in severe COPD. Clinical and Impact: Reliable detection of patient inspiratory activity offers a practical tool to guide real-time ventilator adjustments and reduce patient-ventilator asynchronies","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"14 ","pages":"55-66"},"PeriodicalIF":4.4,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11363213","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：