Objective: To address the limitations of conventional aphasia therapy by developing and clinically evaluating a machine learning based interactive lab for personalized rehabilitation in post-stroke patients. Methods and Procedures: A four week clinical trial was conducted with 27 aphasia patients, randomly assigned to an experimental group ($n=11$ ) using the Language Interactive Lab and a control group ($n=16$ ) receiving conventional therapy. Language performance was assessed using the Chinese Communicative Aphasia Test (CCAT). System interaction data were also used to train classifiers for aphasia severity and recovery tracking. Results: The experimental group showed statistically significant improvements in 7 out of 9 CCAT subtests ($p lt 0.05$ ) and a highly significant total score increase ($p lt 0.001$ ) compared to the control group. Machine learning classifiers achieved up to 91.7% accuracy in predicting aphasia severity and recovery progression. Conclusion: The proposed interactive lab integrates gamified therapy with real time, explainable machine learning assessment, demonstrates clinical efficacy in improving language outcomes, and offers a scalable framework for AI-driven, adaptive neurorehabilitation that has been clinically validated within a hospital setting and designed to align with Taiwan Food and Drug Administration (TFDA) software-as-a-medical-device (SaMD) regulatory principles for translational deployment in clinical environments and hospital investigational use guidelines. Clinical Impact—The integration of gamified digital therapy with machine learning analytics supports personalized, data driven intervention for aphasia rehabilitation in both clinical and home settings, particularly in resource limited environments. Clinical and Translational Impact Statement—This study supports Clinical Research by demonstrating that AI-powered digital therapy significantly improves language outcomes in post-stroke aphasia patients and offers a pathway to scalable, at home neurorehabilitation.
{"title":"Translational Evaluation of a Machine Learning-Based Interactive Lab for Aphasia Rehabilitation in Post Stroke Patients","authors":"Mukul Kumar;Rei-Zhe Wu;Shih-Ching Yeh;Eric Hsiao-Kuang Wu;Po-Yi Tsai","doi":"10.1109/JTEHM.2025.3638643","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3638643","url":null,"abstract":"Objective: To address the limitations of conventional aphasia therapy by developing and clinically evaluating a machine learning based interactive lab for personalized rehabilitation in post-stroke patients. Methods and Procedures: A four week clinical trial was conducted with 27 aphasia patients, randomly assigned to an experimental group (<inline-formula> <tex-math>$n=11$ </tex-math></inline-formula>) using the Language Interactive Lab and a control group (<inline-formula> <tex-math>$n=16$ </tex-math></inline-formula>) receiving conventional therapy. Language performance was assessed using the Chinese Communicative Aphasia Test (CCAT). System interaction data were also used to train classifiers for aphasia severity and recovery tracking. Results: The experimental group showed statistically significant improvements in 7 out of 9 CCAT subtests (<inline-formula> <tex-math>$p lt 0.05$ </tex-math></inline-formula>) and a highly significant total score increase (<inline-formula> <tex-math>$p lt 0.001$ </tex-math></inline-formula>) compared to the control group. Machine learning classifiers achieved up to 91.7% accuracy in predicting aphasia severity and recovery progression. Conclusion: The proposed interactive lab integrates gamified therapy with real time, explainable machine learning assessment, demonstrates clinical efficacy in improving language outcomes, and offers a scalable framework for AI-driven, adaptive neurorehabilitation that has been clinically validated within a hospital setting and designed to align with Taiwan Food and Drug Administration (TFDA) software-as-a-medical-device (SaMD) regulatory principles for translational deployment in clinical environments and hospital investigational use guidelines. Clinical Impact—The integration of gamified digital therapy with machine learning analytics supports personalized, data driven intervention for aphasia rehabilitation in both clinical and home settings, particularly in resource limited environments. Clinical and Translational Impact Statement—This study supports Clinical Research by demonstrating that AI-powered digital therapy significantly improves language outcomes in post-stroke aphasia patients and offers a pathway to scalable, at home neurorehabilitation.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"561-570"},"PeriodicalIF":4.4,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11271240","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145729291","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}
Cervical intraepithelial neoplasia (CIN) represents a spectrum of premalignant lesions requiring accurate early detection to prevent progression to invasive cervical cancer. Colposcopy with visual inspection using acetic acid (VIA) is the gold standard for CIN assessment but suffers from substantial interobserver variability, limiting diagnostic consistency. We evaluated hyperspectral imaging (HSI) as an objective, non-invasive method for characterizing CIN-related tissue changes. This prospective proof-of-principle clinical study enrolled women with histologically confirmed CIN3 indicated for large-loop excision of the transformation zone (LLETZ). Standardized colposcopic images following VIA were obtained and annotated independently by five certified colposcopists according to IFCPC Rio 2011 classification. These annotations served as pathological tissue region references and were quantitatively assessed using intersection over union metrics to evaluate interobserver agreement. HSI was performed immediately prior to LLETZ using the TIVITA Tissue System, capturing spectral reflectance data across 500–995 nm in 100 wavelength bands. Spatial correspondence between colposcopic and hyperspectral images was achieved through homography transformation based on landmark alignment, allowing expert annotations to be projected into the HSI domain. Reflectance spectra from annotated areas were averaged to calculate four proprietary HSI-derived tissue indices, which revealed significantly higher values in CIN-affected regions compared to healthy tissue (p <0.01, Wilcoxon signed-rank test), suggesting increased vascularization and water content. Our findings highlight conventional colposcopy limitations due to examiner subjectivity and support HSI’s potential to provide reproducible, quantitative biomarkers for CIN. HSI integration into clinical workflows may enhance cervical cancer screening objectivity and enable reliable diagnostics in resource-limited settings. Clinical and Translational Impact Statement— Hyperspectral imaging enables objective detection of cervical intraepithelial neoplasia and could improve diagnostic accuracy while reducing unnecessary biopsies
{"title":"Detection of Cervical Intraepithelial Neoplasia Using Hyperspectral Tissue Signatures","authors":"Ovidiu Jurjuţ;Martin Weiss;Yannick Daniel;Sabine Matovina;Felix Neis;Katharina Rall;Katharina Schöpp;Melanie Henes;Walter Linzenbold;Sara Y. Brucker;Jürgen Andress","doi":"10.1109/JTEHM.2025.3630878","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3630878","url":null,"abstract":"Cervical intraepithelial neoplasia (CIN) represents a spectrum of premalignant lesions requiring accurate early detection to prevent progression to invasive cervical cancer. Colposcopy with visual inspection using acetic acid (VIA) is the gold standard for CIN assessment but suffers from substantial interobserver variability, limiting diagnostic consistency. We evaluated hyperspectral imaging (HSI) as an objective, non-invasive method for characterizing CIN-related tissue changes. This prospective proof-of-principle clinical study enrolled women with histologically confirmed CIN3 indicated for large-loop excision of the transformation zone (LLETZ). Standardized colposcopic images following VIA were obtained and annotated independently by five certified colposcopists according to IFCPC Rio 2011 classification. These annotations served as pathological tissue region references and were quantitatively assessed using intersection over union metrics to evaluate interobserver agreement. HSI was performed immediately prior to LLETZ using the TIVITA Tissue System, capturing spectral reflectance data across 500–995 nm in 100 wavelength bands. Spatial correspondence between colposcopic and hyperspectral images was achieved through homography transformation based on landmark alignment, allowing expert annotations to be projected into the HSI domain. Reflectance spectra from annotated areas were averaged to calculate four proprietary HSI-derived tissue indices, which revealed significantly higher values in CIN-affected regions compared to healthy tissue (p <0.01, Wilcoxon signed-rank test), suggesting increased vascularization and water content. Our findings highlight conventional colposcopy limitations due to examiner subjectivity and support HSI’s potential to provide reproducible, quantitative biomarkers for CIN. HSI integration into clinical workflows may enhance cervical cancer screening objectivity and enable reliable diagnostics in resource-limited settings. Clinical and Translational Impact Statement— Hyperspectral imaging enables objective detection of cervical intraepithelial neoplasia and could improve diagnostic accuracy while reducing unnecessary biopsies","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"532-539"},"PeriodicalIF":4.4,"publicationDate":"2025-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11236451","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612106","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: Environmental noise poses a major barrier to the accuracy of self-administered hearing tests conducted outside clinical settings. There is a pressing need for effective noise control solutions to enable reliable hearing threshold measurements in everyday environments. This study introduces an optimized active noise cancellation (ANC) technique based on auditory masking characteristics. Method: The method was implemented in a mobile hearing test system using calibrated true wireless Bluetooth earphones. Electroacoustic validation and clinical testing were conducted across four ANC scenarios: normal, generic ANC off, generic ANC on, and optimized ANC on in 65 dB(A) pink noise. Results: A total of 50 participants completed hearing tests at eight frequencies (0.25–8 kHz), and results were compared to standard audiometry. The optimized ANC yielded the highest signal-to-noise ratio in noisy conditions and demonstrated strong agreement with standard hearing thresholds (r = 0.99, p <.01) in normal environments. Under 65 dB(A) noise, the proposed method significantly outperformed generic ANC with smaller hearing measurement error, improving threshold accuracy across most frequencies. Conclusion: The proposed ANC technique enhances hearing test reliability in noisy conditions, supporting accurate, self-administered hearing assessments outside clinical settings. This technology has strong potential for home or community-based hearing healthcare applications.
目的：环境噪声是在临床环境之外进行的自我听力测试准确性的主要障碍。迫切需要有效的噪声控制解决方案，以便在日常环境中实现可靠的听力阈值测量。本文介绍了一种基于听觉掩蔽特性的优化主动降噪技术。方法：采用校准后的真无线蓝牙耳机在移动听力测试系统中实施该方法。电声验证和临床测试在四种情况下进行：正常、普通ANC关闭、普通ANC打开和65 dB(A)粉红噪声下的优化ANC打开。结果：共有50名参与者完成了8个频率（0.25-8 kHz）的听力测试，并将结果与标准听力学进行了比较。优化后的ANC在噪声条件下产生最高的信噪比，与正常环境下的标准听力阈值非常吻合（r = 0.99, p < 0.01）。在65 dB(A)噪声下，该方法显著优于一般的ANC，具有较小的听力测量误差，提高了大多数频率的阈值精度。结论：提出的ANC技术提高了噪声条件下听力测试的可靠性，支持临床之外准确的、自我管理的听力评估。这项技术在家庭或社区听力保健应用方面具有很大的潜力。
{"title":"Optimized Active Noise Cancellation for Hearing Tests Using Auditory Masking Characteristics","authors":"Hsiu-Lien Cheng;Ying-Hui Lai;Po-Hsun Huang;Wen-Huei Liao","doi":"10.1109/JTEHM.2025.3629999","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3629999","url":null,"abstract":"Objective: Environmental noise poses a major barrier to the accuracy of self-administered hearing tests conducted outside clinical settings. There is a pressing need for effective noise control solutions to enable reliable hearing threshold measurements in everyday environments. This study introduces an optimized active noise cancellation (ANC) technique based on auditory masking characteristics. Method: The method was implemented in a mobile hearing test system using calibrated true wireless Bluetooth earphones. Electroacoustic validation and clinical testing were conducted across four ANC scenarios: normal, generic ANC off, generic ANC on, and optimized ANC on in 65 dB(A) pink noise. Results: A total of 50 participants completed hearing tests at eight frequencies (0.25–8 kHz), and results were compared to standard audiometry. The optimized ANC yielded the highest signal-to-noise ratio in noisy conditions and demonstrated strong agreement with standard hearing thresholds (r = 0.99, p <.01) in normal environments. Under 65 dB(A) noise, the proposed method significantly outperformed generic ANC with smaller hearing measurement error, improving threshold accuracy across most frequencies. Conclusion: The proposed ANC technique enhances hearing test reliability in noisy conditions, supporting accurate, self-administered hearing assessments outside clinical settings. This technology has strong potential for home or community-based hearing healthcare applications.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"540-551"},"PeriodicalIF":4.4,"publicationDate":"2025-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11230825","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145674800","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 : 2025-10-24DOI: 10.1109/JTEHM.2025.3625388
Verónica Barroso-García;Fernando Vaquerizo-Villar;Gonzalo C. Gutiérrez-Tobal;Ehab Dayyat;David Gozal;Timo Leppänen;Roberto Hornero
Objective: Approaches based on a single-channel airflow has shown great potential for simplifying pediatric obstructive sleep apnea (OSA) diagnosis. However, analysis has been limited to feature-engineering techniques, restricting identification of complex respiratory patterns, and reducing diagnostic performance in automated models. Here, we propose deep-learning and explainable artificial intelligence (XAI) to estimate the pediatric OSA severity from airflow, while ensuring transparency in automatic decisions. Technology or Method: We used 3,672 overnight airflow recordings from four pediatric datasets. A convolutional neural network (CNN)-based regression model was trained to estimate the apnea-hypopnea index (AHI) and predict OSA severity. We evaluated and compared Gradient-Weighted Class Activation Mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP) to identify the airflow regions where the CNN focuses for predictions. Results: The proposed model demonstrated high concordance between the actual and estimated AHI (intraclass correlation coefficient from 0.69 to 0.87 in the test group), and high diagnostic performance: four-class Cohen’s kappa between 0.37 and 0.43 and accuracies of 82.03%, 97.09%, and 99.03% for three OSA severity cutoffs (i.e. 1, 5, and 10 e/h) in the test group. The interpretability analysis with Grad-CAM and SHAP revealed that the CNN accurately identifies apneic events by focusing on their onset and offset. Both techniques provided complementary information about the model’s decision-making. While Grad-CAM highlighted respiratory events with abrupt signal changes, SHAP captured more subtle patterns with noise included. Conclusions: Accordingly, our model can help automatically detect pediatric OSA and offers clinicians an explainable approach that enhances credibility and usability, thus providing a path toward clinical translation in early diagnosis. Clinical Impact: This study presents an interpretable deep-learning tool using airflow to accurately detect pediatric obstructive sleep apnea, enabling early, objective diagnosis and supporting clinical decision-making through identification of relevant respiratory patterns.
{"title":"An Explainable Deep-Learning Approach to Detect Pediatric Sleep Apnea From Single-Channel Airflow","authors":"Verónica Barroso-García;Fernando Vaquerizo-Villar;Gonzalo C. Gutiérrez-Tobal;Ehab Dayyat;David Gozal;Timo Leppänen;Roberto Hornero","doi":"10.1109/JTEHM.2025.3625388","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3625388","url":null,"abstract":"Objective: Approaches based on a single-channel airflow has shown great potential for simplifying pediatric obstructive sleep apnea (OSA) diagnosis. However, analysis has been limited to feature-engineering techniques, restricting identification of complex respiratory patterns, and reducing diagnostic performance in automated models. Here, we propose deep-learning and explainable artificial intelligence (XAI) to estimate the pediatric OSA severity from airflow, while ensuring transparency in automatic decisions. Technology or Method: We used 3,672 overnight airflow recordings from four pediatric datasets. A convolutional neural network (CNN)-based regression model was trained to estimate the apnea-hypopnea index (AHI) and predict OSA severity. We evaluated and compared Gradient-Weighted Class Activation Mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP) to identify the airflow regions where the CNN focuses for predictions. Results: The proposed model demonstrated high concordance between the actual and estimated AHI (intraclass correlation coefficient from 0.69 to 0.87 in the test group), and high diagnostic performance: four-class Cohen’s kappa between 0.37 and 0.43 and accuracies of 82.03%, 97.09%, and 99.03% for three OSA severity cutoffs (i.e. 1, 5, and 10 e/h) in the test group. The interpretability analysis with Grad-CAM and SHAP revealed that the CNN accurately identifies apneic events by focusing on their onset and offset. Both techniques provided complementary information about the model’s decision-making. While Grad-CAM highlighted respiratory events with abrupt signal changes, SHAP captured more subtle patterns with noise included. Conclusions: Accordingly, our model can help automatically detect pediatric OSA and offers clinicians an explainable approach that enhances credibility and usability, thus providing a path toward clinical translation in early diagnosis. Clinical Impact: This study presents an interpretable deep-learning tool using airflow to accurately detect pediatric obstructive sleep apnea, enabling early, objective diagnosis and supporting clinical decision-making through identification of relevant respiratory patterns.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"517-531"},"PeriodicalIF":4.4,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11216356","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145510122","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 : 2025-10-24DOI: 10.1109/JTEHM.2025.3625144
Beatriz S. Arruda;Moaad Benjaber;John Fleming;Robert Toth;Colin G. McNamara;Andrew Sharott;Timothy Denison;Hayriye Cagnan
Background: Tremor is the most common movement disorder and a prevalent symptom of neurodegenerative conditions such as Parkinson’s disease (PD). Given the limitations of medication, which may not effectively treat tremor, and the limited availability of surgical treatments such as deep brain stimulation, there is a pressing clinical need for non-invasive therapeutic alternatives, including peripheral electrical stimulation. The high variability of PD tremor poses a challenge to such therapies and calls for person-specific stimulation parameters. Methods: We developed a wrist-worn system incorporating an adaptable phase-tracking algorithm designed for real-time estimation of Parkinsonian rest tremor phase. The algorithm dynamically adapts to tremor variability, including changes in the axis of maximum excursion and center frequency. The system was first validated offline, followed by in-clinic feasibility testing in three individuals with PD. The system triggered the delivery of both phasic and open-loop electrical stimulation to the participant’s wrist. Results: Robust phase estimation was achieved both offline and in all participants. The system adapted to changes in tremor dominant axis and center frequency. Modest tremor modulation was observed at select person-specific settings. Conclusion: This work provides a novel platform for research involving tremor phase tracking, accounting for PD tremor variability, and a foundation for developing personalized, non-invasive tremor management strategies. Clinical and Translational Impact Statement—This study presents a wearable system for adaptive tremor phase tracking validated in individuals with Parkinson’s disease and establishes a foundation for further development of personalized non-invasive tremor management strategies. Category: Clinical Research
{"title":"An Adaptable Phase-Tracking System for Parkinsonian Rest Tremor: Design and In-Clinic Feasibility","authors":"Beatriz S. Arruda;Moaad Benjaber;John Fleming;Robert Toth;Colin G. McNamara;Andrew Sharott;Timothy Denison;Hayriye Cagnan","doi":"10.1109/JTEHM.2025.3625144","DOIUrl":"10.1109/JTEHM.2025.3625144","url":null,"abstract":"Background: Tremor is the most common movement disorder and a prevalent symptom of neurodegenerative conditions such as Parkinson’s disease (PD). Given the limitations of medication, which may not effectively treat tremor, and the limited availability of surgical treatments such as deep brain stimulation, there is a pressing clinical need for non-invasive therapeutic alternatives, including peripheral electrical stimulation. The high variability of PD tremor poses a challenge to such therapies and calls for person-specific stimulation parameters. Methods: We developed a wrist-worn system incorporating an adaptable phase-tracking algorithm designed for real-time estimation of Parkinsonian rest tremor phase. The algorithm dynamically adapts to tremor variability, including changes in the axis of maximum excursion and center frequency. The system was first validated offline, followed by in-clinic feasibility testing in three individuals with PD. The system triggered the delivery of both phasic and open-loop electrical stimulation to the participant’s wrist. Results: Robust phase estimation was achieved both offline and in all participants. The system adapted to changes in tremor dominant axis and center frequency. Modest tremor modulation was observed at select person-specific settings. Conclusion: This work provides a novel platform for research involving tremor phase tracking, accounting for PD tremor variability, and a foundation for developing personalized, non-invasive tremor management strategies. Clinical and Translational Impact Statement—This study presents a wearable system for adaptive tremor phase tracking validated in individuals with Parkinson’s disease and establishes a foundation for further development of personalized non-invasive tremor management strategies. Category: Clinical Research","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"507-516"},"PeriodicalIF":4.4,"publicationDate":"2025-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12599896/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145497553","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 : 2025-10-22DOI: 10.1109/JTEHM.2025.3624469
Aaesha Alzaabi;Imran Saied;Tughrul Arslan
Objective: This study describes the design and evaluation of volunteer user trials of an unobtrusive Wi-Fi Channel State Information (CSI) vital sign sensing system in older participants aged 60 years and older in different home environments. Methods and procedures: In terms of experiment design, the implementation of user-centric sensor placement and integration informed consent with various experimental elements in the design of experiments of older people. The implemented signal processing algorithm, which extracts vital signs from the Wi-Fi CSI signal to obtain respiration and heart rate measurements, employs wavelet filtering techniques. For selecting of vital sign signals from the 52 CSI subcarriers, the Principal Component Sample Entropy (PC-SampEn) was implemented to capture the information most relevant to vital signs.Results: Two cardiorespiratory vital sign measurements were validated against wearable ground-truth devices, a respiratory belt and a photoplethysmogram (PPG). The results demonstrated an expected decrease in accuracy and measurement agreement in uncontrolled home environments.Conclusion: Although respiratory rate measurements have demonstrated promising accuracy and agreement in uncontrolled environments, heart rate measurements observed high variability in these scenarios due to challenging signal extraction. Further experiments must be conducted to address the limitation in sample size and the technical challenges in heart rate signal extraction to improve accuracy. Clinical and Translational Impact: This study provides a design of unobtrusive care technology for vital sign sensing for older adults, demonstrated and evaluated in the context of in-home monitoring for healthcare.
{"title":"Design and Evaluation of Volunteer User Trials of Unobtrusive Vital Signs Monitoring for Older People in Care Using Wi-Fi CSI Sensing","authors":"Aaesha Alzaabi;Imran Saied;Tughrul Arslan","doi":"10.1109/JTEHM.2025.3624469","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3624469","url":null,"abstract":"Objective: This study describes the design and evaluation of volunteer user trials of an unobtrusive Wi-Fi Channel State Information (CSI) vital sign sensing system in older participants aged 60 years and older in different home environments. Methods and procedures: In terms of experiment design, the implementation of user-centric sensor placement and integration informed consent with various experimental elements in the design of experiments of older people. The implemented signal processing algorithm, which extracts vital signs from the Wi-Fi CSI signal to obtain respiration and heart rate measurements, employs wavelet filtering techniques. For selecting of vital sign signals from the 52 CSI subcarriers, the Principal Component Sample Entropy (PC-SampEn) was implemented to capture the information most relevant to vital signs.Results: Two cardiorespiratory vital sign measurements were validated against wearable ground-truth devices, a respiratory belt and a photoplethysmogram (PPG). The results demonstrated an expected decrease in accuracy and measurement agreement in uncontrolled home environments.Conclusion: Although respiratory rate measurements have demonstrated promising accuracy and agreement in uncontrolled environments, heart rate measurements observed high variability in these scenarios due to challenging signal extraction. Further experiments must be conducted to address the limitation in sample size and the technical challenges in heart rate signal extraction to improve accuracy. Clinical and Translational Impact: This study provides a design of unobtrusive care technology for vital sign sensing for older adults, demonstrated and evaluated in the context of in-home monitoring for healthcare.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"480-492"},"PeriodicalIF":4.4,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11214363","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455865","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: Therapeutic drug monitoring (TDM) is essential for managing medication dosages in critically ill patients, particularly for antibiotics such as vancomycin. The dynamic physiological conditions of critically ill patients require frequent monitoring of vancomycin levels to ensure therapeutic therapeutic efficacy while minimizing toxicity. Traditional Bayesian methods and pharmacokinetic (PK) models often fail because of the complex and unpredictable nature of these patients’ conditions, as well as the limitations of standard PK modeling.Methods and procedures: This study aimed to establish a gated recurrent unit (GRU)-integrated joint multilayer perceptron network (GointMLP) model to predict sequential vancomycin TDM levels in patients in the intensive care unit. The proposed model consists of three modules to maintain consistent therapeutic vancomycin concentrations while accommodating individual patient differences. By integrating regression and classification predictions, GointMLP provides a dual mechanism for clinicians to verify the reliability of predicted values for informed decision-making. Additionally, we have developed DeepTDM, a comprehensive decision support system designed for real-time vancomycin dose optimization to enhance clinical outcomes.Results: The GointMLP provides more accurate predictions compared to traditional PK models and other machine learning/deep learning approaches. This superior performance is demonstrated not only in local validation cohorts but also in the ethnically diverse MIMIC-IV dataset, validating the model’s robust generalizability.Conclusion: This work addresses the limitations of current methodologies while leveraging advancements in deep learning techniques, particularly demonstrating the effectiveness of GointMLP in enhancing patient outcomes through precise TDM. Efforts are underway to integrate DeepTDM into clinical practice, with the anticipation that it will not only support clinicians in decision-making but also substantially improve therapeutic outcomes for patients undergoing vancomycin therapy. Clinical and Translational Impact Statement: The proposed model and software enable individualized vancomycin dosing for critically ill patients, improving precision dosing and supporting seamless integration into clinical workflows
{"title":"DeepTDM: Deep Learning-Based Prediction of Sequential Therapeutic Drug Monitoring Levels of Vancomycin","authors":"Jinkyeong Park;Dohyun Kim;Donghoon Lee;Minkyu Kim;Yoon Kim;Seon-Sook Han;Yeonjeong Heo;Hyun-Soo Choi","doi":"10.1109/JTEHM.2025.3623605","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3623605","url":null,"abstract":"Objective: Therapeutic drug monitoring (TDM) is essential for managing medication dosages in critically ill patients, particularly for antibiotics such as vancomycin. The dynamic physiological conditions of critically ill patients require frequent monitoring of vancomycin levels to ensure therapeutic therapeutic efficacy while minimizing toxicity. Traditional Bayesian methods and pharmacokinetic (PK) models often fail because of the complex and unpredictable nature of these patients’ conditions, as well as the limitations of standard PK modeling.Methods and procedures: This study aimed to establish a gated recurrent unit (GRU)-integrated joint multilayer perceptron network (GointMLP) model to predict sequential vancomycin TDM levels in patients in the intensive care unit. The proposed model consists of three modules to maintain consistent therapeutic vancomycin concentrations while accommodating individual patient differences. By integrating regression and classification predictions, GointMLP provides a dual mechanism for clinicians to verify the reliability of predicted values for informed decision-making. Additionally, we have developed DeepTDM, a comprehensive decision support system designed for real-time vancomycin dose optimization to enhance clinical outcomes.Results: The GointMLP provides more accurate predictions compared to traditional PK models and other machine learning/deep learning approaches. This superior performance is demonstrated not only in local validation cohorts but also in the ethnically diverse MIMIC-IV dataset, validating the model’s robust generalizability.Conclusion: This work addresses the limitations of current methodologies while leveraging advancements in deep learning techniques, particularly demonstrating the effectiveness of GointMLP in enhancing patient outcomes through precise TDM. Efforts are underway to integrate DeepTDM into clinical practice, with the anticipation that it will not only support clinicians in decision-making but also substantially improve therapeutic outcomes for patients undergoing vancomycin therapy. Clinical and Translational Impact Statement: The proposed model and software enable individualized vancomycin dosing for critically ill patients, improving precision dosing and supporting seamless integration into clinical workflows","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"493-506"},"PeriodicalIF":4.4,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11208607","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145455835","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 : 2025-10-09DOI: 10.1109/JTEHM.2025.3619802
Kelly Long;Ganesh M. Babulal;Sayeh Bayat
Objective: To examine how early pathophysiological changes in Alzheimer’s disease (AD) affect navigational decision-making by analyzing the complexity of driving routes in older adults with and without preclinical AD. Methods: We developed a novel route complexity metric based on the number of left and right turns and the deviation from the most direct path, accounting for cognitive load during navigation. Naturalistic GPS driving data were collected for a year from 111 older adults aged 65–85, with preclinical AD status determined via cerebrospinal fluid amyloid biomarkers. A multiple linear regression model was used to assess the relationship between age, preclinical AD status, and route complexity. Results: The findings of this study indicate that preclinical AD may influence the navigational abilities of older adults. After controlling for age, participants with preclinical AD chose routes with higher baseline complexity than the control group. It further revealed that participants with preclinical AD selected routes with lower complexity as they aged—a trend not observed in healthy controls. Conclusion: Preclinical AD is associated with changes in spatial decision-making that are observable in real-world driving behaviours. The age-related decline in route complexity among those with preclinical AD may reflect compensatory strategies or progressive cognitive changes. Clinical Impact: This study presents a non-invasive, behaviour-based metric that could support early detection of cognitive decline. It may also inform the design of personalized mobility interventions and dementia-friendly mobility systems.
{"title":"Characterizing Navigational Changes in Preclinical Alzheimer’s Disease: A Route Complexity Metric Derived From Naturalistic Driving Data","authors":"Kelly Long;Ganesh M. Babulal;Sayeh Bayat","doi":"10.1109/JTEHM.2025.3619802","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3619802","url":null,"abstract":"Objective: To examine how early pathophysiological changes in Alzheimer’s disease (AD) affect navigational decision-making by analyzing the complexity of driving routes in older adults with and without preclinical AD. Methods: We developed a novel route complexity metric based on the number of left and right turns and the deviation from the most direct path, accounting for cognitive load during navigation. Naturalistic GPS driving data were collected for a year from 111 older adults aged 65–85, with preclinical AD status determined via cerebrospinal fluid amyloid biomarkers. A multiple linear regression model was used to assess the relationship between age, preclinical AD status, and route complexity. Results: The findings of this study indicate that preclinical AD may influence the navigational abilities of older adults. After controlling for age, participants with preclinical AD chose routes with higher baseline complexity than the control group. It further revealed that participants with preclinical AD selected routes with lower complexity as they aged—a trend not observed in healthy controls. Conclusion: Preclinical AD is associated with changes in spatial decision-making that are observable in real-world driving behaviours. The age-related decline in route complexity among those with preclinical AD may reflect compensatory strategies or progressive cognitive changes. Clinical Impact: This study presents a non-invasive, behaviour-based metric that could support early detection of cognitive decline. It may also inform the design of personalized mobility interventions and dementia-friendly mobility systems.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"471-479"},"PeriodicalIF":4.4,"publicationDate":"2025-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11197551","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145352142","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 : 2025-09-23DOI: 10.1109/JTEHM.2025.3613609
Huawei Jiang;Husna Mutahira;Shibo Wei;Mannan Saeed Muhammad
Objective: The detection of heart abnormalities using electrocardiograms (ECG) is a critical task in medical diagnostics. A lot of literature has utilized ResNet and Transformer architectures to detect heart disease based on ECG signals. Recently, a new class of algorithms has emerged, challenging these established methods. A selective state space model (SSM) called Mamba has exhibited promising potential as an alternative to Transformers due to its efficient handling of longer sequences. In this context, we propose a Mamba-based model for detecting heart abnormalities, named ECG-Mamba. Recognizing that common data augmentation methods such as MixUp and CutMix do not perform well with Mamba on ECG data, we introduce a data augmentation technique called non-uniform-mix to enhance the model’s performance.Methods and procedures: ECG-Mamba is based on Vision Mamba (Vim), a variant of Mamba that utilizes a bidirectional SSM, enhancing its capability to process ECG data effectively. To address the sensitivity of the Mamba model to noise and the lack of suitable data augmentation techniques, we propose a data augmentation algorithm that conservatively introduces data augmentation by performing non-uniform operations on the dataset across different epochs. Specifically, we apply MixUp to a portion of the dataset in different epochs.Results: Experimental results indicate that ECG-Mamba outperforms the best algorithms in the PhysioNet/Computing in Cardiology (CinC) Challenges of 2020 and 2021 based on the AUPRC and AUROC, specifically with ECG-Mamba achieving an AUPRC score 16.6% higher than the best algorithm in the PhysioNet/CinC Challenge 2021 on 12-lead ECGs, reaching 0.61. Moreover, with the proposed data augmentation method Non-Uniform-Mix, ECG-Mamba’s AUPRC reached 0.6271, representing a 2.8% improvement.Conclusion: The ECG-Mamba model, based on the SSM, demonstrates potential in detecting cardiac abnormalities from ECG data. Although the model surpasses existing algorithms, it exhibits sensitivity to noise, requiring careful data augmentation. The proposed conservative data augmentation technique addresses this challenge and improves the model’s performance, suggesting a promising direction for future research in ECG analysis using SSMs. The implementation is publicly available at https://huggingface.co/poult/ECGMambaVersionOfJTEHM2020-2021_final.Clinical and Translational Impact Statement: ECG-Mamba enhances heart abnormality detection, enabling early diagnosis and personalised treatment in resource-limited and telemedicine settings. Using real-world data from the PhysioNet/CinC Challenges 2020 and 2021, it accurately models multiple concurrent cardiac conditions, reflecting complex clinical scenarios. Its conservative Non-Uniform-Mix augmentation mitigates noise sensitivity, improving accuracy and reliability for seamless integration into clinical workflows, thus supporting evidence-based practice and addressing healthcare disparities.
目的：利用心电图检测心脏异常是医学诊断中的一项重要任务。许多文献利用ResNet和Transformer架构来检测基于心电信号的心脏病。最近，一类新的算法出现了，挑战这些既定的方法。选择性状态空间模型（SSM）称为曼巴已经显示出有希望的潜力，作为替代变形金刚由于其有效的处理较长的序列。在这种情况下，我们提出了一种基于曼巴的检测心脏异常的模型，称为ecg -曼巴。认识到常见的数据增强方法如MixUp和CutMix在曼巴心电图数据上表现不佳，我们引入了一种称为非均匀混合的数据增强技术来提高模型的性能。方法和步骤：ECG-Mamba是基于视觉曼巴（Vim），曼巴的一种变体，利用双向SSM，增强其有效处理ECG数据的能力。为了解决曼巴模型对噪声的敏感性和缺乏合适的数据增强技术，我们提出了一种数据增强算法，该算法通过在不同时代的数据集上执行非均匀操作来保守地引入数据增强。具体来说，我们将MixUp应用于不同时代的部分数据集。结果：实验结果表明，在基于AUPRC和AUROC的2020年和2021年的PhysioNet/Computing in Cardiology （cinology）挑战赛中，ECG-Mamba的表现优于最佳算法，特别是在12联头心电图上，ECG-Mamba的AUPRC得分比最佳算法高出16.6%，达到0.61。此外，采用本文提出的数据增强方法Non-Uniform-Mix， ECG-Mamba的AUPRC达到0.6271，提高2.8%。结论：基于SSM的ECG- mamba模型显示了从ECG数据检测心脏异常的潜力。尽管该模型超越了现有的算法，但它对噪声很敏感，需要仔细地增强数据。所提出的保守数据增强技术解决了这一挑战，提高了模型的性能，为使用ssm进行心电分析的未来研究提供了一个有希望的方向。该技术的实施可在https://huggingface.co/poult/ECGMambaVersionOfJTEHM2020-2021_final.Clinical和转化影响声明中公开获得：ECG-Mamba增强了心脏异常检测，使资源有限和远程医疗环境中的早期诊断和个性化治疗成为可能。使用来自PhysioNet/CinC挑战2020和2021的真实世界数据，它准确地模拟了多种并发心脏病，反映了复杂的临床场景。其保守的非均匀混合增强功能减轻了噪声敏感性，提高了与临床工作流程无缝集成的准确性和可靠性，从而支持循证实践并解决医疗保健差异。
{"title":"ECG-Mamba: Cardiac Abnormality Classification With Non-Uniform-Mix Augmentation on 12-Lead ECGs","authors":"Huawei Jiang;Husna Mutahira;Shibo Wei;Mannan Saeed Muhammad","doi":"10.1109/JTEHM.2025.3613609","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3613609","url":null,"abstract":"Objective: The detection of heart abnormalities using electrocardiograms (ECG) is a critical task in medical diagnostics. A lot of literature has utilized ResNet and Transformer architectures to detect heart disease based on ECG signals. Recently, a new class of algorithms has emerged, challenging these established methods. A selective state space model (SSM) called Mamba has exhibited promising potential as an alternative to Transformers due to its efficient handling of longer sequences. In this context, we propose a Mamba-based model for detecting heart abnormalities, named ECG-Mamba. Recognizing that common data augmentation methods such as MixUp and CutMix do not perform well with Mamba on ECG data, we introduce a data augmentation technique called non-uniform-mix to enhance the model’s performance.Methods and procedures: ECG-Mamba is based on Vision Mamba (Vim), a variant of Mamba that utilizes a bidirectional SSM, enhancing its capability to process ECG data effectively. To address the sensitivity of the Mamba model to noise and the lack of suitable data augmentation techniques, we propose a data augmentation algorithm that conservatively introduces data augmentation by performing non-uniform operations on the dataset across different epochs. Specifically, we apply MixUp to a portion of the dataset in different epochs.Results: Experimental results indicate that ECG-Mamba outperforms the best algorithms in the PhysioNet/Computing in Cardiology (CinC) Challenges of 2020 and 2021 based on the AUPRC and AUROC, specifically with ECG-Mamba achieving an AUPRC score 16.6% higher than the best algorithm in the PhysioNet/CinC Challenge 2021 on 12-lead ECGs, reaching 0.61. Moreover, with the proposed data augmentation method Non-Uniform-Mix, ECG-Mamba’s AUPRC reached 0.6271, representing a 2.8% improvement.Conclusion: The ECG-Mamba model, based on the SSM, demonstrates potential in detecting cardiac abnormalities from ECG data. Although the model surpasses existing algorithms, it exhibits sensitivity to noise, requiring careful data augmentation. The proposed conservative data augmentation technique addresses this challenge and improves the model’s performance, suggesting a promising direction for future research in ECG analysis using SSMs. The implementation is publicly available at <uri>https://huggingface.co/poult/ECGMambaVersionOfJTEHM2020-2021_final</uri>.Clinical and Translational Impact Statement: ECG-Mamba enhances heart abnormality detection, enabling early diagnosis and personalised treatment in resource-limited and telemedicine settings. Using real-world data from the PhysioNet/CinC Challenges 2020 and 2021, it accurately models multiple concurrent cardiac conditions, reflecting complex clinical scenarios. Its conservative Non-Uniform-Mix augmentation mitigates noise sensitivity, improving accuracy and reliability for seamless integration into clinical workflows, thus supporting evidence-based practice and addressing healthcare disparities.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"461-470"},"PeriodicalIF":4.4,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11176036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145315324","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 : 2025-09-18DOI: 10.1109/JTEHM.2025.3611498
Miaoxin Ji;Hongru Dong;Lina Guo;Wen LI
Objective: Parkinson’s disease (PD) diagnosis relies on the evaluation of motor and non-motor symptoms, with gait abnormalities serving as a key marker for early detection. Traditional clinical assessment often relies on visual gait analysis, which is a subjective process prone to bias. This study introduces a PD severity classification method that leverages gait features. Methods: A Spatial-temporal Convolutional neural network-Transformer (ST-CNN-Transformer) model for PD severity classification was established. Multimodal gait data, including foot acceleration, angular velocity, and Vertical Ground Reaction Force (VGRF), were collected in collaboration with Xiangyang First People’s Hospital, Hubei Province. Zero-velocity points (ZVPs) were detected using the Generalized Likelihood Ratio Test (GLRT), and gait cycle features were extracted from inertial measurement unit data for precise segmentation. The ST-CNN-Transformer model captures spatial-temporal features and periodic correlations. Results: Evaluation on a dataset comprising 10 healthy controls and 30 PD patients yielded a classification accuracy of 98.81%, surpassing existing gait-based methods for PD severity classification. Conclusion: This study introduces a deep learning (DL) approach to automating PD severity classification by integrating ZVP and gait segmentation derived from multimodal data. The proposed model significantly enhances diagnostic accuracy. Significance: By combining DL with GLRT-based gait segmentation and multimodal gait analysis, this study proposes a robust and interpretable PD severity assessment framework that contributes to more accurate and objective clinical decision-making.
{"title":"Diagnosis and Severity Rating of Parkinson’s Disease Based on Multimodal Gait Signal Analysis With GLRT and ST-CNN-Transformer Networks","authors":"Miaoxin Ji;Hongru Dong;Lina Guo;Wen LI","doi":"10.1109/JTEHM.2025.3611498","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3611498","url":null,"abstract":"Objective: Parkinson’s disease (PD) diagnosis relies on the evaluation of motor and non-motor symptoms, with gait abnormalities serving as a key marker for early detection. Traditional clinical assessment often relies on visual gait analysis, which is a subjective process prone to bias. This study introduces a PD severity classification method that leverages gait features. Methods: A Spatial-temporal Convolutional neural network-Transformer (ST-CNN-Transformer) model for PD severity classification was established. Multimodal gait data, including foot acceleration, angular velocity, and Vertical Ground Reaction Force (VGRF), were collected in collaboration with Xiangyang First People’s Hospital, Hubei Province. Zero-velocity points (ZVPs) were detected using the Generalized Likelihood Ratio Test (GLRT), and gait cycle features were extracted from inertial measurement unit data for precise segmentation. The ST-CNN-Transformer model captures spatial-temporal features and periodic correlations. Results: Evaluation on a dataset comprising 10 healthy controls and 30 PD patients yielded a classification accuracy of 98.81%, surpassing existing gait-based methods for PD severity classification. Conclusion: This study introduces a deep learning (DL) approach to automating PD severity classification by integrating ZVP and gait segmentation derived from multimodal data. The proposed model significantly enhances diagnostic accuracy. Significance: By combining DL with GLRT-based gait segmentation and multimodal gait analysis, this study proposes a robust and interpretable PD severity assessment framework that contributes to more accurate and objective clinical decision-making.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"450-460"},"PeriodicalIF":4.4,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11172342","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145255901","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：