Pub Date : 2024-02-12DOI: 10.1109/JTEHM.2024.3365300
Jan-Willem Klok;Jessica Groenewegen;Olivier Temmerman;Niels Van Straten;Bart Van Straten;Jenny Dankelman;Tim Horeman
Objective: Cemented total hip arthroplasty (THA) demonstrates superior survival rates compared to uncemented procedures. Nevertheless, most younger patients opt for uncemented THA, as removing well-fixed bone cement in the femur during revisions is complex, particularly the distal cement plug. This removal procedure often increases the risk of femoral fracture or perforation, haemorrhage and weakening bone due to poor drill control and positioning. Aim of this study was to design a novel drill guide to improve drill positioning. Methods and procedures: A novel orthopaedic drill guide was developed, featuring a compliant centralizer activated by a drill guide actuator. Bone models were prepared to assess centralizing performance. Three conditions were tested: drilling without guidance, guided drilling with centralizer activation held, and guided drilling with centralizer activation released. Deviations from the bone centre were measured at the entry and exit point of the drill. Results: In the centralizing performance test, the drill guide significantly reduced drill hole deviations in both entry and exit points compared to the control ( $p < 0.05$ ). The absolute deviation on the exit side of the cement plug was 10.59mm (SD 1.56) for the ‘No drill guide‘ condition, 3.02mm (SD 2.09) for ‘Drill guide – hold‘ and 2.12mm (SD 1.71) for ‘Drill guide – release‘. The compliant drill guide centralizer significantly lowered the risk of cortical bone perforation during intramedullary canal drilling in the bone models due to better control of the cement drill position. Clinical and Translational Impact Statement: The drill guide potentially reduces perioperative risks in cemented femoral stem revision. Future research should identify optimal scenarios for its application.
{"title":"Design and In Vitro Validation of an Orthopaedic Drill Guide for Femoral Stem Revision in Total Hip Arthroplasty","authors":"Jan-Willem Klok;Jessica Groenewegen;Olivier Temmerman;Niels Van Straten;Bart Van Straten;Jenny Dankelman;Tim Horeman","doi":"10.1109/JTEHM.2024.3365300","DOIUrl":"10.1109/JTEHM.2024.3365300","url":null,"abstract":"Objective: Cemented total hip arthroplasty (THA) demonstrates superior survival rates compared to uncemented procedures. Nevertheless, most younger patients opt for uncemented THA, as removing well-fixed bone cement in the femur during revisions is complex, particularly the distal cement plug. This removal procedure often increases the risk of femoral fracture or perforation, haemorrhage and weakening bone due to poor drill control and positioning. Aim of this study was to design a novel drill guide to improve drill positioning. Methods and procedures: A novel orthopaedic drill guide was developed, featuring a compliant centralizer activated by a drill guide actuator. Bone models were prepared to assess centralizing performance. Three conditions were tested: drilling without guidance, guided drilling with centralizer activation held, and guided drilling with centralizer activation released. Deviations from the bone centre were measured at the entry and exit point of the drill. Results: In the centralizing performance test, the drill guide significantly reduced drill hole deviations in both entry and exit points compared to the control (\u0000<inline-formula> <tex-math>$p < 0.05$ </tex-math></inline-formula>\u0000). The absolute deviation on the exit side of the cement plug was 10.59mm (SD 1.56) for the ‘No drill guide‘ condition, 3.02mm (SD 2.09) for ‘Drill guide – hold‘ and 2.12mm (SD 1.71) for ‘Drill guide – release‘. The compliant drill guide centralizer significantly lowered the risk of cortical bone perforation during intramedullary canal drilling in the bone models due to better control of the cement drill position. Clinical and Translational Impact Statement: The drill guide potentially reduces perioperative risks in cemented femoral stem revision. Future research should identify optimal scenarios for its application.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"340-347"},"PeriodicalIF":3.4,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10433182","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139953799","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 : 2024-01-31DOI: 10.1109/JTEHM.2024.3360865
Maksym A. Jopek;Krzysztof Pastuszak;Sebastian Cygert;Myron G. Best;Thomas Wurdinger;Jacek Jassem;Anna J. Żaczek;Anna Supernat
The field of cancer diagnostics has been revolutionized by liquid biopsies, which offer a bridge between laboratory research and clinical settings. These tests are less invasive than traditional biopsies and more convenient than routine imaging methods. Liquid biopsies allow studying of tumor-derived markers in bodily fluids, enabling the development of more precise cancer diagnostic tests for screening, disease monitoring, and therapy personalization. This study presents a multiclass approach based on deep learning to analyze and classify diseases based on blood platelet RNA. Its primary objective is to enhance cancer-type diagnosis in clinical settings by leveraging the power of deep learning combined with high-throughput sequencing of liquid biopsy. Ultimately, the study demonstrates the potential of this approach to accurately identify the patient’s type of cancer. Methods: The developed method classifies patients using heatmap images, generated based on gene expression arranged according to the Kyoto Encyclopedia of Genes and Genomes pathways. The images represent samples of patients with ovarian cancer, endometrial cancer, glioblastoma, non-small cell lung cancer, and sarcoma, as well as cancer patients with brain metastasis. Results: Our deep learning-based models reached 66.51% balanced accuracy when distinguishing between those 6 sites of cancer origin and 90.5% balanced accuracy on a location-specific dataset where cancer types from close locations were grouped. The developed models were further investigated with an explainable artificial intelligence-based approach (XAI) - SHAP. They returned a set of 60 genes with the highest impact on the models’ decision-making process. Conclusions: Our results show that deep-learning methods are a promising opportunity for cancer detection and could support clinicians’ decision-making process in finding the solution for the black-box problem. Clinical and Translational Impact Statement— Utilizing TEPs-based liquid biopsies and deep learning, our study offers a novel approach to early cancer detection, highlighting cancer origin. The integration of Explainable AI reinforces trust in predictive outcomes. Category: Early/Pre-Clinical Research.
{"title":"Deep Learning-Based, Multiclass Approach to Cancer Classification on Liquid Biopsy Data","authors":"Maksym A. Jopek;Krzysztof Pastuszak;Sebastian Cygert;Myron G. Best;Thomas Wurdinger;Jacek Jassem;Anna J. Żaczek;Anna Supernat","doi":"10.1109/JTEHM.2024.3360865","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3360865","url":null,"abstract":"The field of cancer diagnostics has been revolutionized by liquid biopsies, which offer a bridge between laboratory research and clinical settings. These tests are less invasive than traditional biopsies and more convenient than routine imaging methods. Liquid biopsies allow studying of tumor-derived markers in bodily fluids, enabling the development of more precise cancer diagnostic tests for screening, disease monitoring, and therapy personalization. This study presents a multiclass approach based on deep learning to analyze and classify diseases based on blood platelet RNA. Its primary objective is to enhance cancer-type diagnosis in clinical settings by leveraging the power of deep learning combined with high-throughput sequencing of liquid biopsy. Ultimately, the study demonstrates the potential of this approach to accurately identify the patient’s type of cancer. Methods: The developed method classifies patients using heatmap images, generated based on gene expression arranged according to the Kyoto Encyclopedia of Genes and Genomes pathways. The images represent samples of patients with ovarian cancer, endometrial cancer, glioblastoma, non-small cell lung cancer, and sarcoma, as well as cancer patients with brain metastasis. Results: Our deep learning-based models reached 66.51% balanced accuracy when distinguishing between those 6 sites of cancer origin and 90.5% balanced accuracy on a location-specific dataset where cancer types from close locations were grouped. The developed models were further investigated with an explainable artificial intelligence-based approach (XAI) - SHAP. They returned a set of 60 genes with the highest impact on the models’ decision-making process. Conclusions: Our results show that deep-learning methods are a promising opportunity for cancer detection and could support clinicians’ decision-making process in finding the solution for the black-box problem. Clinical and Translational Impact Statement— Utilizing TEPs-based liquid biopsies and deep learning, our study offers a novel approach to early cancer detection, highlighting cancer origin. The integration of Explainable AI reinforces trust in predictive outcomes. Category: Early/Pre-Clinical Research.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"306-313"},"PeriodicalIF":3.4,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10418148","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139738978","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 : 2024-01-22DOI: 10.1109/JTEHM.2024.3357287
Pasquale Arpaia;Renato Cuocolo;Allegra Fullin;Ludovica Gargiulo;Francesca Mancino;Nicola Moccaldi;Ersilia Vallefuoco;Paolo De Blasiis
Executive functions (EFs) are neurocognitive processes planning and regulating daily life actions. Performance of two simultaneous tasks, requiring the same cognitive resources, lead to a cognitive fatigue. Several studies investigated cognitive-motor task and the interference during walking, highlighting an increasing risk of falls especially in elderly and people with neurological diseases. A few studies instrumentally explored relationship between activation-no-activation of two EFs (working memory and inhibition) and spatial-temporal gait parameters. Aim of our study was to detect activation of inhibition and working memory during progressive difficulty levels of cognitive tasks and spontaneous walking using, respectively, wireless electroencephalography (EEG) and 3D-gait analysis. Thirteen healthy subjects were recruited. Two cognitive tasks were performed, activating inhibition (Go-NoGo) and working memory (N-back). EEG features (absolute and relative power in different bands) and kinematic parameters (7 spatial-temporal ones and Gait Variable Score for 9 range of motion of lower limbs) were analyzed. A significant decrease of stride length and an increase of external-rotation of foot progression were found during dual task with Go-NoGo. Moreover, a significant correlation was found between the relative power in the delta band at channels Fz, C4 and progressive difficulty levels of Go-NoGo (activating inhibition) during walking, whereas working memory showed no correlation. This study reinforces the hypothesis of the prevalent involvement of inhibition with respect to working memory during dual task walking and reveals specific kinematic adaptations. The foundations for EEG-based monitoring of cognitive processes involved in gait are laid. Clinical and Translational Impact Statement: Clinical and instrumental evaluation and training of executive functions (as inhibition), during cognitive-motor task, could be useful for rehabilitation treatment of gait disorder in elderly and people with neurological disease.
{"title":"Executive Functions Assessment Based on Wireless EEG and 3D Gait Analysis During Dual-Task: A Feasibility Study","authors":"Pasquale Arpaia;Renato Cuocolo;Allegra Fullin;Ludovica Gargiulo;Francesca Mancino;Nicola Moccaldi;Ersilia Vallefuoco;Paolo De Blasiis","doi":"10.1109/JTEHM.2024.3357287","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3357287","url":null,"abstract":"Executive functions (EFs) are neurocognitive processes planning and regulating daily life actions. Performance of two simultaneous tasks, requiring the same cognitive resources, lead to a cognitive fatigue. Several studies investigated cognitive-motor task and the interference during walking, highlighting an increasing risk of falls especially in elderly and people with neurological diseases. A few studies instrumentally explored relationship between activation-no-activation of two EFs (working memory and inhibition) and spatial-temporal gait parameters. Aim of our study was to detect activation of inhibition and working memory during progressive difficulty levels of cognitive tasks and spontaneous walking using, respectively, wireless electroencephalography (EEG) and 3D-gait analysis. Thirteen healthy subjects were recruited. Two cognitive tasks were performed, activating inhibition (Go-NoGo) and working memory (N-back). EEG features (absolute and relative power in different bands) and kinematic parameters (7 spatial-temporal ones and Gait Variable Score for 9 range of motion of lower limbs) were analyzed. A significant decrease of stride length and an increase of external-rotation of foot progression were found during dual task with Go-NoGo. Moreover, a significant correlation was found between the relative power in the delta band at channels Fz, C4 and progressive difficulty levels of Go-NoGo (activating inhibition) during walking, whereas working memory showed no correlation. This study reinforces the hypothesis of the prevalent involvement of inhibition with respect to working memory during dual task walking and reveals specific kinematic adaptations. The foundations for EEG-based monitoring of cognitive processes involved in gait are laid. Clinical and Translational Impact Statement: Clinical and instrumental evaluation and training of executive functions (as inhibition), during cognitive-motor task, could be useful for rehabilitation treatment of gait disorder in elderly and people with neurological disease.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"268-278"},"PeriodicalIF":3.4,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10411910","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139676113","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: A change in handwriting is an early sign of Parkinson’s disease (PD). However, significant inter-person differences in handwriting make it difficult to identify pathological handwriting, especially in the early stages. This paper reports the testing of NeuroDiag, a software-based medical device, for the automated detection of PD using handwriting patterns. NeuroDiag is designed to direct the user to perform six drawing and writing tasks, and the recordings are then uploaded onto a server for analysis. Kinematic information and pen pressure of handwriting are extracted and used as baseline parameters. NeuroDiag was trained based on 26 PD patients in the early stage of the disease and 26 matching controls. Methods: Twenty-three people with PD (PPD) in their early stage of the disease, 25 age-matched healthy controls (AMC), and 7 young healthy controls were recruited for this study. Under the supervision of a consultant neurologist or their nurse, the participants used NeuroDiag. The reports were generated in real-time and tabulated by an independent observer. Results: The participants were able to use NeuroDiag without assistance. The handwriting data was successfully uploaded to the server where the report was automatically generated in real-time. There were significant differences in the writing speed between PPD and AMC (P<0.001). NeuroDiag showed 86.96% sensitivity and 76.92% specificity in differentiating PPD from those without PD. Conclusion: In this work, we tested the reliability of NeuroDiag in differentiating between PPD and AMC for real-time applications. The results show that NeuroDiag has the potential to be used to assist neurologists and for telehealth applications. Clinical and Translational Impact Statement — This pre-clinical study shows the feasibility of developing a community-wide screening program for Parkinson’s disease using automated handwriting analysis software, NeuroDiag.
{"title":"NeuroDiag: Software for Automated Diagnosis of Parkinson’s Disease Using Handwriting","authors":"Quoc Cuong Ngo;Nicole McConnell;Mohammod Abdul Motin;Barbara Polus;Arup Bhattacharya;Sanjay Raghav;Dinesh Kant Kumar","doi":"10.1109/JTEHM.2024.3355432","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3355432","url":null,"abstract":"Objective: A change in handwriting is an early sign of Parkinson’s disease (PD). However, significant inter-person differences in handwriting make it difficult to identify pathological handwriting, especially in the early stages. This paper reports the testing of NeuroDiag, a software-based medical device, for the automated detection of PD using handwriting patterns. NeuroDiag is designed to direct the user to perform six drawing and writing tasks, and the recordings are then uploaded onto a server for analysis. Kinematic information and pen pressure of handwriting are extracted and used as baseline parameters. NeuroDiag was trained based on 26 PD patients in the early stage of the disease and 26 matching controls. Methods: Twenty-three people with PD (PPD) in their early stage of the disease, 25 age-matched healthy controls (AMC), and 7 young healthy controls were recruited for this study. Under the supervision of a consultant neurologist or their nurse, the participants used NeuroDiag. The reports were generated in real-time and tabulated by an independent observer. Results: The participants were able to use NeuroDiag without assistance. The handwriting data was successfully uploaded to the server where the report was automatically generated in real-time. There were significant differences in the writing speed between PPD and AMC (P<0.001). NeuroDiag showed 86.96% sensitivity and 76.92% specificity in differentiating PPD from those without PD. Conclusion: In this work, we tested the reliability of NeuroDiag in differentiating between PPD and AMC for real-time applications. The results show that NeuroDiag has the potential to be used to assist neurologists and for telehealth applications. Clinical and Translational Impact Statement — This pre-clinical study shows the feasibility of developing a community-wide screening program for Parkinson’s disease using automated handwriting analysis software, NeuroDiag.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"291-297"},"PeriodicalIF":3.4,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10403837","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139704516","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 : 2024-01-04DOI: 10.1109/JTEHM.2024.3349916
Mieli Luukinen;Henna Pitkänen;Timo Leppänen;Juha Töyräs;Anna Sigridur Islind;Samu Kainulainen;Henri Korkalainen
Objective: The aim of this study was to assess how the photoplethysmogram frequency and amplitude responses to arousals from sleep differ between arousals caused by apneas and hypopneas with and without blood oxygen desaturations, and spontaneous arousals. Stronger arousal causes were hypothesized to lead to larger and faster responses. Methods and procedures: Photoplethysmogram signal segments during and around respiratory and spontaneous arousals of 876 suspected obstructive sleep apnea patients were analyzed. Logistic functions were fit to the mean instantaneous frequency and instantaneous amplitude of the signal to detect the responses. Response intensities and timings were compared between arousals of different causes. Results: The majority of the studied arousals induced photoplethysmogram responses. The frequency response was more intense ( ${p} < 0.001$ ) after respiratory than spontaneous arousals, and after arousals caused by apneas compared to those caused by hypopneas. The amplitude response was stronger ( ${p} < 0.001$ ) following hypopneas associated with blood oxygen desaturations compared to those that were not. The delays of these responses relative to the electroencephalogram arousal start times were the longest ( ${p} < 0.001$ ) after arousals caused by apneas and the shortest after spontaneous arousals and arousals caused by hypopneas without blood oxygen desaturations. Conclusion: The presence and type of an airway obstruction and the presence of a blood oxygen desaturation affect the intensity and the timing of photoplethysmogram responses to arousals from sleep. Clinical impact: The photoplethysmogram responses could be used for detecting arousals and assessing their intensity, and the individual variation in the response intensity and timing may hold diagnostically significant information.
{"title":"Variation in the Photoplethysmogram Response to Arousal From Sleep Depending on the Cause of Arousal and the Presence of Desaturation","authors":"Mieli Luukinen;Henna Pitkänen;Timo Leppänen;Juha Töyräs;Anna Sigridur Islind;Samu Kainulainen;Henri Korkalainen","doi":"10.1109/JTEHM.2024.3349916","DOIUrl":"10.1109/JTEHM.2024.3349916","url":null,"abstract":"Objective: The aim of this study was to assess how the photoplethysmogram frequency and amplitude responses to arousals from sleep differ between arousals caused by apneas and hypopneas with and without blood oxygen desaturations, and spontaneous arousals. Stronger arousal causes were hypothesized to lead to larger and faster responses. Methods and procedures: Photoplethysmogram signal segments during and around respiratory and spontaneous arousals of 876 suspected obstructive sleep apnea patients were analyzed. Logistic functions were fit to the mean instantaneous frequency and instantaneous amplitude of the signal to detect the responses. Response intensities and timings were compared between arousals of different causes. Results: The majority of the studied arousals induced photoplethysmogram responses. The frequency response was more intense (\u0000<inline-formula> <tex-math>${p} < 0.001$ </tex-math></inline-formula>\u0000) after respiratory than spontaneous arousals, and after arousals caused by apneas compared to those caused by hypopneas. The amplitude response was stronger (\u0000<inline-formula> <tex-math>${p} < 0.001$ </tex-math></inline-formula>\u0000) following hypopneas associated with blood oxygen desaturations compared to those that were not. The delays of these responses relative to the electroencephalogram arousal start times were the longest (\u0000<inline-formula> <tex-math>${p} < 0.001$ </tex-math></inline-formula>\u0000) after arousals caused by apneas and the shortest after spontaneous arousals and arousals caused by hypopneas without blood oxygen desaturations. Conclusion: The presence and type of an airway obstruction and the presence of a blood oxygen desaturation affect the intensity and the timing of photoplethysmogram responses to arousals from sleep. Clinical impact: The photoplethysmogram responses could be used for detecting arousals and assessing their intensity, and the individual variation in the response intensity and timing may hold diagnostically significant information.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"328-339"},"PeriodicalIF":3.4,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10380637","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139953793","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 : 2023-12-18DOI: 10.1109/JTEHM.2023.3344035
Hojjat Salehinejad;Anne M. Meehan;Pedro J. Caraballo;Bijan J. Borah
Objective: Deterioration index (DI) is a computer-generated score at a specific frequency that represents the overall condition of hospitalized patients using a variety of clinical, laboratory and physiologic data. In this paper, a contrastive transfer learning method is proposed and validated for early prediction of adverse events in hospitalized patients using DI scores. Methods and procedures: An unsupervised contrastive learning (CL) model with a classifier is proposed to predict adverse outcome using a single temporal variable (DI scores). The model is pretrained on an unsupervised fashion with large-scale time series data and fine-tuned with retrospective DI score data. Results: The performance of this model is compared with supervised deep learning models for time series classification. Results show that unsupervised contrastive transfer learning with a classifier outperforms supervised deep learning solutions. Pretraining of the proposed CL model with large-scale time series data and fine-tuning that with DI scores can enhance prediction accuracy. Conclusion: A relationship exists between longitudinal DI scores of a patient and the corresponding outcome. DI scores and contrastive transfer learning can be used to predict and prevent adverse outcomes in hospitalized patients. Clinical impact: This paper successfully developed an unsupervised contrastive transfer learning algorithm for prediction of adverse events in hospitalized patients. The proposed model can be deployed in hospitals as an early warning system for preemptive intervention in hospitalized patients, which can mitigate the likelihood of adverse outcomes.
目的：恶化指数（DI恶化指数（DI）是一种计算机生成的特定频率的分数，它利用各种临床、实验室和生理数据来代表住院患者的整体状况。本文提出并验证了一种对比迁移学习方法，用于利用 DI 评分早期预测住院患者的不良事件。方法和程序：本文提出了一种带有分类器的无监督对比学习（CL）模型，利用单一时间变量（DI 评分）预测不良后果。该模型利用大规模时间序列数据进行无监督预训练，并利用回顾性 DI 评分数据进行微调。结果：该模型的性能与用于时间序列分类的有监督深度学习模型进行了比较。结果表明，带有分类器的无监督对比迁移学习优于有监督深度学习解决方案。利用大规模时间序列数据对所提出的 CL 模型进行预训练，并利用 DI 分数对其进行微调，可以提高预测准确性。结论患者的纵向 DI 分数与相应的结果之间存在关系。DI 评分和对比迁移学习可用于预测和预防住院患者的不良预后。临床影响：本文成功开发了一种用于预测住院患者不良事件的无监督对比迁移学习算法。所提出的模型可作为预警系统部署在医院中，对住院病人进行先期干预，从而降低不良后果发生的可能性。
{"title":"Contrastive Transfer Learning for Prediction of Adverse Events in Hospitalized Patients","authors":"Hojjat Salehinejad;Anne M. Meehan;Pedro J. Caraballo;Bijan J. Borah","doi":"10.1109/JTEHM.2023.3344035","DOIUrl":"https://doi.org/10.1109/JTEHM.2023.3344035","url":null,"abstract":"Objective: Deterioration index (DI) is a computer-generated score at a specific frequency that represents the overall condition of hospitalized patients using a variety of clinical, laboratory and physiologic data. In this paper, a contrastive transfer learning method is proposed and validated for early prediction of adverse events in hospitalized patients using DI scores. Methods and procedures: An unsupervised contrastive learning (CL) model with a classifier is proposed to predict adverse outcome using a single temporal variable (DI scores). The model is pretrained on an unsupervised fashion with large-scale time series data and fine-tuned with retrospective DI score data. Results: The performance of this model is compared with supervised deep learning models for time series classification. Results show that unsupervised contrastive transfer learning with a classifier outperforms supervised deep learning solutions. Pretraining of the proposed CL model with large-scale time series data and fine-tuning that with DI scores can enhance prediction accuracy. Conclusion: A relationship exists between longitudinal DI scores of a patient and the corresponding outcome. DI scores and contrastive transfer learning can be used to predict and prevent adverse outcomes in hospitalized patients. Clinical impact: This paper successfully developed an unsupervised contrastive transfer learning algorithm for prediction of adverse events in hospitalized patients. The proposed model can be deployed in hospitals as an early warning system for preemptive intervention in hospitalized patients, which can mitigate the likelihood of adverse outcomes.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"215-224"},"PeriodicalIF":3.4,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10363391","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139034302","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 : 2023-12-07DOI: 10.1109/JTEHM.2023.3340345
Dosti Aziz;Sztahó Dávid
Objective: Despite speech being the primary communication medium, it carries valuable information about a speaker’s health, emotions, and identity. Various conditions can affect the vocal organs, leading to speech difficulties. Extensive research has been conducted by voice clinicians and academia in speech analysis. Previous approaches primarily focused on one particular task, such as differentiating between normal and dysphonic speech, classifying different voice disorders, or estimating the severity of voice disorders. Methods and procedures: This study proposes an approach that combines transfer learning and multitask learning (MTL) to simultaneously perform dysphonia classification and severity estimation. Both tasks use a shared representation; network is learned from these shared features. We employed five computer vision models and changed their architecture to support multitask learning. Additionally, we conducted binary ‘healthy vs. dysphonia’ and multiclass ‘healthy vs. organic and functional dysphonia’ classification using multitask learning, with the speaker’s sex as an auxiliary task. Results: The proposed method achieved improved performance across all classification metrics compared to single-task learning (STL), which only performs classification or severity estimation. Specifically, the model achieved F1 scores of 93% and 90% in MTL and STL, respectively. Moreover, we observed considerable improvements in both classification tasks by evaluating beta values associated with the weight assigned to the sex-predicting auxiliary task. MTL achieved an accuracy of 77% compared to the STL score of 73.2%. However, the performance of severity estimation in MTL was comparable to STL. Conclusion: Our goal is to improve how voice pathologists and clinicians understand patients’ conditions, make it easier to track their progress, and enhance the monitoring of vocal quality and treatment procedures. Clinical and Translational Impact Statement: By integrating both classification and severity estimation of dysphonia using multitask learning, we aim to enable clinicians to gain a better understanding of the patient’s situation, effectively monitor their progress and voice quality.
目的：尽管语言是主要的交流媒介，但它也承载着有关说话者健康、情感和身份的宝贵信息。各种疾病都会影响发声器官，导致说话困难。嗓音临床医生和学术界对语音分析进行了广泛的研究。以往的方法主要集中于某一特定任务，如区分正常语音和发音障碍语音、对不同嗓音疾病进行分类或估计嗓音疾病的严重程度。方法和程序：本研究提出了一种结合迁移学习和多任务学习（MTL）的方法，可同时进行发音障碍分类和严重程度评估。这两项任务都使用共享表征；网络是从这些共享特征中学习的。我们采用了五种计算机视觉模型，并改变了它们的架构以支持多任务学习。此外，我们还使用多任务学习进行了二元 "健康 vs. 发声困难 "和多类 "健康 vs. 器质性和功能性发声困难 "分类，并将说话者的性别作为辅助任务。结果与只进行分类或严重程度估计的单任务学习（STL）相比，所提出的方法在所有分类指标上都取得了更好的性能。具体来说，该模型在 MTL 和 STL 中的 F1 分数分别达到了 93% 和 90%。此外，通过评估与分配给性别预测辅助任务的权重相关的贝塔值，我们还观察到这两项分类任务都有相当大的改进。MTL 的准确率为 77%，而 STL 为 73.2%。不过，MTL 在严重程度估计方面的表现与 STL 不相上下。结论我们的目标是改善嗓音病理学家和临床医生对患者病情的了解，使他们更容易跟踪病情进展，并加强对嗓音质量和治疗过程的监控。临床和转化影响声明：通过使用多任务学习将发音障碍的分类和严重程度评估结合起来，我们的目标是让临床医生更好地了解患者的情况，有效地监测他们的病情进展和嗓音质量。
{"title":"Multitask and Transfer Learning Approach for Joint Classification and Severity Estimation of Dysphonia","authors":"Dosti Aziz;Sztahó Dávid","doi":"10.1109/JTEHM.2023.3340345","DOIUrl":"https://doi.org/10.1109/JTEHM.2023.3340345","url":null,"abstract":"Objective: Despite speech being the primary communication medium, it carries valuable information about a speaker’s health, emotions, and identity. Various conditions can affect the vocal organs, leading to speech difficulties. Extensive research has been conducted by voice clinicians and academia in speech analysis. Previous approaches primarily focused on one particular task, such as differentiating between normal and dysphonic speech, classifying different voice disorders, or estimating the severity of voice disorders. Methods and procedures: This study proposes an approach that combines transfer learning and multitask learning (MTL) to simultaneously perform dysphonia classification and severity estimation. Both tasks use a shared representation; network is learned from these shared features. We employed five computer vision models and changed their architecture to support multitask learning. Additionally, we conducted binary ‘healthy vs. dysphonia’ and multiclass ‘healthy vs. organic and functional dysphonia’ classification using multitask learning, with the speaker’s sex as an auxiliary task. Results: The proposed method achieved improved performance across all classification metrics compared to single-task learning (STL), which only performs classification or severity estimation. Specifically, the model achieved F1 scores of 93% and 90% in MTL and STL, respectively. Moreover, we observed considerable improvements in both classification tasks by evaluating beta values associated with the weight assigned to the sex-predicting auxiliary task. MTL achieved an accuracy of 77% compared to the STL score of 73.2%. However, the performance of severity estimation in MTL was comparable to STL. Conclusion: Our goal is to improve how voice pathologists and clinicians understand patients’ conditions, make it easier to track their progress, and enhance the monitoring of vocal quality and treatment procedures. Clinical and Translational Impact Statement: By integrating both classification and severity estimation of dysphonia using multitask learning, we aim to enable clinicians to gain a better understanding of the patient’s situation, effectively monitor their progress and voice quality.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"233-244"},"PeriodicalIF":3.4,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10347235","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139034042","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}
Malignant glioma (MG) is the most common type of primary malignant brain tumors. Surgical resection of MG remains the cornerstone of therapy and the extent of resection correlates with patient survival. A limiting factor for resection, however, is the difficulty in differentiating the tumor from normal tissue during surgery. Fluorescence imaging is an emerging technique for real-time intraoperative visualization of MGs and their boundaries. However, most clinical grade neurosurgical operative microscopes with fluorescence imaging ability are hampered by low adoption rates due to high cost, limited portability, limited operation flexibility, and lack of skilled professionals with technical knowledge. To overcome the limitations, we innovatively integrated miniaturized light sources, flippable filters, and a recording camera to the surgical eye loupes to generate a wearable fluorescence eye loupe (FLoupe) device for intraoperative imaging of fluorescent MGs. Two FLoupe prototypes were constructed for imaging of Fluorescein and 5-aminolevulinic acid (5-ALA), respectively. The wearable FLoupe devices were tested on tumor-simulating phantoms and patients with MGs. Comparable results were observed against the standard neurosurgical operative microscope (PENTERO® 900) with fluorescence kits. The affordable and wearable FLoupe devices enable visualization of both color and fluorescence images with the same quality as the large and expensive stationary operative microscopes. The wearable FLoupe device allows for a greater range of movement, less obstruction, and faster/easier operation. Thus, it reduces surgery time and is more easily adapted to the surgical environment than unwieldy neurosurgical operative microscopes. Clinical and Translational Impact Statement—The affordable and wearable fluorescence imaging device developed in this study enables neurosurgeons to observe brain tumors with the same clarity and greater flexibility compared to bulky and costly operative microscopes.
{"title":"A Wearable Fluorescence Imaging Device for Intraoperative Identification of Human Brain Tumors","authors":"Mehrana Mohtasebi;Chong Huang;Mingjun Zhao;Siavash Mazdeyasna;Xuhui Liu;Samaneh Rabienia Haratbar;Faraneh Fathi;Jinghong Sun;Thomas Pittman;Guoqiang Yu","doi":"10.1109/JTEHM.2023.3338564","DOIUrl":"https://doi.org/10.1109/JTEHM.2023.3338564","url":null,"abstract":"Malignant glioma (MG) is the most common type of primary malignant brain tumors. Surgical resection of MG remains the cornerstone of therapy and the extent of resection correlates with patient survival. A limiting factor for resection, however, is the difficulty in differentiating the tumor from normal tissue during surgery. Fluorescence imaging is an emerging technique for real-time intraoperative visualization of MGs and their boundaries. However, most clinical grade neurosurgical operative microscopes with fluorescence imaging ability are hampered by low adoption rates due to high cost, limited portability, limited operation flexibility, and lack of skilled professionals with technical knowledge. To overcome the limitations, we innovatively integrated miniaturized light sources, flippable filters, and a recording camera to the surgical eye loupes to generate a wearable fluorescence eye loupe (FLoupe) device for intraoperative imaging of fluorescent MGs. Two FLoupe prototypes were constructed for imaging of Fluorescein and 5-aminolevulinic acid (5-ALA), respectively. The wearable FLoupe devices were tested on tumor-simulating phantoms and patients with MGs. Comparable results were observed against the standard neurosurgical operative microscope (PENTERO® 900) with fluorescence kits. The affordable and wearable FLoupe devices enable visualization of both color and fluorescence images with the same quality as the large and expensive stationary operative microscopes. The wearable FLoupe device allows for a greater range of movement, less obstruction, and faster/easier operation. Thus, it reduces surgery time and is more easily adapted to the surgical environment than unwieldy neurosurgical operative microscopes. Clinical and Translational Impact Statement—The affordable and wearable fluorescence imaging device developed in this study enables neurosurgeons to observe brain tumors with the same clarity and greater flexibility compared to bulky and costly operative microscopes.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"225-232"},"PeriodicalIF":3.4,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10339301","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139081243","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 : 2023-11-27DOI: 10.1109/JTEHM.2023.3336889
Kaya Kuru;Darren Ansell;Dave Hughes;Benjamin Jon Watkinson;Fabrizio Gaudenzi;Martin Jones;David Lunardi;Noreen Caswell;Adela Rabella Montiel;Peter Leather;Daniel Irving;Kina Bennett;Corrin McKenzie;Paula Sugden;Carl Davies;Christian Degoede
Our study was designed to develop a customisable, wearable, and comfortable medical device – the text so-called “MyPAD” that monitors the fullness of the bladder, triggering an alarm indicating the need to void, in order to prevent badwetting – i.e., treating Nocturnal Enuresis (NE) at the text pre-void stage using miniaturised mechatronics with Artificial Intelligence (AI). The developed features include: multiple bespoke ultrasound (US) probes for sensing, a bespoke electronic device housing custom US electronics for signal processing, a bedside alarm box for processing the echoed pulses and generating alarms, and a phantom to mimic the human body. The validation of the system is conducted on the text tissue-mimicking phantom and volunteers using Bidirectional Long Short-Term Memory Recurrent Neural Networks (Bi-LSTM-RNN) and Reinforcement Learning (RL). A Se value of 99% and a Sp value of 99.5% with an overall accuracy rate of 99.3% are observed. The obtained results demonstrate successful empirical evidence for the viability of the device, both in monitoring bladder expansion to determine voiding need and in reinforcing the continuous learning and customisation of the device for bladder control through consecutive uses. Clinical impact: MyPAD will treat the NE better and efficiently against other techniques currently used (e.g., post-void alarms) and will i) replace those techniques quickly considering sufferers’ condition while being treated by other approaches, and ii) enable children to gain control of incontinence over time and consistently have dry nights. Category: Early/Pre-Clinical Research
{"title":"Treatment of Nocturnal Enuresis Using Miniaturised Smart Mechatronics With Artificial Intelligence","authors":"Kaya Kuru;Darren Ansell;Dave Hughes;Benjamin Jon Watkinson;Fabrizio Gaudenzi;Martin Jones;David Lunardi;Noreen Caswell;Adela Rabella Montiel;Peter Leather;Daniel Irving;Kina Bennett;Corrin McKenzie;Paula Sugden;Carl Davies;Christian Degoede","doi":"10.1109/JTEHM.2023.3336889","DOIUrl":"https://doi.org/10.1109/JTEHM.2023.3336889","url":null,"abstract":"Our study was designed to develop a customisable, wearable, and comfortable medical device – the text so-called “MyPAD” that monitors the fullness of the bladder, triggering an alarm indicating the need to void, in order to prevent badwetting – i.e., treating Nocturnal Enuresis (NE) at the text pre-void stage using miniaturised mechatronics with Artificial Intelligence (AI). The developed features include: multiple bespoke ultrasound (US) probes for sensing, a bespoke electronic device housing custom US electronics for signal processing, a bedside alarm box for processing the echoed pulses and generating alarms, and a phantom to mimic the human body. The validation of the system is conducted on the text tissue-mimicking phantom and volunteers using Bidirectional Long Short-Term Memory Recurrent Neural Networks (Bi-LSTM-RNN) and Reinforcement Learning (RL). A Se value of 99% and a Sp value of 99.5% with an overall accuracy rate of 99.3% are observed. The obtained results demonstrate successful empirical evidence for the viability of the device, both in monitoring bladder expansion to determine voiding need and in reinforcing the continuous learning and customisation of the device for bladder control through consecutive uses. Clinical impact: MyPAD will treat the NE better and efficiently against other techniques currently used (e.g., post-void alarms) and will i) replace those techniques quickly considering sufferers’ condition while being treated by other approaches, and ii) enable children to gain control of incontinence over time and consistently have dry nights. Category: Early/Pre-Clinical Research","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"204-214"},"PeriodicalIF":3.4,"publicationDate":"2023-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10328832","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138485029","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 : 2023-11-21DOI: 10.1109/JTEHM.2023.3335608
Andrea Moglia;Luca Marsilio;Matteo Rossi;Maria Pinelli;Emanuele Lettieri;Luca Mainardi;Alfonso Manzotti;Pietro Cerveri
Objective: Recent advancements in augmented reality led to planning and navigation systems for orthopedic surgery. However little is known about mixed reality (MR) in orthopedics. Furthermore, artificial intelligence (AI) has the potential to boost the capabilities of MR by enabling automation and personalization. The purpose of this work is to assess Holoknee prototype, based on AI and MR for multimodal data visualization and surgical planning in knee osteotomy, developed to run on the HoloLens 2 headset. Methods: Two preclinical test sessions were performed with 11 participants (eight surgeons, two residents, and one medical student) executing three times six tasks, corresponding to a number of holographic data interactions and preoperative planning steps. At the end of each session, participants answered a questionnaire on user perception and usability. Results: During the second trial, the participants were faster in all tasks than in the first one, while in the third one, the time of execution decreased only for two tasks (“Patient selection” and “Scrolling through radiograph”) with respect to the second attempt, but without statistically significant difference (respectively $p$ = 0.14 and $p$ = 0.13, $p < 0.05$ ). All subjects strongly agreed that MR can be used effectively for surgical training, whereas 10 (90.9%) strongly agreed that it can be used effectively for preoperative planning. Six (54.5%) agreed and two of them (18.2%) strongly agreed that it can be used effectively for intraoperative guidance. Discussion/Conclusion: In this work, we presented Holoknee, the first holistic application of AI and MR for surgical planning for knee osteotomy. It reported promising results on its potential translation to surgical training, preoperative planning, and surgical guidance. Clinical and Translational Impact Statement - Holoknee can be helpful to support surgeons in the preoperative planning of knee osteotomy. It has the potential to impact positively the training of the future generation of residents and aid surgeons in the intraoperative stage.
{"title":"Mixed Reality and Artificial Intelligence: A Holistic Approach to Multimodal Visualization and Extended Interaction in Knee Osteotomy","authors":"Andrea Moglia;Luca Marsilio;Matteo Rossi;Maria Pinelli;Emanuele Lettieri;Luca Mainardi;Alfonso Manzotti;Pietro Cerveri","doi":"10.1109/JTEHM.2023.3335608","DOIUrl":"https://doi.org/10.1109/JTEHM.2023.3335608","url":null,"abstract":"Objective: Recent advancements in augmented reality led to planning and navigation systems for orthopedic surgery. However little is known about mixed reality (MR) in orthopedics. Furthermore, artificial intelligence (AI) has the potential to boost the capabilities of MR by enabling automation and personalization. The purpose of this work is to assess Holoknee prototype, based on AI and MR for multimodal data visualization and surgical planning in knee osteotomy, developed to run on the HoloLens 2 headset. Methods: Two preclinical test sessions were performed with 11 participants (eight surgeons, two residents, and one medical student) executing three times six tasks, corresponding to a number of holographic data interactions and preoperative planning steps. At the end of each session, participants answered a questionnaire on user perception and usability. Results: During the second trial, the participants were faster in all tasks than in the first one, while in the third one, the time of execution decreased only for two tasks (“Patient selection” and “Scrolling through radiograph”) with respect to the second attempt, but without statistically significant difference (respectively \u0000<inline-formula> <tex-math>$p$ </tex-math></inline-formula>\u0000 = 0.14 and \u0000<inline-formula> <tex-math>$p$ </tex-math></inline-formula>\u0000 = 0.13, \u0000<inline-formula> <tex-math>$p < 0.05$ </tex-math></inline-formula>\u0000). All subjects strongly agreed that MR can be used effectively for surgical training, whereas 10 (90.9%) strongly agreed that it can be used effectively for preoperative planning. Six (54.5%) agreed and two of them (18.2%) strongly agreed that it can be used effectively for intraoperative guidance. Discussion/Conclusion: In this work, we presented Holoknee, the first holistic application of AI and MR for surgical planning for knee osteotomy. It reported promising results on its potential translation to surgical training, preoperative planning, and surgical guidance. Clinical and Translational Impact Statement - Holoknee can be helpful to support surgeons in the preoperative planning of knee osteotomy. It has the potential to impact positively the training of the future generation of residents and aid surgeons in the intraoperative stage.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"279-290"},"PeriodicalIF":3.4,"publicationDate":"2023-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10325506","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139676277","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：