Shankar Subramaniam;Metin Akay;Mark A. Anastasio;Vasudev Bailey;David Boas;Paolo Bonato;Ashutosh Chilkoti;Jennifer R. Cochran;Vicki Colvin;Tejal A. Desai;James S. Duncan;Frederick H. Epstein;Stephanie Fraley;Cecilia Giachelli;K. Jane Grande-Allen;Jordan Green;X. Edward Guo;Isaac B. Hilton;Jay D. Humphrey;Chris R Johnson;George Karniadakis;Michael R. King;Robert F. Kirsch;Sanjay Kumar;Cato T. Laurencin;Song Li;Richard L. Lieber;Nigel Lovell;Prashant Mali;Susan S. Margulies;David F. Meaney;Brenda Ogle;Bernhard Palsson;Nicholas A. Peppas;Eric J. Perreault;Rick Rabbitt;Lori A. Setton;Lonnie D. Shea;Sanjeev G. Shroff;Kirk Shung;Andreas S. Tolias;Marjolein C.H. van der Meulen;Shyni Varghese;Gordana Vunjak-Novakovic;John A. White;Raimond Winslow;Jianyi Zhang;Kun Zhang;Charles Zukoski;Michael I. Miller
{"title":"Grand Challenges at the Interface of Engineering and Medicine","authors":"Shankar Subramaniam;Metin Akay;Mark A. Anastasio;Vasudev Bailey;David Boas;Paolo Bonato;Ashutosh Chilkoti;Jennifer R. Cochran;Vicki Colvin;Tejal A. Desai;James S. Duncan;Frederick H. Epstein;Stephanie Fraley;Cecilia Giachelli;K. Jane Grande-Allen;Jordan Green;X. Edward Guo;Isaac B. Hilton;Jay D. Humphrey;Chris R Johnson;George Karniadakis;Michael R. King;Robert F. Kirsch;Sanjay Kumar;Cato T. Laurencin;Song Li;Richard L. Lieber;Nigel Lovell;Prashant Mali;Susan S. Margulies;David F. Meaney;Brenda Ogle;Bernhard Palsson;Nicholas A. Peppas;Eric J. Perreault;Rick Rabbitt;Lori A. Setton;Lonnie D. Shea;Sanjeev G. Shroff;Kirk Shung;Andreas S. Tolias;Marjolein C.H. van der Meulen;Shyni Varghese;Gordana Vunjak-Novakovic;John A. White;Raimond Winslow;Jianyi Zhang;Kun Zhang;Charles Zukoski;Michael I. Miller","doi":"10.1109/OJEMB.2024.3351717","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3351717","url":null,"abstract":"Over the past two decades Biomedical Engineering has emerged as a major discipline that bridges societal needs of human health care with the development of novel technologies. Every medical institution is now equipped at varying degrees of sophistication with the ability to monitor human health in both non-invasive and invasive modes. The multiple scales at which human physiology can be interrogated provide a profound perspective on health and disease. We are at the nexus of creating “avatars” (herein defined as an extension of “digital twins”) of human patho/physiology to serve as paradigms for interrogation and potential intervention. Motivated by the emergence of these new capabilities, the IEEE Engineering in Medicine and Biology Society, the Departments of Biomedical Engineering at Johns Hopkins University and Bioengineering at University of California at San Diego sponsored an interdisciplinary workshop to define the grand challenges that face biomedical engineering and the mechanisms to address these challenges. The Workshop identified five grand challenges with cross-cutting themes and provided a roadmap for new technologies, identified new training needs, and defined the types of interdisciplinary teams needed for addressing these challenges. The themes presented in this paper include: 1) accumedicine through creation of avatars of cells, tissues, organs and whole human; 2) development of smart and responsive devices for human function augmentation; 3) exocortical technologies to understand brain function and treat neuropathologies; 4) the development of approaches to harness the human immune system for health and wellness; and 5) new strategies to engineer genomes and cells.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"1-13"},"PeriodicalIF":5.8,"publicationDate":"2024-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10443312","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139916656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"MFEM-CIN: A Lightweight Architecture Combining CNN and Transformer for the Classification of Pre-Cancerous Lesions of the Cervix","authors":"Peng Chen;Fobao Liu;Jun Zhang;Bing Wang","doi":"10.1109/OJEMB.2024.3367243","DOIUrl":"10.1109/OJEMB.2024.3367243","url":null,"abstract":"<italic>Goal:</i>\u0000 Cervical cancer is one of the most common cancers in women worldwide, ranking among the top four. Unfortunately, it is also the fourth leading cause of cancer-related deaths among women, particularly in developing countries where incidence and mortality rates are higher compared to developed nations. Colposcopy can aid in the early detection of cervical lesions, but its effectiveness is limited in areas with limited medical resources and a lack of specialized physicians. Consequently, many cases are diagnosed at later stages, putting patients at significant risk. \u0000<italic>Methods:</i>\u0000 This paper proposes an automated colposcopic image analysis framework to address these challenges. The framework aims to reduce the labor costs associated with cervical precancer screening in undeserved regions and assist doctors in diagnosing patients. The core of the framework is the MFEM-CIN hybrid model, which combines Convolutional Neural Networks (CNN) and Transformer to aggregate the correlation between local and global features. This combined analysis of local and global information is scientifically useful in clinical diagnosis. In the model, MSFE and MSFF are utilized to extract and fuse multi-scale semantics. This preserves important shallow feature information and allows it to interact with the deep feature, enriching the semantics to some extent. \u0000<italic>Conclusions:</i>\u0000 The experimental results demonstrate an accuracy rate of 89.2% in identifying cervical intraepithelial neoplasia while maintaining a lightweight model. This performance exceeds the average accuracy achieved by professional physicians, indicating promising potential for practical application. Utilizing automated colposcopic image analysis and the MFEM-CIN model, this research offers a practical solution to reduce the burden on healthcare providers and improve the efficiency and accuracy of cervical cancer diagnosis in resource-constrained areas.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"216-225"},"PeriodicalIF":5.8,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10440497","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139949490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mingyang Zang;Pooja Mukund;Britney Forsyth;Andrew F. Laine;Kaveri A. Thakoor
{"title":"Predicting Clinician Fixations on Glaucoma OCT Reports via CNN-Based Saliency Prediction Methods","authors":"Mingyang Zang;Pooja Mukund;Britney Forsyth;Andrew F. Laine;Kaveri A. Thakoor","doi":"10.1109/OJEMB.2024.3367492","DOIUrl":"10.1109/OJEMB.2024.3367492","url":null,"abstract":"<italic>Goal:</i>\u0000 To predict physician fixations specifically on ophthalmology optical coherence tomography (OCT) reports from eye tracking data using CNN based saliency prediction methods in order to aid in the education of ophthalmologists and ophthalmologists-in-training. \u0000<italic>Methods:</i>\u0000 Fifteen ophthalmologists were recruited to each examine 20 randomly selected OCT reports and evaluate the likelihood of glaucoma for each report on a scale of 0-100. Eye movements were collected using a Pupil Labs Core eye-tracker. Fixation heat maps were generated using fixation data. \u0000<italic>Results:</i>\u0000 A model trained with traditional saliency mapping resulted in a correlation coefficient (CC) value of 0.208, a Normalized Scanpath Saliency (NSS) value of 0.8172, a Kullback–Leibler (KLD) value of 2.573, and a Structural Similarity Index (SSIM) of 0.169. \u0000<italic>Conclusions</i>\u0000: The TranSalNet model was able to predict fixations within certain regions of the OCT report with reasonable accuracy, but more data is needed to improve model accuracy. Future steps include increasing data collection, improving quality of data, and modifying the model architecture.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"191-197"},"PeriodicalIF":5.8,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10440538","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139949515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"EEG Information Transfer Changes in Different Daily Fatigue Levels During Drowsy Driving","authors":"Kuan-Chih Huang;Chun-Ying Tseng;Chin-Teng Lin","doi":"10.1109/OJEMB.2024.3367496","DOIUrl":"10.1109/OJEMB.2024.3367496","url":null,"abstract":"A significant issue for traffic safety has been drowsy driving for decades. A number of studies have investigated the effects of acute fatigue on spectral power; and recent research has revealed that drowsy driving is associated with a variety of brain connections in a specific cortico-cortical pathway. In spite of this, it is still unclear how different brain regions are connected in drowsy driving at different levels of daily fatigue. This study identified the brain connectivity-behavior relationship among three different daily fatigue levels (low-, median- and high-fatigue) with the EEG data transfer entropy. According to the results, only low- and medium-fatigue groups demonstrated an inverted U-shaped change in connectivity from high performance to poor behavioral performance. In addition, from low- to high-fatigue groups, connectivity magnitude decreased in the frontal region and increased in the occipital region. These study results suggest that brain connectivity and driving behavior would be affected by different levels of daily fatigue.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"180-190"},"PeriodicalIF":5.8,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10440464","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139949381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cristian Drudi;Maximiliano Mollura;Li-wei H. Lehman;Riccardo Barbieri
{"title":"A Reinforcement Learning Model for Optimal Treatment Strategies in Intensive Care: Assessment of the Role of Cardiorespiratory Features","authors":"Cristian Drudi;Maximiliano Mollura;Li-wei H. Lehman;Riccardo Barbieri","doi":"10.1109/OJEMB.2024.3367236","DOIUrl":"10.1109/OJEMB.2024.3367236","url":null,"abstract":"<italic>Goal:</i>\u0000 The purpose of this study is to evaluate the importance of cardiorespiratory variables within a Reinforcement Learning (RL) recommendation system aimed at establishing optimal strategies for drug treatment of septic patients in the intensive care unit (ICU). \u0000<italic>Methods:</i>\u0000 We developed a RL model in order to establish drug administration strategies for septic patients using only a set of cardiorespiratory variables. We then compared this model with other RL models trained with a different set of features. We selected patients meeting the Sepsis-3 criteria from the Multi-parameter Intelligent Monitoring in Intensive Care (MIMIC III) database, resulting in a total of 20,496 ICU admissions. A Markov Decision Process (MDP) was built on the extracted discrete time-series. A policy iteration algorithm was used to obtain the optimal AI policy for the MDP. The policy performance was then evaluated using the WIS estimator. The process was repeated for each set of variables and compared to a set of baseline benchmark policies. \u0000<italic>Results:</i>\u0000 The model trained with cardiorespiratory variables outperformed all other models considered, resulting in a 95% confidence lower bound score of 97.48. This finding highlights the importance of cardiovascular variables in the clinical RL recommendation system. \u0000<italic>Conclusions:</i>\u0000 We established an efficient RL model for sepsis treatment in the ICU and demonstrated that cardiorespiratory variables provides critical information in devising optimal policies. Given the potentially continuous availability of cardiorespiratory features extracted from bedside physiological waveform monitoring, the proposed framework paves the way for a real time recommendation system for sepsis treatment.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"806-815"},"PeriodicalIF":2.7,"publicationDate":"2024-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10439998","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139949610","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Saúl Langarica;Diego de la Vega;Nawel Cariman;Martín Miranda;David C. Andrade;Felipe Núñez;Maria Rodriguez-Fernandez
{"title":"Deep Learning-Based Glucose Prediction Models: A Guide for Practitioners and a Curated Dataset for Improved Diabetes Management","authors":"Saúl Langarica;Diego de la Vega;Nawel Cariman;Martín Miranda;David C. Andrade;Felipe Núñez;Maria Rodriguez-Fernandez","doi":"10.1109/OJEMB.2024.3365290","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3365290","url":null,"abstract":"Accurate short- and mid-term blood glucose predictions are crucial for patients with diabetes struggling to maintain healthy glucose levels, as well as for individuals at risk of developing the disease. Consequently, numerous efforts from the scientific community have focused on developing predictive models for glucose levels. This study harnesses physiological data collected from wearable sensors to construct a series of data-driven models based on deep learning approaches. We systematically compare these models to offer insights for practitioners and researchers venturing into glucose prediction using deep learning techniques. Key questions addressed in this work encompass the comparison of various deep learning architectures for this task, determining the optimal set of input variables for accurate glucose prediction, comparing population-wide, fine-tuned, and personalized models, and assessing the impact of an individual's data volume on model performance. Additionally, as part of our outcomes, we introduce a meticulously curated dataset inclusive of data from both healthy individuals and those with diabetes, recorded in free-living conditions. This dataset aims to foster research in this domain and facilitate equitable comparisons among researchers.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"467-475"},"PeriodicalIF":5.8,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10433750","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141308718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Guest Editorial Introduction to the Special Section on Image-Guided Therapies","authors":"Dieter Haemmerich;Punit Prakash","doi":"10.1109/OJEMB.2024.3364075","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3364075","url":null,"abstract":"Numerous medical imaging modalities are clinically available and widely used in disease diagnosis and monitoring therapy response. Imaging data are also increasingly being used for constructing patient-specific computational models to inform design and evaluation of devices, and for personalized planning of interventions. Several of these imaging modalities – e.g., ultrasound imaging, computed tomography (CT), and magnetic resonance imaging (MRI) – can also provide real-time image data. In concert with advances in therapy delivery devices and systems, this real-time capability has enabled image-guided therapies, where multiple image series are acquired during a procedure and are used for therapy guidance. This special issue presents six research studies to highlight recent advances in this research area.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"86-87"},"PeriodicalIF":5.8,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10428939","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139942786","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Samuel Dolphin;Maren Downing;Mia Cirrincione;Adam Samuta;Kevin Leite;Kimberly Noble;Brian Walsh
{"title":"Information Accessibility in the Form of Braille","authors":"Samuel Dolphin;Maren Downing;Mia Cirrincione;Adam Samuta;Kevin Leite;Kimberly Noble;Brian Walsh","doi":"10.1109/OJEMB.2024.3364065","DOIUrl":"10.1109/OJEMB.2024.3364065","url":null,"abstract":"Braille is often proposed by the uninformed as the optimal solution to providing an alternative to visual information to the visually impaired. The purpose of this article is to highlight the complexity of the braille user population and discuss the importance of understanding the use of braille as a solution for equal access of information. As part of the National Institute of Biomedical Imaging and Bioengineering (NIBIB) Rapid Acceleration of Diagnostics (RADx) Tech program and its goal to make home tests accessible to people with disabilities, a series of interviews with industry experts was conducted to better understand braille technologies and the braille user space. Published literature findings provided additional context and support to these interviews. It was found that expert consensus and data from published literature vary. The braille user population is complex and lacks consistent characterization. Visually printed media should not be solely relied on to communicate information. In conclusion, braille is one solution for improving access to information. Understanding the unique needs of braille users and how they engage with information in a world that is heavily reliant on visual content, is a critical step in developing and implementing non-visual alternatives that will collectively address information access.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"205-209"},"PeriodicalIF":5.8,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10428077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139949492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Feedback Type May Change the EMG Pattern and Kinematics During Robot Supported Upper Limb Reaching Task","authors":"Yasuhiro Kato;Toshiaki Tsuji;Imre Cikajlo","doi":"10.1109/OJEMB.2024.3363137","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3363137","url":null,"abstract":"Haptic interfaces and virtual reality (VR) technology have been increasingly introduced in rehabilitation, facilitating the provision of various feedback and task conditions. However, correspondence between the feedback/task conditions and movement strategy during reaching tasks remains a question. To investigate movement strategy, we assessed velocity parameters and peak latency of electromyography. Ten neuromuscularly intact volunteers participated in the measurement using haptic interface and VR. Concurrent visual feedback and various terminal feedback (e.g., visual, haptic, visual and haptic) were given. Additionally, the object size for the reaching task was changed. The results demonstrated terminal haptic feedback had a significant impact on kinematic parameters; showed \u0000<inline-formula><tex-math>$0.7,pm {,1.4}$</tex-math></inline-formula>\u0000 s (\u0000<inline-formula><tex-math>$p,< .05$</tex-math></inline-formula>\u0000) shorter movement time and \u0000<inline-formula><tex-math>$0.01,pm {,0.08}$</tex-math></inline-formula>\u0000 m/s (\u0000<inline-formula><tex-math>$p,< .05$</tex-math></inline-formula>\u0000) higher mean velocity compared to no terminal feedback. Also, smaller peak latency was observed in different muscle regions based on the object size.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"173-179"},"PeriodicalIF":5.8,"publicationDate":"2024-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10423822","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139942743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Harry J. Davies;Ghena Hammour;Hongjian Xiao;Patrik Bachtiger;Alexander Larionov;Philip L. Molyneaux;Nicholas S. Peters;Danilo P. Mandic
{"title":"Physically Meaningful Surrogate Data for COPD","authors":"Harry J. Davies;Ghena Hammour;Hongjian Xiao;Patrik Bachtiger;Alexander Larionov;Philip L. Molyneaux;Nicholas S. Peters;Danilo P. Mandic","doi":"10.1109/OJEMB.2024.3360688","DOIUrl":"https://doi.org/10.1109/OJEMB.2024.3360688","url":null,"abstract":"The rapidly increasing prevalence of debilitating breathing disorders, such as chronic obstructive pulmonary disease (COPD), calls for a meaningful integration of artificial intelligence (AI) into respiratory healthcare. Deep learning techniques are “data hungry” whilst patient-based data is invariably expensive and time consuming to record. To this end, we introduce a novel COPD-simulator, a physical apparatus with an easy to replicate design which enables rapid and effective generation of a wide range of COPD-like data from healthy subjects, for enhanced training of deep learning frameworks. To ensure the faithfulness of our domain-aware COPD surrogates, the generated waveforms are examined through both flow waveforms and photoplethysmography (PPG) waveforms (as a proxy for intrathoracic pressure) in terms of duty cycle, sample entropy, FEV\u0000<sub>1</sub>\u0000/FVC ratios and flow-volume loops. The proposed simulator operates on healthy subjects and is able to generate FEV\u0000<sub>1</sub>\u0000/FVC obstruction ratios ranging from greater than 0.8 to less than 0.2, mirroring values that can observed in the full spectrum of real-world COPD. As a final stage of verification, a simple convolutional neural network is trained on surrogate data alone, and is used to accurately detect COPD in real-world patients. When training solely on surrogate data, and testing on real-world data, a comparison of true positive rate against false positive rate yields an area under the curve of 0.75, compared with 0.63 when training solely on real-world data.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"5 ","pages":"148-156"},"PeriodicalIF":5.8,"publicationDate":"2024-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10417113","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139937085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}