2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)最新文献_第2页

A virtual/digital pet Point-of-Care system for self-management of COPD patients 用于COPD患者自我管理的虚拟/数字宠物护理点系统

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744060

D. Arvind, T. Georgescu, W. Bao, C. A. Bates

{"title":"A virtual/digital pet Point-of-Care system for self-management of COPD patients","authors":"D. Arvind, T. Georgescu, W. Bao, C. A. Bates","doi":"10.1109/HI-POCT54491.2022.9744060","DOIUrl":"https://doi.org/10.1109/HI-POCT54491.2022.9744060","url":null,"abstract":"Pulmonary rehabilitation is recommended for COPD patients to help manage their long-term condition. The objectives of the point-of-care system are: remote observability of patients by continuous monitoring of their vital signs of respiratory rate and respiratory effort; encourage adherence to the pulmonary rehabilitation regime and correct execution of the exercises. The point-of-care system consists of the Respeck sensor device worn as a plaster on the chest to monitor respiratory rate/flow and physical activity, and a mobile app to (i) orchestrate the pulmonary rehabilitation exercises; (ii) an e-pet to engage the patient to exercise regularly; (iii) handle communication of Respeck data with the Cloud-based server. A dashboard provides the Care Team of physiotherapists, respiratory nurses and doctors with (i) the current status and historical trends of breathing rate/flow; (ii) classification of their static (lying down, sitting/standing, and dynamic (walking, running, climbing stairs) physical activities; (iii) correctness and frequency of their pulmonary rehabilitation exercises; (iv) level of interaction with their virtual/digital pet. Results are presented on the evaluation of the virtual/digital feature by respiratory physiotherapists ahead of deployment with COPD patients.Clinical Relevance—The point-of-care system can classify the correctness of the ten pulmonary rehabilitation exercises using machine learning techniques with a maximum accuracy of 93% to provide the Care Team confidence their charges are performing exercises correctly when unsupervised. Results are summarised for a survey of nine pulmonary physiotherapists on their evaluation of the efficacy of using the Respeck and the App in a Point-of-Care system (POCS) for COPD patients.","PeriodicalId":283503,"journal":{"name":"2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134619261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Wearable Exam Stress Dataset for Predicting Grades using Physiological Signals 使用生理信号预测成绩的可穿戴考试压力数据集

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744065

Md. Rafiul Amin, D. S. Wickramasuriya, R. Faghih

引用次数: 4

Capillary Flow Dynamics of Blood With Varied Hematocrit in Microfluidic Platforms 微流控平台中不同红细胞压积的血液流变动力学研究

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744073

B. Nunna, Yudong Wang, N. Talukder, Eon Soo Lee

{"title":"Capillary Flow Dynamics of Blood With Varied Hematocrit in Microfluidic Platforms","authors":"B. Nunna, Yudong Wang, N. Talukder, Eon Soo Lee","doi":"10.1109/HI-POCT54491.2022.9744073","DOIUrl":"https://doi.org/10.1109/HI-POCT54491.2022.9744073","url":null,"abstract":"Blood is a complex fluid with non-newtonian behavior. Though the blood plasma is newtonian in nature, the Red Blood Cells (RBCs) in the blood contribute to the non-newtonian behavior. The study of the influence of the hematocrit (percentage of RBCs in the whole blood) in the capillary flow of the whole blood is highly desired to understand the non-newtonian flow of blood and change on the flow dynamics of whole blood with different concentrations of RBCs. In the capillary flow dynamics, the study of contact angle and its variations play a key role. So, in this manuscript the contact angle of the whole blood drop and the flow velocity of the whole blood with different hematocrit on the polydimethylsiloxane (PDMS) surface is studied with detailed scientific experiments. The contact angle was measured for whole blood drop with hematocrit of 35%, 40%, 45%, and 50% as 34°, 38°, 44°, and 48° respectively. Also, the flow velocity that is directly influenced by the contact angle in the capillary flow is measured with whole blood with hematocrit of 35%, 40%, 45%, and 50% as 9.23 mm/s, 8.45 mm/s, 7.32 mm/s, and 6.67 mm/s respectively. The experimental results helps to conclude that the increased hematocrit in the whole blood is increasing the contact angle and decreasing the flow velocity.Clinical Relevance—The study of the capillary flow dynamics of whole blood with different hematocrit helps the physicians to establish more accurate analysis of blood flow with different concentrations of RBCs.","PeriodicalId":283503,"journal":{"name":"2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125430425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Normalizing Flow for Synthetic Medical Images Generation 用于合成医学图像生成的归一化流程

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744072

Mustafa Hajij, Ghada Zamzmi, Rahul Paul, Lokenda Thukar

{"title":"Normalizing Flow for Synthetic Medical Images Generation","authors":"Mustafa Hajij, Ghada Zamzmi, Rahul Paul, Lokenda Thukar","doi":"10.1109/HI-POCT54491.2022.9744072","DOIUrl":"https://doi.org/10.1109/HI-POCT54491.2022.9744072","url":null,"abstract":"Deep generative models, such as generative adversarial network (GAN) and variational autoencoder (VAE), have been utilized extensively for medical image generation. While these models made remarkable progress in medical image synthesis, they can not explicitly learn the probability density function of the input data and are highly sensitive to the hyperparameter selections. To mitigate these issues, a new type of deep generative model, called Normalizing Flows (NFs), have emerged in recent years. In this paper, we investigate NFs as an alternative for synthesizing medical images. In particular, we utilize realNVP, a popular NF model for the purpose of synthesizing medical images. To evaluate our synthesized images, we propose to utilize Wasserstien distance along with the permutation test to quantify the quality of the generated images. Within our quantifying metric, our results indicate that the two sample distributions, the first being the samples obtained from our NF model and second being the original dataset, are similar providing a promising indication of normalizing flow’s capability in medical images generation.","PeriodicalId":283503,"journal":{"name":"2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127793933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Machine Learning Model Deployment Using Real-Time Physiological Monitoring: Use Case of Detecting Delayed Cerebral Ischemia 使用实时生理监测的机器学习模型部署:检测延迟性脑缺血的用例

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744076

H. Cao, Joshua Finer, M. Megjhani, Daniel Nametz, Virginia Lorenzi, Lena Mamykina, Richard Meyers, S. Rossetti, Soojin Park

{"title":"Machine Learning Model Deployment Using Real-Time Physiological Monitoring: Use Case of Detecting Delayed Cerebral Ischemia","authors":"H. Cao, Joshua Finer, M. Megjhani, Daniel Nametz, Virginia Lorenzi, Lena Mamykina, Richard Meyers, S. Rossetti, Soojin Park","doi":"10.1109/HI-POCT54491.2022.9744076","DOIUrl":"https://doi.org/10.1109/HI-POCT54491.2022.9744076","url":null,"abstract":"Deploying machine learning models in a clinical setting is challenging. Here we demonstrated a modular model deployment pipeline for for ContinuOuS Monitoring tool for delayed cerebral IsChemia (COSMIC) that was successfully implemented on a trained and validated temporal machine learning algorithm that detects delayed cerebral ischemia after subarachnoid hemorrhage. The pipeline was able to ingest demographic data and near real-time continuous physiological data, run through a model, and output the results twice a day automatically. It was a highly collaborative effort among clinical neurologists, the research team, and the IT innovation team. We illustrate the technical run time challenges and mitigations in each of the three components of the pipeline: data, model (modular), and output communication. Future work is user-centered participatory design and rapid agile prototyping of effective model output communication and clinical trial of efficacy in order to understand how the clinical decision support tool performs and is adopted in a real clinical setting.","PeriodicalId":283503,"journal":{"name":"2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128220659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Explainability Analysis of Black Box SVM models for Hepatic Steatosis Screening 黑箱支持向量机模型在肝脂肪变性筛查中的可解释性分析

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744067

R. Deo, S. Panigrahi

{"title":"Explainability Analysis of Black Box SVM models for Hepatic Steatosis Screening","authors":"R. Deo, S. Panigrahi","doi":"10.1109/HI-POCT54491.2022.9744067","DOIUrl":"https://doi.org/10.1109/HI-POCT54491.2022.9744067","url":null,"abstract":"Non-Alcoholic Fatty Liver Disease (NAFLD) or HS is one of the major causes of chronic liver diseases worldwide. Identifying the NAFLD condition at an early stage allows for preventative care and potential disease remission.To this end, our research group is addressing this issue by developing a computational model for decision support for Hepatic Steatosis (HS) or NAFLD screening. Our recent work included the development of machine learning models using seven physiological parameters (demographic, lipids, and liver biochemical parameters). Although the developed models show potential for screening, there is a need for further improving the model performance. Considering the complex nature of this condition and its interaction with different physiological parameters, we identified the contribution of the individual parameters in predicting the target (HS). The objective of this paper is to identify how different features contribute to a given model prediction by using an explainable artificial intelligence (XAI) technique called Partial Dependency. Results from partial dependency analysis and plots are summarized in this paper along with insights related to model performance. We identified the top three individual important predictors (ALT, AST, and Glucose levels) for both male and female. The models both for the male and female populations were analyzed separately to incorporate the pathobiological difference in NAFLD morphology in male vs female population.Clinical Relevance—The current study and obtained results do not have immediate clinical implications. However, this work paves the path for a potential computational model, which after required validation and testing, could be used as a decision support system for Hepatic Steatosis screening.","PeriodicalId":283503,"journal":{"name":"2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121399444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Leapfrogging Medical AI in Low-Resource Contexts Using Edge Tensor Processing Unit 利用边缘张量处理单元实现低资源环境下的跨越式医疗人工智能

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744071

Priyanshu Sinha, J. Gichoya, S. Purkayastha

{"title":"Leapfrogging Medical AI in Low-Resource Contexts Using Edge Tensor Processing Unit","authors":"Priyanshu Sinha, J. Gichoya, S. Purkayastha","doi":"10.1109/HI-POCT54491.2022.9744071","DOIUrl":"https://doi.org/10.1109/HI-POCT54491.2022.9744071","url":null,"abstract":"With each passing year, the state-of-the-art deep learning neural networks grow larger in size, requiring larger computing and power resources. The high compute resources required by these large networks are alienating the majority of the world population that lives in low-resource settings and lacks the infrastructure to benefit from these advancements in medical AI. Current state-of-the-art medical AI, even with cloud resources, is a bit difficult to deploy in remote areas where we don’t have good internet connectivity. We demonstrate a cost-effective approach to deploying medical AI that could be used in limited resource settings using Edge Tensor Processing Unit (TPU). We trained and optimized a classification model on the Chest X-ray 14 dataset and a segmentation model on the Nerve ultrasound dataset using INT8 Quantization Aware Training. Thereafter, we compiled the optimized models for Edge TPU execution. We find that the inference performance on edge TPUs is 10x faster compared to other embedded devices. The optimized model is 3x and 12x smaller for the classification and segmentation respectively, compared to the full precision model. In summary, we show the potential of Edge TPUs for two medical AI tasks with faster inference times, which could potentially be used in low-resource settings for medical AI-based diagnostics. We finally discuss some potential challenges and limitations of our approach for real-world deployments.","PeriodicalId":283503,"journal":{"name":"2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134068781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Novel Smartphone-based & Personalized Atrial Fibrillation Detection: A Preliminary Study 一种新的基于智能手机的个性化心房颤动检测:初步研究

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744074

F. Tabei, Mostafa M Abohelwa, Daniel Davis, Pooja Sethi, K. Nugent, Jo Woon Chong

引用次数: 0

A System-On-Chip Assay for Bilirubin Levels Measurement in Whole Blood Using Photodegradation Kinetics 利用光降解动力学测量全血中胆红素水平的系统芯片试验

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744057

Jean Pierre Ndabakuranye, S. Prawer, A. Ahnood

{"title":"A System-On-Chip Assay for Bilirubin Levels Measurement in Whole Blood Using Photodegradation Kinetics","authors":"Jean Pierre Ndabakuranye, S. Prawer, A. Ahnood","doi":"10.1109/HI-POCT54491.2022.9744057","DOIUrl":"https://doi.org/10.1109/HI-POCT54491.2022.9744057","url":null,"abstract":"Bilirubin is clinically confirmed as a biomarker for liver health and is used to assess the prognosis of cirrhosis. Optical and chemical methods have long been utilized for blood bilirubin biosensing. While spectrophotometric techniques provide more accurate results, measurements may not be practical due to the instrument complexity and space requirements as they require volumetric equipment and reagents are sometimes preprocessed. These steps are rather time-consuming and can be detrimental in cases of emergency. Several studies have attempted and used the dual-wavelength approach to overcome these limitations; however, although this creates the possibility of Point-of-Care (PoC) and fast testing, it suffers from reduced accuracy. This paper investigated the feasibility of PoC bilirubin monitoring by photodegradation kinetics using a system-on-chip (SoC). Porcine blood was used, and bilirubin levels were kept within the pathophysiological ranges projected from healthy individuals (<1.2 mg/dL) and cirrhotic patients (up to 50 mg/dL). Our findings suggest that bilirubin can be measured with high sensitivity in blood using bilirubin degradation profiles. This technique can be incorporated with the dual-wavelength approach to increase the reliability and accuracy of point-of-care testing for bilirubin levels, primarily for neonatal hyperbilirubinemia and cirrhotic adults.","PeriodicalId":283503,"journal":{"name":"2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121081820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Kirigami-Patterned Highly Stable and Strain Insensitive Sweat pH and Temperature Sensors for Long-term Wearable Applications kirigami图案高度稳定和应变不敏感的汗液pH和温度传感器，用于长期可穿戴应用

2022 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) Pub Date : 2022-03-10 DOI: 10.1109/HI-POCT54491.2022.9744070

Tanzila Noushin, N. I. Hossain, Shawana Tabassum

引用次数: 7