Healthcare Technology Letters最新文献

{"title":"Diabetes prediction using machine learning and explainable AI techniques","authors":"Isfafuzzaman Tasin,&nbsp;Tansin Ullah Nabil,&nbsp;Sanjida Islam,&nbsp;Riasat Khan","doi":"10.1049/htl2.12039","DOIUrl":"10.1049/htl2.12039","url":null,"abstract":"<p>Globally, diabetes affects 537 million people, making it the deadliest and the most common non-communicable disease. Many factors can cause a person to get affected by diabetes, like excessive body weight, abnormal cholesterol level, family history, physical inactivity, bad food habit etc. Increased urination is one of the most common symptoms of this disease. People with diabetes for a long time can get several complications like heart disorder, kidney disease, nerve damage, diabetic retinopathy etc. But its risk can be reduced if it is predicted early. In this paper, an automatic diabetes prediction system has been developed using a private dataset of female patients in Bangladesh and various machine learning techniques. The authors used the Pima Indian diabetes dataset and collected additional samples from 203 individuals from a local textile factory in Bangladesh. Feature selection algorithm mutual information has been applied in this work. A semi-supervised model with extreme gradient boosting has been utilized to predict the insulin features of the private dataset. SMOTE and ADASYN approaches have been employed to manage the class imbalance problem. The authors used machine learning classification methods, that is, decision tree, SVM, Random Forest, Logistic Regression, KNN, and various ensemble techniques, to determine which algorithm produces the best prediction results. After training on and testing all the classification models, the proposed system provided the best result in the XGBoost classifier with the ADASYN approach with 81% accuracy, 0.81 F1 coefficient and AUC of 0.84. Furthermore, the domain adaptation method has been implemented to demonstrate the versatility of the proposed system. The explainable AI approach with LIME and SHAP frameworks is implemented to understand how the model predicts the final results. Finally, a website framework and an Android smartphone application have been developed to input various features and predict diabetes instantaneously. The private dataset of female Bangladeshi patients and programming codes are available at the following link: https://github.com/tansin-nabil/Diabetes-Prediction-Using-Machine-Learning.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"10 1-2","pages":"1-10"},"PeriodicalIF":2.1,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/htl2.12039","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9384370","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":"Validity and feasibility of remote measurement systems for functional movement and posture assessments in people with axial spondylarthritis","authors":"Erin Hannink,&nbsp;Maedeh Mansoubi,&nbsp;Neil Cronin,&nbsp;Benjamin Wilkins,&nbsp;Ali A. Najafi,&nbsp;Benjamin Waller,&nbsp;Helen Dawes","doi":"10.1049/htl2.12038","DOIUrl":"10.1049/htl2.12038","url":null,"abstract":"<p>Introduction: This study aimed to estimate the criterion validity of functional movement and posture measurement using remote technology systems in people with and without Axial spondylarthritis (axSpA).</p><p>Methods: Validity and agreement of the remote-technology measurement of functional movement and posture were tested cross-sectionally and compared to a standard clinical measurement by a physiotherapist. The feasibility of remote implementation was tested in a home environment. There were two cohorts of participants: people with axSpA and people without longstanding back pain. In addition, a cost-consequence analysis was performed.</p><p>Results: Sixty-two participants (31 with axSPA, 53% female, age = 45(SD14), BMI = 26.6(SD4.6) completed the study. In the axSpA group, cervical rotation, lumbar flexion, lumbar side flexion, shoulder flexion, hip abduction, tragus-to-wall and thoracic kyphosis showed a significant moderate to strong correlation; in the non-back pain group, the same measures showed significant correlation ranging from weak to strong.</p><p>Conclusions: Although not valid for clinical use in its current form, the remote technologies demonstrated moderate to strong correlation and agreement in most functional and postural tests measured in people with AxSA. Testing the CV-aided system in a home environment suggests it is a safe and feasible method. Yet, validity testing in this environment still needs to be performed.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 6","pages":"110-118"},"PeriodicalIF":2.1,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9731560/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10361200","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":"Alzheimer's disease classification using cluster-based labelling for graph neural network on heterogeneous data","authors":"Niamh McCombe,&nbsp;Jake Bamrah,&nbsp;Jose M. Sanchez-Bornot,&nbsp;David P. Finn,&nbsp;Paula L. McClean,&nbsp;KongFatt Wong-Lin,&nbsp;Alzheimer's Disease Neuroimaging Initiative (ADNI)","doi":"10.1049/htl2.12037","DOIUrl":"10.1049/htl2.12037","url":null,"abstract":"<p>Biomarkers for Alzheimer's disease (AD) diagnosis do not always correlate reliably with cognitive symptoms, making clinical diagnosis inconsistent. In this study, the performance of a graphical neural network (GNN) classifier based on data-driven diagnostic classes from unsupervised clustering on heterogeneous data is compared to the performance of a classifier using clinician diagnosis as an outcome. Unsupervised clustering on tau-positron emission tomography (PET) and cognitive and functional assessment data was performed. Five clusters embedded in a non-linear uniform manifold approximation and project (UMAP) space were identified. The individual clusters revealed specific feature characteristics with respect to clinical diagnosis of AD, gender, family history, age, and underlying neurological risk factors (NRFs). In particular, one cluster comprised mainly diagnosed AD cases. All cases within this cluster were re-labelled AD cases. The re-labelled cases are characterized by high cerebrospinal fluid amyloid beta (CSF Aβ) levels at a younger age, even though Aβ data was not used for clustering. A GNN model was trained using the re-labelled data with a multiclass area-under-the-curve (AUC) of 95.2%, higher than the AUC of a GNN trained on clinician diagnosis (91.7%; <i>p</i> = 0.02). Overall, our work suggests that more objective cluster-based diagnostic labels combined with GNN classification may have value in clinical risk stratification and diagnosis of AD.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 6","pages":"102-109"},"PeriodicalIF":2.1,"publicationDate":"2022-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9731537/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10729996","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":"A systematic comparison of the accuracy of monocular RGB tracking and LiDAR for neuronavigation","authors":"Talha Khan,&nbsp;Jacob T. Biehl,&nbsp;Edward G. Andrews,&nbsp;Dmitriy Babichenko","doi":"10.1049/htl2.12036","DOIUrl":"10.1049/htl2.12036","url":null,"abstract":"<p>With the advent of augmented reality (AR), the use of AR-guided systems in the field of medicine has gained traction. However, the wide-scale adaptation of these systems requires highly accurate and reliable tracking. In this work, the tracking accuracy of two technology platforms, LiDAR and Vuforia, are developed and rigorously tested for a catheter placement neurological procedure. Several experiments (900) are performed for each technology across various combinations of catheter lengths and insertion trajectories. This analysis shows that the LiDAR platform outperformed Vuforia; which is the state-of-the-art in monocular RGB tracking solutions. LiDAR had 75% less radial distance error and 26% less angle deviation error. Results provide key insights into the value and utility of LiDAR-based tracking in AR guidance systems.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 6","pages":"91-101"},"PeriodicalIF":2.1,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/d6/3d/HTL2-9-91.PMC9731545.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10361198","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":"A UAV-based portable health clinic system for coronavirus hotspot areas","authors":"Mustafa Siham Qassab,&nbsp;Qutaiba Ibrahim Ali","doi":"10.1049/htl2.12035","DOIUrl":"10.1049/htl2.12035","url":null,"abstract":"<p>This study applied the World Health Organization (WHO) guidelines to redesign the Portable Health Clinic (PHC), as a Remote Healthcare System (RHS), for the spread of COVID-19 containment. Additionally, the proposed drone-based system not only collects people data but also classifies the case according to the main symptoms of coronavirus using the COVID-19 triage process (CT-process) based on the analysis of measurement readings taken from patients, where drones are used in a swarm as a PHC platform and are equipped with the required sensors and essential COVID-19 medications for testing and treating people at their doorstep autonomously when a full curfew is imposed. This paper describes a complete framework and proposes currently in production hardware to build the suggested system, considering the effect of the extra payload weight on drone's durability. In addition, part of the proposed application was simulated using OPNET simulation tool. This work highlights the main aspects that should be considered when designing drone swarm-based system and distributing the roles on system nodes with the main focus on the controlling messages for inter-swarm and intra-swarm communication and coordination.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 4-5","pages":"77-90"},"PeriodicalIF":2.1,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9535778/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33503862","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":"Mobile application tool for remote rehabilitation after discharge from coronavirus disease-19 rehabilitation unit","authors":"Daniele Emedoli,&nbsp;Federica Alemanno,&nbsp;Elise Houdayer,&nbsp;Luigia Brugliera,&nbsp;Sandro Iannaccone,&nbsp;Andrea Tettamanti","doi":"10.1049/htl2.12033","DOIUrl":"10.1049/htl2.12033","url":null,"abstract":"<p>A smartphone application (Medico-Amico) has been developed by the collaboration of San Raffaele Scientific Institute and Khymeia Group S.R.L. with the aim of providing physical exercises and communicating with patients after their hospitalization in a coronavirus disease (COVID)-rehabilitation unit. Thirty patients used the application for remote rehabilitation for 4 weeks. They were prescribed personalized motor exercises to perform three times a week. Clinicians could interact with each patient by an encrypted video call in order to give encouragement, mental support, modify intensity during training sessions, or to prescribe new exercises. Patients were asked to perform motor exercises and also to monitor their vital signs, such as temperature, blood pressure, and oxygen saturation, inserting scores in a specific section of the application. After 4 weeks of remote rehabilitation patients showed improvements in independence during activity of daily living and strength. Also, satisfaction and mobile application usability scores reached patients’ appreciation and enjoyment.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 4-5","pages":"70-76"},"PeriodicalIF":2.1,"publicationDate":"2022-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9535743/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33503863","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":"Functional requirements of a mobile-based application for stroke self-management: A Delphi study","authors":"Hamidreza Tadayon,&nbsp;Seyed Ali Masoud,&nbsp;Ehsan Nabovati,&nbsp;Hossein Akbari,&nbsp;Mehrdad Farzandipour,&nbsp;Masoud Babaei","doi":"10.1049/htl2.12034","DOIUrl":"10.1049/htl2.12034","url":null,"abstract":"<p>This study aimed to determine the functional requirements of a self-management mobile application for stroke survivors. For extracting the initial functional requirements, a literature review as well as interviews with 17 patients and caregivers were done. The results were analyzed using the content analysis method. The initial extracted requirements were then provided to the specialists by the Delphi technique to determine the final functional requirements. Content validity ratio (CVR) and content validity index (CVI) were calculated according to the Lawshe model. Criteria for item approval included CVR &gt; 0.49 and CVI &gt; 0.79. Finally, the approved items were turned into a five-point Likert scale questionnaire and were then provided to 53 experts and items with a mean score higher than 3.75 were approved. Functional requirements including creating a user account, educational material, support services, providing reminders and alerts for drugs administration and physician appointments, and rehabilitation exercises (to improve balance, upper and lower extremities rehabilitation, and activities of daily living (ADLs)) were approved. Most of the approved functional requirements were related to rehabilitation exercises for improving upper limb motor function. The experts did not approve the requirements for using splints and slings or the recommendation to take some medications.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 4-5","pages":"55-69"},"PeriodicalIF":2.1,"publicationDate":"2022-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/41/7a/HTL2-9-55.PMC9535756.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33511325","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":"Hospital surface disinfection using ultraviolet germicidal irradiation technology: A review","authors":"Robert Scott,&nbsp;Lovleen Tina Joshi,&nbsp;Conor McGinn","doi":"10.1049/htl2.12032","DOIUrl":"10.1049/htl2.12032","url":null,"abstract":"<p>Ultraviolet germicidal irradiation (UVGI) technologies have emerged as a promising alternative to biocides as a means of surface disinfection in hospitals and other healthcare settings. This paper reviews the methods used by researchers and clinicians in deploying and evaluating the efficacy of UVGI technology. The type of UVGI technology used, the clinical setting where the device was deployed, and the methods of environmental testing that the researchers followed are investigated. The findings suggest that clinical UVGI deployments have been growing steadily since 2010 and have increased dramatically since the start of the COVID-19 pandemic. Hardware platforms and operating procedures vary considerably between studies. Most studies measure efficacy of the technology based on the objective measurement of bacterial bioburden reduction; however, studies conducted over longer durations have examined the impact of UVGI on the reduction of healthcare associated infections (HCAIs). Future trends include increased automation and the use of UVGI technologies that are safer for use around people. Although existing evidence seems to support the efficacy of UVGI as a tool capable of reducing HCAIs, more research is needed to measure the magnitude of these effects and to establish recommended best practices.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 3","pages":"25-33"},"PeriodicalIF":2.1,"publicationDate":"2022-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9160814/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44059049","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":"Multiscale depth of anaesthesia prediction for surgery using frontal cortex electroencephalography","authors":"Ejay Nsugbe,&nbsp;Stephanie Connelly","doi":"10.1049/htl2.12025","DOIUrl":"10.1049/htl2.12025","url":null,"abstract":"<p>Hypnotic and sedative anaesthetic agents are employed during multiple medical interventions to prevent patient awareness. Careful titration of agent dosing is required to avoid negative side effects; the accuracy thereof may be improved by Depth of Anaesthesia Monitoring. This work investigates the potential of a patient specific depth monitoring prediction using electroencephalography recorded neural oscillation from the frontal lobe of 10 patients during sedation, where a comparison of the prediction accuracy was made across five different approaches to post-processing; Noise Assisted-Empirical Mode Decomposition, the Raw Signal, Linear Series Decomposition Learner, Deep Wavelet Scattering and Deep Learning features. These methods towards anaesthesia depth prediction were investigated using the Bispectral Index as ground truth, where it was seen that the Raw Signal, enhanced feature set and a low complexity classification model (Linear Discriminant Analysis) provided the best classification accuracy, in the region of 85.65 % ±10.23 % across the 10 subjects. Subsequent work in this area would now build on these results and validate the best performing methods on a wider cohort of patients, investigate means of continuous DoA estimation using regressions, and also feature optimisation exercises in order to further streamline and reduce the computation complexity of the designed model.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 3","pages":"43-53"},"PeriodicalIF":2.1,"publicationDate":"2022-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/htl2.12025","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49183273","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":"Predicting cumulative effect of lifestyle risk factors for complex disease","authors":"Emmanuel Effiok,&nbsp;Enjie Liu,&nbsp;Jon Hitchcock","doi":"10.1049/htl2.12021","DOIUrl":"10.1049/htl2.12021","url":null,"abstract":"<p>In medical domain, risk factors are often used to model disease predictions. In order to make the most use of the predictive models, linking the model with real patient data generates personalized disease progression and predictions. However, the risk factors are fragmented all over medical literature, certain risks can be accumulated for a disease and the aggregated probability may increase or decrease the occurrence of a disease. In this paper, a risk predictive framework which forms a base for a complete risk prediction model that can be used for various health applications is proposed.</p>","PeriodicalId":37474,"journal":{"name":"Healthcare Technology Letters","volume":"9 3","pages":"34-42"},"PeriodicalIF":2.1,"publicationDate":"2022-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/htl2.12021","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45516393","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}