{"title":"AsTFSONN: A Unified Framework Based on Time-Frequency Domain Self-Operational Neural Network for Asthmatic Lung Sound Classification","authors":"Arka Roy, U. Satija","doi":"10.1109/MeMeA57477.2023.10171911","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171911","url":null,"abstract":"Asthma is one of the most severe chronic respiratory diseases which can be diagnosed using several modalities, such as lung function test or spirometric measures, peak flow meter-based measures, sputum eosinophils, pathological speech, and wheezing events of the lung auscultation sound, etc. Lung sound examinations are more accurate for diagnosing respiratory problems since these are associated with respiratory abnormalities occurred due to pulmonary disorders. In this paper, we propose a time-frequency domain self-operational neural network (SONN) based framework, namely, AsTFSONN, to efficiently categorize asthmatic lung sound signals, which uses the SONN-based heterogeneous neural model by incorporating an additional non-linearity into the neural network architecture, unlike the vanilla convolutional neural model that uses homogeneous perceptions which resemble the fundamental linear neuron model. The proposed framework comprises three major stages: pre-processing of the input lung sounds, mel-spectrogram time-frequency representation (TFR) extraction, and finally, classification using AsTFSONN based on the mel-spectrogram images. The proposed framework supersedes the notable prior works of asthma classification based on lung sounds and other diagnostic modalities by achieving the highest accuracy, specificity, sensitivity, and ICBHI-score of 98.50%, 98.80%, 98.11%, and 98.46%, respectively, using lung sounds as the input diagnostic modality, as evaluated on publicly available chest wall lung sound dataset.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132000122","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}
Nosheen Jillani, A. Khattak, Muhammad Zubair Asghar, Hayyat Ullah
{"title":"Efficient Diagnosis of Liver Disease using Deep Learning Technique","authors":"Nosheen Jillani, A. Khattak, Muhammad Zubair Asghar, Hayyat Ullah","doi":"10.1109/MeMeA57477.2023.10171906","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171906","url":null,"abstract":"The diagnoses a patient receives can have significant repercussions for enhancing patient safety, investigation, and policymaking. Medical practitioners employ a variety of pathologic techniques to arrive at conclusions about their patients’ states in clinical information. The field of medical diagnosis has seen renewed efforts from clinicians in recent years. When Artificial Intelligence (AI) and Deep Learning (DL) are used in tandem with clinical data, they can greatly enhance the accuracy of disease diagnoses. The use of computers and internet has made it possible to acquire data and visualize previously inaccessible findings, such as addressing the issue of missing values in clinical research. Decision-making can be aided by problem-specific Deep Learning algorithms. In order to automatically identify illness specimens, effective predictive methods are essential. In this regard, this work employs techniques of deep learning to distinguish liver patients from normal persons. In this research, we make a prediction of liver illness using a Deep Learning model called BiLSTM. This model is able to keep track of long-term relationships in both the forward and the backward direction. The efficiency of the model’s predictions came out to be 93.00% overall. According to the findings, the implementation of a hybrid model seems to have enhanced the predictive accuracy.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133361092","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}
Gabriela Grońska, Elisabetta Peri, X. Long, J. V. Dijk, M. Mischi
{"title":"Removal of electrocardiographic interference and artifacts from diaphragm electromyography","authors":"Gabriela Grońska, Elisabetta Peri, X. Long, J. V. Dijk, M. Mischi","doi":"10.1109/MeMeA57477.2023.10171861","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171861","url":null,"abstract":"Diaphragmatic electromyography (dEMG) holds the potential to monitor respiration. However, its acquisition is affected by electrocardiographic (ECG) interference and motion artifacts, making its investigation and use in clinical practice still challenging. Singular value decomposition (SVD) methods have been reported in the literature denoising the dEMG. Here a new ratio index criterion is combined with a SVD based algorithm to aid this challenge. The advantage of the proposed approach is in use of the frequency spectrum as a reference to remove unwanted components from the signal. Two synthetic datasets combining EMG with ECG only and with ECG and motion artifacts were tested using a signal-to-noise ratio ranging from −20 to 0dB to assess the performance of the method. The performance was compared with an earlier developed SVD-based algorithm that employed a calibration curve for the selection of unwanted components. Our results show that our new proposed method reached significantly better performance in both time and frequency domains for the majority of presented SNRs in the dataset containing artifacts. Additionally for the same dataset, the method obtained the average median improvement in the SNR of 12 dB and, the average median percentage improvement of 157% in the reconstructed EMG signal. The solution does not need an additional reference for the ECG. Its performance was proven on the data containing not only electrocardiographic disturbance but also motion artifacts, showing promise for further use on the real data.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129541996","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}
Ashima, Vibham Kumar Dubey, Rahul Shukla, Bijit Basumatary, A. Sahani
{"title":"Portable, wireless and easy to use device for Negative Pressure Wound Therapy","authors":"Ashima, Vibham Kumar Dubey, Rahul Shukla, Bijit Basumatary, A. Sahani","doi":"10.1109/MeMeA57477.2023.10171870","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171870","url":null,"abstract":"Wound healing is a natural biological process in the human body, achieved through four interdependent, precisely and highly programmed phases. Every wound is unique and is affected by various factors hence optimization of wound healing mechanism based on the complexity of wound is of utmost importance. NPWT has emerged to be a prominent systematic wound treatment practice for chronic wounds such as arterial ulcers, diabetic foot ulcers, non healing surgical wounds, pressure ulcers, traumatic wounds, vasculitic ulcers (leg), venous stasis ulcers, etc. Typically, an optimum pressure range of 88 to 125 mmHg exhibits positive and promising effects in this kind of therapy. Despite assisting the wound healing mechanism in many ways, this method poses certain problems too. The key to this process lies in optimization of the value of negative pressure, duration of negative pressure application, and the number of times the treatment has to be performed based on the type of wound. Here in this study our aim is the modification of negative-pressure wound therapy such that we make this device portable, wireless and easy to operate on different negative pressure settings. Other than these optimizations we have incorporated the process of instillation wherein wound flushing is done with help of saline, antiseptic, anti-infective drugs or growth factor solutions.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116207713","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}
Luisa De Palma, V. D'Alessandro, F. Attivissimo, A. Nisio, A. Lanzolla
{"title":"ECG wave segmentation algorithm for complete P-QRS-T detection","authors":"Luisa De Palma, V. D'Alessandro, F. Attivissimo, A. Nisio, A. Lanzolla","doi":"10.1109/MeMeA57477.2023.10171894","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171894","url":null,"abstract":"Electrocardiogram (ECG) is a simple and fast test that provides the graphical representation of the electrical signal obtained by the heart’s activity and is widely employed to detect functional heart conditions. Indeed, its segmentation and feature extraction are required to produce a diagnosis. This paper focuses on the development of a segmentation technique for QRS complex, T waves and P waves of ECG waveforms that can be useful to detect cardiac diseases. Despite many proposed algorithms have already successfully accomplished the problem of QRS complex ECG segmentation, there is still a lack in the performance of these detectors on P and T waves. The proposed algorithm is based on a threshold calculated using the Otsu’s method to detect R-peaks in the ECG waveform. In addition, it allows to segment all the other ECG waves using wavelet filters and local maxima algorithm. Each segmented wave is defined with onset and offset. This method is evaluated on ECG signals acquired with a single lead heart rate monitor verifying if a wave and its onset and offset are detected or not and using mean time error and IOU (Intersection over Union) as evaluation metrics.Experimental results presented in this paper demonstrate that the proposed algorithm achieves 100 % of R-peak and QRS complex detection for the considered dataset. In addition, also P peak and T peak are detected with a score of 100 %.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"115 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128662594","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}
{"title":"Exploring Respiratory Parameters Related to Psychophysiological Indexes of Mental Health","authors":"Miyu Suzuki, Hiroki Sato","doi":"10.1109/MeMeA57477.2023.10171945","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171945","url":null,"abstract":"Psychophysiological indexes based on questionnaire scores and heart rate variability analysis are widely used as mental health indexes. In this study, we focused on respiratory information and aimed to explore respiratory parameters related to psychophysiological indexes of mental health. Seven respiratory parameters were used: respiratory rate, inhalation time, exhalation time, exhalation-inhalation ratio, inhalation time variability, exhalation time variability, and exhalation-inhalation ratio variability. Furthermore, the seven respiratory parameters were analyzed using representative psychophysiological indexes: relaxation scale, anxiety scale (STAI), sleep scale (PSQI-J), and pulse wave, EEG. Twenty-eight university students participated in the experiment. Simultaneous measurements with a band-type respiration sensor, an optical pulse wave sensor, and an electrode-type EEG sensor were performed for 5 min in a resting state after obtaining answers to each questionnaire, and finally, answers to the questionnaires were obtained again. A correlation analysis of the respiratory parameters and psychophysiological indexes revealed a positive correlation (r=0.41 and r=0.44, respectively) between state anxiety and the variability of inhalation and exhalation times (p<0.05). This result suggests that the variability of inhalation and exhalation times can potentially be used for mental health assessment.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116967013","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}
Raj Kiran V, Rahul Manoj, S. Ponkalaivani, P. Nabeel, J. Joseph
{"title":"Effect of Fiduciary Point Choice on Pulse Wave Velocity-based Cuffless Pulse Pressure Estimation: Ex-vivo Study","authors":"Raj Kiran V, Rahul Manoj, S. Ponkalaivani, P. Nabeel, J. Joseph","doi":"10.1109/MeMeA57477.2023.10171935","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171935","url":null,"abstract":"Superiority of central blood pressure (BP) (especially its pulsatile component; pulse pressure (PP)) over that of brachial has been underlined recently through several clinical studies. Local pulse wave velocity (PWV) based cuffless methods using Bramwell-Hill (BH) equation are popularly employed to assess PP. These approaches assume PWV to be constant, whereas, it changes with pressure. Pertaining to this, literature is unclear on which instantaneous local PWV value should be chosen within the cardiac cycle for PP evaluation. Since local PWV can be measured from various fiducial points spread across the blood pulse cycle, it may be relevant to investigate on the choice of particular one(s) for reliable PP calculation. We have conducted an ex-vivo study in this regard employing an excised ovine artery, emulating 21 independent flow conditions by changing the PP and mean arterial pressure (MAP). The measured end-diastolic (ED) PWV was lower than the peak-systolic (PS) PWV by 32%, and in theory they are the extremities of PWV within a cardiac cycle. An underestimation of 26% was observed in the PP evaluated using ED-PWV and overestimation of 30% using PS-PWV. The PWV that is expected to yield an exact PP value corresponded to the instant in the blood pulse cycle where its mean occurred. The ED-PWV underestimated and the PS-PWV over-estimated the expected PWV by 17% and 14%, respectively, which explains the deviations in the estimated PPs. The time instant of the first derivate maximum being closer to that of the cycle’s mean makes it a potential choice for measuring PWV for PP estimation.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114255585","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}
{"title":"Tomographic tactile sensor-based finger motion analysis system to identify number of grasping fingers for evaluating fine motor skills","authors":"Ryunosuke Asahi, Shunsuke Yoshimoto, Hiroki Sato","doi":"10.1109/MeMeA57477.2023.10171917","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171917","url":null,"abstract":"Finger movements are closely related to development disabilities such as autism spectrum disorder (ASD). These results suggest that a quantitative evaluation of finger movements may be applied to the early diagnosis of cognitive decline and autism in infants and young children. Therefore, we developed a novel automatic finger motion analysis system based on a tomographic tactile sensor by-using coupled conductors with a continuous sensing surface and conductive material with a high degree of freedom (DOF) of shape. Further, we developed two cylindrical sensors, with diameters of 25 and 50 mm, utilizing the high DOF of geometry. To evaluate the developed sensors, we conducted two validations-60-segment cross-validation and holdout validation–to identify the number of fingers engaged in grasping by adults. AlexNet was used for identification of the used reconstruction image; k-nearest neighbors (KNN) and Support vector machine (SVM) were used for the measurement of the voltage vector. According to the results, these accuracies exceeding the chance level was obtained for all participants of both validations. In addition, an average accuracy of approximately 90% was acquired using the measured voltage vector. In conclusion, the study findings indicate that the proposed device could be used for early diagnosis of ASD in infants and cognitive decline in older adults.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"279 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124484652","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}
Michela Franzo', Simona Pascucci, M. Serrao, F. Marinozzi, F. Bini
{"title":"Breakthrough in Occupational Therapy with Mixed-Reality exergaming for cerebellar ataxia patients","authors":"Michela Franzo', Simona Pascucci, M. Serrao, F. Marinozzi, F. Bini","doi":"10.1109/MeMeA57477.2023.10171955","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171955","url":null,"abstract":"Occupational therapy is a rehabilitation program that aim to recover or maintain the skills needed in daily life activities in order to preserve autonomy. Technologies, such as Virtual Reality and Augmented Reality, have found application in this field where their benefits have been recognised. The aim of this study is to present a mixed reality app for occupational therapy specifically implemented for ataxic patients. The app is implemented in Unity with the integration of the Vuforia asset and it is built for HoloLens2 device. The app can detect a real mug and provide virtual audio-visive feedback to the user during the action of reaching the mug. The audio-visive feedbacks were designed in accordance with an expert. Feedbacks were employed in order to increase concentration on the target and confidence in successfully autonomously complete the action of reaching the target following a virtual straight line. This app could be improved by integrating room-scanning new objects to be detect and feedback according to patient’s necessities. Hardware limitations of the HoloLens2 were for this type of application. However, this system has the potential to be of daily support to patients with neuromotor disorders as well as, with the necessary customisation, to the elderly and visually impaired.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128975323","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}
Keely Gibb, Nikita Yovchev, C. Aubertin, K. Greenwood, S. Redpath, A. Ibey, A. Chan, J. R. Green, R. Langlois
{"title":"Developing an Instrumentation Package to Measure Noise and Vibration in Neonatal Patient Transport","authors":"Keely Gibb, Nikita Yovchev, C. Aubertin, K. Greenwood, S. Redpath, A. Ibey, A. Chan, J. R. Green, R. Langlois","doi":"10.1109/MeMeA57477.2023.10171888","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171888","url":null,"abstract":"Inter-facility transport is often necessary for patients requiring specialized medical care. In the case of neonatal patients, specialized transport systems are used to ensure continuous care during transport. Concerns relating to physical stressors to which the patients are exposed during transport has motivated our ongoing study on evaluating and mitigating vibration and acoustic noise in these systems. Regardless of the various testing configurations, whether they be full-scale vehicle tests or laboratory shaker tests, reliable and consistent data collection practices are desired. An instrumentation package, designed to measure noise and vibration of the transport system, is currently in development to ultimately improve the safety of patients during transport. This system is intended to promote standard data collection practices and ultimately the aggregation of findings from independent studies into a single database. Requirements for the system have been defined, and early stages of sensor selection and prototyping are underway. The current configuration of sensors can successfully collect acceleration, angular rate, and sound level data. Additional sensors can be integrated into the system, to allow for multiple locations of interest to be studied simultaneously. Future work will improve the efficiency of the data collection script, the automation of data processing, and the physical implementation of the system.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131392234","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}