Publications
Advances in Evaluating Fluid Levels: Bioimpedance in Patients with Kidney Failure
Jul 2, 2024Journal NTU Journal of Engineering and Technology
Publisher Northern Technical University
DOI https://doi.org/10.56286/ntujet.v3i2.882
Issue 2
Volume 3
This study delves deeply into the various facets of bioimpedance analysis as it relates to the development of chronic kidney disease (CKD). The use of bioimpedance spectroscopy (BIS) to evaluate the effectiveness of peritoneal dialysis (PD) and determine dialysis adequacy using variables like volume (V) and Kt/V is at the heart of this compilation. The investigations closely look at how important water distribution is for the advancement of CKD and how that affects patient outcomes. Evaluation of several body composition measurement methods is emphasized, especially the combination of the bioelectrical impedance analysis (BIA) ratio and the dry mass index (DMI). By applying the BIA TBW Watson ratio, these approaches provide important insights into the relationships between fluid volume and physiological indicators, such as body mass index (BMI) and total body water (TBW). The study emphasizes the differences in fluid overload diagnosis between conventional clinical assessments and sophisticated bioimpedance techniques, particularly in older patients with chronic kidney disease (CKD), underscoring the need for proper monitoring and intervention. Bioimpedance analysis is crucial to understanding chronic renal disease and associated cardiac complications, as shown in the assembled study. Bioimpedance analysis, used in devices like the Body Composition Monitor (BCM), is highlighted in this study collection to monitor hydration and improve dialysis adequacy. Bioimpedance analysis improves illness treatment, giving chronic renal failure and heart failure patients a more precise and nuanced grasp of fluid management, according to the literature.
A Review of Enhancement Techniques for Cone Beam Computed Tomography Images
Jul 1, 2024Journal NTU Journal of Engineering and Technology
Publisher Northern Technical University
DOI https://doi.org/10.56286/ntujet.v3i2.877
Issue 2
Volume 3
Cone Beam Computed Tomography (CBCT) has emerged as a valuable imaging modality for various medical applications due to its ability to provide three-dimensional information with minimal radiation exposure. However, CBCT images often suffer from inherent limitations, such as increased noise, artifacts, and reduced spatial resolution. This paper presents a comprehensive review of image processing techniques employed to enhance the quality of CBCT images, addressing the challenges posed by acquisition hardware and image reconstruction algorithms. The review covers a range of preprocessing and post-processing methods, including denoising, artifact correction, and resolution improvement techniques. These methods encompass various mathematical algorithms, machine learning approaches, and hybrid models, which aim to mitigate the imperfections present in CBCT data while preserving diagnostically relevant information. Additionally, this paper discusses the application of deep learning methods, convolutional neural networks, and generative adversarial networks in CBCT image enhancement. These advanced techniques have shown promise in tackling the complex nature of CBCT data and optimizing image quality.
Machine learning Techniques for Spondylolisthesis Diagnosis: a review
Jul 1, 2024Journal NTU Journal of Engineering and Technology
Publisher Northern Technical University
DOI https://doi.org/10.56286/ntujet.v3i2.768
Issue 2
Volume 3
Spondylolisthesis, a condition marked by vertebral slippage, presents a challenge in medical diagnosis and grading. This study examines previous research on image processing for spondylolisthesis severity evaluation. Methodologies, sample sizes, algorithms, and measurement accuracy are the main topics of interest. The study shows the potential of computer-assisted methods for diagnosing spondylolisthesis, particularly in situations where qualified medical personnel are scarce. Machine learning techniques and deep learning models, including convolutional neural networks (CNNs), are utilized to accurately detect and assess spondylolisthesis. Notably, these findings address a gap in previous research by measuring spondylolisthesis severity and distinguishing between normal and abnormal spines. The analysis emphasizes the significance of selecting the appropriate modality and data quality, with X-rays predominating as the preferred imaging technique. This review highlights how deep learning and machine learning models can improve spondylolisthesis diagnosis, enabling enhanced diagnosis and treatment methods.
Invasive and Non-Invasive Glucose Monitoring Systems: A Review and Comparative Study
Nov 13, 2023Journal Przegląd Elektrotechniczny
Publisher Przegląd Elektrotechniczny
DOI https://doi.org/10.56286/ntujet.v3i2.768
Issue 11
Volume 2023
As the incidence of diabetes has expanded worldwide in recent years, an increasing number of patients are experiencing pain and infections because to the invasive nature of the majority of commercial glucose measurement systems. The availability of reliable, low-cost, painless, noninvasive technology will promote patient compliance to routine blood glucose monitoring. The life of the diabetic patient will thereafter significantly improve. Several technologies have been proposed and developed by scientists and researchers in an attempt to enhance their effectiveness. This study reviewed both invasive and non-invasive glucose monitoring techniques, with an emphasis on optical methods. Non-invasive glucose monitoring devices that are painless, sensitive, and transportable are being suggested and developed to better understand glucose levels.
Inpatient WiFi-enabled medication dispenser for improving ward-based clinical pharmacy services
Feb 1, 2023Journal Indonesian Journal of Electrical Engineering and Computer Science
Publisher Institute of Advanced Engineering and Science
DOI https://doi.org/10.11591/ijeecs.v29.i2.pp687-693
Issue 2
Volume 29
Medications are vital for patients and especially for those who are receiving treatment in hospitals. Providing medications for these people is essential to maintain their health. On the other hand, medication dispensing error is one of the most common challenges that face clinical pharmacists and medical staff. These errors frequently occurred due to poor medication systems and/or human factors (i.e. environmental conditions, fatigue or staff shortage). These factors may affect prescribing, transcribing, administration, dispensing and monitoring practices which can result in disability, severe harm and even death. Avoiding medication dispensing errors is the key motivation of this paper. Consequently, a biometric-based dispensing system has been designed and implemented. The system can be installed at hospital wards and used for delivering and monitoring inpatients doses. It consists of three parts; hardware, software and mechanical part. Three 4-phase stepper motors are used for controlling the mechanical part of this system. An optical fingerprint sensor is used which is compatible with the ESP32 low power SoC for scanning patients’ fingerprints to recognize and store their data. The system directly updates its database whenever is used by the inpatients, so that nobody can get additional doses. This system is cost effective, reliable and easy to use.
The predictive value of cortical activity during motor imagery for subacute spinal cord injury-induced neuropathic pain
Jan 25, 2023Journal Clinical Neurophysiology
Publisher Elsevier
DOI https://doi.org/10.1016/j.clinph.2023.01.006
Volume 148
Objective The aim of this study is to explore whether cortical activation and its lateralization during motor imagery (MI) in subacute spinal cord injury (SCI) are indicative of existing or upcoming central neuropathic pain (CNP). Methods Multichannel electroencephalogram was recorded during MI of both hands in four groups of participants: able-bodied (N = 10), SCI and CNP (N = 11), SCI who developed CNP within 6 months of EEG recording (N = 10), and SCI who remained CNP-free (N = 10). Source activations and its lateralization were derived in four frequency bands in 20 regions spanning sensorimotor cortex and pain matrix. Results Statistically significant differences in lateralization were found in the theta band in premotor cortex (upcoming vs existing CNP, p = 0.036), in the alpha band at the insula (healthy vs upcoming CNP, p = 0.012), and in the higher beta band at the somatosensory association cortex (no CNP vs upcoming CNP, p = 0.042). People with upcoming CNP had stronger activation compared to those with no CNP in the higher beta band for MI of both hands. Conclusions Activation intensity and lateralization during MI in pain-related areas might hold a predictive value for CNP. Significance The study increases understanding of the mechanisms underlying transition from asymptomatic to symptomatic early CNP in SCI.
Effective Connectivity in Spinal Cord Injury-Induced Neuropathic Pain
Aug 23, 2022Journal Sensors
Publisher MDPI
DOI https://doi.org/10.3390/s22176337
Issue 17
Volume 22
Aim: The aim of this study was to differentiate the effects of spinal cord injury (SCI) and central neuropathic pain (CNP) on effective connectivity during motor imagery of legs, where CNP is typically experienced. Methods: Multichannel EEG was recorded during motor imagery of the legs in 3 groups of people: able-bodied (N = 10), SCI with existing CNP (N = 10), and SCI with no CNP (N = 20). The last group was followed up for 6 months to check for the onset of CNP. Source reconstruction was performed to obtain cortical activity in 17 areas spanning sensorimotor regions and pain matrix. Effective connectivity was calculated using the directed transfer function in 4 frequency bands and compared between groups. Results: A total of 50% of the SCI group with no CNP developed CNP later. Statistically significant differences in effective connectivity were found between all groups. The differences between groups were not dependent on the frequency band. Outflows from the supplementary motor area were greater for the able-bodied group while the outflows from the secondary somatosensory cortex were greater for the SCI groups. The group with existing CNP showed the least differences from the able-bodied group, appearing to reverse the effects of SCI. The connectivities involving the pain matrix were different between able-bodied and SCI groups irrespective of CNP status, indicating their involvement in motor networks generally. Significance: The study findings might help guide therapeutic interventions targeted at the brain for CNP alleviation as well as motor recovery post SCI.
Hardware implementation of Sobel edge detection system for blood cells images-based field programmable gate array
Apr 1, 2022Journal Indonesian Journal of Electrical Engineering and Computer Science
Publisher Institute of Advanced Engineering and Science
DOI https://doi.org/10.11591/ijeecs.v26.i1.pp86-95
Issue 1
Volume 26
The microscopic-blood image has been used to diagnose various diseases according to the morphological specifications of red and white blood cells. However, the manual analysis and procedures are not accurate due to the human error. Therefore, several studies conducted to find new techniques to perform this analysis using computer algorithms. The complexity of these algorithms led to thinking in simpler ways or to the hardware solutions. On the other hand, edge detection is a mathematical procedure that play an essential role in the field of medical image processing. It is considered as one of the foundations' processes for other procedures, such as the segmentation and the classification of the image. The Sobel filter is one of the conventional methods that is used to perform the edge detection process. It is based on finding the local contrast for the level of intensity of the image. This paper presents a proposed and a new method for detecting the edges of cells in the microscopic blood images using Sobel filter and its hardware implementation on the field programmable gate array (FPGA) chip. Three different techniques are proposed: MATLAB, OpenCV standard code, and FPGA customize code which give the best visual results, minimum timing results than the others.
Leukocytes identification using augmentation and transfer learning based convolution neural network
Apr 1, 2022Journal TELKOMNIKA Telecommunication Computing Electronics and Control
Publisher Institute of Advanced Engineering and Science
DOI https://doi.org/10.12928/TELKOMNIKA.v20i2.23163
Issue 2
Volume 20
Most haematological diseases can be diagnosed using the morphological analysis of the microscopic blood image. The basic routine of the morphological analysis can be performed using the microscopic device which requires the skills and experiences of the haematologists. An inexperienced haematologist can lead to critical human errors. Therefore, this paper aims to propose an automated classification system used to classify different types of leukocytes based on the convolution neural network (CNN) algorithm. CNN has achieved robust performance in various fields especially in medical applications. A dataset of microscopic blood cells images of the conforming tags (basophil, eosinophil, erythroblast, lymphocyte, monocyte, neutrophil, and platelet) was used to train and test the proposed algorithm. The augmentation and deep transfer approaches were used to improve and enhance the performance of the CNN algorithm. The overall accuracy of the proposed classifier was 98% with Visual Geometry Group-19 (VGG-19). The obtained accuracy was higher than the state-of-art algorithms. To conclude that using the augmentation and deep transfer approaches with VGG-19 can obtain better classification results.
Chapter 10 - EEG biomarkers of pain and applications of machine learning
Jan 1, 2022Journal Spinal Cord Injury Pain
Publisher Academic Press
DOI https://doi.org/10.1016/B978-0-12-818662-6.00019-4
Sensory mechanical and thermal tests are widely used biomarkers of Central Neuropathic Pain (CNP) in people with Spinal Cord Injury. They are used to diagnose, and in some cases to predict the risk of developing CNP. In this chapter, we propose neuroimaging EEG biomarkers for diagnosis and prediction of CNP in people with chronic and subacute CNP. EEG biomarkers utilize inexpensive technology and do not rely on the level of preservation of sensation. Due to its ability to record dynamically changing events on the order of milliseconds, EEG is suitable for creating biomarkers in relaxed state as well as during a cognitive function, which can complement each other. We provide a review of the state-of-the-art EEG markers of CNP followed by several examples from our own research. We present diagnostic and prognostic EEG biomarkers of CNP based on machine learning, derived from EEG in resting state and during imagined movements of paralyzed and nonparalyzed limbs in people with subacute and chronic SCI.
Recognition of multifont English electronic prescribing based on convolution neural network algorithm
Sep 14, 2020Journal Bio-Algorithms and Med-Systems
Publisher De Gruyter
DOI https://doi.org/10.1016/B978-0-12-818662-6.00019-4
Issue 3
Volume 16
The printed character recognition is an efficient and automatic method for inputting information to a computer nowadays that is used to translate the printed or handwritten images into an editable and readable text file. This paper aims to recognize a multifont and multisize of the English language printed word for a smart pharmacy purpose. The recognition system has been based on a convolution neural network (CNN) approach where line, word, and character are separately corrected, and then each of the separated characters is fed into the CNN algorithm for recognition purposes. The OpenCV open-source library has been used for preprocessing, which can segment English characters accurately and efficiently, and for recognition, the Keras library with the backend of TensorFlow has been used. The training and testing data sets have been designed to include 23 different fonts with six different sizes. The CNN algorithm achieves the highest accuracy of 96.6% comparing to the other state-of-the-art machine learning methods. The higher classification accuracy of the CNN approach shows that this type of algorithm is ideal for the English language printed word recognition. The highest error rate after testing the system using English electronic prescribing written with all proposed font-types is 0.23% in Georgia font.
Thingspeak-based respiratory rate streaming system for essential monitoring purposes
Jul 8, 2020Journal Bio-Algorithms and Med-Systems
Publisher De Gruyter
DOI https://doi.org/10.1515/bams-2020-0007
Issue 3
Volume 16
Chronic obstructive pulmonary diseases are the most common disease worldwide. Asthma and sleep apnea are the most prevalent of pulmonary diseases. Patients with such chronic diseases require special care and continuous monitoring to avoid any respiratory deterioration. Therefore, the development of a dedicated and reliable sensor with the aid of modern technologies for measuring and monitoring respiratory parameters is very necessary nowadays. This study aims to develop a small and cost-effective respiratory rate sensor. A microcontroller and communication technology (NodeMCU) with the ThingSpeak platform is used in the proposed system to view and process the respiratory rate data every 60 s. The total current consumption of the proposed sensor is about 120 mA. Four able-bodied participants were recruited to test and validate the developed system. The results show that the developed sensor and the proposed system can be used to measure and monitor the respiratory rate. The demonstrated system showed applicable, repeatable, and acceptable results.
Microcontroller based in vitro hematocrit measurement system
May 1, 2020Journal Indonesian Journal of Electrical Engineering and Computer Science
Publisher Institute of Advanced Engineering and Science
DOI https://doi.org/10.11591/ijeecs.v18.i2.pp717-723
Issue 2
Volume 18
The hematocrit (HCT) is the most important measurement in the blood profile. It has been used for early diagnose of the specific blood diseases such as anaemia, leukaemia and malaria. The microhematocrit is the conventional method of measurement of HCT manually which is timeconsuming and uncertain due to human error. An automated system for measuring hematocrit will minimize the human-error and the time which will give the ability for medical staff to serve more patients. This paper aims to demonstrate an automated system for measuring the HCT based on microcontroller. The designed system based on Arduino Atmega 2560 microcontroller and combination array of lighting emitting diode and photodetectors. The transmission and the absorption characteristics of the red light (660nm) through the centrifuged blood sample in a capillary tube are calculated and used to determine the HCT. The outputs are analyzed to determine the haemoglobin (HB) and packed cell volume (PCV). The significant correlation (r=0.9856, p=3.106*10-4) between the PCV readings of the proposed system and the conventional method has been observed. The most important finding is the precise of PCV and HB readings for the proposed system compared with previous automated methods as well as the conventional method have been obtained.
Streaming in-patient BPM data to the cloud with a real-time monitoring system
Dec 1, 2019Journal TELKOMNIKA Telecommunication Computing Electronics and Control
Publisher Institute of Advanced Engineering and Science
DOI http://doi.org/10.12928/telkomnika.v17i6.13263
Issue 6
Volume 17
Monitoring the heart activities for old people or people with medical history (Arrhythmia or CHD) is targeted by most new medical technologies. This paper demonstrated an in-patient real-time monitoring system for heart rate estimation. A ratio of beats per minute (BPM) is continuously recorded, streamed and archived to the cloud via WeMos WiFi development board. This cost effective system is simply based on two sub-systems: BPM data acquisition through pulse sensor and WeMos-based communication systems. The streamed BPM data are saved instantaneously in Google drive as spreadsheets which can only be accessed by authorized persons wherever the internet service is available. Thus, the person in charge can remotely observe the patient’s status and do analytics for the archived data. A pilot study with eight subjects was carried out to validate the developed BPM tele-monitoring system. Encouraging results have been achieved.
Controlling a motorized electric wheelchair based on face tilting
Oct 11, 2019Journal Bio-Algorithms and Med-Systems
Publisher De Gruyter
DOI http://doi.org/10.1515/bams-2019-0033
Volume 2019
Disability, specifically impaired upper and/or lower limbs, has a direct impact on the patients’ quality of life. Nowadays, motorized wheelchairs supported by a mobility-aided technique have been devised to improve the quality of life of these patients by increasing their independence. This study aims to present a platform to control a motorized wheelchair based on face tilting. A real-time tracking system of face tilting using a webcam and a microcontroller circuit has been designed and implemented. The designed system is dedicated to control the movement directions of the motorized wheelchair. Four commands were adequate to perform the required movements for the motorized wheelchair (forward, right, and left, as well as stopping status). The platform showed an excellent performance regarding controlling the motorized wheelchair using face tilting, and the position of the eyes was shown as the most useful face feature to track face tilting.
Electroencephalographic Predictors of Neuropathic Pain in Subacute Spinal Cord Injury
Nov 1, 2018Journal The Journal of Pain
Publisher Elsevier
DOI https://doi.org/10.1016/j.jpain.2018.04.011
Issue 11
Volume 19
t is widely believed that cortical changes are a consequence of longstanding neuropathic pain (NP). In this article, we demonstrate that NP in individuals with subacute spinal cord injury (SCI) has characteristic electroencephalography markers (EEG) that precede the onset of pain. EEG was recorded in a relaxed state and during motor imagination tasks in 10 able-bodied participants and 31 patients with subacute SCI (11 with NP, 10 without NP, and 10 who had pain develop within 6 months of EEG recording). All 20 patients with SCI initially without NP were tested for mechanically induced allodynia, but only 1 patient, who later had pain develop, reported an unpleasant sensation. The EEG reactivity to eye opening was reduced in the alpha band and absent in the theta and beta bands in the patients who later developed pain and was reduced in those who already had pain. Alpha band power was reduced at BA7 in both the relaxed state and during motor imagination in patients who either had or later developed pain compared with those without pain. All SCI groups had reduced dominant alpha frequency and beta band power at BA7. EEG reactivity to eye opening and reduced spontaneous and induced alpha activity over the parietal cortex were predictors of future NP, as well as markers of existing NP.
Prediction of central neuropathic pain in spinal cord injury based on EEG classifier
Aug 1, 2018Journal Clinical Neurophysiology
Publisher Elsevier
DOI https://doi.org/10.1016/j.clinph.2018.04.750
Issue 8
Volume 129
To create a classifier based on electroencephalography (EEG) to identify spinal cord injured (SCI) participants at risk of developing central neuropathic pain (CNP) by comparing them with patients who had already developed pain and with able bodied controls. Multichannel EEG was recorded in the relaxed eyes opened and eyes closed states in 10 able bodied participants and 31 subacute SCI participants (11 with CNP, 10 without NP and 10 who later developed pain within 6 months of the EEG recording). Up to nine EEG band power features were classified using linear and non-linear classifiers. Three classifiers (artificial neural networks ANN, support vector machine SVM and linear discriminant analysis LDA) achieved similar average performances, higher than 85% on a full set of features identifying patients at risk of developing pain and achieved comparably high performance classifying between other groups. With only 10 channels, LDA and ANN achieved 86% and 83% accuracy respectively, identifying patients at risk of developing CNP. Transferable learning classifier can detect patients at risk of developing CNP. EEG markers of pain appear before its physical symptoms. Simple and complex classifiers have comparable performance.
Central neuropathic pain in paraplegia alters movement related potentials
Jun 15, 2018Journal Clinical Neurophysiology
Publisher Elsevier
DOI https://doi.org/10.1016/j.clinph.2018.05.020
Issue 8
Volume 129
Spinal Cord Injured (SCI) persons with and without Central Neuropathic Pain (CNP) show different oscillatory brain activities during imagination of movement. This study investigates whether they also show differences in movement related cortical potentials (MRCP). SCI paraplegic patients with no CNP (n = 8), with CNP in their lower limbs (n = 8), and healthy control subjects (n = 10) took part in the study. EEG clustering involved independent component analysis, equivalent current dipole fitting, and Measure Projection to define cortical domains that have functional modularity during the motor imagery task. Three domains were identified: limbic system, sensory-motor cortex and visual cortex. The MRCP difference between the groups of SCI with and without CNP was reflected in a domain located in the limbic system, while the difference between SCI patients and control subjects was in the sensorimotor domain. Differences in MRCP morphology between patients and healthy controls were visible for both paralysed and non paralysed limbs. SCI but not CNP affects the movement preparation, and both SCI and CNP affect sensory processes.
The effect of voluntary modulation of the sensory-motor rhythm during different mental tasks on H reflex
Aug 1, 2016Journal International Journal of Psychophysiology
Publisher Elsevier
DOI https://doi.org/10.1016/j.ijpsycho.2016.06.005
Volume 106
Objectives The aim of this study was to explore the possibility of the short-term modulation of the soleus H reflex through self-induced modulation of the sensory-motor rhythm (SMR) as measured by electroencephalography (EEG) at Cz. Methods Sixteen healthy participants took part in one session of neuromodulation. Motor imagery and mental math were strategies for decreasing SMR, while neurofeedback was used to increase SMR. H reflex of the soleus muscle was elicited by stimulating tibial nerve when SMR reached a pre-defined threshold and was averaged over 5 trials. Results Neurofeedback and mental math both resulted in the statistically significant increase of H reflex (p = 1.04·10− 6 and p = 5.47·10− 5 respectively) while motor imagery produced the inconsistent direction of H reflex modulation (p = 0.57). The average relative increase of H reflex amplitude was for neurofeedback 19.0 ± 5.4%, mental math 11.1 ± 3.6% and motor imagery 2.6 ± 1.0%. A significant negative correlation existed between SMR amplitude and H reflex for all tasks at Cz and C4. Conclusions It is possible to achieve a short-term modulation of H reflex through short-term modulation of SMR. Various mental tasks dominantly facilitate H reflex irrespective of direction of SMR modulation.
Design and Implementation of Microcontroller Based Portable Drug Delivery System
Sep 8, 2011Journal Eng. & Tech. Journal
Publisher University of Technology
DOI https://www.uotechnology.edu.iq/tec_magaz/volum292011/No.12.2011/text/Text%20(16).pdf
Issue 12
Volume 29
Portable drug delivery system or portable syringe pump system is a small infusion pump used to gradually deliver drugs, at low doses and at a constant or controllable rate of drug to a patient who needs to take a drug dose regularly in specific periods all the day. The aim of this research is to design and perform a prototype of a portable drug delivery system controlled by micro controller. The micro controller will control the dose of liquid or medication which will be given to the patient and the time of repetition of the dose. The dose rate will be adjusted by controlling the operation of stepper motor which will drive the syringe pump through fine mechanism set.