Heart failure (HF) is a critical condition in which the accurate prediction of mortality plays a vital role in guiding patient management decisions. However, clinical datasets used for mortality prediction in HF often suffer from an imbalanced distribution of classes, posing significant challenges. In this paper, we explore preprocessing methods for enhancing one-month mortality prediction in HF patients. We present a comprehensive preprocessing framework including scaling, outliers processing and resampling as key techniques. We also employed an aware encoding approach to effectively handle missing values in clinical datasets. Our study utilizes a comprehensive dataset from the Persian Registry Of cardio Vascular disease (PROVE) with a significant class imbalance. By leveraging appropriate preprocessing techniques and Machine Learning (ML) algorithms, we aim to improve mortality prediction performance for HF patients. The results reveal an average enhancement of approximately 3.6% in F1 score and 2.7% in MCC for tree-based models, specifically Random Forest (RF) and XGBoost (XGB). This demonstrates the efficiency of our preprocessing approach in effectively handling Imbalanced Clinical Datasets (ICD). Our findings hold promise in guiding healthcare professionals to make informed decisions and improve patient outcomes in HF management.
The shoulder complex consists of various joints which correspond to specific degrees of freedom (DOF). Musculoskeletal modeling is a method to reconstruct the real motions that involved a big challenge to simulation accuracy. Different shoulder models with various DOF and constraint definitions are available although the accuracy of the simulation is still debated. Thus, the objective of this study was to evaluate DOF and constraint definitions of shoulder models for inverse kinematics (IK) simulation during the middle direct punch (MDP). The experimental marker data in twenty elite martial arts players (65.4±5.8 kg, 172±7.8 cm, 29.5±8.5 years) were collected during the MDP. Four models were chosen as base models (M3, three-DOF between humerus and trunk Glenohumeral joint; M9, three-DOF for Scapulothoracic joint, three-DOF for Acromioclavicular joint, and three-DOF for Glenohumeral joint; Mst, coupled motions for scapula, clavicle, and humerus; Mel, an ellipsoid mobilizer for the Sternoclavicular joint). The subject-specific models were generated for each subject and model by marker data in static posture and scaling tools of OpenSim. The inverse kinematics tool of OpenSim was used to reconstruct MDP motion via models. RMS of marker error was used to compare models as indicators. Results represented significant differences in RMS of marker error for various models during the MDP tasks (P<0.05). Results illustrated the RMS of marker error for model Mel was minimum (12.87±0.09mm), whereas the RMS of marker error for all subject-specific models was lower than generic models. Based on the results the best model is model Mel which indicated this musculoskeletal model of the shoulder complex can reconstruct the MDP motion better than other represented models. In addition, our results indicated using the subject-specific model instead of generic models is vital to access reliable results. The results of this study would be utilized by sport science researchers, sports medicine doctors, coaches, trainers, and players to simulate shoulder motion by musculoskeletal modeling.
Image registration is the process of matching the coordinate systems of two or more images. Medical image registration has been used in a variety of applications such as segmentation, motion tracking, etc. Recently, the use of deep neural networks has been demonstrated as a useful approach to registration problems. In this article, we propose two separate novel Convolutional Neural Network (CNN) architectures for multi-modal rigid and affine registration of the CT-MRI images of the brain. A dataset consisting of CT-MRI images of 37 subjects was used for training and evaluation of the networks. For both networks, the proposed models achieved a high mutual information value between predicted CT images and their corresponding MRIs and a mean dice score of 0.984 for rigid registration.
In the past, many people lost their lives due to superficial wound infections. Over time, the importance of wound healing as the reconstruction of the body's first defense barrier, the skin, became more important. Today, traditional medicine has given way to reconstructive medicine. Tissue engineering has always been a pioneer in the development and application of new methods as the main branch of reconstructive medicine. In this research, a Nano-Scaffold was designed and fabricated for skin Tissue engineering with unique properties using electrospinning method. In this project, to increase the function of the scaffold, two nanoparticles containing two types of drugs have been used, which is considered as a hybrid drug delivery system. Concomitant use of layered double hydroxide hybrid (LDH) nanoparticles containing curcumin and imidazole zeolite (ZIF-8) containing aspirin in poly-lactic acid scaffolding will accelerate wound healing and reduce inflammation. After processing two layered double hydroxide nanoparticles containing curcumin and imidazole zeolite containing aspirin, these two nanoparticles were loaded on poly-lactic acid nanofibers. By adding 3% by weight of nanoparticles to poly-lactic acid, the tensile strength increased from 1.31 MPa to 1.6 MPa, the contact angle increased from 59 ° to 120 ° and cell viability (within 72 hours) increased from 49% to 88%. Tests performed on the scaffold confirmed its biocompatibility.
Gait analysis is one of the major topics in rehabilitation and sport. Tracking and determining gait phases can be done using various sensors and methods. In this paper, a fuzzy logic method is proposed to analyze and detect the five phases of a gait cycle using ground reaction force (GRF) and its gradient. The proposed method enables better detection adaptability at different walking speeds and body weights compared with the traditional threshold algorithms. In this algorithm, the GRF, measured by an insole equipped with force sensing resistors (FSR) and GRF gradient, which represent the plantar pressure transmission during a cycle, is passed through a set of fuzzy rules to detect the five gaits. A genetic algorithm (GA) is also applied for optimizing the fuzzy logic membership functions to reach minimum detection delay. A cost function is defined based on the difference between the normal reference gait and the output of the fuzzy logic gait phases. Detected phases are IC (initial contact), LR (loading response), MS (mid-stance), PS (pre-swing), and SW (swing). It is shown that the proposed method reaches a highly reliable performance of phase detection, especially for the initial contact (IC) and toe-off (TO). The average detection delays for the IC and TO phases, using the fuzzy-based method for three walking speeds of 0.4, 0.85, and 1.3 m/s, were -14.3±16.9ms and 1.24±17.0ms, respectively, and the average duration of stance and swing phases are 61.42% and 38.58%, respectively.
The brain is considered the body's most important organ, and the clearance of waste products from the brain is of vital importance. In the past, it was believed that the brain had no efficient disposal system due to its lack of lymphatic vessels. Also, it was thought that the only phenomenon in the brain is diffusion, and substances transportation was purely dependent on it. But not long ago, the ideas about the disposal system and brain phenomena were challenged after the rediscovery of the Glymphatic system. In this research, using the porous fluid-solid interaction approach, the Glymphatic system and the factors affecting its functioning have been investigated. The findings indicate that the increase in wall displacement does not cause significant changes in the volume exchange fraction of the perivascular space. Moreover, the reduction of displacement leads to a corresponding decrease in velocity magnitude in the perivascular spaces, which makes the conditions favorable for waste products to settle. Another finding of this research is that the wall oscillations are more effective in the paths adjacent to thicker ducts compared to the paths adjacent to narrower ducts so that the increase in wall oscillations causes an increase of 4.38 and 1.73 times respectively in the mentioned paths, which indicates that the influence of these oscillations is fading in the paths adjacent to narrower channels. Based on the results, the perivascular pathways have the ability to experience the Péclet number greater than one, which means that diffusion is not the only phenomenon in the brain. But in the porous tissue of the brain, the Péclet number still has smaller values than one.
The regions of the brain may be viewed as nodes in a complex network where information is dynamically transferred through synchronization. Synchronization plays an important role in learning, emotions, and motion. However, neurological disorders such as epilepsy are known to result from abnormal brain synchronization. Coupled Kuramoto model with a little integration of the neurological factors can be a suitable model of the brain network. In this paper, we present an open-loop data-driven control strategy to effectively desynchronize the activity of brain regions during a simulated seizure episode without making any assumptions about the dynamics of the brain. In order to quantify the significance of network nodes, we used an energy-based optimization problem. Then, we evaluated our control methods using a genuine connectome with 80 regions and demonstrated that our approach remarkably decreased synchrony between phases of the oscillations of the brain during the epileptic seizure. Finally, we conclude that brain epilepsy synchronization can be controlled by applying external inputs to the chosen optimal set of driver nodes.
Knee replacement surgery is a common treatment for patients with end-stage knee arthrosis. Unfortunately, the age of patients suffering from this condition and requiring knee joint replacement is decreasing, leading to an increase in the need for revision surgeries. Therefore, using suitable prostheses can increase the durability of joint replacement and the success of this procedure. For this purpose, in this research, three materials, Co-Cr, Ti6AI4V, and FGM, were examined by the finite element method. An accurate three-dimensional model of the distal part of the femur bone was developed, and after designing the stem, its volume was subtracted from the bone, and the final assembly model and material properties were assigned to it. The models were subjected to jogging (6Km/h) and walking loading conditions. The findings of this research showed that in both loading conditions, the Co-Cr stem was subjected to stress more than twice the stress applied to the other two stems. Also, jogging applies more stress to the stem-bone construct than walking. According to the results of this research, it can be said that the use of FGM and Ti6A14V stems is preferable, although the construction costs should also be considered. In addition, examining more active movements can be influential in determining movement limitations after revision surgery.
Parkinson's disease (PD) is a neurological disorder based on changes in dynamic brain activity, which can be partially ameliorated with invasive Deep Brain Stimulation. Galvanic vestibular stimulation (GVS), a non-invasive method, could potentially improve the motor symptoms of Parkinson's disease, but the mechanisms are unclear. Biomarkers based on the electroencephalogram (EEG) are being actively pursued. Here we examine the properties of EEG microstates as a potential GVS-sensitive EEG biomarker, whereby multichannel, broadband EEG signals are approximated by a sequence of discrete spatial patterns. We used the Microstate Analysis plugin for EEGLAB and compared the characteristics between healthy (n=20) and people with PD (n=22, stimulated/sham, and OFF Medication/ ON Medication). We extracted 25 Microstate related features from 4 different microstates (‘A’ - ‘D’) and examined their differences between groups (a healthy control group was considered as the reference to extract the feature values). Overall disease severity, as assessed by the clinical Unified Parkinson's Disease Rating Scale (UPDRS) Part 3, was predictable from microstate features. The duration of microstate A - selected by LASSO during UPDRS prediction- was significantly changed by both types of GVS stimuli (multi-sine 50–100 Hz (GVS1), and multi-sine 100–150 Hz (GVS2)), but not medication. The fraction of total recording time for microstate C, also a key feature in disease prediction, was found to be selectively affected GVS1 only. The above results suggest that GVS may provide benefits complementary to medication but in a stimulus-dependent manner. These results could potentially guide optimal GVS design in the pursuit of complementary therapies.
Dirofilaria immitis (D. immitis) or Heartworm is the most pathogenic filariae in dogs which also occasionally infects humans. Dirofilariasis has been found all over the world, and in Iran, on average, 11.5% of dogs are infected. Microscopic examination, the modified Knott method, is a definitive and very common diagnosis method for detecting microfilariae in peripheral blood. It is inexpensive, relatively quick, and does not require advanced and expensive laboratory equipment. However, identification and differentiation of microfilariae from artifacts stand on the abilities and expertise of technicians. The aim of this study was to remove this limitation by developing an artificial intelligence, deep learning-based system that detects microfilariae in blood slides and differentiates microfilaria from thread-like artifacts automatically. To this end, blood samples (n=300) were obtained from stray dogs in Guilan province. The existence of microfilariae was assessed by modified Knott's test under microscopic examinations which identified 29 cases infected with microfilaria. These positive results were confirmed with conventional PCR. The Microfilariae measuring found 295.13±14.9 µm in length and 5.8±0.43 µm in width. The images captured of microfilariae and artifacts were applied to educate and test the suggested deep learning-based system. The developed system diagnoses D. immitis with an accuracy of greater than 95% and thus, can be widely used for epidemiological studies. Since the microfilariae can be miss-diagnosed with thread-shaped artifacts, the proposed system plays an effective role in accurate and reliable diagnosis of D. immitis and can be used in field studies.
Topography of extracellular matrix plays a major role in many biological events including tissue healing, morphogenesis and growth. It is known that matrix constitution and mechanical properties are deciding factors in governing the fate of its inhabitant cells. Besides the direct mechanical cues, matrices also facilitate the release and uptake of certain chemicals and participate in cell-cell and cell- ECM crosstalk. Mechanical strains in the matrix are proved to direct endothelial cell migration and elongation leading to angiogenesis, and there is a consensus that matrix stiffness, fiber density and fiber orientation can enhance angiogenesis in the preferred direction of stiffness gradient. In this study, we specifically investigated the role of topography in guidance of endothelial self-reorganization prompted by the effect of fluid flow hindrance and facilitation in certain directions. We adopted our previous model of fluid flow guided angiogenesis for cellular responses. Lattice Boltzmann model of fluid flow was adopted and modified to study the effect of unidirectional and randomly oriented fibers. To study the effect of fiber orientation, we customized a previously proposed model of porosity in lattice Boltzmann to suit this purpose. This model could reproduce the effects of fiber orientations in matrix on endothelial migration and vasculogenesis. Simulations showed better confluency of formed lumens when prescribed flow is in the direction of fiber orientation. These results can have further implications in understanding endothelial complications in certain diseases as well as in tumor angiogenesis and metastasis.
Devices that imitate the functions of human skin are known as “electronic skin,” and they must have characteristics like high sensitivity, a wide dynamic range, high spatial homogeneity, cheap cost, wide area easy processing, and the ability to distinguish between diverse external inputs. Here, we describe a flexible droplet-based microfluidic-assisted emulsion self-assembly (DMESA) method for producing highly efficient capacitive pressure sensors based on three-dimensional microstructures for electronic skin applications. Our method may produce evenly sized micropores that self-assemble across a vast area in an ordered close-packed manner, leading to excellent spatial homogeneity. Dynamic amplitude and sensitivity were readily regulated to as high as 0.62 kPa -1 and up to 100 kPa by adjusting the micropore size, which can be simply adjusted from 100 to 600 µm. Our gadget may be molded into a variety of forms and printed on curved surfaces. These examples show how our method and sensors may be used for a broad range of e-skin applications.
In this paper, blood pressure measurement is done non-invasively and by a corrected oscillometric method. First, the cuff is inflated to the desired value, and then by opening a valve the air pressure in the cuff decreases almost linearly between 2~4mmHg/s. To achieve the oscillometric graph, the output signal during deflation is band-pass filtered and then amplified. To remove different artifacts and noises from the oscillogram, a correction curve based on Gaussian distribution is fitted on it. Then using fixed coefficients with the help of Mean Arterial Pressure (MAP), the values of systolic and diastolic pressure are calculated. The values of R Squared obtained for systolic and diastolic pressures before fitting the curve are -0.178 and 0.389, and after fitting are 0.625 and -0.012, respectively.
biomedical diagnostic tool for the detection of tumors in the brain since it provides detailed and comprehensive information associated with the brain's anatomical structures. The radiologist can detect the existence of malignancies or aberrant cell growths using MRI images. Early-stage brain tumor diagnosis and treatment are greatly aided by MRI image processing. This study inquires about a method for classifying MRI brain images into without tumors and brain tumors to detect tumors using these images. These days, researchers can create reliable Computer-Aided Diagnosis (CAD) systems for identifying tumors and healthy brains thanks to the benefits of machine learning. A crucial stage in any machine-learning model is feature extraction. Time-frequency analysis techniques are more effective for image classification applications since they provide localized information. We suggested using the Discrete Cosine-based Stockwell Transform (DCST) to extract the efficacious features from brain MRI images and create the feature matrix after pre-processing and segmentation. The feature matrix's dimension was decreased using the chi-square test. A Support Vector Machine (SVM) classifies the selected features at the end. We employed a dataset containing 7023 brain MRI images divided into four classes: tumors of the pituitary, glioma, meningioma, and without tumors. For binary classification into brain tumors and no tumors, we attained an accuracy of 97.71%.
One of the main challenges of using polyaniline (PANI) in tissue engineering, is the cytotoxicity of PANI dopants, which compromises their biocompatibility. Herein, we aimed to substitute a biocompatible dopant instead of other cytotoxic dopants such as, camphor sulfonic acid (CSA). For this purpose, poly-L-lactic acid (PLLA) was used as a carrier polymer, PANI as a conductive agent, and AA as a biological factor and PANI dopant. Conductive scaffolds were fabricated via electrospinning. Finally, the morphology of the scaffolds was evaluated using a scanning electron microscope (SEM). By adding PANI, CSA and AA dopants to PLLA, we observed a decrease in the diameter of nanofibers from 841 ± 181 nm to 468 ± 62 nm and from 841 ± 181 nm to 546 ± 77 nm, respectively. The conductivity of the scaffolds was measured by the two-point probe, which was 9.7 × 10–5 in the PANI-CSA scaffold and 4 × 10–5 in the PANI-AA scaffold. Considering that the acidity of CSA is higher than the acidity of AA, its polymer solution has more conductivity and leads to a decrease in the diameter of nanofibers. Therefore, we proposed that PANI-AA-based nanofibers can be used as a bioactive conductive scaffold for bone tissue engineering. Since AA does not have the cytotoxicity of CSA and in addition to playing a biological role that causes bone differentiation, it also has the role of a dopant for PANI.
In recent years, wearable exoskeleton robots have been growingly used for rehabilitation or movement assistive purposes. Despite the growing application of these robots in various domains, such as physical therapy, the movement synchronization between robots and human bodies remains a challenging problem. This paper aims to achieve better synchronization by predicting human movement. Although several works have been presented in this domain, the robustness of these predictions has received less attention. This paper aims to provide a robust prediction using Completion-Generative Adversarial Networks (CGAN) that are learned based on the Huber loss function. Specifically, we reshape the 3D-joint-position-time series (jointxaxesxtime) into multivariate time series ((jointxaxes) xtime) and pass them to a CGAN. We use the Huber loss function to improve the GAN performance and offer higher robustness against noise in real-world applications. The proposed method is evaluated on an actual human gait dataset and compared with several recent works in this domain. Results show that the proposed method is superior to the previous works in prediction error, particularly in terms of achieving a better signal-to-noise ratio.
The biggest organ of the body is the skin, which is crucial in protecting from numerous infections and illnesses. One of the methods of wound healing is the use of hydrogel wound dressings, which accelerates the healing process by moisturizing the wound environment. In this research, an attempt has been made to synthesize a hydrogel dressing with suitable physical and mechanical properties by freeze-thawing cycles. polyvinyl alcohol (PVA) and gelatin materials have been used due to their biocompatibility, biodegradability and water absorption properties, and imidazole zeolite framework-8 (Zif-8) nanoparticles have been used due to improve mechanical properties and biocompatibility. The novelty of this research is implementing Zif-8 in the PVA/Gel for the first time. Hydrogel wound dressings were analyzed via field emission scanning electron microscopy, energy-dispersive X-ray spectroscopy, Fourier transform infrared spectroscopy, mechanical characteristics, swelling, and degradability tests. The microscopic images show the non-porous surface and the surface roughness has increased with the addition of nanoparticles. Fourier Transform Infrared Spectroscopy shows the elements and chemical structure of the nature of hydrogels. In the analysis of mechanical properties, the PGZ 70:30 sample had the maximum ultimate tensile strength (344.3876±8.31 kPa) and Young's modulus (448±2.31 kPa), which is suitable for skin patch applications. With the addition of nanoparticles, hydrogel swelling was decreased and the rate of degradation was accelerated. The results show that the synthesized hydrogel can be promising for wound healing.
Transcranial Direct-Current Stimulation (tDCS), as a safe and non-invasive neuromodulator, has been recently the center of attention for the treatment and management of neurological disorders. However, the intervening mechanisms of tDCS are not completely understood, and in consequence, it was not possible or advisable to utilize it as an effective treatment. In this work, by integrating a neural mass model of the thalamocortical system, which can generate and induce different types of seizures, and the physiological aspects of the interaction between tDCS and the brain, such as permissible current and how it must be involved in different neural populations, we have proposed a basic model. Then, by connecting several units of the basic model and applying a learning rule to calculate properly the connectivity weights between units, a multi-zone model is established. Our simulation results explained the ever-increasing connectivity between pre-and post-stimulation, an accepted feature of tDCS. Then, we described computationally (based on bifurcation analysis) how this change in connectivity can lead to a reduction in epileptic susceptibility.
Brain-Computer Interface (BCI) systems establish a control and communication relationship between the human brain and computers including robots or other devices to help individuals with severe motor disabilities. The classification of motor and mental imagery electroencephalogram (EEG) signals is complicated because these signals are usually case-specific and distinct models must be trained for each subject to process and classify his/her EEG signals. Moreover, in BCI systems EEG signals are processed online, so the time latency must be very low. In this paper, we have proposed a method based on signal-to-image conversion to investigate image processing techniques in the pair-wise classification of motor and mental imagery EEG signals. We first decomposed EEG signals of each trial into four sub-bands. Then, for each sub-band, we converted EEG time series to 2-dimensional (2D) images using covariance between signals of all channels. Then, statistical, textural and PCA-based features were extracted from these images and fed to a support vector machine (SVM) classifier. Our results were promising in the offline processing and achieved an average classification accuracy of 79.57%.
Metal-organic frameworks (MOFs) are suitable as carriers for drug delivery systems (DDSs) due to their large specific surface area and high biocompatibility. In the present study, paclitaxel (PTX) as an anticancer drug was loaded into MIL-100 (Fe) to reduce the abuse side effects of PTX and enhance its efficacy through the controlled release of PTX from MOF. MIL-100 (Fe) was synthesized via the hydrothermal technique and characterized through BET, FESEM, FTIR, and XRD analysis. The BET surface area of MIL-100 (Fe) was found to be 1336 m 2 g -1 . Drug release profiles from synthesized MIL-100 (Fe) and pharmacokinetic studies were investigated. The PTX release data of MIL-100 (Fe) was evaluated under pH values of 5.5, and 7.4, at temperatures of 37 °C. The biocompatibility of drug-loaded MIL-100 (Fe) was also assessed by incubating them in MCF-7 breast cancer cells. The maximum cytotoxicity of MCF-7 cancer cells treated with MIL-100 (Fe)/PTX 10 µg mL -1 was found to be 77%. It can be concluded that MIL-100 (Fe) can be used as an effective pH-sensitive carrier to load anticancer drugs. Therefore, all these findings indicate that MIL-100(Fe) is a promising drug delivery platform for PTX and the treatment of various cancers.
