Automatic identification of hypertension and assessment of its secondary effects using artificial intelligence: A systematic review (2013-2023).

Artificial Intelligence (AI) techniques are increasingly used in computer-aided diagnostic tools in medicine. These techniques can also help to identify Hypertension (HTN) in its early stage, as it is a global health issue. Automated HTN detection uses socio-demographic, clinical data, and physiological signals. Additionally, signs of secondary HTN can also be identified using various imaging modalities. This systematic review examines related work on automated HTN detection. We identify datasets, techniques, and classifiers used to develop AI models from clinical data, physiological signals, and fused data (a combination of both). Image-based models for assessing secondary HTN are also reviewed. The majority of the studies have primarily utilized single-modality approaches, such as biological signals (e.g., electrocardiography, photoplethysmography), and medical imaging (e.g., magnetic resonance angiography, ultrasound). Surprisingly, only a small portion of the studies (22 out of 122) utilized a multi-modal fusion approach combining data from different sources. Even fewer investigated integrating clinical data, physiological signals, and medical imaging to understand the intricate relationships between these factors. Future research directions are discussed that could build better healthcare systems for early HTN detection through more integrated modeling of multi-modal data sources.

Automated detection of pain levels using deep feature extraction from shutter blinds-based dynamic-sized horizontal patches with facial images.

Pain intensity classification using facial images is a challenging problem in computer vision research. This work proposed a patch and transfer learning-based model to classify various pain intensities using facial images. The input facial images were segmented into dynamic-sized horizontal patches or "shutter blinds". A lightweight deep network DarkNet19 pre-trained on ImageNet1K was used to generate deep features from the shutter blinds and the undivided resized segmented input facial image. The most discriminative features were selected from these deep features using iterative neighborhood component analysis, which were then fed to a standard shallow fine k-nearest neighbor classifier for classification using tenfold cross-validation. The proposed shutter blinds-based model was trained and tested on datasets derived from two public databases-University of Northern British Columbia-McMaster Shoulder Pain Expression Archive Database and Denver Intensity of Spontaneous Facial Action Database-which both comprised four pain intensity classes that had been labeled by human experts using validated facial action coding system methodology. Our shutter blinds-based classification model attained more than 95% overall accuracy rates on both datasets. The excellent performance suggests that the automated pain intensity classification model can be deployed to assist doctors in the non-verbal detection of pain using facial images in various situations (e.g., non-communicative patients or during surgery). This system can facilitate timely detection and management of pain.

RLMD-PA: A Reinforcement Learning-Based Myocarditis Diagnosis Combined with a Population-Based Algorithm for Pretraining Weights.

Myocarditis is heart muscle inflammation that is becoming more prevalent these days, especially with the prevalence of COVID-19. Noninvasive imaging cardiac magnetic resonance (CMR) can be used to diagnose myocarditis, but the interpretation is time-consuming and requires expert physicians. Computer-aided diagnostic systems can facilitate the automatic screening of CMR images for triage. This paper presents an automatic model for myocarditis classification based on a deep reinforcement learning approach called as reinforcement learning-based myocarditis diagnosis combined with population-based algorithm (RLMD-PA) that we evaluated using the Z-Alizadeh Sani myocarditis dataset of CMR images prospectively acquired at Omid Hospital, Tehran. This model addresses the imbalanced classification problem inherent to the CMR dataset and formulates the classification problem as a sequential decision-making process. The policy of architecture is based on convolutional neural network (CNN). To implement this model, we first apply the artificial bee colony (ABC) algorithm to obtain initial values for RLMD-PA weights. Next, the agent receives a sample at each step and classifies it. For each classification act, the agent gets a reward from the environment in which the reward of the minority class is greater than the reward of the majority class. Eventually, the agent finds an optimal policy under the guidance of a particular reward function and a helpful learning environment. Experimental results based on standard performance metrics show that RLMD-PA has achieved high accuracy for myocarditis classification, indicating that the proposed model is suitable for myocarditis diagnosis.

Automated Diagnosis and Assessment of Cardiac Structural Alteration in Hypertension Ultrasound Images.

Hypertension (HTN) is a major risk factor for cardiovascular diseases. At least 45% of deaths due to heart disease and 51% of deaths due to stroke are the result of hypertension. According to research on the prevalence and absolute burden of HTN in India, HTN positively correlated with age and was present in 20.6% of men and 20.9% of women. It was estimated that this trend will increase to 22.9% and 23.6% for men and women, respectively, by 2025. Controlling blood pressure is therefore important to lower both morbidity and mortality. Computer-aided diagnosis (CAD) is a noninvasive technique which can determine subtle myocardial structural changes at an early stage. In this work, we show how a multi-resolution analysis-based CAD system can be utilized for the detection of early HTN-induced left ventricular heart muscle changes with the help of ultrasound imaging. Firstly, features were extracted from the ultrasound imagery, and then the feature dimensions were reduced using a locality sensitive discriminant analysis (LSDA). The decision tree classifier with contourlet and shearlet transform features was later employed for improved performance and maximized accuracy using only two features. The developed model is applicable for the evaluation of cardiac structural alteration in HTN and can be used as a standalone tool in hospitals and polyclinics.

Artificial Intelligence Enabled Personalised Assistive Tools to Enhance Education of Children with Neurodevelopmental Disorders-A Review.

Mental disorders (MDs) with onset in childhood or adolescence include neurodevelopmental disorders (NDDs) (intellectual disability and specific learning disabilities, such as dyslexia, attention deficit disorder (ADHD), and autism spectrum disorders (ASD)), as well as a broad range of mental health disorders (MHDs), including anxiety, depressive, stress-related and psychotic disorders. There is a high co-morbidity of NDDs and MHDs. Globally, there have been dramatic increases in the diagnosis of childhood-onset mental disorders, with a 2- to 3-fold rise in prevalence for several MHDs in the US over the past 20 years. Depending on the type of MD, children often grapple with social and communication deficits and difficulties adapting to changes in their environment, which can impact their ability to learn effectively. To improve outcomes for children, it is important to provide timely and effective interventions. This review summarises the range and effectiveness of AI-assisted tools, developed using machine learning models, which have been applied to address learning challenges in students with a range of NDDs. Our review summarises the evidence that AI tools can be successfully used to improve social interaction and supportive education. Based on the limitations of existing AI tools, we provide recommendations for the development of future AI tools with a focus on providing personalised learning for individuals with NDDs.

Role of Artificial Intelligence in COVID-19 Detection.

The global pandemic of coronavirus disease (COVID-19) has caused millions of deaths and affected the livelihood of many more people. Early and rapid detection of COVID-19 is a challenging task for the medical community, but it is also crucial in stopping the spread of the SARS-CoV-2 virus. Prior substantiation of artificial intelligence (AI) in various fields of science has encouraged researchers to further address this problem. Various medical imaging modalities including X-ray, computed tomography (CT) and ultrasound (US) using AI techniques have greatly helped to curb the COVID-19 outbreak by assisting with early diagnosis. We carried out a systematic review on state-of-the-art AI techniques applied with X-ray, CT, and US images to detect COVID-19. In this paper, we discuss approaches used by various authors and the significance of these research efforts, the potential challenges, and future trends related to the implementation of an AI system for disease detection during the COVID-19 pandemic.

Multistage Optimization Using a Modified Gaussian Mixture Model in Sperm Motility Tracking.

Infertility is a condition whereby pregnancy does not occur despite having unprotected sexual intercourse for at least one year. The main reason could originate from either the male or the female, and sometimes, both contribute to the fertility disorder. For the male, sperm disorder was found to be the most common reason for infertility. In this paper, we proposed male infertility analysis based on automated sperm motility tracking. The proposed method worked in multistages, where the first stage focused on the sperm detection process using an improved Gaussian Mixture Model. A new optimization protocol was proposed to accurately detect the motile sperms prior to the sperm tracking process. Since the optimization protocol was imposed in the proposed system, the sperm tracking and velocity estimation processes are improved. The proposed method attained the highest average accuracy, sensitivity, and specificity of 92.3%, 96.3%, and 72.4%, respectively, when tested on 10 different samples. Our proposed method depicted better sperm detection quality when qualitatively observed as compared to other state-of-the-art techniques.

Advances in bioactive glass-containing injectable hydrogel biomaterials for tissue regeneration.

Successful tissue regeneration requires a scaffold with tailorable biodegradability, tissue-like mechanical properties, structural similarity to extracellular matrix (ECM), relevant bioactivity, and cytocompatibility. In recent years, injectable hydrogels have spurred increasing attention in translational medicine as a result of their tunable physicochemical properties in response to the surrounding environment. Furthermore, they have the potential to be implanted via minimally invasive procedures while enabling deep penetration, which is considered a feasible alternative to traditional open surgical procedures. However, polymeric hydrogels may lack sufficient stability and bioactivity in physiological environments. Composite hydrogels containing bioactive glass (BG) particulates, synergistically combining the advantages of their constituents, have emerged as multifunctional biomaterials with tailored mechanical properties and biological functionalities. This review paper highlights the recent advances in injectable composite hydrogel systems based on biodegradable polymers and BGs. The influence of BG particle geometry, composition, and concentration on gel formation, rheological and mechanical behavior as well as hydration and biodegradation of injectable hydrogels have been discussed. The applications of these composite hydrogels in tissue engineering are additionally described, with particular attention to bone and skin. Finally, the prospects and current challenges in the development of desirable injectable bioactive hydrogels for tissue regeneration are discussed to outline a roadmap for future research. STATEMENT OF SIGNIFICANCE: Developing a biomaterial that can be readily available for surgery, implantable via minimally invasive procedures, and be able to effectively stimulate tissue regeneration is one of the grand challenges in modern biomedicine. This review summarizes the state-of-the-art of injectable bioactive glass-polymer composite hydrogels to address several challenges in bone and soft tissue repair. The current limitations and the latest evolutions of these composite biomaterials are critically examined, and the roles of design parameters, such as composition, concentration, and size of the bioactive phase, and polymer-glass interactions on the rheological, mechanical, biological, and overall functional performance of hydrogels are detailed. Existing results and new horizons are discussed to provide a state-of-the-art review that may be useful for both experienced and early-stage researchers in the biomaterials community.

Polymeric Hydrogel Systems as Emerging Biomaterial Platforms to Enable Hemostasis and Wound Healing.

Broad interest in developing new hemostatic technologies arises from unmet needs in mitigating uncontrolled hemorrhage in emergency, surgical, and battlefield settings. Although a variety of hemostats, sealants, and adhesives are available, development of ideal hemostatic compositions that offer a range of remarkable properties including capability to effectively and immediately manage bleeding, excellent mechanical properties, biocompatibility, biodegradability, antibacterial effect, and strong tissue adhesion properties, under wet and dynamic conditions, still remains a challenge. Benefiting from tunable mechanical properties, high porosity, biocompatibility, injectability and ease of handling, polymeric hydrogels with outstanding hemostatic properties have been receiving increasing attention over the past several years. In this review, after shedding light on hemostasis and wound healing processes, the most recent progresses in hydrogel systems engineered from natural and synthetic polymers for hemostatic applications are discussed based on a comprehensive literature review. Most studies described used in vivo models with accessible and compressible wounds to assess the hemostatic performance of hydrogels. The challenges that need to be tackled to accelerate the translation of these novel hemostatic hydrogel systems to clinical practice are emphasized and future directions for research in the field are presented.

Self-Healing Polyester Urethane Supramolecular Elastomers Reinforced with Cellulose Nanocrystals for Biomedical Applications.

Stretchable self-healing urethane-based biomaterials have always been crucial for biomedical applications; however, the strength is the main constraint of utilization of these healable materials. Here, a series of novel, healable, elastomeric, supramolecular polyester urethane nanocomposites of poly(1,8-octanediol citrate) and hexamethylene diisocyanate reinforced with cellulose nanocrystals (CNCs) are introduced. Nanocomposites with various amounts of CNCs from 10 to 50 wt% are prepared using solvent casting technique followed by the evaluation of their microstructural features, mechanical properties, healability, and biocompatibility. The synthesized nanocomposites indicate significantly higher tensile modulus (approximately 36-500-fold) in comparison to the supramolecular polymer alone. Upon exposure to heat, the materials can reheal, but nevertheless when the amount of CNC is greater than 10 wt%, the self-healing ability of nanocomposites is deteriorated. These materials are capable of rebonding ruptured parts and fully restoring their mechanical properties. In vitro cytotoxicity test of the nanocomposites using human dermal fibroblasts confirms their good cytocompatibility. The optimized structure, self-healing attributes, and noncytotoxicity make these nanocomposites highly promising for tissue engineering and other biomedical applications.

Analysis of the interface pressure exerted by the Chêneau brace in patients with double-curve adolescent idiopathic scoliosis.

The Chêneau brace has proven its effectiveness in treating the adolescent idiopathic scoliosis patients. However, no studies reported on the analysis of interface pressure in double-curve adolescent idiopathic scoliosis patients. In this study, we evaluated the interface pressure of the Chêneau brace action in double-curve adolescent idiopathic scoliosis patient treatment. A total of 72 (60 girls and 12 boys) patients aged 10 years and above participated in the study. The F-Socket transducers (9811E) were used to evaluate the pressure on the right thoracic and left thoracolumbar curves between normal and maximum strap tension and variation in these interface pressures with other tasks. Each patient was asked to do nine different tasks corresponding to daily activities, and the interface pressures for each activity were recorded for both normal and maximum tension. The resultant mean peak pressure in double-curve adolescent idiopathic scoliosis was higher for right thoracic curves than left thoracolumbar curves in all tasks. The pressure significantly increased at the task of maximal inspiration (p < 0.0001) for both types of curves for normal and maximum tension. The degrees of correction for the thoracic and thoracolumbar curves were 23.2% and 34.5%, respectively, after 6 months of brace use (23 h per day). Hence, we could not find any substantial correlation between mean peak pressure in the standing position and degree of scoliosis correction for two curves having r = 0.158, p = 0.356 and r = -0.024, p = 0.889 values.

Elastomeric biocomposite of silver-containing mesoporous bioactive glass and poly(1,8-octanediol citrate): Physiochemistry and in vitro antibacterial capacity in tissue engineering applications.

A novel series of silver-doped mesoporous bioactive glass/poly(1,8-octanediol citrate) (AgMBG/POC) elastomeric biocomposite scaffolds were successfully constructed by a salt-leaching technique for the first time and the effect of inclusion of different AgMBG contents (5, 10, and 20 wt%) on physicochemical and biological properties of pure POC elastomer was evaluated. Results indicated that AgMBG particles were uniformly dispersed in the POC matrix and increasing the AgMBG concentration into POC matrix up to 20 wt% enhanced thermal behaviour, mechanical properties and water uptake ability of the composite scaffolds compared to those from POC. The 20%AgMBG/POC additionally showed higher degradation rate in Tris(hydroxymethyl)-aminomethane-HCl (Tris-HCl) compared with pure POC and lost about 26% of its initial weight after soaking for 28 days. The AgMBG phase incorporation also significantly endowed the resulting composite scaffolds with efficient antibacterial properties against Escherichia coli and Staphylococcus aureus bacteria while preserving their favorable biocompatibility with soft tissue cells (i.e., human dermal fibroblast cells). Taken together, our results suggest that the synergistic effect of both AgMBG and POC make these newly designed AgMBG/POC composite scaffold an attractive candidate for soft tissue engineering applications.

Well-ordered mesoporous silica and bioactive glasses: promise for improved hemostasis.

Immediate control of uncontrolled bleeding and infection are essential for saving lives in both combat and civilian arenas. Inorganic well-ordered mesoporous silica and bioactive glasses have recently shown great promise for accelerating hemostasis and infection control. However, to date, there has been no comprehensive report assessing their specific mechanism of action in accelerating the hemostasis process and exerting an antibacterial effect. After providing a brief overview of the hemostasis process, this review presents a critical overview of the recently developed inorganic mesoporous silica and bioactive glass-based materials proposed for hemostatic clinical applications and specifically investigates their unique characteristics that render them applicable for hemostatic applications and preventing infections. This article also identifies promising new research directions that should be undertaken to ascertain the effectiveness of these materials for hemostatic applications.

Comparative efficacy of hemorrhage control of a novel mesoporous bioactive glass versus two commercial hemostats.

Mesoporous bioactive glass containing 1% Ga2O3 (1%Ga-MBG) is attractive for hemorrhage control because of its surface chemistry which can promote blood-clotting. The present study compares this proprietary inorganic coagulation accelerator with two commercial hemostats, CeloxTM (CX) and QuikClot Advanced Clotting Sponge PlusTM (ACS+). The results indicate that the number of adherent platelets were higher on the 1%Ga-MBG and CX surfaces than ACS+ whereas a greater contact activation was seen on 1%Ga-MBG and ACS+ surfaces than CX. 1%Ga-MBG not only resulted in larger platelet aggregates and more extensive platelet pseudopodia compared to CX and ACS+ but also significantly accelerated the intrinsic pathways of the clotting cascade. In vitro thrombin generation assays also showed that CX and ACS+ induced low levels of thrombin formation while 1%Ga-MBG had significantly higher values. 1%Ga-MBG formed a larger red blood cell aggregate than both CX and ACS+. Direct exposure of 1%Ga-MBG to fibroblast cells increased cell viability after 3 days relative to CX and ACS+, inferring excellent cytocompatibility. The results of this study promote 1%Ga-MBG as a promising hemostat compared to the commercially available products as it possesses essential factors required for coagulation activation.

Feature-Based Retinal Image Registration Using D-Saddle Feature.

Retinal image registration is important to assist diagnosis and monitor retinal diseases, such as diabetic retinopathy and glaucoma. However, registering retinal images for various registration applications requires the detection and distribution of feature points on the low-quality region that consists of vessels of varying contrast and sizes. A recent feature detector known as Saddle detects feature points on vessels that are poorly distributed and densely positioned on strong contrast vessels. Therefore, we propose a multiresolution difference of Gaussian pyramid with Saddle detector (D-Saddle) to detect feature points on the low-quality region that consists of vessels with varying contrast and sizes. D-Saddle is tested on Fundus Image Registration (FIRE) Dataset that consists of 134 retinal image pairs. Experimental results show that D-Saddle successfully registered 43% of retinal image pairs with average registration accuracy of 2.329 pixels while a lower success rate is observed in other four state-of-the-art retinal image registration methods GDB-ICP (28%), Harris-PIIFD (4%), H-M (16%), and Saddle (16%). Furthermore, the registration accuracy of D-Saddle has the weakest correlation (Spearman) with the intensity uniformity metric among all methods. Finally, the paired t-test shows that D-Saddle significantly improved the overall registration accuracy of the original Saddle.

Development of poly (1, 8-octanediol citrate)/chitosan blend films for tissue engineering applications.

Blends of poly (1, 8-octanediol citrate) (POC) and chitosan (CS) were prepared through solution casting technique. Films with different component fractions (POC/CS: 100/0, 90/10, 80/20, 70/30, 60/40, and 0/100) were successfully prepared and characterized for their mechanical, thermal, structural and morphological properties as well as biocompatibility. The incorporation of CS to POC significantly increased tensile strength and elastic modulus and presented limited influences on pH variation which is important to the biocompatibility of biomaterial implants. The assessment of surface topography indicated that blending could enhance and control the surface roughness of the pure films. POC/CS blends well-supported human dermal fibroblast cells attachment and proliferation, and thus can be used for a range of tissue engineering applications.

Potency and Cytotoxicity of a Novel Gallium-Containing Mesoporous Bioactive Glass/Chitosan Composite Scaffold as Hemostatic Agents.

Chitosan-based hemostats are promising candidates for immediate hemorrhage control. However, they have some disadvantages and require further improvement to achieve the desired hemostatic efficiency. Here, a series of 1% Ga2O3-containing mesoporous bioactive glass-chitosan composite scaffolds (Ga-MBG/CHT) were constructed by the lyophilization process and the effect of various concentrations of Ga-MBG (10, 30, and 50 wt %) on the hemostatic function of the CHT scaffold was assessed as compared to that of Celox Rapid gauze (CXR), a current commercially available chitosan-coated hemostatic gauze. The prepared scaffolds exhibited >79% porosity and showed increased water uptake compared to that in CXR. The results of coagulation studies showed that pure CHT and composite scaffolds exhibited increased hemostatic performance with respect to CXR. Furthermore, the composite scaffold with the highest Ga-MBG content (50 wt %) had increased capability to enhancing thrombus generation, blood clotting, and platelet adhesion and aggregation than that of the scaffold made of pure CHT. The antibacterial efficacy and biocompatibility of the prepared scaffolds were also assessed by a time-killing assay and an Alamar Blue assay, respectively. Our results show that the antibacterial effect of 50% Ga-MBG/CHT was more pronounced than that of CHT and CXR. The cell viability results also demonstrated that Ga-MBG/CHT composite scaffolds had good biocompatibility, which facilitates the spreading and proliferation of human dermal fibroblast cells even with 50 wt % Ga-MBG loading. These results suggest that Ga-MBG/CHT scaffolds could be a promising hemostatic candidate for improving hemostasis in critical situations.

Discriminating dengue-infected hepatic cells (WRL-68) using dielectrophoresis.

Dielectrophoresis (DEP), the induced movement of dielectric particles placed in a nonuniform electric field, has been used as a potential technique for manipulation and separation of many biological samples without destructive consequences to the cell. Cells of the same genotype in different physiological and pathological states have unique morphological and structural features, therefore, it is possible to differentiate between them using their DEP responses. This paper reports the experimental discrimination of normal and dengue-infected human hepatic fetal epithelial cells (WRL-68 cells) based on their DEP crossover frequency, at which no resultant movement occurs in the cells in response to the DEP force. A microarray dot electrode was used to conduct the DEP experiments. The DEP forces applied to the cells were quantified by analyzing the light intensity shift within the electrode's dot region based on the Cumulative Modal Intensity Shift image analysis technique. The differences in dielectric properties between infected and uninfected cells were exploited by plotting a unique DEP spectrum for each set of cells. We observed that the crossover frequency decreased from 220 kHz for the normal WRL-68 cells to 140 kHz after infection with the dengue virus in a medium conductivity of 100 µS/cm. We conclude that the change in the DEP crossover frequency between dengue-infected cells and their healthy counterparts should allow direct characterization of these cell types by exploiting their electrophysiological properties.

Inorganic hemostats: The state-of-the-art and recent advances.

Hemorrhage is the most common cause of death both in hospitals and on the battlefield. The need for an effective hemostatic agent remains, since all injuries are not amenable to tourniquet use. There are many topical hemostatic agents and dressings available to control severe bleeding. This article reviews the most commonly used inorganic hemostats, subcategorized as zeolite and clay-based hemostats. Their hemostatic functions as well as their structural properties that are believed to induce hemostasis are discussed. The most important findings from in vitro and in vivo experiments are also covered.

Computational local stiffness analysis of biological cell: High aspect ratio single wall carbon nanotube tip.

Carbon nanotubes (CNTs) are potentially ideal tips for atomic force microscopy (AFM) due to the robust mechanical properties, nanoscale diameter and also their ability to be functionalized by chemical and biological components at the tip ends. This contribution develops the idea of using CNTs as an AFM tip in computational analysis of the biological cells. The proposed software was ABAQUS 6.13 CAE/CEL provided by Dassault Systems, which is a powerful finite element (FE) tool to perform the numerical analysis and visualize the interactions between proposed tip and membrane of the cell. Finite element analysis employed for each section and displacement of the nodes located in the contact area was monitored by using an output database (ODB). Mooney-Rivlin hyperelastic model of the cell allows the simulation to obtain a new method for estimating the stiffness and spring constant of the cell. Stress and strain curve indicates the yield stress point which defines as a vertical stress and plan stress. Spring constant of the cell and the local stiffness was measured as well as the applied force of CNT-AFM tip on the contact area of the cell. This reliable integration of CNT-AFM tip process provides a new class of high performance nanoprobes for single biological cell analysis.