Search

Background: Epilepsy is a severe disorder of the central nervous system that predisposes the person to recurrent seizures. Fifty million people worldwide suffer from epilepsy; after Alzheimer’s and stroke, it is the third widespread nervous disorder. Objective: In this paper, an algorithm to detect the onset of epileptic seizures based on the analysis of brain electrical signals (EEG) has been proposed. 844 hours of EEG were recorded form 23 pediatric patients consecutively with 163 occurrences of seizures. Signals had been collected from Children’s Hospital Boston with a sampling frequency of 256 Hz through 18 channels in order to assess epilepsy surgery. By selecting effective features from seizure and non-seizure signals of each individual and putting them into two categories, the proposed algorithm detects the onset of seizures quickly and with high sensitivity. Method: In this algorithm, L-sec epochs of signals are displayed in form of a thirdorder tensor in spatial, spectral and temporal spaces by applying wavelet transform. Then, after applying general tensor discriminant analysis (GTDA) on tensors and calculating mapping matrix, feature vectors are extracted. GTDA increases the sensitivity of the algorithm by storing data without deleting them. Finally, K-Nearest neighbors (KNN) is used to classify the selected features. Results: The results of simulating algorithm on algorithm standard dataset shows that the algorithm is capable of detecting 98 percent of seizures with an average delay of 4.7 seconds and the average error rate detection of three errors in 24 hours. Conclusion: Today, the lack of an automated system to detect or predict the seizure onset is strongly felt.

Background: Breast cancer is currently one of the leading causes of death among women worldwide. The diagnosis and separation of cancerous tumors in mammographic images require accuracy, experience and time, and it has always posed itself as a major challenge to the radiologists and physicians. Objective: This paper proposes a new algorithm which draws on discrete wavelet transform and adaptive K-means techniques to transmute the medical images implement the tumor estimation and detect breast cancer tumors in mammograms in early stages. It also allows the rapid processing of the input data. Method: In the frst step, after designing a flter, the discrete wavelet transform is applied to the input images and the approximate coeffcients of scaling components are constructed. Then, the different parts of image are classifed in continuous spectrum. In the next step, by using adaptive K-means algorithm for initializing and smart choice of clusters’ number, the appropriate threshold is selected. Finally, the suspicious cancerous mass is separated by implementing the image processing techniques. Results: We Received 120 mammographic images in LJPEG format, which had been scanned in Gray-Scale with 50 microns size, 3% noise and 20% INU from clinical data taken from two medical databases (mini-MIAS and DDSM). The proposed algorithm detected tumors at an acceptable level with an average accuracy of 92.32% and sensitivity of 90.24%. Also, the Kappa coeffcient was approximately 0.85, which proved the suitable reliability of the system performance. Conclusion: The exact positioning of the cancerous tumors allows the radiologist to determine the stage of disease progression and suggest an appropriate treatment in accordance with the tumor growth. The low PPV and high NPV of the system is a warranty of the system and both clinical specialists and patients can trust its output.

Alcohol production and consumption have been prohibited in Iran for over four decades, leading to a typical underestimation of its consumption. This study aimed to assess the prevalence of alcohol consumption, its associated factors, and estimate per capita alcohol consumption among Iran's adult population. In this population-based survey, 27,874 adults from across Iran were selected using systematic proportional-to-size cluster sampling. Alcohol consumption was evaluated through a modified Persian version of the STEPS questionnaires from previous studies, applied over different timespans. Per capita consumption was calculated using the quantity-frequency method, expressed in liters of pure alcohol. Adjusted odds ratios were reported for associates of alcohol consumption concerning metabolic risk factors, sociodemographic elements, and lifestyle variables. The prevalence of lifetime alcohol consumption was 6.9% (95% CI 6.5-7.2) in the adult population, with a notable sex difference (males: 13.7% [95% CI 13-14.4]; females: 1.4% [95% CI 1.1-1.6]). The 12 month prevalence was 3.8% (95% CI 3.6-4.1). For individuals aged 18 and older, the per capita alcohol consumption in Iran was 0.12 L. Factors such as being a lifetime smoker, younger, wealthier, and having 7-12 years of education were significantly linked to higher alcohol consumption. Significant associations were also observed between alcohol consumption and having a history of heart attacks (OR = 2.04, 95% CI 1.44-2.89), and physical injuries (OR = 1.88, 95% CI 1.34-2.64). The estimated lifetime and 12-month prevalence of alcohol use in our study were higher among some of the subpopulations. The findings also revealed a complex relationship between alcohol consumption, behavioral risk factors, and metabolic profiles. Consequently, immediate preventive measures tailored to each factor's association with alcohol use are recommended., (© 2024. The Author(s).)

Colorectal cancer (CRC) is the second leading cause of cancer death in the world, so digital pathology is essential for assessing prognosis. Due to the increasing resolution and quantity of whole slide images (WSIs), as well as the lack of annotated information, previous methodologies cannot be generalized as effective decision-making systems. Since deep learning (DL) methods can handle large-scale applications, they can provide a viable alternative to histopathology image (HI) analysis. DL architectures, however, may not be sufficient to classify CRC tissues based on anatomical histopathology data. A dilated ResNet (dResNet) structure and attention module are used to generate deep feature maps in order to classify multiple tissues in HIs. In addition, neighborhood component analysis (NCA) overcomes the constraint of computational complexity. Data is fed into a deep support vector machine (SVM) based on an ensemble learning algorithm called DeepSVM after the features have been selected. CRC-5000 and NCT-CRC-HE-100 K datasets were analyzed to validate and test the hybrid procedure. We demonstrate that the hybrid model achieves 98.75% and 99.76% accuracy on CRC datasets. The results showed that only pathologists' labels could successfully classify unseen WSIs. Furthermore, the hybrid deep learning method outperforms state-of-the-art approaches in terms of computational efficiency and time. Using the proposed mechanism for tissue analysis, it will be possible to correctly predict CRC based on accurate pathology image classification., (© 2023. The Author(s).)

Purpose: The study aims to classify the eyes with proliferative diabetic retinopathy (PDR) and non-proliferative diabetic retinopathy (NPDR) based on the optical coherence tomography angiography (OCTA) vascular density maps using a supervised machine learning algorithm., Methods: OCTA vascular density maps (at superficial capillary plexus (SCP), deep capillary plexus (DCP), and total retina (R) levels) of 148 eyes from 78 patients with diabetic retinopathy (45 PDR and 103 NPDR) was used to classify the images to NPDR and PDR groups based on a supervised machine learning algorithm known as the support vector machine (SVM) classifier optimized by a genetic evolutionary algorithm., Results: The implemented algorithm in three different models reached up to 85% accuracy in classifying PDR and NPDR in all three levels of vascular density maps. The deep retinal layer vascular density map demonstrated the best performance with a 90% accuracy in discriminating between PDR and NPDR., Conclusions: The current study on a limited number of patients with diabetic retinopathy demonstrated that a supervised machine learning-based method known as SVM can be used to differentiate PDR and NPDR patients using OCTA vascular density maps., (© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.)

The vast majority of sleep disturbances are caused by various types of sleep arousal. To diagnose sleep disorders and prevent health problems such as cardiovascular disease and cognitive impairment, sleep arousals must be accurately detected. Consequently, sleep specialists must spend considerable time and effort analyzing polysomnography (PSG) recordings to determine the level of arousal during sleep. The development of an automated sleep arousal detection system based on PSG would considerably benefit clinicians. We quantify the EEG-ECG by using Lyapunov exponents, fractals, and wavelet transforms to identify sleep stages and arousal disorders. In this paper, an efficient hybrid-learning method is introduced for the first time to detect and assess arousal incidents. Modified drone squadron optimization (mDSO) algorithm is used to optimize the support vector machine (SVM) with radial basis function (RBF) kernel. EEG-ECG signals are preprocessed samples from the SHHS sleep dataset and the PhysioBank challenge 2018. In comparison to other traditional methods for identifying sleep disorders, our physiological signals correlation innovation is much better than similar approaches. Based on the proposed model, the average error rate was less than 2%-7%, respectively, for two-class and four-class issues. Additionally, the proper classification of the five sleep stages is determined to be accurate 92.3% of the time. In clinical trials of sleep disorders, the hybrid-learning model technique based on EEG-ECG signal correlation features is effective in detecting arousals., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2023 Afsoon Badiei et al.)

Background: Following global commitments to prevent and control non-communicable diseases, we sought to estimate national and sub-national trends in diabetes mortality in Iran and assess its association with socioeconomic factors. Methods: In a systematic analytical study, to assess the correlation between diabetes mortality and socioeconomic factors, we used data obtained from the Death Registration System (DRS), the Spatio-temporal model and Gaussian Process Regression (GPR) levels and the diabetes mortality trends, which were estimated by sex, age and year at national and sub-national levels from 1990 to 2015. Results: Between the years 1990 and 2015, the age-standardized diabetes mortality rate (per 100,000) increased from 3.40 (95% UI: 2.33 to 4.99) to 7.72 (95% UI: 5.51 to 10.78) in males and from 4.66 (95% UI: 3.23 to 6.76) to 10.38 (95% UI: 7.54 to 14.23) in females. In 1990, the difference between the highest age-standardized diabetes mortality rate among males was 3.88 times greater than the lowest (5.97 vs. 1.54), and in 2015 this difference was 3.96 times greater (14.65 vs. 3.70). This provincial difference was higher among females and was 5.13 times greater in 1990 (8.41 vs. 1.64) and 5.04 times greater in 2015 (19.87 vs. 3.94). The rate of diabetes mortality rose with urbanization yet declined with an increase in wealth and years of schooling as the main socio-economic factors. Conclusion: The rising trend of diabetes mortality rate at the national level and the sub-national disparities associated with socioeconomic status in Iran warrant the implementation of specific interventions recommended by the '25 by 25' goal., (© 2022 Iran University of Medical Sciences.)

Competing Interests: The authors report no conflict of interest.

Malignancies and diseases of various genetic origins can be diagnosed and classified with microarray data. There are many obstacles to overcome due to the large size of the gene and the small number of samples in the microarray. A combination strategy for gene expression in a variety of diseases is described in this paper, consisting of two steps: identifying the most effective genes via soft ensembling and classifying them with a novel deep neural network. The feature selection approach combines three strategies to select wrapper genes and rank them according to the k-nearest neighbour algorithm, resulting in a very generalisable model with low error levels. Using soft ensembling, the most effective subsets of genes were identified from three microarray datasets of diffuse large cell lymphoma, leukaemia, and prostate cancer. A stacked deep neural network was used to classify all three datasets, achieving an average accuracy of 97.51%, 99.6%, and 96.34%, respectively. In addition, two previously unreported datasets from small, round blue cell tumors (SRBCTs)and multiple sclerosis-related brain tissue lesions were examined to show the generalisability of the model method., (© 2022 The Authors. IET Systems Biology published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology.)

Competing Interests: The authors report no conflict of interest.

Introduction: To integrate and execute a proper preventive plan and reduce the risk of non-communicable diseases (NCDs), policy makers need to have access to both reliable data and a unique definition of metabolic syndrome (MetS). This study was conducted on the data collected by cross-sectional studies of WHO's STEPwise approach to surveillance of NCD risk factors (STEPs) to estimate the national and sub-national prevalence rates of MetS in Iran in 2016., Materials and Methods: The prevalence of MetS was estimated among 18,414 individuals aged ≥25 years living in urban and rural areas of Iran using various definition criteria; National Cholesterol Education Program Adult Treatment Panel III 2004 (ATP III), International Diabetes Federation (IDF), American Heart Association/National Heart, Lung, and Blood Institute (AHA/NHLBI), Joint Interim Statement (JIS). Regional IDF (RIDF) and JIS (RJIS) were defined using ethnicity-specific values of waist circumference for the country., Results: National prevalence rate of MetS based on ATP III, IDF, AHA/NHLBI, JIS, RIDF and RJIS criteria were 38.3% (95% CI 37.4-39.1), 43.5% (42.7-44.4), 40.9% (40.1-41.8), 47.6% (46.8-48.5), 32.0% (31.2-32.9), and 40.8% (40.0-41.7), respectively. The prevalence was higher among females, in urban residents, and those aged 65-69 years. MetS was expected to affect about 18.7, 21.3, 20.0, 23.3, 15.7, and 20.0 million Iranians, respectively, based on ATP III, IDF, AHA/NHLBI, JIS, RIDF and RJIS. The two most common components noted in this population were reduced high-density lipoprotein cholesterol (HDL-C) levels and central obesity., Conclusion: High prevalence rate of MetS among Iranian adults is alarming, especially among females, urban residents, and the elderly. The JIS definition criteria is more appropriate to determine higher number of Iranians at risk of NCDs. Proper management and prevention of MetS is required to adopt multiple national plans including lifestyle modifications, medical interventions, and public education on NCDs risk factors., Competing Interests: The authors have declared that no competing interests exist.

Competing Interests: The authors report no conflict of interest.

Background: Iran lacks a population level comprehensive assessment of stroke epidemiology. Using data from the NASBOD Study, we estimated the mortality of stroke among the Iranian population from 1990 to 2015., Methods: Data were collected from all the available sources including the national death registration system and two major cemeteries. After addressing incompleteness of child and adult death data and by using mixed effect model, spatio-temporal model and Gaussian Process Regression, levels and trends of child and adult mortality were estimated. By considering cause fraction to these estimates; cause specific mortality was estimated. In these process wealth index, urbanization, and years of schooling were used as covariates., Results: In 2015, the age-standardized stroke mortality rate due was 47.76 (95% UI: 34.68-65.03) for males and 40.16 (30.38-5 2.72) for females, per 100,000 population. Stroke occurrence for both ischemic and non-ischemic strokes showed decreasing trends in both sexes after 2001-2002, at national and sub-national levels. The highest and lowest mortality rates between provinces ranged from 52.11 (40.3-66.66) to 24.47 (18.71-31.79) in men and from 65.51 (47.13-89.41) to 30.43 (21.95-41.82) in women per 100,000 population., Conclusion: Although age-standardized rates of stroke mortality are falling, in the past three decades, the absolute number of people who have had a stroke has increased. Stroke mortality remains high in Iran.

Background: Under-five mortality is considered an indicator of population well-being and health equality in societies. Under-five mortality caused by nutritional deficiencies is a public health concern in developing countries. In this study, we aimed to report the trend and mortality rate of nutritional deficiencies from 1995 to 2015 in children aged under five years., Methods: In this study, we used the death registration system (DRS) data to estimate age- and sex-specific nutritional deficiency mortality rates at national and sub-national levels in Iran from 1995 to 2015. The Iranian DRS used the 10th revision of International Classification of Diseases (ICD-10) but we report our results based on Global Burden of Diseases (GBD) study codes. We used the average annual percent change (AAPC) to quantify trend in under-five mortality rate attributable to nutritional deficiencies from 1995 to 2015., Results: At national level, mortality rates in both sexes were 8.53 (95% uncertainty interval [UI]: 7.69-9.47), 1.04 (0.86-1.36), and 0.37 (95% UI: 0.28-0.57) per 100,000 in 1995, 2005, and 2015, respectively. AAPC was estimated between 1995 and 2015. At sub-national level, the highest and lowest mortality rates across provinces ranged from 17.7 per 100000 in 1995 to 1.1 per 100000 in 2015. In the latest years, protein-energy malnutrition (PEM) was the most frequent cause of mortality among other nutritional deficiencies., Conclusion: The results show a substantial reduction in terms of mortality caused by nutritional deficiencies at national, as well as provincial, level among children under-five years of age., (© 2020 The Author(s). This is an open-access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.)

Background: Insufficient physical activity (IPA) is one of the leading causes of premature mortality through the increased burden of non-communicable diseases. From 1990 to 2017, the percentage of low physical activity attributable disability-adjusted life years (DALY) increased globally by 1.5 times and 2-fold in Iran, causing more than 1.2 million deaths worldwide and 18,000 deaths in Iran in 2017. Reports suggest that Iran, a developing middle-income country, suffers from a high level of IPA. Socioeconomic and cultural alterations along with the country's developments expose the population to IPA risk. We aimed to describe IPA prevalence in Iran's adult population, categorized by demographics, geographical region, and activity domains to assess the present pattern of physical inactivity and its domains in the country., Methods: In 2016, in order to represent Iran's adult population, adult participants (n: 30541) from 30 provinces were selected using systematic proportional to size cluster sampling. Physical activity (PA) was assessed via the Global Physical Activity Questionnaire, calculating the Metabolic Equivalent of Task (MET) value in minutes per week for work, recreation, and transport domains. Insufficient physical activity (IPA) was defined according to WHO's recommendation (less than 600 METs per week). Adjusted odds ratios of IPA associates for sociodemographic, lifestyle related variables, and metabolic risk factors were reported., Results: A high prevalence of IPA was seen in the total population (54.7%, 95%CI: 54.0-55.3) with a considerable difference between the two genders (males: 45.3% (95%CI: 44.3-46.3); females: 61.9% (95%CI: 61.0-62.7)). Work-related activity was the domain with the greatest percentage of total PA, whereas, both genders lacked recreational activities. In our findings, being female, a housekeeper, younger and living in urban areas were significantly associated with higher levels of IPA. Moreover, insufficient fruit and vegetable consumption, lack of alcohol consumption, having a personal vehicle, and finally, having a medical history of diabetes were significantly associated with the presence of IPA in our population. Among the study population, 33.6% (95%CI: 33.0-34.2) had at least 4 h of sedentary behavior in a typical day., Conclusions: Widespread IPA among the Iranian adult population is of major concern. In our findings, we observed a considerable gap in the prevalence and pattern of IPA between the two genders. Additionally, IPA was associated with living in urban areas, unhealthy lifestyle habits and a history of other metabolic risk factors. Thus, a prompt initiative for population-specific actions should be taken.

Zinc sulfide semiconductor nanoparticles were synthesized in an aqueous solution of polyvinyl pyrrolidone via a simple microwave irradiation method. The effect of the polymer concentration and the type of sulfur source on the particle size and dispersion of the final ZnS nanoparticle product was carefully examined. Microwave heating generally occurs by two main mechanisms: dipolar polarization of water and ionic conduction of precursors. The introduction of the polymer affects the heating rate by restriction of the rotational motion of dipole molecules and immobilization of ions. Consequently, our results show that the presence of the polymer strongly affects the nucleation and growth rates of the ZnS nanoparticles and therefore determines the average particle size and the dispersion. Moreover, we found that PVP adsorbed on the surface of the ZnS nanoparticles by interaction of the C-N and C=O with the nanoparticle's surface, thereby affording protection from agglomeration by steric hindrance. Generally, with increasing PVP concentration, mono-dispersed colloidal solutions were obtained and at the optimal PVP concentration (5%), sufficiently small size and narrow size distributions were obtained from both sodium sulfide and thioacetamide sulfur sources. Finally, the sulfur source directly influences the reaction mechanism and the final particle morphology, as well as the average size.