Search

Early identification of acute gout is crucial, enabling healthcare professionals to implement targeted interventions for rapid pain relief and preventing disease progression, ensuring improved long-term joint function. In this study, we comprehensively explored the potential early detection of gout flares (GFs) based on nurses’ chief complaint notes in the Emergency Department (ED). Addressing the challenge of identifying GFs prospectively during an ED visit, where documentation is typically minimal, our research focused on employing alternative Natural Language Processing (NLP) techniques to enhance detection accuracy. We investigated GF detection algorithms using both sparse representations by traditional NLP methods and dense encodings by medical domain-specific Large Language Models (LLMs), distinguishing between generative and discriminative models. Three methods were used to alleviate the issue of severe data imbalances, including oversampling, class weights, and focal loss. Extensive empirical studies were performed on the Gout Emergency Department Chief Complaint Corpora. Sparse text representations like tf-idf proved to produce strong performances, achieving F1 scores higher than 0.75. The best deep learning models were RoBERTa-large-PM-M3-Voc and BioGPT, which had the best F1 scores for each dataset, with a 0.8 on the 2019 dataset and a 0.85 F1 score on the 2020 dataset, respectively. We concluded that although discriminative LLMs performed better for this classification task when compared to generative LLMs, a combination of using generative models as feature extractors and employing a support vector machine for classification yielded promising results comparable to those obtained with discriminative models.

Human capability to perform routine tasks declines with age and age-related problems. Remote human activity recognition (HAR) is beneficial for regular monitoring of the elderly population. This paper addresses the problem of the continuous detection of daily human activities using a mm-wave Doppler radar. In this study, two strategies have been employed: the first method uses un-equalized series of activities, whereas the second method utilizes a gradient-based strategy for equalization of the series of activities. The dynamic time warping (DTW) algorithm and Long Short-term Memory (LSTM) techniques have been implemented for the classification of un-equalized and equalized series of activities, respectively. The input for DTW was provided using three strategies. The first approach uses the pixel-level data of frames (UnSup-PLevel). In the other two strategies, a convolutional variational autoencoder (CVAE) is used to extract Un-Supervised Encoded features (UnSup-EnLevel) and Supervised Encoded features (Sup-EnLevel) from the series of Doppler frames. The second approach for equalized data series involves the application of four distinct feature extraction methods: i.e., convolutional neural networks (CNN), supervised and unsupervised CVAE, and principal component Analysis (PCA). The extracted features were considered as an input to the LSTM. This paper presents a comparative analysis of a novel supervised feature extraction pipeline, employing Sup-ENLevel-DTW and Sup-EnLevel-LSTM, against several state-of-the-art unsupervised methods, including UnSUp-EnLevel-DTW, UnSup-EnLevel-LSTM, CNN-LSTM, and PCA-LSTM. The results demonstrate the superiority of the Sup-EnLevel-LSTM strategy. However, the UnSup-PLevel strategy worked surprisingly well without using annotations and frame equalization.

The prediction of protein-protein interactions (PPIs) is essential to understand the cellular processes from a medical perspective. Among the various machine learning techniques, kernel-based Support Vector Machine (SVM) has been commonly employed to discriminate between interacting and non-interacting protein pairs. The main drawback of employing the kernel-based SVM to datasets with many features, such as the primary sequence-based protein-protein dataset, is the significant increase in computational time of training stage. This increase in computational time is mainly due to the presence of the kernel in solving the quadratic optimisation problem (QOP) involved in nonlinear SVM. In order to fix this issue, we propose a novel and efficient computational algorithm by approximating the kernel-based SVM using a low-rank truncated Mercer series as well as desired. As a result, the QOP for the approximated kernel-based SVM will be very tractable in the sense that there is a significant reduction in computational time of training and validating stages. We illustrate the novelty of the proposed method by predicting the PPIs of “S. Cerevisiae” where the protein features extracted using the multiscale local descriptor (MLD), and then we compare the predictive performance of the proposed low-rank approximation with the existing methods. Finally, the new method results in significant reduction in computational time for predicting PPIs with almost as accuracy as kernel-based SVM.

Abstract Background Sleep disorders, which are among the foremost important medical care issues, are prevalent in pregnancy. The present study is a meta-analysis of the prevalence of insomnia in the third trimester of pregnancy. This study aims to systematically review the overall prevalence of insomnia in the third trimester of pregnancy through conducting a meta-analysis. Method The literature used in this meta-analysis for the topic discussed above were obtained through searching several databases, including SID, MagIran, IranDoc, Scopus, Embase, Web of Science (WoS), PubMed Science Direct and Google Scholar databases without time limitation until December 2020. Articles developed based on cross-sectional studies were included in the study. The heterogeneity of studies was investigated using the I2 index. Also, the possible effects of heterogeneity in the studied studies are investigated using meta-regression analysis. Result In 10 articles and 8798 participants aged between11–40, the overall prevalence of insomnia in the third trimester of pregnancy based on meta-analysis was 42.4% (95% CI: 32.9–52.5%). It was reported that as the sample size increases, the prevalence of insomnia in the third trimester of pregnancy increases. Conversely, as the year of research increases, the prevalence of insomnia in the third trimester of pregnancy decreases. Both of these differences were statistically significant (P

Abstract Background Stress, anxiety, and depression are some of the most important research and practice challenges for psychologists, psychiatrists, and behavioral scientists. Due to the importance of issue and the lack of general statistics on these disorders among the Hospital staff treating the COVID-19 patients, this study aims to systematically review and determine the prevalence of stress, anxiety and depression within front-line healthcare workers caring for COVID-19 patients. Methods In this research work, the systematic review, meta-analysis and meta-regression approaches are used to approximate the prevalence of stress, anxiety and depression within front-line healthcare workers caring for COVID-19 patients. The keywords of prevalence, anxiety, stress, depression, psychopathy, mental illness, mental disorder, doctor, physician, nurse, hospital staff, 2019-nCoV, COVID-19, SARS-CoV-2 and Coronaviruses were used for searching the SID, MagIran, IranMedex, IranDoc, ScienceDirect, Embase, Scopus, PubMed, Web of Science (ISI) and Google Scholar databases. The search process was conducted in December 2019 to June 2020. In order to amalgamate and analyze the reported results within the collected studies, the random effects model is used. The heterogeneity of the studies is assessed using the I 2 index. Lastly, the data analysis is performed within the Comprehensive Meta-Analysis software. Results Of the 29 studies with a total sample size of 22,380, 21 papers have reported the prevalence of depression, 23 have reported the prevalence of anxiety, and 9 studies have reported the prevalence of stress. The prevalence of depression is 24.3% (18% CI 18.2–31.6%), the prevalence of anxiety is 25.8% (95% CI 20.5–31.9%), and the prevalence of stress is 45% (95% CI 24.3–67.5%) among the hospitals’ Hospital staff caring for the COVID-19 patients. According to the results of meta-regression analysis, with increasing the sample size, the prevalence of depression and anxiety decreased, and this was statistically significant (P

Abstract Background Cardiovascular disease is the cause of more than 50% of mortalities globally, and this rate has grown by 8.6% since the 60 s. One of the risk factors associated with cardiovascular disease and its resulting mortality rate is the metabolic syndrome. Different studies have reported inconsistent rates for the metabolic syndrome. However, no comprehensive study has been conducted to combine the results of existing studies. Thus, the present study was performed with the aim of determining the prevalence of metabolic syndrome among cardiovascular patients in Iran through a systematic review and meta-analysis. Method : In this review study, the Scientific Information Database, Google Scholar, Science Direct, Scopus, PubMed, and Web of Science (ISI), databases were searched from January 2005 and until May 2020, to identify and extract related articles. To conduct the analysis, a random effects model was used, and the heterogeneity of the studies was examined using the I2 index. Data analysis was performed within Comprehensive Meta-Analysis (version 2) software. Results The prevalence of metabolic syndrome in cardiovascular patients in Iran in the 27 papers examined with a sample size of 44,735 patients was 34.2% (95% CI: 26.8–42.6%). A sensitivity analysis was performed to ensure the stability of the results, these results show that by omitting the prevalence from each study, the overall prevalence (34.2%) does not change significantly. the highest prevalence of metabolic syndrome in studies conducted in the period between 2015 and 2020, and this was reported as 55.3 (95% CI: 47.9–62.3) and the highest prevalence of metabolic syndrome in studies conducted in the methods of diagnosis IDF, and the rate was reported as 48 (95% CI: 36.5–59.8). based on meta-regression as the year of research increased, the prevalence of metabolic syndrome in cardiovascular patients in Iran also increased. However, with the increase in sample size, this prevalence decreased (p

Abstract Background Physical activity and exercise are among the most important, simplest, and cheapest approaches to anxiety treatment, especially for the elderly. Their positive effects on improvement of mental disorders in the elderly have attracted a considerable level of attention. Therefore, the present study was conducted to determine the effect of sport on reducing anxiety in the elderly using meta-analysis. Methods In this study, national and international databases of SID, MagIran, IranMedex, IranDoc, Cochrane, Embase, ScienceDirect, Scopus, PubMed, and Web of Science were searched to find studies published electronically from 1999 to 2019. Heterogeneity between the collected studies was determined using the Cochran's test (Q) and I2. Due to presence of heterogeneity, the random effects model was used to estimate the standardized mean difference of sport test scores obtained from the measurement of anxiety reduction among the elderly, between the intervention group before and after the test. Results In this meta-analysis and systematic review, 19 papers finally met the inclusion criteria. The overall sample size of all collected studies for the meta-analysis was 841 s. Mean anxiety score before and after intervention were 38.7 ± 5.6 33.7 ± 3.4 respectively, denoting a decrease in anxiety score after intervention. Conclusion Results of this study indicates that Sport significantly reduces Anxiety in the Elderly. Therefore, a regular exercise program can be considered as a part of the elderly care program.

Abstract Background The Dupuytren disease is a benign fibroproliferative disorder that leads to the formation of the collagen knots and fibres in the palmar fascia. The previous studies reveal different levels of Dupuytren’s prevalence worldwide; hence, this study uses meta-analysis to approximate the prevalence of Dupuytren globally. Methods In this study, systematic review and meta-analysis have been conducted on the previous studies focused on the prevalence of the Dupuytren disease. The search keywords were Prevalence, Prevalent, Epidemiology, Dupuytren Contracture, Dupuytren and Incidence. Subsequently, SID, MagIran, ScienceDirect, Embase, Scopus, PubMed and Web of Science databases and Google Scholar search engine were searched without a lower time limit and until June 2020. In order to analyse reliable studies, the stochastic effects model was used and the I 2 index was applied to test the heterogeneity of the selected studies. Data analysis was performed within the Comprehensive Meta-Analysis Software version 2.0. Results By evaluating 85 studies (10 in Asia, 56 in Europe, 2 in Africa and 17 studies in America) with a total sample size of 6628506 individuals, the prevalence of Dupuytren disease in the world is found as 8.2% (95% CI 5.7–11.7%). The highest prevalence rate is reported in Africa with 17.2% (95% CI 13–22.3%). According to the subgroup analysis, in terms of underlying diseases, the highest prevalence was obtained in patients with type 1 diabetes with 34.1% (95% CI 25–44.6%). The results of meta-regression revealed a decreasing trend in the prevalence of Dupuytren disease by increasing the sample size and the research year (P < 0.05). Conclusion The results of this study show that the prevalence of Dupuytren disease is particularly higher in alcoholic patients with diabetes. Therefore, the officials of the World Health Organization should design measures for the prevention and treatment of this disease.

This study presents a novel approach for real-time flood control by optimizing operation of a reservoir during the flood. However, the fundamental operational challenge of using this method is to determine optimized decisions of the reservoir management before the occurrence of flood, and optimal use of the pre-release to reduce the flood damages. In addition to this optimization challenge, since the timely forecasts are derived by employing the probabilistic methods, they would always associate with uncertainty. As a result, quantifying and considering these uncertainties in the flood control would result in reducing the risk of flood damage that can be evaluated by minimizing the expected value of the damage. Timely and continuous forecasting of inflow and reservoir operation management will be implemented before the occurrence of flood until it ends. In order to address the above challenges, a novel simulation-optimization methodology, by taking into account uncertainty, is developed; and illustrated on a case study of Dez reservoir, as a highly important reservoir system in south-west of Iran, to optimize the performance of this reservoir, during the floods. Accordingly, a new water resource management has been proposed and tested. The results derived from the proposed method, indicate a significant reduction in the peak release from the reservoir and the improved operation of the Dez reservoir in controlling the flood at real-time, which will reduce damages in the downstream area.

Abstract Background In all epidemics, healthcare staff are at the centre of risks and damages caused by pathogens. Today, nurses and physicians are faced with unprecedented work pressures in the face of the COVID-19 pandemic, resulting in several psychological disorders such as stress, anxiety and sleep disturbances. The aim of this study is to investigate the prevalence of sleep disturbances in hospital nurses and physicians facing the COVID-19 patients. Method A systematic review and metanalysis was conducted in accordance with the PRISMA criteria. The PubMed, Scopus, Science direct, Web of science, CINHAL, Medline, and Google Scholar databases were searched with no lower time-limt and until 24 June 2020. The heterogeneity of the studies was measured using I2 test and the publication bias was assessed by the Egger’s test at the significance level of 0.05. Results The I2 test was used to evaluate the heterogeneity of the selected studies, based on the results of I2 test, the prevalence of sleep disturbances in nurses and physicians is I2: 97.4% and I2: 97.3% respectively. After following the systematic review processes, 7 cross-sectional studies were selected for meta-analysis. Six studies with the sample size of 3745 nurses were examined in and the prevalence of sleep disturbances was approximated to be 34.8% (95% CI: 24.8-46.4%). The prevalence of sleep disturbances in physicians was also measured in 5 studies with the sample size of 2123 physicians. According to the results, the prevalence of sleep disturbances in physicians caring for the COVID-19 patients was reported to be 41.6% (95% CI: 27.7-57%). Conclusion Healthcare workers, as the front line of the fight against COVID-19, are more vulnerable to the harmful effects of this disease than other groups in society. Increasing workplace stress increases sleep disturbances in the medical staff, especially nurses and physicians. In other words, increased stress due to the exposure to COVID-19 increases the prevalence of sleep disturbances in nurses and physicians. Therefore, it is important for health policymakers to provide solutions and interventions to reduce the workplace stress and pressures on medical staff.

Abstract Background Curcumin is herbal compound that has been shown to have anti-cancer effects in pre-clinical and clinical studies. The anti-cancer effects of curcumin include inhibiting the carcinogenesis, inhibiting angiogenesis, and inhibiting tumour growth. This study aims to determine the Clinical effects of curcumin in different types of cancers using systematic review approach. Methods A systematic review methodology is adopted for undertaking detailed analysis of the effects of curcumin in cancer therapy. The results presented in this paper is an outcome of extracting the findings of the studies selected from the articles published in international databases including SID, MagIran, IranMedex, IranDoc, Google Scholar, ScienceDirect, Scopus, PubMed and Web of Science (ISI). These databases were thoroughly searched, and the relevant publications were selected based on the plausible keywords, in accordance with the study aims, as follows: prevalence, curcumin, clinical features, cancer. Results The results are derived based on several clinical studies on curcumin consumption with chemotherapy drugs, highlighting that curcumin increases the effectiveness of chemotherapy and radiotherapy which results in improving patient’s survival time, and increasing the expression of anti-metastatic proteins along with reducing their side effects. Conclusion The comprehensive systematic review presented in this paper confirms that curcumin reduces the side effects of chemotherapy or radiotherapy, resulting in improving patients’ quality of life. A number of studies reported that, curcumin has increased patient survival time and decreased tumor markers’ level.

Abstract Background RLS is known as one of the most common movement disorders during pregnancy, which is most aggravated in the third trimester of pregnancy and can affect up to one-third of pregnant women. This study intends to determine the total prevalence of RLS in the third trimester of pregnancy through a systematic review. Methods The present study was conducted via meta-analysis method up to 2019. The papers related to the subject of interest were obtained through searching in SID, MagIran, IranDoc, Scopus, Embase, Web of Science (ISI), PubMed, Science Direct, and Google Scholar databases. Heterogeneity of the studies was examined via I2 index, and the data were analyzed in Comprehensive meta-analysis software. Results In investigating 10 papers capturing 2431 subjects within the age range of 25–39 years, the total prevalence of RLS in the third trimester of pregnancy based on meta-analysis was obtained as 22.9% (95% CI: 14.7–33.8%). Further, as the sample size increased, the RLS prevalence diminished, while with increase in years, this prevalence increased, where this difference was statistically significant (P

Abstract Background Despite many benefits of the physical activity on physical and mental health of patients with Multiple Sclerosis (MS), the activity level in these patients is still very limited, and they continue to suffer from impairment in functioning ability. The main aim of this study is thus to closely examine exercise’s effect on fatigue of patients with MS worldwide, with particular interest on Iran based on a comprehensive systematic review and meta-analysis. Methods The studies used in this systematic review were selected from the articles published from 1996 to 2019, in national and international databases including SID, Magiran, Iranmedex, Irandoc, Google Scholar, Cochrane, Embase, ScienceDirect, Scopus, PubMed and Web of Science (ISI). These databases were thoroughly searched, and the relevant ones were selected based on some plausible keywords to the aim of this study. Heterogeneity index between studies was determined using Cochran’s test and I2. Due to heterogeneity in studies, the random effects model was used to estimate standardized mean difference. Results From the systematic review, a meta-analysis was performed on 31 articles which were fulfilled the inclusion criteria. The sample including of 714 subjects was selected from the intervention group, and almost the same sample size of 720 individuals were selected in the control group. Based on the results derived from this meta-analysis, the standardized mean difference between the intervention group before and after the intervention was respectively estimated to be 23.8 ± 6.2 and 16.9 ± 3.2, which indicates that the physical exercise reduces fatigue in patients with MS. Conclusion The results of this study extracted from a detailed meta-analysis reveal and confirm that physical exercise significantly reduces fatigue in patients with MS. As a results, a regular exercise program is strongly recommended to be part of a rehabilitation program for these patients.

Abstract Background Depression is one of the most common psychiatric disorders in the older adult and one of the most common risk factors for suicide in the older adult. Studies show different and inconsistent prevalence rates in Iran. This study aims to determine the prevalence of severe depression in Iranian older adult through a meta-analysis approach. Methods The present meta-analysis was conducted between January 2000–August 2019. Articles related to the subject matter were obtained by searching Scopus, Sciencedirect, SID, magiran, Barakat Knowledge Network System, Medline (PubMed), and Google Scholar databases. The heterogeneity of the studies was evaluated using I2 index and the data were analyzed in Comprehensive Meta-Analysis software. Results In a study of 3948 individuals aged 50–90 years, the overall prevalence of severe depression in Iranian older adult was 8.2% (95% CI, 4.14–6.3%) based on meta-analysis. Also, in order to investigate the effects of potential factors (sample size and year of study) on the heterogeneity of severe depression in Iranian older adult, meta-regression was used. It was reported that the prevalence of severe depression in Iranian older adult decreased with increasing sample size and increasing years of the study, which is significantly different (P

Due to the dynamic nature of the food supply chain system, food supply management could suffer because of, and be interrupted by, unforeseen events. Considering the perishable nature of fresh food products and their short life cycle, fresh food companies feel immense pressure to adopt an efficient and proactive risk management system. The risk management aspects within the food supply chains have been addressed in several studies. However, only a few studies focus on the complex interactions between the various types of risks impacting food supply chain functionality and dynamic feedback effects, which can generate a reliable risk management system. This paper strives to contribute to this evident research gap by adopting a system dynamics modelling approach to generate a systemic risk management model. The system dynamics model serves as the basis for the simulation of risk index values and can be explored in future work to further analyse the dynamic risk’s effect on the food supply chain system’s behaviour. According to a literature review of published research from 2017 to 2021, nine different risks across the food supply chain were identified as a subsection of the major risk categories: macro-level and operational risks. Following this stage, two of the risk groups identified first were integrated with a developed system dynamics model to conduct this research and to evaluate the interaction between the risks and the functionality of the three main dairy supply chain processes: production, logistics, and retailing. The key findings drawn from this paper can be beneficial for enhancing managerial discernment regarding the critical role of system dynamics models for analysing various types of risks across the food supply chain process and improving its efficiency.

Background. Senescence refers to spontaneous and progressive irreversible degenerative changes in which both the physical and psychological power diminish significantly. Hypertension is the most common cardiovascular disease in the elderly. Several studies have been conducted regarding the effect of exercise on reducing the blood pressure of the elderly, which have found contradictory results. One of the uses of meta-analysis study is responding to these assumptions and resolving the discrepancies. Accordingly, the aim of the present study is to determine the impact of exercise on the blood pressure of older adults. Method. In this research, in order to find electronic published papers from 1992 to 2019, the papers published in both domestic and foreign databases including SID, MagIran, IranMedex, IranDox, Gogole Scholar, Cohrane, Embase, Science Direct, Scopus, PubMed, and Web of Science (ISI) were used. Heterogeneity index between the studies was determined based on Cochran test Q(c) and I2. Considering existence of heterogeneity, random effects model was employed to estimate the standardized subtraction of the mean exercise test score for reduction of blood pressure in the older adults across the intervention group before and after the test. Results. In this meta-analysis and systematic review, eventually 69 papers met the inclusion criteria. The total number of participants was 2272 in the pre- and postintervention groups when examining the systolic changes and 2252 subjects in the pre- and postintervention groups when inspecting the diastolic changes. The standardized mean difference in examining the systolic changes before the intervention was 137.1 ± 8.09 and 132.98 ± 0.96 after the intervention; when exploring the diastolic changes, the pre- and postintervention values were 80.3 ± 0.85 and 76.0 ± 6.56, respectively, where these differences were statistically significant (P

The safety of vulnerable road users is of paramount importance as transport moves towards fully automated driving. The richness of real-world data required for testing autonomous vehicles is limited and furthermore, available data do not present a fair representation of different scenarios and rare events. Before deploying autonomous vehicles publicly, their abilities must reach a safety threshold, not least with regards to vulnerable road users, such as pedestrians. In this paper, we present a novel Generative Adversarial Networks named the Ped-Cross GAN. Ped-Cross GAN is able to generate crossing sequences of pedestrians in the form of human pose sequences. The Ped-Cross GAN is trained with the Pedestrian Scenario dataset. The novel Pedestrian Scenario dataset, derived from existing datasets, enables training on richer pedestrian scenarios. We demonstrate an example of its use through training and testing the Ped-Cross GAN. The results show that the Ped-Cross GAN is able to generate new crossing scenarios that are of the same distribution from those contained in the Pedestrian Scenario dataset. Having a method with these capabilities is important for the future of transport, as it will allow for the adequate testing of Connected and Autonomous Vehicles on how they correctly perceive the intention of pedestrians crossing the street, ultimately leading to fewer pedestrian casualties on our roads.

Assuring the safety of automated vehicles is essential for their timely introduction and acceptance by policymakers and the public. To assess their safe design and robust decision making in response to all possible scenarios, new methods that use a scenario-based testing approach are needed, as testing on public roads in normal traffic would require driving millions of kilometres. We make use of the scenario-based testing approach and propose a method to model simulated scenarios using Gaussian Process based models to predict untested scenario outcomes. This enables us to efficiently determine the performance boundary, where the safe and unsafe scenarios can be evidently distinguished from each other. We present an iterative method that optimises the parameter space of a logical scenario towards the most critical scenarios on this performance boundary. Additionally, we conduct a novel probabilistic sensitivity analysis by efficiently computing several variance-based sensitivity indices using the Gaussian Process models and evaluate the relative importance of the scenario input parameters on the scenario outcome. We critically evaluate and investigate the usefulness of the proposed Gaussian Process based approach as a very efficient surrogate model, which can model the logical scenarios effectively in the presence of uncertainty. The proposed approach is applied on an exemplary logical scenario and shows viability in finding concrete critical scenarios. The reported results, derived from the proposed approach, could pave the way to more efficient testing of automated vehicles and instruct further physical tests on the determined critical scenarios.