clustering

This study aims to improve the accuracy and reliability of migraine detection by combining the localized component filtering (LCF) method with the electroencephalographic (EEG) spectral asymmetry index (SASI) method. The integration of LCF and SASI in the frequency domain under 3 Hz photic stimulation offers a novel approach for robust classification. EEG recordings from 13 control subjects and 15 migraineurs were used in this study. The SASI values, obtained from LCF pre-processed signals, served as features for classification. The K-means clustering algorithm was applied, and the accuracy was evaluated using the silhouette values method. The combination of the LCF method with the SASI technique resulted in a 17% improvement in clustering accuracy, achieving an overall accuracy of around 87%. This new approach outperformed the histogram K-means clustering method and the SASI technique used alone. The accuracy attained by this combined approach was as high as multi-layer perceptron (MLP) and superior to K-means clustering, which are two well-known approaches of artificial and machine learning (ML) clustering methods, respectively. This study presents a novel and effective approach by combining LCF and SASI for migraine detection, which enhances classification accuracy and provides valuable insights into migraine-related brain activity. Accurate and reliable detection of migraine can lead to more effective treatment and management of the condition, ultimately improving the quality of life for migraine sufferers.

The incidence of hyperlipidemia in Iran is on a consistent rise, potentially contributing significantly to increased susceptibility to cardiovascular diseases and other health complications linked to elevated blood lipid levels. This study employs hierarchical Bayesian model to assess the heightened lipid risk on a broader scale across Iran's provinces. Thise model play a pivotal role in spatial modeling, adeptly handling uncertainties arising from diverse spatial data sources.

This study included individuals diagnosed with hyperlipidemia from all provinces of Iran in 2019. The primary focus of the investigation included essential variables such as the mean age, gender distribution, and the documented incidence of hyperlipidemia cases in each province. Population data, stratified by province, age group, and gender, were sourced from the Iranian Statistics Center database. Utilizing a direct approach, disease prevalence and expected case numbers were calculated. The analysis employed the Besag-York-Mollié (BYM) model, with parameter estimation executed through the Hamiltonian Monte Carlo method.

In this investigation, the prevalence and spatial distribution of hyperlipidemia were explored within a diverse population of 1,609,538 patients across various regions in Iran. The relative risk of hyperlipidemia surpassed 1 in 16% of Iranian provinces (posterior probability > 0.8), with a calculated 95% confidence interval of 0.304 to 0.879. The overall prevalence of hyperlipidemia was determined to be 0.815. Significant heterogeneity in hyperlipidemia was identified among different provinces, with Tehran exhibiting the highest relative risk (RR=1.701; 95% CrI: 1.69, 1.713). Notably, gender (RR=1.008; CI: 1.007, 1.009 for males and RR=1.005; CI: 1.003, 1.007 for females) and age were not found to have a statistically significant effect on the relative risk of the disease.

In conclusion, this investigation employed hierarchical Bayesian models to evaluate the prevalence and spatial distribution of hyperlipidemia across the provinces of Iran. The analysis unveiled a significant escalation in the relative risk of hyperlipidemia in 16% of Iranian provinces, underscoring the spatial heterogeneity in disease prevalence. This study contributes invaluable insights into the spatial dynamics of hyperlipidemia in Iran, establishing a groundwork for the formulation of targeted public health strategies.

Hypertension, a severe chronic disease and a primary risk factor for cardiovascular issues, poses significant challenges in treatment and decision-making for physicians. Recommender systems present a promising avenue for enhancing hypertension care decision-making processes. However, traditional approaches such as collaborative filtering encounter challenges like data sparsity and scalability. To address these challenges, machine learning based recommender systems have been explored. This study presents an enhanced collaborative filtering method, integrating clustering and group recommendation techniques. The proposed research aggregates group recommendations for each cluster using static and dynamic methods. For new patients, three similarity measures are employed to select relevant recommendations from the most similar case cluster. The findings demonstrate the model's satisfactory performance, particularly when employing dynamic group recommendation and Euclidean similarity, showcasing improved accuracy in terms of Mean Absolute Error (MAE).

In the last few decades, in many research fields, different methods were introduced to discover groups with the same trends in longitudinal data. The clustering process is an unsupervised learning method, which classifies longitudinal data based on different criteria by performing algorithms. The current study was performed with the aim of reviewing various methods of longitudinal data clustering, including two general categories of non-parametric methods and model-based methods. PubMed, SCOPUS, ISI, Ovid, and Google Scholar were searched between 2000 and 2021. According to our systematic review, the non-parametric k-means Clustering Method utilizing Euclidean distance emerges as a leading approach for clustering longitudinal data This research, with an overview of the studies done in the field of clustering, can help researchers as a toolbox to choose various methods of longitudinal data clustering in idea generation and choosing the appropriate method in the classification and analysis of longitudinal data.

Identifying different groups of customers and their preferences and needs enable countries to gain a competitive advantage in the medical tourism market. We aimed to segment medical tourists from West Asian countries seeking medical services in Iran.

This cross-sectional study was conducted on 596 medical tourists who sought medical services in Iran in 2021. Data were collected using a valid questionnaire. Segmentation was performed based on medical tourism attributes (medical, destination, and tourism attributes), using cluster analysis methods; wards, and K means. The segments ' evaluation and profiling were conducted using discriminant analysis, chi-square, and one-way ANOVA tests.

Our study divided the market into five segments: health seekers (3.8%), health and destination seekers (8.9%), tourism seekers (17.8%), infrastructure seekers (10.23%), and perfectionism (59.45%). In all segments, the health attributes were of high importance. The perfectionism segment registered the highest score in all three attributes (more than 5 of 6).

Improving health attributes and offering luxurious medical services can be the main strategy for Iran to attract the most medical tourists and achieve a good position in this marketplace. The implication of this study is policymaking for targeting the most profitable segment of this marketplace.

 The results from the analysis of COVID-19 literature by employing text-mining techniques are of particular importance for researchers, policymakers, and planners of medical sciences at the national and international levels, avoiding parallel research and waste of time and budget. The paper explore emerging topics and the trend of scientific words at the national and international levels in the subject area of COVID-19.

 This applied research was conducted by employing the text-mining and its related algorithms and classifying texts. The population consists of all COVID-19 articles indexed in PubMed Central® (PMC). The number of records retrieved was 160,862 items until June 10, 2021. Among these, 3143 national and 157,719 international COVID-19 articles. Python and its related libraries were applied. The most significant words were also identified and reported based on TF-IDF weighting. Emerging topics were identified according to the weighted average growth.

"COVID", "infect", and "cell" were among the most important words used in international COVID-19 articles. In addition, the most important words in the national COVID-19 articles were "patient", "SARS-Cov", and "COVID".

 Among the most important conclusions that can be inferred from the trend of word change used in the COVID-19 literature is that the most significant words in international literature differ significantly from those in national literature, as international research focuses on COVID-19 and the infections caused by it. In contrast, national research focuses on COVID-19 and patients. Another significant result is the annual word-changing national and international literature.

This study aimed to detect gene signatures in RNA-sequencing (RNA-seq) data using Pareto-optimal cluster size identification.

RNA-seq has emerged as an important technology for transcriptome profiling in recent years. Gene expression signatures involving tens of genes have been proven to be predictive of disease type and patient response to treatment.

Data related to the liver cancer RNA-seq dataset, which included 35 paired hepatocellular carcinoma (HCC) and non-tumor tissue samples, was used in this study. The differentially expressed genes (DEGs) were identified after performing pre-filtering and normalization. After that, a multi-objective optimization technique, namely multi-objective optimization for collecting cluster alternatives (MOCCA), was used to discover the Pareto-optimal cluster size for these DEGs. Then, the k-means clustering method was performed on the RNA-seq data. The best cluster, as a signature for the disease, was found by calculating the average Spearman's correlation score of all genes in the module in a pair-wise manner. All analyses were performed in the R 4.1.1 package in virtual space with 100 Gb of RAM memory.

Using MOCCA, eight Pareto-optimal clusters were obtained. Ultimately, two clusters with the greatest average Spearman's correlation coefficient scores were chosen as gene signatures. Eleven prognosticgenes involved in HCC's abnormal metabolism were identified. In addition, three differentially expressed pathways were identified between tumor and non-tumor tissues.

These identified metabolic prognostic genes help us to provide more powerfulprognostic information and enhance survival prediction for HCC patients. In addition, Pareto-optimal cluster size identification is suggested for gene signature in other RNA-Seq data.

Depression is a prevalent illness in the world. Given the importance of mental disorders, many researchers have investigated the effects of different variables on average depression scores. In this study, we decided to investigate the effect of some explanatory variables on the average depression score.

The data were obtained from the second phase of the cohort of the Kerman Coronary Artery Diseases Risk Factors study (KERCADRS), which was performed in 2014-2018. We used the cluster-wise linear regression model to find more accurate relationships between depression scores and predictor variables.

The total number of the subjects in this study was 9811, out of whom 2144 were allocated to cluster 1, 4540 to cluster 2, and 3127 to cluster 3. The average depression score was 13.76 7.6 in cluster 1, 4.39 4.7 in cluster 2, and 10.83 6.7 in cluster 3. However, the average depression score for all the data was 8.5 7.2. In all the clusters, the average depression score of females was significantly greater than that of men (p-value<0.0001). In cluster 1, the age category of 35-54, in cluster 2, the age category of 55-80, and in cluster 3, the age category of 15-34 had a maximum average depression score.

we can name the three clusters to low ( cluster 2), medium ( cluster 3 ), and high (cluster 1) depression score with respect to age group with the maximum ADS in each cluster. that they are 55-80 years old, 15-34 years old and 35-54 years old in cluster 2 ( low), cluster 3 ( medium) and cluster 1( high) respectively.

Social media platforms such as Facebook, WhatsApp, and Instagram etc., are becoming very popular now not only for youth but for all walks of life. People are more often seen in busy in tweeting, chatting, or putting selfies. No one actually knows the mental state of a person in the online platform. In this article, we will be focusing on how social media is affecting issues such as road accident, murder, and suicide. The research is done by three parts.

Google Form analysis, machine learning used for prediction, and by sentimental analysis of what people think in twitter. All the datasets are based in India. From these datasets, the different machine learning algorithm is used to do the analysis. The project strives to bring the real‑world solution in the matter of advancement.

The static data analysis and dynamic data analysis shows the various sentimental analysis and predictions and the technique to predict different mental states. Thus we get clearly about the current world is getting into social issues. This research findings helps to bring social awareness among the current generation by understanding the sensitivity of the youths.

Thus through this paper we get known clearly how the current world is getting into social issues like victim of murders or road accidents or committing suicide. The paper clearly helps us to understand the sensitivity of the youths. Therefore brings a social awareness among the current generation.

Because milk and milk products play a vital role in human nutrition, dairy cattle farmers are working in increasing milk production or changing its composition. For this reason, researching the genes which play an important role in milk production and its composition is of high value. Information theory is an interdisciplinary branch of mathematics which overlaps with communications engineering, biology, and medicine. It has been used in genetic and bioinformatics analyses such as the biological structures and sequences.

In this study, a total of 20 microRNAs from those affecting the breast tissue and mammary glands have been extracted from the microRNA database. For each microRNA sequence, the entropy values of the first- to third-order were calculated and the Kullback-Leibler divergence criteria were estimated. Then, the Kullback-Leibler divergence matrix of the microRNAs was considered as the inputs for clustering methods. All calculations were performed in the R program. The biological pathway of each target was predicted using the KEGG server.

MicroRNAs are divided into two main groups based upon comparing and analyzing all the created clusters. The first group contains 18 microRNA and the second group contains 2 microRNAs at the first- and third-order entropies. The second-order entropy contains 19 microRNA in the first group and only 1 microRNA in the second group. The clustering topology changes as the entropy order changes from 1 to 3, with the most significant changes being seen in the clustering resulted from the third-order entropy.

In the proposed method of clustering, we obtained a biological grouping of genes. There is a good concordance between most of the microRNAs within one cluster and their biological pathway.  The algorithm is applicable for clustering a range of genes and even genomes based on their DNA sequences entropy. Our method can help assign and predict the biological activity of those genes that lack robust annotations because it relies only on the DNA sequence and length of the genes.

This study examined the effect of bilingualism on the processing of clustering and switching in verbal fluency tasks in Farsi-Balochi bilinguals.

Ninety participants entered this study, including 45 Farsi monolinguals and 45 Farsi-Balochi bilinguals. All participants were male university students between the ages of 18 to 24 years. Verbal fluency tests were performed and the clustering and switching scores were calculated. Data was analyzed in SPSS-16 software.

The monolingual group obtained a score of 32.84 in the total semantic fluency task and 24.13 in the phonemic fluency task, while the bilingual group obtained 30.70 in the semantic task and 29.37 in the phonemic task. The number of switches between the clusters and the mean cluster size were 35.82 and 2.6 in the monolingual group and 38.65 and 2.26 in the bilingual group, respectively. The difference between groups in phonemic fluency, phonemic switching, and semantic clustering was significant (p˂0.05).

The bilingual group performed better in phonemic fluency and switched more between the clusters. Meanwhile, the monolinguals produced more words in each cluster than the bilinguals.

(i) Cluster analysis and partitioning samples based on cardio-cerebrovascular histories and length of stay (LOS); (ii) Determining related demographic and medical factors in individual clusters; and (iii) Comparing clusters based on 12-month health outcomes.

The statistical population of the study included 2,293 stroke patients hospitalized in Imam Reza hospital of Kermanshah city from January 1, 2015, to December 31, 2016. After a one-year follow-up, the data collection window was closed on December 31, 2017. The patients’ data were extracted from the electronic hospital information system (HIS). Two-step cluster analysis (TSCA), chi-square, Fisher exact, Kruskal-Wallis, and Mann-Whitney U tests, as well as multinomial logistic regression analysis were the analysis methods.

This model suggested five distinct clusters: the patients (i) without any cardio-cerebrovascular history and LOS = 5 days (36.2%); (ii) without any cardio-cerebrovascular history and LOS = 6 days (21.6%); (iii) with cerebrovascular history and LOS = 6 days (18.6%); (iv) with cardiovascular history and LOS = 6 days (16.1%); and (v) with cardio-cerebrovascular history and LOS = 6 days (7.5%). Hypertension, diabetes, and smoking were respectively the most significant modifiable risk factors, while sex, cerebrovascular diseases in the family, and age were respectively the most significant non-modifiable risk factors in high-risk clusters and LOS = 6 days. Compared to Cluster 1 (reference), during a one-year follow-up, a larger number of members in Clusters 3 and 5 were readmitted and/or expired.

Considering the modifiable risk factors identified in the current study, providing programs for preventing readmission and potential death caused by stroke for Clusters 3 and 5 seems essential