Investigating response behavior through TF-IDF and Word2vec text analysis: A case study of PISA 2012 problem-solving process data.

The process data in computer-based problem-solving evaluation is rich in valuable implicit information. However, its diverse and irregular structure poses challenges for effective feature extraction, leading to varying degrees of information loss in existing methods. Process-response behavior exhibits similarities to textual data in terms of the key units and contextual relationships. Despite the scarcity of relevant research, exploring text analysis methods for feature recognition in process data is significant. This study investigated the efficacy of Term Frequency-Inverse Document Frequency (TF-IDF) and Word to Vector (Word2vec) in extracting response behavior features and compared the predictive, analytical, and clustering effects of classical machine learning methods (supervised and unsupervised) on response behavior. An analysis of the PISA 2012 computer-based problem-solving dataset revealed that TF-IDF effectively extracted key response behaviors, whereas Word2vec captured effective features from sequenced response behaviors. In addition, in supervised machine learning using both methods, the random forest model based on TF-IDF performed the best, followed by the SVM model based on Word2vec. Word2vec-based models outperformed TF-IDF-based ones in the F1-score, accuracy, and recall (except for precision) across the logistic regression, k-nearest neighbor, and support vector machine algorithms. In unsupervised machine learning, the k-means algorithm effectively clustered different response behavior patterns extracted by these methods. The findings underscore the theoretical and methodological transferability of these text analysis methods in educational and psychological assessment contexts. This study offers valuable insights for research and practice in similar domains by yielding rich feature representations, supplementing fine-grained assessment evidence, fostering personalized learning, and introducing novel insights for educational assessment.

Traditional Machine Learning, Deep Learning, and BERT (Large Language Model) Approaches for Predicting Hospitalizations From Nurse Triage Notes: Comparative Evaluation of Resource Management.

BACKGROUND: Predicting hospitalization from nurse triage notes has the potential to augment care. However, there needs to be careful considerations for which models to choose for this goal. Specifically, health systems will have varying degrees of computational infrastructure available and budget constraints. OBJECTIVE: To this end, we compared the performance of the deep learning, Bidirectional Encoder Representations from Transformers (BERT)-based model, Bio-Clinical-BERT, with a bag-of-words (BOW) logistic regression (LR) model incorporating term frequency-inverse document frequency (TF-IDF). These choices represent different levels of computational requirements. METHODS: A retrospective analysis was conducted using data from 1,391,988 patients who visited emergency departments in the Mount Sinai Health System spanning from 2017 to 2022. The models were trained on 4 hospitals' data and externally validated on a fifth hospital's data. RESULTS: The Bio-Clinical-BERT model achieved higher areas under the receiver operating characteristic curve (0.82, 0.84, and 0.85) compared to the BOW-LR-TF-IDF model (0.81, 0.83, and 0.84) across training sets of 10,000; 100,000; and ~1,000,000 patients, respectively. Notably, both models proved effective at using triage notes for prediction, despite the modest performance gap. CONCLUSIONS: Our findings suggest that simpler machine learning models such as BOW-LR-TF-IDF could serve adequately in resource-limited settings. Given the potential implications for patient care and hospital resource management, further exploration of alternative models and techniques is warranted to enhance predictive performance in this critical domain. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1101/2023.08.07.23293699.

A novel optimization-assisted multi-scale and dilated adaptive hybrid deep learning network with feature fusion for event detection from social media.

Social media networks become an active communication medium for connecting people and delivering new messages. Social media can perform as the primary channel, where the globalized events or instances can be explored. Earlier models are facing the pitfall of noticing the temporal and spatial resolution for enhancing the efficacy. Therefore, in this proposed model, a new event detection approach from social media data is presented. Firstly, the essential data is collected and undergone for pre-processing stage. Further, the Bidirectional Encoder Representations from Transformers (BERT) and Term Frequency Inverse Document Frequency (TF-IDF) are employed for extracting features. Subsequently, the two resultant features are given to the multi-scale and dilated layer present in the detection network of GRU and Res-Bi-LSTM, named as Multi-scale and Dilated Adaptive Hybrid Deep Learning (MDA-HDL) for event detection. Moreover, the MDA-HDL network's parameters are tuned by Improved Gannet Optimization Algorithm (IGOA) to enhance the performance. Finally, the execution of the system is done over the Python platform, where the system is validated and compared with baseline methodologies. The accuracy findings of model acquire as 94.96 for dataset 1 and 96.42 for dataset 2. Hence, the recommended model outperforms with the superior results while detecting the social events.

Risk Stratification, Intention to Fast, and Outcomes of Fasting During Ramadan in People With Diabetes Presenting to a Tertiary Care Hospital.

OBJECTIVE: The objectives of this study were to evaluate the stratification of people with diabetes mellitus (DM) based on the International Diabetes Federation-Diabetes and Ramadan 2021 risk calculator into different risk categories and assess their intentions to fast and outcomes of fasting during the holy month of Ramadan. METHODS: This was a 3-month prospective study that was performed from February 9, 2023, to May 6, 2023 (6 weeks before Ramadan until 6 weeks after Ramadan), at a tertiary care hospital in Pakistan. Data regarding glycemic control, characteristics and complications of diabetes, comorbidities, and the various factors that influence fasting were gathered from patients of either sex aged 18 to 80 years with any type of diabetes. The International Diabetes Federation-Diabetes and Ramadan 2021 risk calculation and recommendation were made accordingly for each patient. RESULTS: This study comprised of 460 participants with DM, with 174 males (37.8%) and 286 females (62.2%). The risk categorization showed that 209 (45.4%), 107 (23.3%), and 144 (31.3%) of the participants were in the low-, moderate-, and high-risk categories, respectively. Of the 144 high-risk patients who fasted, 57.9% experienced hypoglycemia (P <.0001). The recommendation of fasting showed statistically significant differences with risk categories, intention to fast, hypoglycemia, type of DM, duration of DM, level of glycemic control, and days of fasting (P <.001). CONCLUSION: A statistically significant number of participants in the high-risk group who fasted experienced complications. This reiterates the importance of rigorous adherence to the medical recommendations.

Comparison of Ten Surrogate Insulin Resistance and Obesity Markers to Identify Metabolic Syndrome in Mexican Adults.

Metabolic syndrome (MetS) is a group of clinical traits directly linked to type 2 diabetes mellitus and cardiovascular diseases, whose prevalence has been rising nationally and internationally. We aimed to evaluate ten known and novel surrogate markers of insulin resistance and obesity to identify MetS in Mexican adults. The present cross-sectional study analyzed 10575 participants from ENSANUT-2018. The diagnosis of MetS was based on the Adult Treatment Panel III (ATP III) criteria and International Diabetes Federation (IDF) criteria, stratified by sex and age group. According to ATP III, the best biomarker was the metabolic score for insulin resistance (METS-IR) in men aged 20-39 and 40-59 years and lipid accumulation product (LAP) in those aged ≥60 years. The best biomarker was LAP in women aged 20-39 and triglyceride-glucose index (TyG) in those aged 40-59 and ≥60 years. Using the IDF criteria, the best biomarker was LAP in men of all ages. TyG gave the best results in women of all ages. The best biomarker for diagnosis of MetS in Mexican adults depends on the criteria, including sex and age group. LAP and TyG are easy to obtain, inexpensive, and especially useful at the primary care level.

Automatic text classification of drug-induced liver injury using document-term matrix and XGBoost.

Introduction: Regulatory agencies generate a vast amount of textual data in the review process. For example, drug labeling serves as a valuable resource for regulatory agencies, such as U.S. Food and Drug Administration (FDA) and Europe Medical Agency (EMA), to communicate drug safety and effectiveness information to healthcare professionals and patients. Drug labeling also serves as a resource for pharmacovigilance and drug safety research. Automated text classification would significantly improve the analysis of drug labeling documents and conserve reviewer resources. Methods: We utilized artificial intelligence in this study to classify drug-induced liver injury (DILI)-related content from drug labeling documents based on FDA's DILIrank dataset. We employed text mining and XGBoost models and utilized the Preferred Terms of Medical queries for adverse event standards to simplify the elimination of common words and phrases while retaining medical standard terms for FDA and EMA drug label datasets. Then, we constructed a document term matrix using weights computed by Term Frequency-Inverse Document Frequency (TF-IDF) for each included word/term/token. Results: The automatic text classification model exhibited robust performance in predicting DILI, achieving cross-validation AUC scores exceeding 0.90 for both drug labels from FDA and EMA and literature abstracts from the Critical Assessment of Massive Data Analysis (CAMDA). Discussion: Moreover, the text mining and XGBoost functions demonstrated in this study can be applied to other text processing and classification tasks.

Exploring optimal deep tunnel sewer systems to enhance urban pluvial flood resilience in the gangnam region, South Korea.

Urban pluvial flooding is becoming a global concern, exacerbated by urbanization and climate change, especially in rapidly developing areas where existing sewer systems lag behind growth. In order to minimize a system's functional failures during extreme rainfalls, localized engineering solutions are required for urban areas chronically suffering from pluvial floods. This study critically evaluates the Deep Tunnel Sewer System (DTSS) as a robust grey infrastructure solution for enhancing urban flood resilience, with a case study in the Gangnam region of Seoul, South Korea. To do so, we integrated a one-dimensional sewer model with a rapid flood spreading model to identify optimal routes and conduit diameters for the DTSS, focusing on four flood-related metrics: the total flood volume, the flood duration, the peak flooding rate, and the number of flooded nodes. Results indicate that, had the DTSS been in place, it could have reduced historical flood volumes over the last decade by 50.1-99.3%, depending on the DTSS route. Regarding the conduit diameter, an 8 m diameter was found to be optimal for minimizing all flood-related metrics. Our research also developed the Intensity-Duration-Frequency (IDF) surfaces in three dimensions, providing a correlation between simulated flood-related metrics and design rainfall characteristics to distinguish the effect of DTSS on flood risk reduction. Our findings demonstrate how highly engineered solutions can enhance urban flood resilience, but they may still face challenges during extreme heavy rainfalls with a 80-year frequency or above. This study contributes to rational decision-making and emergency management in the face of increasing urban pluvial flood risks.

Climate change impacts on rainfall intensity-duration-frequency curves in local scale catchments.

The increasing intensity and frequency of rainfall events, a critical aspect of climate change, pose significant challenges in the construction of intensity-duration-frequency (IDF) curves for climate projection. These curves are crucial for infrastructure development, but the non-stationarity of extreme rainfall raises concerns about their adequacy under future climate conditions. This research addresses these challenges by investigating the reasons behind the IPCC climate report's evidence about the validity that rainfall follows the Clausius-Clapeyron (CC) relationship, which suggests a 7% increase in precipitation per 1 °C increase in temperature. Our study provides guidelines for adjusting IDF curves in the future, considering both current and future climates. We calculate extreme precipitation changes and scaling factors for small urban catchments in Barranquilla, Colombia, a tropical region, using the bootstrapping method. This reveals the occurrence of a sub-CC relationship, suggesting that the generalized 7% figure may not be universally applicable. In contrast, our comparative analysis with Illinois, USA, an inland city in the north temperate zone, shows adherence to the CC relationship. This emphasizes the need for local parameter calculations rather than relying solely on the generalized 7% figure.

Diabetes mellitus, the fastest growing global public health concern: Early detection should be focused.

Background and Aims: Diabetes is recognized as a significant factor in both mortality and morbidity worldwide, affecting various demographics regardless of geographic location, age group, or gender. This correspondence aims to express concern and draw the attention of leaders and policymakers worldwide to this critical public health issue. Methods: A thorough literature search was conducted utilizing various databases, including Google Scholar, PubMed, Science Direct, and the International Diabetes Federation (IDF) website, to collect the required data. Keywords were strategically applied to enhance search results, with preference given to English-language articles containing pertinent information. Results: According to the 2021 report by the IDF, approximately 537 million individuals globally were affected with diabetes, constituting roughly 10.5% of the world's populace. This condition incurred healthcare expenditures totaling $966 billion. Projections indicate a surge in diabetes cases to 783 million by 2045, with associated healthcare costs estimated to surpass $1054 billion. However, almost half of all people with diabetes are unaware of their medical condition, with the highest prevalence of undiagnosed diabetes Mellitus (DM) found in low and middle-income countries (LMICs) of the regions of Africa, the Western Pacific, and Southeast Asia. Conclusion: Collaborating with the World Health Organization (WHO), LMIC governments should improve healthcare accessibility, including more frequent diabetes screenings for individuals aged ≥ 45 years and younger individuals at elevated risk of having a family history.

Qatar's Silent Epidemic: A Comprehensive Meta-analysis on the Prevalence of Metabolic Syndrome.

BACKGROUND: Metabolic syndrome comprises various conditions like abdominal obesity, insulin resistance, elevated triglyceride levels, reduced HDL, and high blood pressure, which pose significant health challenges globally. It's imperative to determine its prevalence in specific populations to formulate effective preventive measures. OBJECTIVE: This systematic review and meta-analysis aimed to determine the prevalence of metabolic syndrome in the Qatari population. METHODS: Using the PRISMA guidelines, a systematic search was executed on PubMed until July 2023 with keywords "Metabolic syndrome" and "Qatar." Eligibility criteria included human subjects, studies assessing metabolic syndrome components, and research conducted in Qatar or on Qatari subjects. The quality of the studies was evaluated using the Newcastle-Ottawa Scale (NOS). Pooled prevalence rates were calculated using the inverse variance weighting metaanalysis. RESULTS: Out of 237 studies, 14 met our inclusion criteria, with a combined sample size of 14,772 from the Qatari population. The overall pooled prevalence of metabolic syndrome was 26%. The ATP III and IDF criteria exhibited significant differences in prevalence rates, with the IDF criteria showing a higher prevalence. Age ≥ 40 years demonstrated a higher prevalence compared to the younger group. Studies post-2018 reported a decreasing trend in metabolic syndrome prevalence. CONCLUSION: The prevalence of metabolic syndrome in the Qatari population is comparable to rates in the Middle East. The study underscores the need for tailored interventions and strategies, especially targeting the older age group. Continuous research and monitoring are essential to track and understand the disease's progression in Qatar.

Prevalence and correlates of metabolic syndrome among adults in freetown, Sierra Leone: A comparative analysis of NCEP ATP III, IDF and harmonized ATP III criteria.

Background: Metabolic syndrome (MetS) is a global health concern, especially for low and middle-income countries with limited resources and information. The study's objective was to assess the prevalence of MetS in Freetown, Sierra Leone, using the National Cholesterol Education Program (NCEP) Adult Treatment Panel III (ATP III), International Diabetes Federation (IDF) and Harmonize ATP III. Additionally, we aimed to establish the concordance between these three different criteria used. Methods: This community-based health screening survey was conducted from October 2019 to October 2022. A multistage stratified random design was used to select adults aged 20 years and above. Mean, interquartile range (IQR), and logistic regression were used for statistical analysis. The kappa coefficient statistics resolved the agreement between these defined criteria. Results: The prevalence for NCEP ATP III, Harmonize ATP III and IDF criteria was 11.8 % (95 % CI: 9.0-15.15), 14.3 % (95 % CI: 11.3-18.0), and 8.5 % (95 % CI: 6.2-11.2), respectively for the 2394 selected adults. The kappa coefficient (κ) agreement between the MetS is: Harmonized ATP III and IDF criteria = [(208 (60.8 %); (κ = 0.62)]; Harmonized ATP III and NCEP ATP III = [(201 (58.7 %); (κ = 0.71)]; while IDF and NCEP ATP III was [(132 (38.6 %); (κ = 0.52)]. In the multivariable regression analysis, waist circumference correlated with all three MetS criteria: ATP III [AOR = 0.85; C.I 95 %: (0.40-1.78), p = 0.032], Harmonized ATP III [AOR = 1.14; C.I 95 %: (0.62-2.11), p = 0.024], IDF [AOR = 1.06; C.I 95 % (0.52-2.16), p = 0.018]. Conclusion: We reported a high prevalence of MetS in Freetown, Sierra Leone and identified waist circumference as a major risk factor for MetS. This underscores the crucial role of health education and effective management of MetS in Sierra Leone.

Validity of the International Diabetes Federation risk stratification score of Ramadan fasting in individuals with diabetes mellitus.

OBJECTIVES: To assess the validity of the new International Diabetes Federation-Diabetes and Ramadan International Alliance (IDF-DAR) risk stratification tool for Ramadan fasting in predicting diabetic patients' ability to fast safely. METHODS: A prospective observational study was carried out during Ramadan 2022 at the Diabetes Center, King Fahad Hospital, Al-Madinah Al-Munawarah, Saudi Arabia. The IDF-DAR risk stratification tool was used to calculate fasting risk for diabetic patients pre-Ramadan. The patients were allocated into 3 categories: high, moderate, and low risk. Fasting was left up to the patients and their healthcare providers. Participants filled out a log-sheet each day of Ramadan showing whether they completed the fast. A final interview was carried out after Ramadan to assess patients' fasting experiences. RESULTS: We included 466 patients with diabetes: 79.4% with T2DM and 20.6% with T1DM. Based on the IDF-DAR score, 265 (56.9%) patients were classified as high risk, 115 (24.7%) as moderate risk, and 86 (18.4%) as low risk. Non-fasting the whole month of Ramadan was statistically relevant to the IDF-DAR risk stratification score. High-risk individuals were more likely to experience hypoglycemia and hyperglycemia than those with a moderate or low risk. But overall, 70.4% of people at moderate risk and 53.2% of the ones at high risk observed Ramadan's complete fast. CONCLUSION: The IDF-DAR has proven to be reliable and valid for predicting the risk of adverse events associated with fasting in diabetic patients. Nonetheless, it might overestimate the risk of fasting for some patients.

Comparing the association of two metabolic syndrome definitions, NCEP ATP III and IDF, with the risk of developing atherosclerotic cardiovascular disease: An analytical cross-sectional study.

INTRODUCTION: Atherosclerotic cardiovascular diseases (ASCVD) are significant sources of mortality and morbidity with substantial economic implications and preventive measures play key roles in this regard. Metabolic syndrome (MetS) is a common condition, and its association with ASCVD and mortality has made it clinically important. However, controversies persist regarding the best definition for MetS. Here in, we investigated the ability of the International Diabetes Federation (IDF) and the National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III) in the prediction of ASCVD incidence. METHODS: We conducted an investigation on individuals diagnosed with MetS as part of the "Kerman Coronary Artery Diseases Risk Factor Study" (KERCADRS). This study was a cohort study conducted on a population aged 15-75 years residing in Kerman, Iran to assess the risk of ASCVD. We employed ACC/AHA ASCVD Risk Estimator for predicting ASCVD occurrence in the future and then compared the results with different definitions of MetS including IDF and NCEP ATP III. RESULTS: Patients with MetS consistent with NCEP ATP III had higher ASCVD risk scores than those with IDF (10.63 ± 10.989 vs. 9.50 ± 9.357). NCEP ATP III had better overall performance in terms of specificity, accuracy, sensitivity and positive and negative predictive values especially in higher ASCVD risk score categories. The agreement between IDF and NCEP ATP III was none to slight (Cohen's Kappa <0.2) except for IDF in the group of ASCVD >30%, which revealed no agreement (Cohen's Kappa = 0). CONCLUSION: NCEP ATP III has better overall performance compared to IDF. The ability of NCEP ATP III increases as the ASCVD risk score goes higher. IDF may be useful in primary screening and patients with lower ASCVD risk scores.

iTTCA-MVL: A multi-view learning model based on physicochemical information and sequence statistical information for tumor T cell antigens identification.

Immunotherapy is an emerging treatment method aimed at activating the human immune system and relying on its own immune function to kill cancer cells and tumor tissues. It has the advantages of wide applicability and minimal side effects. Effective identification of tumor T cell antigens (TTCAs) will help researchers understand their functions and mechanisms and carry out research on anti-tumor vaccine development. Considering that using biological experimental technology to identify TTCAs can be costly and time-consuming, it is necessary to develop a robust bioinformatics computing tool. At present, different machine learning models have been proposed for identifying TTCAs, but there is still room for further improvement in their performance. To establish a TTCA predictor with better prediction performance, we propose a prediction model called iTTCA-MVL in this paper. We extracted three sets of features from the views of physicochemical information and sequence statistics, namely the distribution descriptor of composition, transition, and distribution (CTDD), TF-IDF, and LSA topic. Then, we used least squares support vector machines (LSSVMs) as submodels and Hilbert‒Schmidt independence criteria (HSIC) as constraints to establish an independent and complementary multi-view learning model. The prediction accuracy of iTTCA-MVL on the independent test set is 0.873, and Matthew's correlation coefficient is 0.747, which is significantly better than those of existing methods. Therefore, iTTCA-MVL is an excellent prediction tool that researchers can use to accurately identify TTCAs.

Prevalence of Diabetes in India: A Review of IDF Diabetes Atlas 10th Edition.

Diabetes is a severe chronic disease that arises when insulin generation is insufficient, or the generated insulin cannot be used in the body, resulting a long-term metabolic disorder. Diabetes affects an estimated 537 million adults worldwide between the age of 20 to 79 (10.5% of all adults in this age range). By 2030, 643 million people will have diabetes globally, increasing to 783 million by 2045. According to the IDF 10th edition, the incidence of diabetes has been rising in South-East Asia (SEA) nations for at least 20 years, and current estimates have outperformed all previous forecasts. This review aims to provide updated estimates and future projections of diabetes prevalence at the national and global levels by using data from the 10th edition of the IDF Diabetes Atlas 2021. For this review, we studied more than 60 previously published related articles from various sources, such as PubMed and Google Scholar, and we extracted 35 studies out of 60. however, we used only 34 studies directly related to diabetes and its prevalence at the global, SEA, and Indian levels. This review article concludes that in 2021 more than 1 in 10 adults worldwide developed diabetes. The estimated prevalence of diabetes in adults (20 to 79 years) has more than tripled since the first edition in 2000, rising from an estimated 151 million (4.6% of the world's population at the time) to 537.5 million (10.5%) of the world's population today. The prevalence rate will be higher than 12.8% by 2045. In addition, this study indicates that the incidence of diabetes in the world, Southeast Asia, and India was 10.5%, 8.8%, and 9.6%, respectively, throughout 2021 and will rise to 12.5%, 11.5%, and 10.9%, respectively by 2045.

Metabolic Syndrome Among Adolescents Aged 10-19 Years in India: A Systematic Review and Meta-Analysis.

Metabolic syndrome (MetS) is a group of metabolic abnormalities that include disturbed glucose metabolism, dyslipidemia, abdominal obesity, and arterial hypertension. Nutritional and lifestyle modifications have increased the risk of cardiometabolic disorders among adolescents. Studies conducted in various parts of India have shown a wide range of prevalence among adolescents aged 10-19 years. The various criteria for defining MetS have led to controversial diagnoses, providing inconsistent findings. Additionally, there is a paucity of national-level estimates on the prevalence of MetS in India. Therefore, this systematic review and meta-analysis were conducted to estimate the prevalence of MetS among adolescents. A comprehensive search was conducted to identify studies that reported the prevalence of MetS among adolescents in India. The search was performed using several databases, including PubMed, Embase, ScienceDirect, Scopus, Medline, Web of Science, Google, and Google Scholar. Relevant data were extracted and assessed for quality using the Critical Appraisal Skills Programme (CASP) guidelines. To estimate the pooled prevalence and explore heterogeneity, a random effects model and I2 statistic were used. Subgroup analyses were conducted based on criteria for defining MetS, sex, study setting, and study site. Sensitivity analysis was performed, and publication bias was also explored. A sample size of 19044 adolescents from 16 studies was included in the meta-analysis. The pooled prevalence of Mets among adolescents using the International Diabetes Federation (IDF) criteria was 3.4% (95% CI: 1.1-6.6%, I2=97.1%) and the National Cholesterol Education Program - Adult Treatment Panel III (NCEP-ATP III) criteria were 5.0% (95% CI: 3.3-6.9%, I2=95.9). The subgroup analyses did not reveal the reasons for heterogeneity, but sensitivity analysis showed a substantial change in the pooled estimate. Our study findings show that the prevalence of MetS among Indian adolescents is higher compared to other countries posing a challenge to address the necessity of intervention among adolescents. Standardizing the definition of MetS is necessary to avoid inconsistency in the estimates. The study findings highlight the need to strengthen existing adolescent programs through the encouragement of increased physical activity and the adoption of nutritious well-balanced diets to mitigate the burden of MetS among adolescents in India.

IDF-11774 Induces Cell Cycle Arrest and Apoptosis by Inhibiting HIF-1α in Gastric Cancer.

Hypoxia-inducible factor-1 alpha (HIF-1α) is a regulatory factor of intracellular oxygen supersession. The expression or increased activity of HIF-1α is closely related to various human cancers. Previously, IDF-11774 was demonstrated to inhibit HSP70 chaperone activity and suppress the accumulation of HIF-1α. In this study, we aimed to determine the effects of IDF-11774 on gastric cancer cell lines. Treatment with IDF-11774 was found to markedly decrease the proliferation, migration, and invasion of the gastric cancer cell lines. Furthermore, the phosphorylation levels of extracellular signal-regulated kinase 1/2, p38, and Jun N-terminal kinase in the mitogen-activated protein kinase signaling pathways were markedly increased in a dose-dependent manner, ultimately promoting apoptosis via the induction of cell cycle arrest. Our findings indicate that HIF-1α inhibitors are potent drugs for the treatment of gastric cancer.

A Kullback-Liebler divergence-based representation algorithm for malware detection.

Background: Malware, malicious software, is the major security concern of the digital realm. Conventional cyber-security solutions are challenged by sophisticated malicious behaviors. Currently, an overlap between malicious and legitimate behaviors causes more difficulties in characterizing those behaviors as malicious or legitimate activities. For instance, evasive malware often mimics legitimate behaviors, and evasion techniques are utilized by legitimate and malicious software. Problem: Most of the existing solutions use the traditional term of frequency-inverse document frequency (TF-IDF) technique or its concept to represent malware behaviors. However, the traditional TF-IDF and the developed techniques represent the features, especially the shared ones, inaccurately because those techniques calculate a weight for each feature without considering its distribution in each class; instead, the generated weight is generated based on the distribution of the feature among all the documents. Such presumption can reduce the meaning of those features, and when those features are used to classify malware, they lead to a high false alarms. Method: This study proposes a Kullback-Liebler Divergence-based Term Frequency-Probability Class Distribution (KLD-based TF-PCD) algorithm to represent the extracted features based on the differences between the probability distributions of the terms in malware and benign classes. Unlike the existing solution, the proposed algorithm increases the weights of the important features by using the Kullback-Liebler Divergence tool to measure the differences between their probability distributions in malware and benign classes. Results: The experimental results show that the proposed KLD-based TF-PCD algorithm achieved an accuracy of 0.972, the false positive rate of 0.037, and the F-measure of 0.978. Such results were significant compared to the related work studies. Thus, the proposed KLD-based TF-PCD algorithm contributes to improving the security of cyberspace. Conclusion: New meaningful characteristics have been added by the proposed algorithm to promote the learned knowledge of the classifiers, and thus increase their ability to classify malicious behaviors accurately.

A standardized European hexagon gridded dataset based on OpenStreetMap POIs.

Point of interest (POI) data refers to information about the location and type of amenities, services, and attractions within a geographic area. This data is used in urban studies research to better understand the dynamics of a city, assess community needs, and identify opportunities for economic growth and development. POI data is beneficial because it provides a detailed picture of the resources available in a given area, which can inform policy decisions and improve the quality of life for residents. This paper presents a large-scale, standardized POI dataset from OpenStreetMap (OSM) for the European continent. The dataset's standardization and gridding make it more efficient for advanced modeling, reducing 7,218,304 data points to 988,575 without significant resolution loss, suitable for a broader range of models with lower computational demands. The resulting dataset can be used to conduct advanced analyses, examine POI spatial distributions, conduct comparative regional studies, and research to help enhance the understanding of the distribution of economic activity and attractions, and subsequently help in the understanding of the economic health, growth potential, and cultural opportunities of an area. The paper describes the materials and methods used in generating the dataset, including OSM data retrieval, processing, standardization, hexagonal grid generation, and point count aggregations. The dataset can be used independently or integrated with other relevant datasets for more comprehensive spatial distribution studies in future research.

Improved prediction of drug-induced liver injury literature using natural language processing and machine learning methods.

Drug-induced liver injury (DILI) is an adverse hepatic drug reaction that can potentially lead to life-threatening liver failure. Previously published work in the scientific literature on DILI has provided valuable insights for the understanding of hepatotoxicity as well as drug development. However, the manual search of scientific literature in PubMed is laborious and time-consuming. Natural language processing (NLP) techniques along with artificial intelligence/machine learning approaches may allow for automatic processing in identifying DILI-related literature, but useful methods are yet to be demonstrated. To address this issue, we have developed an integrated NLP/machine learning classification model to identify DILI-related literature using only paper titles and abstracts. For prediction modeling, we used 14,203 publications provided by the Critical Assessment of Massive Data Analysis (CAMDA) challenge, employing word vectorization techniques in NLP in conjunction with machine learning methods. Classification modeling was performed using 2/3 of the data for training and the remainder for test in internal validation. The best performance was achieved using a linear support vector machine (SVM) model on the combined vectors derived from term frequency-inverse document frequency (TF-IDF) and Word2Vec, resulting in an accuracy of 95.0% and an F1-score of 95.0%. The final SVM model constructed from all 14,203 publications was tested on independent datasets, resulting in accuracies of 92.5%, 96.3%, and 98.3%, and F1-scores of 93.5%, 86.1%, and 75.6% for three test sets (T1-T3). Furthermore, the SVM model was tested on four external validation sets (V1-V4), resulting in accuracies of 92.0%, 96.2%, 98.3%, and 93.1%, and F1-scores of 92.4%, 82.9%, 75.0%, and 93.3%.