Public Response to Federal Electronic Cigarette Regulations Analyzed Using Social Media Data Through Natural Language Processing: Topic Modeling Study.

BACKGROUND: e-Cigarette (electronic cigarette) use has been a public health issue in the United States. On June 23, 2022, the US Food and Drug Administration (FDA) issued marketing denial orders (MDOs) to Juul Labs Inc for all their products currently marketed in the United States. However, one day later, on June 24, 2022, a federal appeals court granted a temporary reprieve to Juul Labs that allowed it to keep its e-cigarettes on the market. As the conversation around Juul continues to evolve, it is crucial to gain insights into the sentiments and opinions expressed by individuals on social media. OBJECTIVE: This study aims to conduct a comprehensive analysis of tweets before and after the ban on Juul, aiming to shed light on public perceptions and sentiments surrounding this contentious topic and to better understand the life cycle of public health-related policy on social media. METHODS: Natural language processing (NLP) techniques were used, including state-of-the-art BERTopic topic modeling and sentiment analysis. A total of 6023 tweets and 22,288 replies or retweets were collected from Twitter (rebranded as X in 2023) between June 2022 and October 2022. The encoded topics were used in time-trend analysis to depict the boom-and-bust cycle. Content analyses of retweets were also performed to better understand public perceptions and sentiments about this contentious topic. RESULTS: The attention surrounding the FDA's ban on Juul lasted no longer than a week on Twitter. Not only the news (ie, tweets with a YouTube link that directs to the news site) related to the announcement itself, but the surrounding discussions (eg, potential consequences of this ban or block and concerns toward kids or youth health) diminished shortly after June 23, 2022, the date when the ban was officially announced. Although a short rebound was observed on July 4, 2022, which was contributed by the suspension on the following day, discussions dried out in 2 days. Out of the top 50 most retweeted tweets, we observed that, except for neutral (23/45, 51%) sentiment that broadcasted the announcement, posters responded more negatively (19/45, 42%) to the FDA's ban. CONCLUSIONS: We observed a short life cycle for this news announcement, with a preponderance of negative sentiment toward the FDA's ban on Juul. Policy makers could use tactics such as issuing ongoing updates and reminders about the ban, highlighting its impact on public health, and actively engaging with influential social media users who can help maintain the conversation.

Machine learning-guided strategies for reaction conditions design and optimization.

This review surveys the recent advances and challenges in predicting and optimizing reaction conditions using machine learning techniques. The paper emphasizes the importance of acquiring and processing large and diverse datasets of chemical reactions, and the use of both global and local models to guide the design of synthetic processes. Global models exploit the information from comprehensive databases to suggest general reaction conditions for new reactions, while local models fine-tune the specific parameters for a given reaction family to improve yield and selectivity. The paper also identifies the current limitations and opportunities in this field, such as the data quality and availability, and the integration of high-throughput experimentation. The paper demonstrates how the combination of chemical engineering, data science, and ML algorithms can enhance the efficiency and effectiveness of reaction conditions design, and enable novel discoveries in synthetic chemistry.

From the discovery of a novel arepavirus in diseased arecanut palms (Areca catechu L.) in India to the identification of known and novel arepaviruses in bee and plant transcriptomes through data-mining.

Arecanut palm is a commercially important plantation crop valued for its nut. In this investigation, we report the discovery of a putative novel arepavirus, named areca palm necrotic ringspot virus 2 (ANRSV2), in necrotic ringspot diseased areca palms in Bantwal, Dakshina Kannada, Karnataka, India through RNA-sequencing and transmission electron microscopy. Further, the presence of ANRSV2 in the diseased samples was confirmed through reverse transcriptase-polymerase chain reaction assays. In addition, by mining public domain transcriptome data for arepaviral sequences, we identified a putative novel arepavirus in Psychotria rubra, a non-palm host. We recovered the genome sequences of the areca palm necrotic ringspot virus in honey bees, tomato, Onobrychis viciifolia, and Rhamnus heterophylla. These findings broaden our comprehension of arepaviral diversity and host range, and suggest an intriguing possibility of pollen-mediated arepaviral transmission that necessitates empirical validation. Further studies are needed to understand the biology of identified putative novel arepaviruses.

Post-marketing safety concerns with rimegepant based on a pharmacovigilance study.

PURPOSE: This study aimed to comprehensively assess the safety of rimegepant administration in real-world clinical settings. METHODS: Data from the Food and Drug Administration Adverse Event Reporting System (FAERS) spanning the second quarter of 2020 through the first quarter of 2023 were retrospectively analyzed in this pharmacovigilance investigation. This study focuses on employing subgroup analysis to monitor rimegepant drug safety. Descriptive analysis was employed to examine clinical characteristics and concomitant medication of adverse event reports associated with rimegepant, including report season, reporter country, sex, age, weight, dose, and frequency, onset time, et al. Correlation analysis, including techniques such as violin plots, was utilized to explore relationships between clinical characteristics in greater detail. Additionally, four disproportionality analysis methods were applied to assess adverse event signals associated with rimegepant. RESULTS: A total of 5,416,969 adverse event reports extracted from the FAERS database, 10, 194 adverse events were identified as the "primary suspect" (PS) drug attributed to rimegepant. Rimegepant-associated adverse events involved 27 System Organ Classes (SOCs), and the significant SOC meeting all four detection criteria was "general disorders and administration site conditions" (SOC: 10018065). Additionally, new significant adverse events were discovered, including "vomiting projectile" (PT: 10047708), "eructation" (PT: 10015137), "motion sickness" (PT: 10027990), "feeling drunk" (PT: 10016330), "reaction to food additive" (PT: 10037977), etc. Descriptive analysis indicated that the majority of reporters were consumers (88.1%), with most reports involving female patients. Significant differences were observed between female and male patients across age categories, and the concomitant use of rimegepant with other medications was complex. CONCLUSION: This study has preliminarily identified potential new adverse events associated with rimegepant, such as those involving the gastrointestinal system, nervous system, and immune system, which warrant further research to determine their exact mechanisms and risk factors. Additionally, significant differences in rimegepant-related adverse events were observed across different age groups and sexes, and the complexity of concomitant medication use should be given special attention in clinical practice.

Discovery of a novel Wolbachia in Heterodera expands nematode host distribution.

Bioinformatics sequence data mining can reveal hidden microbial symbionts that might normally be filtered and removed as contaminants. Data mining can be helpful to detect Wolbachia, a widespread bacterial endosymbiont in insects and filarial nematodes whose distribution in plant-parasitic nematodes (PPNs) remains underexplored. To date, Wolbachia has only been reported a few PPNs, yet nematode-infecting Wolbachia may have been widespread in the evolutionary history of the phylum based on evidence of horizontal gene transfers, suggesting there may be undiscovered Wolbachia infections in PPNs. The goal of this study was to more broadly sample PPN Wolbachia strains in tylenchid nematodes to enable further comparative genomic analyses that may reveal Wolbachia's role and identify targets for biocontrol. Published whole-genome shotgun assemblies and their raw sequence data from 33 Meloidogyne spp. assemblies, seven Globodera spp. assemblies, and seven Heterodera spp. assemblies were analyzed to look for Wolbachia. No Wolbachia was found in Meloidogyne spp. and Globodera spp., but among seven genome assemblies for Heterodera spp., an H. schachtii assembly from the Netherlands was found to have a large Wolbachia-like sequence that, when re-assembled from reads, formed a complete, circular genome. Detailed analyses comparing read coverage, GC content, pseudogenes, and phylogenomic patterns clearly demonstrated that the H. schachtii Wolbachia represented a novel strain (hereafter, denoted wHet). Phylogenomic tree construction with PhyloBayes showed wHet was most closely related to another PPN Wolbachia, wTex, while 16S rRNA gene analysis showed it clustered with other Heterodera Wolbachia assembled from sequence databases. Pseudogenes in wHet suggested relatedness to the PPN clade, as did the lack of significantly enriched GO terms compared to PPN Wolbachia strains. It remains unclear whether the lack of Wolbachia in other published H. schachtii isolates represents the true absence of the endosymbiont from some hosts.

Adverse events associated with azithromycin and clarithromycin in adults aged ≥65: a disproportionality analysis of the FDA Adverse Event Reporting System (FAERS) database.

BACKGROUND: Azithromycin and clarithromycin are commonly used to treat community-acquired pneumonia in adults aged ≥ 65, such as mycoplasma pneumonia. This study aims to evaluate adverse events (AEs) associated with azithromycin and clarithromycin in this age group by analyzing the FDA Adverse Event Reporting System (FAERS), providing insights for clinical use and management of AEs in this population. RESEARCH DESIGN AND METHODS: We retrieved reports of AEs related to azithromycin and clarithromycin from the FAERS database. Disproportionality analysis was conducted using the Reporting Odds Ratio (ROR), Proportional Reporting Ratio (PRR), Bayesian Confidence Propagation Neural Network (BCPNN), and Multi-Gamma Poisson Shrinkage (MGPS) to identify AEs associated with azithromycin and clarithromycin in adults aged ≥ 65. RESULTS: A total of 2,019 adverse event reports were retrieved for azithromycin, and 2,392 for clarithromycin. Off-label use (n = 349) and drug interactions (n = 487) were the most reported AEs in adults aged ≥ 65 for azithromycin and clarithromycin, respectively. Prolonged QT interval showed the strongest signal among AEs for azithromycin in this age group. Drug interaction-related medication errors had the strongest signal for clarithromycin. Seven signals not explicitly included in the azithromycin package insert were identified in adults aged ≥ 65. Fourteen signals not explicitly included in the clarithromycin package insert were identified. CONCLUSIONS: Among adults aged ≥ 65, cardiac-related adverse events are more closely associated with azithromycin than with clarithromycin. Conversely, AEs related to drug interactions and psychiatric symptoms are more associated with clarithromycin. Additionally, clinicians should be vigilant regarding AEs not specified in the package inserts. The findings of this study may help optimize the selection of azithromycin and clarithromycin based on patient circumstances and assist clinicians in focusing on relevant AEs for early intervention.

Data mining of PubChem bioassay records reveals diverse OXPHOS inhibitory chemotypes as potential therapeutic agents against ovarian cancer.

Focused screening on target-prioritized compound sets can be an efficient alternative to high throughput screening (HTS). For most biomolecular targets, compound prioritization models depend on prior screening data or a target structure. For phenotypic or multi-protein pathway targets, it may not be clear which public assay records provide relevant data. The question also arises as to whether data collected from disparate assays might be usefully consolidated. Here, we report on the development and application of a data mining pipeline to examine these issues. To illustrate, we focus on identifying inhibitors of oxidative phosphorylation, a druggable metabolic process in epithelial ovarian tumors. The pipeline compiled 8415 available OXPHOS-related bioassays in the PubChem data repository involving 312,093 unique compound records. Application of PubChem assay activity annotations, PAINS (Pan Assay Interference Compounds), and Lipinski-like bioavailability filters yields 1852 putative OXPHOS-active compounds that fall into 464 clusters. These chemotypes are diverse but have relatively high hydrophobicity and molecular weight but lower complexity and drug-likeness. These chemotypes show a high abundance of bicyclic ring systems and oxygen containing functional groups including ketones, allylic oxides (alpha/beta unsaturated carbonyls), hydroxyl groups, and ethers. In contrast, amide and primary amine functional groups have a notably lower than random prevalence. UMAP representation of the chemical space shows strong divergence in the regions occupied by OXPHOS-inactive and -active compounds. Of the six compounds selected for biological testing, 4 showed statistically significant inhibition of electron transport in bioenergetics assays. Two of these four compounds, lacidipine and esbiothrin, increased in intracellular oxygen radicals (a major hallmark of most OXPHOS inhibitors) and decreased the viability of two ovarian cancer cell lines, ID8 and OVCAR5. Finally, data from the pipeline were used to train random forest and support vector classifiers that effectively prioritized OXPHOS inhibitory compounds within a held-out test set (ROCAUC 0.962 and 0.927, respectively) and on another set containing 44 documented OXPHOS inhibitors outside of the training set (ROCAUC 0.900 and 0.823). This prototype pipeline is extensible and could be adapted for focus screening on other phenotypic targets for which sufficient public data are available.Scientific contributionHere, we describe and apply an assay data mining pipeline to compile, process, filter, and mine public bioassay data. We believe the procedure may be more broadly applied to guide compound selection in early-stage hit finding on novel multi-protein mechanistic or phenotypic targets. To demonstrate the utility of our approach, we apply a data mining strategy on a large set of public assay data to find drug-like molecules that inhibit oxidative phosphorylation (OXPHOS) as candidates for ovarian cancer therapies.

Current Applications and Future Implications of Artificial Intelligence in Spine Surgery and Research: A Narrative Review and Commentary.

STUDY DESIGN: Narrative review. OBJECTIVES: Artificial intelligence (AI) is being increasingly applied to the domain of spine surgery. We present a review of AI in spine surgery, including its use across all stages of the perioperative process and applications for research. We also provide commentary regarding future ethical considerations of AI use and how it may affect surgeon-industry relations. METHODS: We conducted a comprehensive literature review of peer-reviewed articles that examined applications of AI during the pre-, intra-, or postoperative spine surgery process. We also discussed the relationship among AI, spine industry partners, and surgeons. RESULTS: Preoperatively, AI has been mainly applied to image analysis, patient diagnosis and stratification, decision-making. Intraoperatively, AI has been used to aid image guidance and navigation. Postoperatively, AI has been used for outcomes prediction and analysis. AI can enable curation and analysis of huge datasets that can enhance research efforts. Large amounts of data are being accrued by industry sources for use by their AI platforms, though the inner workings of these datasets or algorithms are not well known. CONCLUSIONS: AI has found numerous uses in the pre-, intra-, or postoperative spine surgery process, and the applications of AI continue to grow. The clinical applications and benefits of AI will continue to be more fully realized, but so will certain ethical considerations. Making industry-sponsored databases open source, or at least somehow available to the public, will help alleviate potential biases and obscurities between surgeons and industry and will benefit patient care.

Uncertainty-aware probabilistic graph neural networks for road-level traffic crash prediction.

Traffic crashes present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic crash prediction model is crucial to address growing public safety concerns and improve the safety of urban mobility systems. Traditional methods face limitations at fine spatiotemporal scales due to the sporadic nature of high-risk crashes and the predominance of non-crash characteristics. Furthermore, while most current models show promising occurrence prediction, they overlook the uncertainties arising from the inherent nature of crashes, and then fail to adequately map the hierarchical ranking of crash risk values for more precise insights. To address these issues, we introduce the Spatiotemporal Zero-Inflated Tweedie Graph Neural Networks (STZITD-GNN), the first uncertainty-aware probabilistic graph deep learning model in road-level daily-basis traffic crash prediction for multi-steps. Our model combines the interpretability of the statistical Tweedie family with the predictive power of graph neural networks, excelling in predicting a comprehensive range of crash risks. The decoder employs a compound Tweedie model, handling the non-Gaussian distribution inherent in crash data, with a zero-inflated component for accurately identifying non-crash cases and low-risk roads. The model accurately predicts and differentiates between high-risk, low-risk, and no-risk scenarios, providing a holistic view of road safety that accounts for the full spectrum of probability and severity of crashes. Empirical tests using real-world traffic data from London, UK, demonstrate that the STZITD-GNN surpasses other baseline models across multiple benchmarks, including a reduction in regression error of up to 34.60% in point estimation metrics and an improvement of above 47% in interval-based uncertainty metrics.

Real-world pharmacovigilance study of FDA adverse event reporting system events for finerenone.

OBJECTIVE: This study analyzed the signal mining of adverse events caused by finerenone based on the US Food and Drug Administration Adverse Event Reporting System (FAERS) and evaluated the drug's safety to provide a reference for the safe administration of this medication in medical institutions. METHODS: FAERS data from the third quarter of 2021 to the fourth quarter of 2023 were used, and the adverse event codes of the Medical Dictionary for Regulatory Activities were compared. After the data were processed, adverse event reports that featured finerenone as the most suspected drug were extracted. RESULTS: A total of 905 reported cases of adverse events including finerenone as the first suspected drug were extracted. The ratio of male to female patients was 1.25, and most were aged 65-85 years (30.1%). The adverse events that were reported more frequently with positive signals were decreased glomerular filtration rate, hyperkalemia, increased blood creatinine, and dizziness. The adverse events that were concentrated on in investigations were metabolism and nutrition disorders and diseases of the renal and urinary system. CONCLUSIONS: Our study identified significant novel adverse events (AEs) signals for finerenone that could provide support for clinical monitoring of and risk identification for finerenone.

AI in Surgery: Navigating Trends and Managerial Implications Through Bibliometric and Text Mining Odyssey.

Background: This research employs bibliometric and text-mining analysis to explore artificial intelligence (AI) advancements within surgical procedures. The growing significance of AI in healthcare underscores the need for healthcare managers to prioritize investments in this technology. Purpose: To assess the increasing impact of AI on surgical practices through a comprehensive analysis of scientific literature, providing insights that can guide managerial decision-making in adopting AI solutions.Research Design: The study analyzes over 6000 scientific articles published since 1990 to evaluate trends and contributions in the field, informing managers about the current landscape of AI in surgery.Study Sample: The research focuses on publications from various influential publishers across North America, Northern Asia, and Eastern & Western Europe, highlighting key markets for AI implementation in surgical settings.Data Collection and Analysis: A bibliometric approach was utilized to identify key contributors and influential journals. At the same time, text-mining techniques highlighted significant keywords related to AI in surgery, aiding managers in recognizing essential areas for further exploration and investment.Results: The year 2022 marked a significant upsurge in publications, indicating widespread AI integration in healthcare. The U.S. emerged as the foremost contributor, followed by China, the UK, Germany, Italy, the Netherlands, and India. Key journals, such as Annals of Surgery and Spine Journal, play a crucial role in disseminating research findings, serving as valuable resources for managers seeking to stay informed.Conclusions: The findings underscore AI's pivotal role in enhancing diagnostic precision, predicting treatment outcomes, and improving operational efficiency in surgical practices. This progress represents a significant milestone in modern medical science, paving the way for intelligent healthcare solutions and further advancements in the field. Healthcare managers should leverage these insights to foster innovation and improve patient care standards.

Evaluation of pollution prevention related deficiencies of ships using association rule mining.

Since marine and environmental pollution is a major problem for the maritime industry, preventive implementations are constantly being developed. In this context, this research aimed to determine the dominant factors in ships detected to have pollution prevention deficiencies in port state control (PSC). A total of 12,530 PSC reports carried out by Paris Memorandum of Understanding (MoU) region between 2017 and 2023 were analyzed with the association rule mining. The Apriori algorithm was performed to reveal hidden and meaningful relationships in the inspections. The dominant variables for inspections that detected pollution prevention deficiencies were ship flag, classification society, number of deficiencies, and inspection type. Association rules revealed that pollution prevention deficiency areas differed interestingly according to geographical region, classification society, and ship age. The findings may be a guide for stakeholders for pollution prevention during ship inspections, and contribute to the achievement of maritime-related Sustainable Development Goals (SDGs).

[Screening and evaluation of core prescriptions for impotence based on network robustness and data mining].

This study aims to explore and analyze ancient proven prescriptions and famous physician cases for treating impotence, so as to obtain the core prescriptions for traditional Chinese medicine(TCM) treatment of impotence. It further selected and evaluated these core prescriptions to provide a demonstration for the development of new drugs for advantageous diseases treated with TCM. Through the retrieval of ancient proven prescriptions and famous physician cases for treating impotence, a database of prescriptions for treating impotence was established, and the TCM inheritance computational platform was used to explore and analyze the medication patterns of these proven prescriptions and famous physician cases. Based on the TCM efficacy prediction platform of network robustness, the interference scores of core prescriptions in the ancient proven prescriptions and famous physician cases were calculated and analyzed. On this basis, the results of ancient proven prescriptions, famous physician cases, and computational analysis were comprehensively evaluated to determine the development priority level of the core prescriptions obtained through clustering. The results revealed that medicines in the ancient proven prescriptions and famous physician cases primarily aimed at tonifying deficiency, promoting blood circulation, eliminating blood stasis, clearing heat, and resolving external symptoms, with a particular focus on warm-natured and sweet-flavored medicines associated with the spleen, liver, kidney, and lung meridians. The core prescriptions obtained from the clustering analysis of ancient proven prescriptions and famous physician cases indicated that ancient proven prescriptions combination 1 had the most perturbing effect on the disease network as determined by network robustness analysis. A comprehensive evaluation indicated that prescription combination 1 had the most optimal development potential. TCM treatment for impotence focused on regulating the functions of the spleen, liver, kidney, and lung, aiming to tonify deficiency, with heat-clearing, blood-activating, stasis-resolving, and exterior-releasing medications supplemented. The obtained ancient proven prescriptions combination 1 exhibited the highest potential development value. The integrated strategy of "ancient proven prescriptions-famous physician cases-computational analysis" can be utilized to screen candidate TCM new drug prescriptions.

iGATTLDA: Integrative graph attention and transformer-based model for predicting lncRNA-Disease associations.

Long non-coding RNAs (lncRNAs) have emerged as significant contributors to the regulation of various biological processes, and their dysregulation has been linked to a variety of human disorders. Accurate prediction of potential correlations between lncRNAs and diseases is crucial for advancing disease diagnostics and treatment procedures. The authors introduced a novel computational method, iGATTLDA, for the prediction of lncRNA-disease associations. The model utilised lncRNA and disease similarity matrices, with known associations represented in an adjacency matrix. A heterogeneous network was constructed, dissecting lncRNAs and diseases as nodes and their associations as edges. The Graph Attention Network (GAT) is employed to process initial features and corresponding adjacency information. GAT identified significant neighbouring nodes in the network, capturing intricate relationships between lncRNAs and diseases, and generating new feature representations. Subsequently, the transformer captures global dependencies and interactions across the entire sequence of features produced by the GAT. Consequently, iGATTLDA successfully captures complex relationships and interactions that conventional approaches may overlook. In evaluating iGATTLDA, it attained an area under the receiver operating characteristic (ROC) curve (AUC) of 0.95 and an area under the precision recall curve (AUPRC) of 0.96 with a two-layer multilayer perceptron (MLP) classifier. These results were notably higher compared to the majority of previously proposed models, further substantiating the model's efficiency in predicting potential lncRNA-disease associations by incorporating both local and global interactions. The implementation details can be obtained from https://github.com/momanyibiffon/iGATTLDA.

Optimising inter-patient image registration for image-based data mining in breast radiotherapy.

Background and purpose: Image-based data mining (IBDM) requires spatial normalisation to reference anatomy, which is challenging in breast radiotherapy due to variations in the treatment position, breast shape and volume. We aim to optimise spatial normalisation for breast IBDM. Materials and methods: Data from 996 patients treated with radiotherapy for early-stage breast cancer, recruited in the REQUITE study, were included. Patients were treated supine (n = 811), with either bilateral or ipsilateral arm(s) raised (551/260, respectively) or in prone position (n = 185). Four deformable image registration (DIR) configurations for extrathoracic spatial normalisation were tested. We selected the best-performing DIR configuration and further investigated two pathways: i) registering prone/supine cohorts independently and ii) registering all patients to a supine reference. The impact of arm positioning in the supine cohort was quantified. DIR accuracy was estimated using Normalised Cross Correlation (NCC), Dice Similarity Coefficient (DSC), mean Distance to Agreement (MDA), 95 % Hausdorff Distance (95 %HD), and inter-patient landmark registration uncertainty (ILRU). Results: DIR using B-spline and normalised mutual information (NMI) performed the best across all evaluation metrics. Supine-supine registrations yielded highest accuracy (0.98 ± 0.01, 0.91 ± 0.04, 0.23 ± 0.19 cm, 1.17 ± 1.18 cm, 0.51 ± 0.26 cm for NCC, DSC, MDA, 95 %HD, and ILRU), followed by prone-prone and supine-prone registrations. Arm positioning had no significant impact on registration performance. For the best DIR strategy, uncertainty of 0.44 and 0.81 cm in the breast and shoulder regions was found. Conclusions: B-spline algorithm using NMI and registered supine and prone cohorts independently provides the most optimal spatial normalisation strategy for breast IBDM.

Machine learning-based evaluation of prognostic factors for mortality and relapse in patients with acute lymphoblastic leukemia: a comparative simulation study.

BACKGROUND: Predicting mortality and relapse in children with acute lymphoblastic leukemia (ALL) is crucial for effective treatment and follow-up management. ALL is a common and deadly childhood cancer that often relapses after remission. In this study, we aimed to apply and evaluate machine learning-based models for predicting mortality and relapse in pediatric ALL patients. METHODS: This retrospective cohort study was conducted on 161 children aged less than 16 years with ALL. Survival status (dead/alive) and patient experience of relapse (yes/no) were considered as the outcome variables. Ten machine learning (ML) algorithms were used to predict mortality and relapse. The performance of the algorithms was evaluated by cross-validation and reported as mean sensitivity, specificity, accuracy and area under the curve (AUC). Finally, prognostic factors were identified based on the best algorithms. RESULTS: The mean accuracy of the ML algorithms for prediction of patient mortality ranged from 64 to 74% and for prediction of relapse, it varied from 64 to 84% on test data sets. The mean AUC of the ML algorithms for mortality and relapse was above 64%. The most important prognostic factors for predicting both mortality and relapse were identified as age at diagnosis, hemoglobin and platelets. In addition, significant prognostic factors for predicting mortality included clinical side effects such as splenomegaly, hepatomegaly and lymphadenopathy. CONCLUSIONS: Our results showed that artificial neural networks and bagging algorithms outperformed other algorithms in predicting mortality, while boosting and random forest algorithms excelled in predicting relapse in ALL patients across all criteria. These results offer significant clinical insights into the prognostic factors for children with ALL, which can inform treatment decisions and improve patient outcomes.

Building a benchmark dataset for the Kurdish news question answering.

This article presents the Kurdish News Question Answering Dataset (KNQAD). The texts are collected from various Kurdish news websites. The ParsHub software is used to extract data from different fields of news, such as social news, religion, sports, science, and economy. The dataset consists of 15,002 news paragraphs with question-answer pairs. For each news paragraph, one or more question-answer pairs are manually created based on the content of the paragraphs. The dataset is pre-processed by cleaning and normalizing the data. During the cleaning process, special characters and stop words are removed, and stemming is used as a normalization step. The distribution of each question type is presented in the KNQAD. Moreover, the complexity of the QA problem is analyzed in the KNQAD by using lexical similarity techniques between questions and answers.

Unlocking Solutions: Innovative Approaches to Identifying and Mitigating the Environmental Impacts of Undocumented Orphan Wells in the United States.

In the United States, hundreds of thousands of undocumented orphan wells have been abandoned, leaving the burden of managing environmental hazards to governmental agencies or the public. These wells, a result of over a century of fossil fuel extraction without adequate regulation, lack basic information like location and depth, emit greenhouse gases, and leak toxic substances into groundwater. For most of these wells, basic information such as well location and depth is unknown or unverified. Addressing this issue necessitates innovative and interdisciplinary approaches for locating, characterizing, and mitigating their environmental impacts. Our survey of the United States revealed the need for tools to identify well locations and assess conditions, prompting the development of technologies including machine learning to automatically extract information from old records (95%+ accuracy), remote sensing technologies like aero-magnetometers to find buried wells, and cost-effective methods for estimating methane emissions. Notably, fixed-wing drones equipped with magnetometers have emerged as cost-effective and efficient for discovering unknown wells, offering advantages over helicopters and quadcopters. Efforts also involved leveraging local knowledge through outreach to state and tribal governments as well as citizen science initiatives. These initiatives aim to significantly contribute to environmental sustainability by reducing greenhouse gases and improving air and water quality.

Construction of store-operated calcium entry-related gene signature for predicting prognosis and indicates immune microenvironment infiltration in stomach adenocarcinomas.

Gastric adenocarcinoma (STAD) is the most prevalent malignancy of the human digestive system and the fourth leading cause of cancer-related death. Calcium pools, especially Ca2+ entry (SOCE) for storage operations, play a crucial role in maintaining intracellular and extracellular calcium balance, influencing cell activity, and facilitating tumor progression. Nevertheless, the prognostic and immunological value of SOCE in STAD has not been systematically studied. The objective of this study was to develop a risk model for SOCE signature and to explore its correlation with clinical characteristics, prognosis, tumor microenvironment (TME), as well as response to immunotherapy, chemotherapy, and targeted drugs. We used the TCGA, GEO (GSE84437 and GSE159929), cBioPortal and TIMER databases to acquire mRNA expression data for STAD, along with patient clinical indicators, single-cell sequencing data, genomic variation information, and correlations of immune cell infiltration. An analysis of SOCE genes based on tumor vs. normal tissue comparisons, pan-cancer dimension, single-cell sequencing, DNA mutation, and copy number variation revealed that SOCE genes significantly impact the survival of STAD patients and are differentially involved in the immune response. SOCE co-expressed genes were identified by Pearson analysis, and subsequently protein-protein interaction (PPI) and gene function enrichment analysis indicated that coexpressed genes were associated with multicellular pathways. Based on TCGA and GSE84437 datasets, a multifactor Cox proportional hazard regression analysis was conducted to identify SOCE co-expressed genes associated with overall survival in STAD patients. Several mRNA prognostic genes, including PTPRJ, GPR146, LTBP3, FBLN1, EFEMP2, ADAMTS7 and LBH, were identified, which could be used as effective prognostic predictors for STAD patients. In both training and test datasets, receiver operating characteristic (ROC) curves were utilized to evaluate and illustrate the predictive capability of this characteristic in forecasting overall survival of STAD patients. The qPCR and human protein atlas (HPA) were employed to assess mRNA expression and protein levels. Furthermore, the ESTIMATE, TIMER, CIBERSORT, QUANTISEQ, MCPCOUNTER, xCell and EPIC algorithms were utilized to perform immune score and analyze immune cell infiltration. It effectively revealed the difference in prognosis and immune cell infiltration in TME between high-risk and low-risk groups based on the risk signature associated with SOCE. Notably, significant differences in tumor immune dysfunction and rejection (TIDE) scores between the two groups, suggesting that patients in the low-risk group may exhibit a more favorable response to ICIS treatment. The GDSC database and R packages for predictive analysis were utilized to analyze responses to chemotherapy and targeted drugs in high-risk and low-risk groups. In summary, the 7-gene signature associated with SOCE serves as a significant biomarker for evaluating the TME and predicting the prognosis of STAD patients. In addition, it may provide valuable insights for developing effective immunotherapy and chemotherapy regiments for patients with STAD.

Predictive models for heat stress assessment in Holstein dairy heifers using infrared thermography and machine learning.

Heat stress is a condition that impairs the animal's productive and reproductive performance, and can be monitored by physiological and environmental variables, including body surface temperature, through infrared thermography. The objective of this work is to develop computational models for classification of heat stress from respiratory rate variable in dairy cattle using infrared thermography. The database used for the construction of the models was obtained from 10 weaned heifers, housed in a climate chamber with temperature control, and submitted to thermal comfort and heat wave treatments. Physiological and environmental data were collected, as well as thermographic images. The machine learning modeling environment used was IBM Watson, IBM's cognitive computing services platform, which has several data processing and mining tools. Classifier models for heat stress were evaluated using the confusion matrix metrics and compared to the traditional method based on Temperature and Humidity Index. The best accuracy obtained for classification of the heat stress level was 86.8%, which is comparable to previous works. The authors conclude that it was possible to develop accurate and practical models for real-time monitoring of dairy cattle heat stress.