Carcinogenic health outcomes associated with endocrine disrupting chemicals exposure in humans: A wide-scope analysis.

Endocrine-disrupting chemicals (EDCs) are persistent and pervasive compounds that pose serious risks. Numerous studies have explored the effects of EDCs on human health, among which tumors have been the primary focus. However, because of study design flaws, lack of effective exposure levels of EDCs, and inconsistent population data and findings, it is challenging to draw clear conclusions on the effect of these compounds on tumor-related outcomes. Our study is the first to systematically integrate observational studies and randomized controlled trials from over 20 years and summarize over 300 subgroup associations. We found that most EDCs promote tumor development, and that exposure to residential environmental pollutants may be a major source of pesticide exposure. Furthermore, we found that phytoestrogens exhibit antitumor effects. The findings of this study can aid in the development of global EDCs regulatory health policies and alleviate the severe risks associated with EDCs exposure.

The relationship between periodontal disease and cancer: Insights from a Systematic Literature Network Analysis.

This paper investigates the relationship between periodontal disease and various cancer types. It provides a comprehensive overview of the existing knowledge about the interaction between periodontal disease and carcinogenesis, explores the underlying biological mechanisms of this connection, and consider the impact of these findings on healthcare practices and future research directions. Utilizing Systematic Literature Network Analysis, which combines bibliometric analysis with Systematic Literature Review, this study analyzes 164 documents from 2000 to 2023. Focus is placed on the 38 most globally cited papers, enabling a targeted and comprehensive analysis of the predominant research within this scope. This review highlights that colorectal, oral, pancreatic, lung, and gastrointestinal cancers have consistent associations with periodontal disease. On the other hand, hematological, breast and prostate cancers show associations with periodontal disease, but these links are less pronounced and more variable, indicating the need for targeted research in these domains. These insights emphasize the necessity for a multidisciplinary healthcare approach, recognizing the systemic implications of periodontal disease.

Case report and literature analysis: pancreatic hepatoid carcinoma with multiple lymph node metastases progressing to liver metastasis after pancreaticoduodenectomy.

Hepatoid carcinoma is an extrahepatic primary tumor displaying characteristics reminiscent of hepatocellular carcinoma differentiation, which is found in various organs, such as the stomach, ovaries, gallbladder, and pancreas. Reports of pancreatic hepatoid carcinoma remain scarce. Consequently, understanding of this disease remains a priority, with no established consensus on its diagnosis and management. Here, we reported the case of a 45-year-old woman diagnosed with hepatoid carcinoma located in the pancreatic head, accompanied by multiple lymph node metastases. Following pancreaticoduodenectomy, the patient developed liver metastases within 3 months. Subsequently, she underwent adjuvant therapy consisting of Teysuno and Durvalumab following microwave ablation for the liver metastases. Remarkably, the patient has survived for one year without significant disease progression. This case underscores the potential efficacy of immunotherapy as a promising treatment option for pancreatic hepatoid carcinoma. Further research and clinical trials are warranted to explore the optimal management strategies for this rare and challenging malignancy.

Clinical and biochemical characteristics, and outcome in 33 patients with ceftriaxone-induced liver injury.

PURPOSE: To summarize the clinical and biochemical characteristics of patients with ceftriaxone-induced liver injury and guide the selection of safe medication. METHODS: Retrieved domestic and foreign databases from inception to October 2023, collected case data conforming to ceftriaxone-induced liver injury, and statistically analyzed the data. RESULTS: A total of 617 articles were retrieved, and 16 articles with 33 cases (10 children, 23 adults) were included. Males represented 60% (18/30), with a male-to-female ratio of 1.5:1. The age of onset ranged from 2 days to 96 years, with 15 of 23 adults (65%) over 55 years old. The time from ceftriaxone use to liver injury fluctuated between 0.5 and 47 days. Only 9 patients (27.3%, 9/33) had clinical symptoms, and the clinical classification was dominated by cholestatic injury (46.2%, 12/26). There was a significant difference in the clinical classification of ceftriaxone-induced liver injury between children and adults (P = 0.0126), with hepatocellular injury predominating in children and cholestatic injury predominating in adults. The severity of liver injury was mainly mild (66.7%, 12/18). Peak values of alanine aminotransferase ranging from 228.5 to 8098 U/L, aspartate aminotransferase ranging from 86.7 to 21575 U/L, alkaline phosphatase ranging from 143 to 2434 U/L, and total bilirubin ranging from 3.35 to 66.1 mg/dL. There was a significant difference in peak values of alkaline phosphatase between children and adults (P = 0.027), with a higher peak value of alkaline phosphatase in adults (1039 ± 716.4 U/L vs. 257 ± 134.9 U/L). Patients with normal imaging examinations accounted for the majority (61.5%, 7/13). The prognosis of 32 patients (97%, 32/33) was good, and one child with sickle cell anemia who developed immune hemolysis, progressive renal failure, and acute liver injury after using ceftriaxone died in the end. CONCLUSION: Ceftriaxone-induced liver injury can occur at any age, with a higher risk in the elderly, and age may be related to the clinical classification. Although the clinical manifestations are not specific, close monitoring of liver biochemical indicators during the use can detect liver injury early. Most cases have a good prognosis, but for people with concomitant sickle cell anemia, it is necessary to be vigilant about the occurrence of severe hemolytic anemia.

Case literature analysis of Fournier's gangrene caused by sodium-glucose protein-2 inhibitors.

Objective: To analyze the clinical characteristics and correlation of Fournier's gangrene induced by sodium-glucose cotransporter protein-2 (SGLT-2) inhibitors, providing references for safe clinical drug use. Methods: The CNKI, WanFang, and PubMed databases were searched, and relevant documents were collected and statistically analyzed. The basic information of patients, drug use information, adverse reactions and outcomes were extracted and analyzed. Results: A total of 12 patients (8 males and 4 females) were included, with an average age of 55.6 years (ranging from 34 to 72 years). SGLT-2 inhibitors associated with Fournier's gangrene include empagliflozin (5 cases), dapagliflozin (5 cases), and canagliflozin (2 cases). Among them, 10 cases reported the time of first medication, ranging from 1 month to 6 years for the occurrence of adverse reactions. The most common concomitant drug was metformin (7 cases). Adverse reactions mainly manifested as redness, swelling and pain in the buttocks, perineum, perianal, scrotum and other positions, accompanied by an increased white blood cell count. Following surgery and antibiotic treatment, all patients showed improved. Conclusion: Fournier's gangrene induced by SGLT-2 inhibitors is rare. If patients using SGLT-2 inhibitors are suspected of having Fournier's gangrene, it is recommended to discontinue the drugs immediately and initiate active treatment to ensure clinical safety.

Quality and Effectiveness of AI Tools for Students and Researchers for Scientific Literature Review and Analysis.

This study scrutinizes free AI tools tailored for supporting literature review and analysis in academic research, emphasizing their response to direct inquiries. Through a targeted keyword search, we cataloged relevant AI tools and evaluated their output variation and source validity. Our results reveal a spectrum of response qualities, with some tools integrating non-academic sources and others depending on outdated information. Notably, most tools showed a lack of transparency in source selection. Our study highlights two key limitations: the exclusion of commercial AI tools and the focus solely on tools that accept direct research queries. This raises questions about the potential capabilities of paid tools and the efficacy of combining various AI tools for enhanced research outcomes. Future research should explore the integration of diverse AI tools, assess the impact of commercial tools, and investigate the algorithms behind response variability. This study contributes to a better understanding of AI's role in academic research, emphasizing the importance of careful selection and critical evaluation of these tools in academic endeavors.

Dataset for five recent years (2019 - 2023) agarwood essential oil research trends: A bibliometric analysis.

Research on Agarwood Essential Oils (AEO) has undergone dynamic evolution, propelled by its diverse applications in industries such as perfumery, pharmaceuticals, and alternative medicine. The aromatic richness and therapeutic potential of these essential oils have sparked a surge in research interest. Despite extensive exploration, there is a need for a comprehensive analysis of trends, patterns, and the impact of AEO research to provide insights for future studies and applications.This work presents a meticulously curated dataset encompassing the last five years of Agarwood Essential Oil (AEO) research trends. Sourced from two reputable scholarly databases, namely Web of Science and Scopus, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol, analyzing the data using Biblioshiny, and spanning the period from 2019 to 2023, the dataset is designed to facilitate a comprehensive understanding of the evolving landscape of AEO studies. It covers a wide array of parameters, including authorship, subject areas, citations, source titles, wordcloud, and keywords. This dataset is made available to researchers, institutions, and decision-makers to provide insights into the academic debates on agarwood oil studies, allowing for a nuanced understanding of the progression of scholarly endeavors within the field. The dataset aims to serve as a valuable resource for researchers, policymakers, and industry stakeholders interested in the multifaceted applications of essential oils. The structured and comprehensive nature of the dataset makes it a valuable asset for exploring historical trends, identifying key contributors, and fostering collaborative initiatives within the AEO research domain.

Factors Underlying Vaccine Hesitancy and Their Mitigations in Saudi Arabia: Protocol for a Systematic Review.

BACKGROUND: Vaccine hesitancy is a growing concern in Saudi Arabia, impacting even well-educated parents. The decision-making process involves various factors such as accessibility, trustworthy information, and the influence of social networks, reflecting a complex interplay of emotional, cultural, social, spiritual, and political dimensions. OBJECTIVE: This review seeks to evaluate the prevalence and trends of vaccine hesitancy, identify contributing factors, and explore potential solutions to enhance immunization rates. This review aligns with global concerns, as the World Health Organization has identified vaccine hesitancy as a top global health threat. METHODS: Our systematic review will follow the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and PICOS (Population, Intervention, Comparison, Outcomes, and Study) criteria for comprehensive assessment. We will conduct a thorough search across various databases, encompassing a wide range of vaccines, and pay special attention to vaccination campaigns and refusals. Inclusion criteria involve descriptive, observational, and analytical studies focusing on factors influencing vaccine acceptance or hesitancy. The study will use the Crowe Critical Appraisal Tool for quality assessment and perform a narrative synthesis to summarize findings thematically. RESULTS: This systematic review is expected to unveil the prevalence and trends of vaccine hesitancy in diverse populations in Saudi Arabia, shedding light on cultural, religious, and social factors contributing to hesitancy. It aims to assess the effectiveness of implemented strategies, enable regional and global comparisons, and provide implications for tailored vaccination policies. Additionally, the review may pinpoint research gaps, guiding future investigations to address and mitigate vaccine hesitancy effectively. CONCLUSIONS: The findings are expected to have direct policy implications and guide interventions to strengthen vaccination programs and improve public health outcomes. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/54680.

A review of the definition, influencing factors, and mechanisms of rapid composting of organic waste.

Composting is a traditional method of treating organic waste. A growing number of studies have been focusing on accelerating the process to achieve "rapid composting." However, the specific definition and influencing factors of rapid composting remain unclear. Therefore, we aimed to gather more insight into the features of rapid composting by reviewing the literature concerning organic waste composting published in the Web of Science database in the past 5 years. We selected 1615 sample studies with "composting" as the subject word and analyzed the effective composting time stated in each study. We defined rapid composting within 15 days using the median test and quartile method. Based on this definition, we summarized the influencing factors of "rapid composting," namely materials, reactors, temperature, and microorganisms. Finally, we summarized two mechanisms related to humus formation during organic waste rapid composting: high temperature-promoting maturation and microbial driving mechanisms. This literature review compiled useful references to help promote the development of rapid composting technology and related equipment.

Literature analysis of ADR after the listing of apatinib / 中国药房

OBJECTIVE To explore the characteristics and regulations of adverse drug reactions （ADR） caused by apatinib， and to provide a reference for the safe use of apatinib in clinic. METHODS Case and group reports on ADR and safety evaluation of apatinib were retrieved from Chinese and English databases such as CNKI， Wanfang medical network， VIP and PubMed since its listing in 2014， literature data were extracted and statistically analyzed after screening. RESULTS Totally 101 cases were included， involving 221 ADR. In the above cases， the male-to-female ratio was 1.24∶1， with the highest proportion of patients aged 51 to 70 years， most of the patients were given a dose of 500 mg or more， and the patients given low dose of apatinib combined with other antitumor drugs were also likely to have ADR. One to two types of adverse reaction were the most common， while the types could reach up to six. Most ADR occurred within 30 days after medication， and the systems/organs involved were mainly the cardiovascular system damage，skin and its accessories damage， gastrointestinal system damage and urinary system damage； the main clinical manifestations were hypertension/aggravation，hand-foot syndrome，abdominal pain diarrhea and albuminuria， etc. Hypertension/aggravation， hand-foot syndrome and myelosuppression were the most common serious ADR. Most ADR could be improved/cured by suspension of administration， dose downregulation and symptomatic treatment. All 4 patients who died had underlying diseases， and their ECOG scores all ≥2 points. Special ADR （such as reversible posterior encephalopathy syndrome， psychiatric disorders， and cognitive impairment） were mostly caused by apatinib itself， or may be caused by apatinib in combination with the primary or underlying disease. CONCLUSIONS Advanced age， large dose， combination medication， underlying diseases and poor physical condition might be the high risks for ADR caused by apatinib. It is recommended to monitor the blood pressure，urine protein and skin of hands and feet of all patients with medication on a daily basis，pay attention to the occurrence of special ADR， and timely detect abnormal states and give effective intervention，so as to avoid the aggravation of ADR and other secondary ADR.

Mining the Health Disparities and Minority Health Bibliome: A Computational Scoping Review and Gap Analysis of 200,000+ Articles.

Without comprehensive examination of available literature on health disparities and minority health (HDMH), the field is left vulnerable to disproportionately focus on specific populations or conditions, curtailing our ability to fully advance health equity. Using scalable open-source methods, we conducted a computational scoping review of more than 200,000 articles to investigate major populations, conditions, and themes in the literature as well as notable gaps. We also compared trends in studied conditions to their relative prevalence in the general population using insurance claims (42MM Americans). HDMH publications represent 1% of articles in MEDLINE. Most studies are observational in nature, though randomized trial reporting has increased five-fold in the last twenty years. Half of all HDMH articles concentrate on only three disease groups (cancer, mental health, endocrine/metabolic disorders), while hearing, vision, and skin-related conditions are among the least well represented despite substantial prevalence. To support further investigation, we also present HDMH Monitor, an interactive dashboard and repository generated from the HDMH bibliome.

Evidence-Based Medicine and Pharmacotherapy Content Alignment.

OBJECTIVE: When effectively executed, content alignment can aid student performance in associated courses. Limited research exists for content alignment of evidence-based medicine (EBM) and pharmacotherapy courses. This study assesses the impact of EBM and pharmacotherapy course alignment on student performance. METHODS: Content alignment included assignment of 6 landmark trials in EBM coursework. The articles were identified by pharmacotherapy instructors as "landmark" to management of associated diseases in the aligned pharmacotherapy semester. Articles were the basis for quizzes over skills taught in the EBM course and were referenced during pharmacotherapy lectures. RESULTS: During the alignment semester, students were more likely to cite specific guidelines and/or primary literature to rationalize pharmacotherapeutic plans on examinations compared with the prealignment period (54% vs 34%). Overall, pharmacotherapy case performance and plan rationale scores were significantly higher in the alignment semester compared with prealignment. Student performance on the Assessing Competency in Evidence-Based Medicine tool improved from the start of the semester (8.64, SD 1.66) to the end (9.5, SD 1.49; mean score +0.86). Comfort in applying EBM analysis to primary literature increased significantly between the first and final assignments, with 6.7% and 71.7% of students self-reporting a high degree of confidence, respectively. Students (73%) reported an enhanced understanding of pharmacotherapy due to alignment compared with a previous semester of pharmacotherapy without alignment. CONCLUSION: The use of landmark trial assignments to align EBM and pharmacotherapy coursework demonstrated a positive impact on student rationale for clinical decision-making and student confidence in evaluating primary literature.

Network Analysis and Natural Language Processing to Obtain a Landscape of the Scientific Literature on Materials Applications.

Recent progress in natural language processing (NLP) enables mining the literature in various tasks akin to knowledge discovery. Obtaining an updated birds-eye view of key research topics and their evolution in a vast, dynamic field such as materials science is challenging even for experienced researchers. In this Perspective paper, we present a landscape of the area of applied materials in selected representative journals based on a combination of methods from network science and simple NLP strategies. We found a predominance of energy-related materials, e.g., for batteries and catalysis, organic electronics, which include flexible sensors and flexible electronics, and nanomedicine with various topics of materials used in diagnosis and therapy. As for the impact calculated through standard metrics of impact factor, energy-related materials and organic electronics are again top of the list across different journals, while work in nanomedicine has been found to have a lower impact in the journals analyzed. The adequacy of the approach to identify key research topics in materials applications was verified indirectly by comparing the topics identified in journals with diverse scopes, including journals that are not specific to materials. The approach can be employed to obtain a fast overview of a given field from the papers published in related scientific journals, which can be adapted or extended to any research area.

An original template solution for FAIR scientific text mining.

This method paper presents a template solution for text mining of scientific literature using the R tm package. Literature to be analyzed can be collected manually or automatically using the code provided with this paper. Once the literature is collected, the three steps for conducting text mining can be performed as outlined below: •loading and cleaning of text from articles,•processing, statistical analysis, and clustering, and•presentation of results using generalized and tailor-made visualizations. The text mining steps can be applied to a single, multiple, or time series groups of documents. References are provided to three published peer reviewed articles that use the presented text mining methodology. The main advantages of our method are: (1) Its suitability for both research and educational purposes, (2) Compliance with the Findable Accessible Interoperable and Reproducible (FAIR) principles, and (3) Code and example data are made available on GitHub under the open-source Apache V2 license.

Thirty-year survey of bibliometrics used in the research literature of pain: Analysis, evolution, and pitfalls.

During the last decades, the emergence of Bibliometrics and the progress in Pain research have led to a proliferation of bibliometric studies on the medical and scientific literature of pain (B/P). This study charts the evolution of the B/P literature published during the last 30 years. Using various searching techniques, 189 B/P studies published from 1993 to August 2022 were collected for analysis-half were published since 2018. Most of the selected B/P publications use classic bibliometric analysis of Pain in toto, while some focus on specific types of Pain with Headache/Migraine, Low Back Pain, Chronic Pain, and Cancer Pain dominating. Each study is characterized by the origin (geographical, economical, institutional, …) and the medical/scientific context over a specified time span to provide a detailed landscape of the Pain research literature. Some B/P studies have been developed to pinpoint difficulties in appropriately identifying the Pain literature or to highlight some general publishing pitfalls. Having observed that most of the recent B/P studies have integrated newly emergent software visualization tools (SVTs), we found an increase of anomalies and suggest that readers exercise caution when interpreting results in the B/P literature details.

The 50 most-cited review papers on physical activity and depression: A bibliometric analysis.

A growing body of literature has demonstrated the preventive role of physical activity in depression, and relevant research is rapidly on the rise. The aim of this study was to conduct a bibliometric analysis of the 50 most-cited review papers on physical activity and depression, thus identifying important research topics and future research directions. METHODS: The 50 most-cited review articles were identified and extracted from the Web of Science Core Collection database (on 31st October 2022), and a bibliometric citation analysis was performed using the Microsoft Excel and VOSviewer software (Version 1.6.18). Information on the country, authors of publications, publishing journals, citations (i.e., total or annual), keywords, and other meaningful data was analysed comprehensively. RESULTS: The 50 most-cited review articles received, on average, 247.5 citations per article. Most review articles were from England, with contributions from some highly cited researchers and research teams. Western countries/regions, such as England, Australia, and the USA were the most influential in publishing review articles on physical activity and depression. The Journal of Affective Disorders and Cochrane Database of Systematic Reviews were the journals that published the most highly cited review articles on physical activity and depression. Important research topics on the literature on physical activity and depression focused on (1) different types of physical activity and depression; (2) intervention studies related to physical activity and depression; (3) fitness and physical activity levels in people with depression; (4) methodological analyses in physical activity and depression studies; and (5) the impact of physical activity on depression in different populations. CONCLUSION: This study reveals that review studies on physical activity and depression have great potential to develop further knowledge. This study also highlights some future research directions, which can serve to effectively advance the knowledge base.

Transportal Tibiotalocalcaneal Nail Ankle Arthrodesis: A Systematic Review of Initial Series.

Background: There is currently a scarcity of information and consensus for transportal (arthroscopic or fluoroscopic) joint preparation during tibiotalocalcaneal (TTC) fusion, and therefore this review aims to summarize the available techniques and to evaluate the outcomes after this procedure. Methods: A systematic electronic search of MEDLINE, EMBASE, and Web of Science was performed for all English-language studies published from their inception to April 4, 2022. All articles addressing arthroscopy in TTC nailing were eligible for inclusion. The PRISMA Checklist guided the reporting and data abstraction. Descriptive statistics are presented. Result: A total of 5 studies with 65 patients were included for analysis. All studies used arthroscopic portals for tibiotalar and subtalar joint preparation (in 4 studies) prior to TTC nailing, with 4 studies using an arthroscope and 1 study using fluoroscopy. The overall major complication rate was 13.8%; however, there was only 1 instance of deep wound infection (1.5%) and 4 instances of surgical site infections (6.2%). Full fusion was achieved in 86% of patients with an average time to fusion of 12.9 weeks. The mean American Orthopaedic Foot & Ankle Society (AOFAS) ankle-hindfoot score preoperatively was 34.0 and postoperatively was 70.5. Conclusion: Although limited by the number of studies, transportal joint preparation during TTC nail ankle fusion is associated with good rates of complications and successful fusion. Level of Evidence: Level III, systematic review of Level III-IV studies.

EvidenceMap: a three-level knowledge representation for medical evidence computation and comprehension.

OBJECTIVE: To develop a computable representation for medical evidence and to contribute a gold standard dataset of annotated randomized controlled trial (RCT) abstracts, along with a natural language processing (NLP) pipeline for transforming free-text RCT evidence in PubMed into the structured representation. MATERIALS AND METHODS: Our representation, EvidenceMap, consists of 3 levels of abstraction: Medical Evidence Entity, Proposition and Map, to represent the hierarchical structure of medical evidence composition. Randomly selected RCT abstracts were annotated following EvidenceMap based on the consensus of 2 independent annotators to train an NLP pipeline. Via a user study, we measured how the EvidenceMap improved evidence comprehension and analyzed its representative capacity by comparing the evidence annotation with EvidenceMap representation and without following any specific guidelines. RESULTS: Two corpora including 229 disease-agnostic and 80 COVID-19 RCT abstracts were annotated, yielding 12 725 entities and 1602 propositions. EvidenceMap saves users 51.9% of the time compared to reading raw-text abstracts. Most evidence elements identified during the freeform annotation were successfully represented by EvidenceMap, and users gave the enrollment, study design, and study Results sections mean 5-scale Likert ratings of 4.85, 4.70, and 4.20, respectively. The end-to-end evaluations of the pipeline show that the evidence proposition formulation achieves F1 scores of 0.84 and 0.86 in the adjusted random index score. CONCLUSIONS: EvidenceMap extends the participant, intervention, comparator, and outcome framework into 3 levels of abstraction for transforming free-text evidence from the clinical literature into a computable structure. It can be used as an interoperable format for better evidence retrieval and synthesis and an interpretable representation to efficiently comprehend RCT findings.

A Rare Case of Biliary Cryptococcosis Clinical Pharmacist Participation in Treatment and Pharmaceutical Care and Literature Review.

Biliary cryptococcosis infection is extremely rare and difficult for preoperative diagnosis. We report a rare case of 61-year-old woman with biliary cryptococcal infection. To explore the general rule and case characteristics of biliary cryptococcal infection and provide a reference for future diagnosis and treatment, we consulted the PubMed database for reported biliary cryptococcal infection from 1985 to 2021. Including the present one, we collected 12 reports, among which half were male and five were younger than 18 years old. Clinical manifestations were mainly jaundice, while in vitro examination revealed bile duct dilatation and bile duct stenosis. In 8 cases (66.67%), symptoms improved or healed after antifungal treatment. Although preoperative misdiagnosis of cryptococcal infection is high, the antifungal treatment is quite effective. Thus, early accurate diagnosis can effectively improve the cure rate of biliary cryptococcosis infected patients.

Development of benchmark datasets for text mining and sentiment analysis to accelerate regulatory literature review.

In the field of regulatory science, reviewing literature is an essential and important step, which most of the time is conducted by manually reading hundreds of articles. Although this process is highly time-consuming and labor-intensive, most output of this process is not well transformed into machine-readable format. The limited availability of data has largely constrained the artificial intelligence (AI) system development to facilitate this literature reviewing in the regulatory process. In the past decade, AI has revolutionized the area of text mining as many deep learning approaches have been developed to search, annotate, and classify relevant documents. After the great advancement of AI algorithms, a lack of high-quality data instead of the algorithms has recently become the bottleneck of AI system development. Herein, we constructed two large benchmark datasets, Chlorine Efficacy dataset (CHE) and Chlorine Safety dataset (CHS), under a regulatory scenario that sought to assess the antiseptic efficacy and toxicity of chlorine. For each dataset, ∼10,000 scientific articles were initially collected, manually reviewed, and their relevance to the review task were labeled. To ensure high data quality, each paper was labeled by a consensus among multiple experienced reviewers. The overall relevance rate was 27.21% (2,663 of 9,788) for CHE and 7.50% (761 of 10,153) for CHS, respectively. Furthermore, the relevant articles were categorized into five subgroups based on the focus of their content. Next, we developed an attention-based classification language model using these two datasets. The proposed classification model yielded 0.857 and 0.908 of Area Under the Curve (AUC) for CHE and CHS dataset, respectively. This performance was significantly better than permutation test (p < 10E-9), demonstrating that the labeling processes were valid. To conclude, our datasets can be used as benchmark to develop AI systems, which can further facilitate the literature review process in regulatory science.