MSR149 An AI-Powered RAG Based Framework for Data Extractions in Systematic Literature Reviews

ObjectivesOur main objective is to assess the inter-reviewer reliability (IRR) reported in published systematic literature reviews (SLRs). Our secondary objective is to determine the expected IRR by authors of SLRs...

Requirements engineering (RE) is an initial activity in the software engineering process that involves many users. The involvement of various users in the RE process raises ambiguity and vagueness in requirements modeling. In addition, traditional RE is a time-consuming activity. Therefore various studies have been conducted to support process automation on RE. This paper conducts a systematic literature review (SLR) to obtain information about RE automation related to RE activities, methods/models, tools, and domains. SLR is done through 5 main stages: definition of research questions, conducting the search, screening for relevant papers, data extraction, mapping, and analysis. The data extraction and mapping are carried out on 155 relevant publications from 2016 to 2022. Based on the results from SLR, around 53% of the research focuses on RE automation in analysis and specifications, 40% focuses on elicitation, validation, and requirements management, and 7% focuses on requirements quality. NLP is the most used method in elicitation and specification, while for analysis, machine learning, NLP, and goal-oriented models are mostly used in automatic RE. Furthermore, many papers use specific models and methods for validation and requirements management. From the domain analysis results, it is obtained that more than half of the papers contribute directly to the RE domain, and some contribute to the development of RE automation in the software application domain.

This systematic literature review (SLR) delves deep into the body of knowledge in Architectural Education where Vedic principles have been used in the context of popular learning theories. The purpose here is to elicit information about the theories of learning and identify the most prominent theories so that the nature of research undertaken so far can be classified based on the contribution of the theories, research focus, and research type. Further, after screening the literature, data extraction and synthesis is carried out leading to the identification of research gaps. Additionally, the factors that emerge through the selected literature have been grouped with their associated variables to provide a future direction for researchers to develop a framework for seamlessly integrating Vedic Architecture (VA) principles and practices into the architectural curriculum. The research methodology utilized in this study adopts an SLR approach characterized by deductive reasoning based on evidence. This deliberate choice aims to ensure a transparent and logical process, minimizing bias through extensive literature searches. The objective is to reach well-founded decisions, procedures, and conclusions that address the specific research questions posed. This review identified that there were four prominent theories used in the context of Architectural education using VA. Experiential Learning Theory (ELT) leads with 31% of the total 97 papers followed by Constructivist Learning Theory (CLT) (26%), Cultural-Historical Activity Theory (CAT) (24%), and Transformative Learning Theory (TLT) with 19 papers (19%). In research focus based classification, model development-based papers (55.7%) dominated the literature. In the classification of research type there were a higher number of papers on empirical research (36.1%). Six key research gaps have been identified that future researchers can attempt to address or fill. Finally, six major factors have been derived from the papers reviewed in this SLR, which could form the foundation for the development of a VA-based educational model. The SLR will assist practitioners and researchers in determining the key factors which need to be considered while developing a holistic model of VA based curriculum in architectural education. The limitation could be the focus laid on only four theories which dominated the contemporary research literature ignoring the other theories. The research is an original contribution to the knowledge base considering the literature from the past 25 years, the period during which the research in VA in architectural education has been active globally. The value addition is in terms of the identification of the underpinning theories to be considered in the development of a holistic model.

Type-III vasa previa (VP) is a rare form of VP, not necessarily associated with other placental or vascular anomalies, in which aberrant vessels run from the placenta to the amniotic membranes, near the internal cervical os, before returning to the placenta. Early diagnosis of Type-III VP is important but technically challenging. The objective of this study was to gather the current available evidence on the perinatal diagnosis and outcome of Type-III VP. A systematic review of the literature on the perinatal diagnosis of atypical Type-III VP was carried out in PubMed, MEDLINE and EMBASE accordingto PRISMA guidelines from inception to March 2023. Data extraction and tabulation were performed by two operators and checked by a third senior author. The quality of the included studies was evaluated using the National Institutes of Health tool for the quality assessment of case-series studies. Our local ultrasound database was searched for previously unreported recent cases. Characteristics of prenatally and postnatally diagnosed Type-III VP, including clinical features and perinatal outcomes, were summarized using descriptive statistics. Eighteen cases of Type-III VP were included, of which 16 were diagnosed prenatally (14 cases were retrieved from 10 publications and two were unpublished cases from our center) and two were diagnosed postnatally (retrieved from two publications). All prenatal cases were diagnosed on transvaginal ultrasound at a mean gestational age of 29 weeks (median, 31 weeks; range, 19-38 weeks). Conception was achieved with in-vitro fertilization in 4/16 (25.0%) cases. There were no prenatal symptoms in 15/18 (83.3%) cases, while in two (11.1%) cases there was vaginal bleeding and in one (5.6%) preterm labor occurred. In 15/18 (83.3%) cases, at least one placental abnormality was observed, including low-lying insertion (9/17), succenturiate or accessory lobe (1/17), velamentous cord insertion (3/18) and marginal insertion (9/18). All prenatally diagnosed cases were liveborn and were delivered by Cesarean section before rupture of membranes at a median gestational age of 35 weeks (range, 32-38 weeks) without neonatal complications. Emergency Cesarean section was performed in 2/16 (12.5%) cases with a prenatal diagnosis and 1/2 (50.0%) cases with a postnatal diagnosis (P = 0.179). Among those with data available, an Apgar score of ≤ 7 was observed in the prenatally vs postnatally diagnosed group in 5/13 vs 1/1 cases, respectively, at the 1-min evaluation and 3/13 vs 1/1 cases, respectively, at the 5-min evaluation. The prenatal diagnosis of Type-III VP is challenging, with few cases reported in the literature; however, it is crucial for minimizing the risk of adverse outcome by enabling early-term elective Cesarean delivery prior to rupture of membranes. Given that clinical manifestations and risk factors are non-specific, and that Type-III VP cannot be excluded when there is a normal cord insertion or a singular placental mass, systematic screening by transvaginal ultrasound in the general pregnant population is recommended, particularly in those with a low-lying or morphologically abnormal placenta and those who conceived using assisted reproductive technology. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

The overwhelming volume of data generated online continuous to grow at an exponential and unprecedented rate. Over 80% of such data is unstructured. Scientific research publications constitute a significant portion of such unstructured data. Systematic literature review (SLR) activity is a rigorous and challenging process. The key challenge in SLR is the automatic extraction of the relevant data from the sheer volume of research publications. Lack of a unified framework has been identified as the key problem. A canonical model, based on the structure of the papers was proposed as the framework for data extraction purposes in SLR. Implemented as a classification problem, traditional machine learning models were used to realise the canonical model. A good accuracy was reported in these traditional models. However, there is room for improvement. This paper presents the result of the work on the same problem using convolutional neural network (CNN), which is more sophisticated (deeper). The results show an improvement over the traditional machine learning models with an accuracy of 85%. Unlike the previous CNN NLP works, this work also demonstrates the application of CNN on a bigger NLP dataset such as the data from the scientific research publications. The result also shows that the CNN performs even better in NLP tasks with bigger datasets.

Fibroids and infertility: an updated systematic review of the evidence

Purpose: The goal of this study is to map the current state of academic knowledge on Industry 5.0 by identifying key technologies, required competencies, and emerging thematic areas through a systematic literature review. Based on this analysis, the study proposes a conceptual framework that synthesizes these findings to support future research and enhance understanding of this evolving industrial paradigm—particularly by identifying critical capabilities for implementing human-centric, sustainable, and resilient strategies aligned with the Sustainable Development Goals (SDGs). Methodology: A systematic literature review was conducted by querying the Scopus and Web of Science databases. This comprised eight steps designed to comprehensively understand existing literature on I5.0. In total, 470 papers were assessed, 112 of which qualified for subsequent data extraction and analysis. Findings: The study organizes existing literature into five key thematic domains that structure current academic knowledge and guide future research on Industry 5.0: (1) Technologies and Digital Development; (2) Education, Skills, and Knowledge, alongside People, Ethics, Health, and Safety; (3) Society, Laws, and Government; (4) Benefits, Challenges, and General Factors, in conjunction with Organizational Strategy and Management; and (5) Sustainability. These domains offer a comprehensive perspective on the core components and interdependencies that characterize the Industry 5.0 paradigm. The findings also indicate that future research should prioritize empirical studies that examine how human-centricity, resilience, and sustainability are being operationalized within real-world industrial contexts. Implications: This study highlights specific gaps for future research, particularly the need to explore how human-centricity, sustainability, and resilience are integrated in practice. For organizations, the findings provide clarity on key technologies, competencies, and strategic priorities, helping guide transitions aligned with the SDGs. Originality: While grounded in a systematic literature review, this study offers originality by structuring dispersed academic knowledge into five thematic domains that reflect the evolving nature of Industry 5.0. The resulting framework does not claim to be a new theoretical model but adds value by connecting concepts, technologies, competencies, and implementation challenges in a coherent and actionable structure. This contribution helps scholars frame future research and offers organizations a clearer path to navigating the Industry 5.0 landscape.

Purpose: This article aims to explore the relationship between strategic planning and e-government, investigating how effective strategic planning can improve e-government initiatives and enhance public service quality. By conducting a systematic literature review (SLR), the article assesses the application of strategic approaches to the digital transformation of public administration. Theoretical Reference: The study builds on the theoretical framework of e-government, digital government, and the strategic management of ICT. Key references include B. Kitchenham's guidelines for systematic reviews and insights from the literature on the role of strategic planning in modernizing public services and enhancing government efficiency. Method: A systematic literature review (SLR) was conducted following B. Kitchenham's (2007) guidelines. Primary studies were selected based on relevance, quality, and coverage of strategic planning and e-government topics. The research protocol included search strategies, selection criteria, data extraction, and synthesis from high-quality digital sources such as Scopus, ProQuest, and Science Direct. Results and Conclusion: The findings reveal that strategic planning is integral to the success of e-government programs, driving improvements in accessibility, transparency, and efficiency in public services. The study highlights that countries with more robust strategic frameworks, such as Indonesia and China, are at the forefront of implementing effective e-government systems. The integration of ICT into strategic government planning results in enhanced public trust and service delivery. Implications of Research: The research provides a comprehensive reference for policymakers and academics on the importance of incorporating strategic planning into e-government initiatives. The insights can guide the design and implementation of more efficient and citizen-focused e-government systems. Originality/Value: This article offers an original contribution by systematically reviewing the literature on the relationship between strategic planning and e-government, filling a gap in the current understanding of how these elements interact to improve public sector performance in the digital age.

Poor students’ academic performance at all educational level nowadays is a significant challenge to educational stakeholders globally. A country’s development is directly connected to the academic performance of its student. There are multiple factors that can influence students’ academic performance, however, teachers’ instructional strategy play a significant role. Immersive education is a pedagogical approach that uses virtual reality, augmented reality, mixed reality, augmented virtuality, 3D and 360 degree immersive technologies for knowledge and skill acquisition. First, the paper introduce immersive education and its categories to distinguish between these technologies. This study was guided by preferred reporting Items for systematic reviews and Meta-Analyses (PRISMA) protocol. The review protocol was designed to guide the conduct of the systematic literature review. The review method comprised of research questions, inclusion and exclusion criteria, literature search strategy, study selection process, data extraction, data synthesis and report writing. This study evaluated empirical literature published in research community on immersive education from 2020 to 2024 by systematic literature review. The findings shows that despite the novelty and importance of immersive education, studies on this innovation is on decline in recent years. Therefore, it is recommended that further research be conducted on this technologies especially on augmented virtuality, 3D and 360 degree immersive technologies to leverage on its benefits in teaching and learning in education systems. .

Software can significantly facilitate the management of the complete systematic literature review process (SLR). However, most specialized software for use in SLR processes is designed to meet the requirements of the health and medical sciences and software engineering, and there is a need for dedicated software for the specific research requirements of the social sciences. Furthermore, most of the software currently used is closed and the open source code alternatives require personnel with expertise in configuration and setup.We present Buhos, an application for managing the complete process of systematic literature reviews that is web-based and developed in Ruby. It offers functionalities for supporting the process of searching, screening, data extraction and reporting. Buhos can be used locally through an in-house web server, as well as in a distributed manner, integrated with other online services.

Cardiovascular disease remains a significant global health burden. Bempedoic acid is a novel, oral adenosine triphosphate-citrate lyase inhibitor that lowers low-density lipoprotein cholesterol (LDL-C). While randomized controlled trials (RCTs) have established its efficacy and safety, evidence from real-world clinical practice is needed. A systematic literature review (SLR) was conducted to identify studies reporting real-world use of bempedoic acid as monotherapy, in fixed dose combination with ezetimibe, or in combination with any other lipid lowering therapy (LLT). MEDLINE, EMBASE, and Cochrane Library were searched from inception to February 19, 2025. Two reviewers independently screened studies, with discrepancies resolved by a third. Data extraction and validation were conducted, and the risk of bias assessed using the Newcastle-Ottawa Scale. Of 269 records, 28 reports on 22 unique studies met the eligibility criteria. Most studies evaluated LDL-C changes from baseline after initiation of bempedoic acid; one pragmatic randomized trial was identified. Bempedoic acid achieved LDL-C reductions of 15% to 39% when added to maximally tolerated statins, 22% to 38% in statin intolerant cohorts, and 18% to 42% in mixed statin intolerant cohorts. Safety data was limited; treatment discontinuation ranged from 9% to 36%, with higher rates in cohorts with greater statin-intolerance. This SLR shows bempedoic acid, with or without other LLTs, achieves a minimum of approximately 20% LDL-C reductions, consistent with RCTs. Data suggests it may be effective as an adjunct to statins and as an oral alternative for statin-intolerant patients.

Chronic sequelae and severe complications of norovirus infection: A systematic review of literature

BackgroundGenerative artificial intelligence (GenAI) shows promise in automating key tasks involved in conducting systematic literature reviews (SLRs), including screening, bias assessment and data extraction. This potential automation is increasingly relevant as pharmaceutical developers face challenging requirements for timely and precise SLRs using the population, intervention, comparator and outcome (PICO) framework, such as those under the impending European Union (EU) Health Technology Assessment Regulation 2021/2282 (HTAR). This proof-of-concept study aimed to evaluate the feasibility, accuracy and efficiency of using GenAI for mass extraction of PICOs from PubMed abstracts.Methodss were retrieved from PubMed using a search string targeting randomised controlled trials. A PubMed clinical study ‘specific/narrow’ filter was also applied. Retrieved abstracts were processed using the OpenAI Batch application programming interface (API), which allowed parallel processing and interaction with Generative Pre-trained Transformer 4 Omni (GPT-4o) via custom Python scripts. PICO elements were extracted using a zero-shot prompting strategy. Results were stored in CSV files and subsequently imported into a PostgreSQL database.ResultsThe PubMed search returned 682,667 abstracts. PICOs from all abstracts were extracted in < 3 h, with an average processing time of 200 s per 1000 abstracts. A total of 395,992,770 tokens were processed, with an average of 580 tokens per abstract. The total cost was $3390. On the basis of a random sample of 350 abstracts, human verification confirmed that GPT-4o accurately and comprehensively extracted 342 (98%) of all PICOs, with only outcome elements rarely missed.ConclusionsUsing GenAI to extract PICOs from clinical study abstracts could fundamentally transform the way SLRs are conducted. By enabling pharmaceutical developers to anticipate PICO requirements, this approach allows for proactive preparation for the EU HTAR process, or other health technology assessments (HTAs), streamlining efficiency and reducing the burden of meeting these requirements.

Abstract---Data mining is extracting data in processing information with the aim of finding important patterns in piles of data. With data mining we can classify, predict, and make a decision. Classification is a way of grouping a data according to the characteristics of a data to be classified. In the process, the classification is divided into two, namely manually and with the help of technology. Manual classification is a classification carried out by humans without the help of technology, while classification with the help of technology has several algorithms, including C4.5, Naive Bayes, Fuzzy, and K-Nearest Neighbor. 5 for classification, a systematic approach is used in the form of a systematic literature review (SLR). SLR is defined as a process in which the identification, assessment, and interpretation of all available research evidence is carried out with the aim of answering a number of research questions

BackgroundGiven the sudden and unexpected nature of an emergency caesarean section (EmCS) coupled with an increased risk of psychological distress, it is particularly important to understand the psychosocial outcomes for women. The aim of this systematic literature review was to identify, collate and examine the evidence surrounding women’s psychosocial outcomes of EmCS worldwide.MethodsThe electronic databases of EMBASE, PubMed, Scopus, and PsycINFO were searched between November 2017 and March 2018. To ensure articles were reflective of original and recently published research, the search criteria included peer-reviewed research articles published within the last 20 years (1998 to 2018). All study designs were included if they incorporated an examination of women’s psychosocial outcomes after EmCS. Due to inherent heterogeneity of study data, extraction and synthesis of both qualitative and quantitative data pertaining to key psychosocial outcomes were organised into coherent themes and analysis was attempted.ResultsIn total 17,189 articles were identified. Of these, 208 full text articles were assessed for eligibility. One hundred forty-nine articles were further excluded, resulting in the inclusion of 66 articles in the current systematic literature review. While meta-analyses were not possible due to the nature of the heterogeneity, key psychosocial outcomes identified that were negatively impacted by EmCS included post-traumatic stress, health-related quality of life, experiences, infant-feeding, satisfaction, and self-esteem. Post-traumatic stress was one of the most commonly examined psychosocial outcomes, with a strong consensus that EmCS contributes to both symptoms and diagnosis.ConclusionsEmCS was found to negatively impact several psychosocial outcomes for women in particular post-traumatic stress. While investment in technologies and clinical practice to minimise the number of EmCSs is crucial, further investigations are needed to develop effective strategies to prepare and support women who experience this type of birth.