Explore the vast range of titles available.

Large-language models (LLMs) show promise for automating evidence synthesis, yet head-to-head evaluations remain scarce. We benchmarked five state-of-the-art LLMs—openai/o1-mini, x-ai/grok-2-1212, meta-llama/Llama-3.3-70B-Instruct, google/Gemini-Flash-1.5-8B, and deepseek/DeepSeek-R1-70B-Distill—on extracting protocol details from transcranial direct-current stimulation (tDCS) trials enrolling older adults. A multi-LLM ensemble pipeline ingested ClinicalTrials.gov records, applied a structured JSON schema, and generated comparable outputs from unstructured text. The pipeline retrieved 83 aging-related tDCS trials—roughly double the yield of a conventional keyword search. Across models, agreement was almost perfect for the binary field brain stimulation used (Fleiss κ ≈ 0.92) and substantial for the categorical primary target (κ ≈ 0.71). Numeric parameters such as stimulation intensity and session duration showed excellent consistency when explicitly reported (ICC 0.95–0.96); secondary targets and free-text duration phrases remained challenging (κ ≈ 0.61; ICC ≈ 0.35). An ensemble consensus (majority vote or averaging) resolved most disagreements and delivered near-perfect reliability on core stimulation attributes (κ = 0.94). These results demonstrate that multi-LLM ensembles can markedly expand trial coverage and reach expert-level accuracy on well-defined fields while still requiring human oversight for nuanced or sparsely reported details. The benchmark and open-source workflow set a solid baseline for future advances in prompt engineering, model specialization, and ensemble strategies aimed at fully automated evidence synthesis in neurostimulation research involving aging populations. Overall, the five-model multi-LLM ensemble doubled the number of eligible aging-related tDCS trials retrieved versus keyword searching and achieved near-perfect agreement on core stimulation parameters (κ ≈ 0.94), demonstrating expert-level extraction accuracy.

In this paper, advancing web scale knowledge extraction and alignment by integrating few sources has been considered by exploring different methods of aggregation and attention in order to focus on image information. An improved model, namely, Wrapper Extraction of Image using DOM and JSON (WEIDJ) has been proposed to extract images and the related information in fastest way. Several models, such as Document Object Model (DOM), Wrapper using Hybrid DOM and JSON (WHDJ), WEIDJ and WEIDJ (no-rules) are been discussed. The experimental results on real world websites demonstrate that our models outperform others, such as Document Object Model (DOM), Wrapper using Hybrid DOM and JSON (WHDJ) in terms of mining in a higher volume of web data from a various types of image format and taking the consideration of web data extraction from deep web.

Accurate assessments of current and future fertility—including overall trends and changing population age structures across countries and regions—are essential to help plan for the profound social, economic, environmental, and geopolitical challenges that these changes will bring. Estimates and projections of fertility are necessary to inform policies involving resource and health-care needs, labour supply, education, gender equality, and family planning and support. The Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2021 produced up-to-date and comprehensive demographic assessments of key fertility indicators at global, regional, and national levels from 1950 to 2021 and forecast fertility metrics to 2100 based on a reference scenario and key policy-dependent alternative scenarios. To estimate fertility indicators from 1950 to 2021, mixed-effects regression models and spatiotemporal Gaussian process regression were used to synthesise data from 8709 country-years of vital and sample registrations, 1455 surveys and censuses, and 150 other sources, and to generate age-specific fertility rates (ASFRs) for 5-year age groups from age 10 years to 54 years. ASFRs were summed across age groups to produce estimates of total fertility rate (TFR). Livebirths were calculated by multiplying ASFR and age-specific female population, then summing across ages 10–54 years. To forecast future fertility up to 2100, our Institute for Health Metrics and Evaluation (IHME) forecasting model was based on projections of completed cohort fertility at age 50 years (CCF50; the average number of children born over time to females from a specified birth cohort), which yields more stable and accurate measures of fertility than directly modelling TFR. CCF50 was modelled using an ensemble approach in which three sub-models (with two, three, and four covariates variously consisting of female educational attainment, contraceptive met need, population density in habitable areas, and under-5 mortality) were given equal weights, and analyses were conducted utilising the MR-BRT (meta-regression—Bayesian, regularised, trimmed) tool. To capture time-series trends in CCF50 not explained by these covariates, we used a first-order autoregressive model on the residual term. CCF50 as a proportion of each 5-year ASFR was predicted using a linear mixed-effects model with fixed-effects covariates (female educational attainment and contraceptive met need) and random intercepts for geographical regions. Projected TFRs were then computed for each calendar year as the sum of single-year ASFRs across age groups. The reference forecast is our estimate of the most likely fertility future given the model, past fertility, forecasts of covariates, and historical relationships between covariates and fertility. We additionally produced forecasts for multiple alternative scenarios in each location: the UN Sustainable Development Goal (SDG) for education is achieved by 2030; the contraceptive met need SDG is achieved by 2030; pro-natal policies are enacted to create supportive environments for those who give birth; and the previous three scenarios combined. Uncertainty from past data inputs and model estimation was propagated throughout analyses by taking 1000 draws for past and present fertility estimates and 500 draws for future forecasts from the estimated distribution for each metric, with 95% uncertainty intervals (UIs) given as the 2·5 and 97·5 percentiles of the draws. To evaluate the forecasting performance of our model and others, we computed skill values—a metric assessing gain in forecasting accuracy—by comparing predicted versus observed ASFRs from the past 15 years (2007–21). A positive skill metric indicates that the model being evaluated performs better than the baseline model (here, a simplified model holding 2007 values constant in the future), and a negative metric indicates that the evaluated model performs worse than baseline. During the period from 1950 to 2021, global TFR more than halved, from 4·84 (95% UI 4·63–5·06) to 2·23 (2·09–2·38). Global annual livebirths peaked in 2016 at 142 million (95% UI 137–147), declining to 129 million (121–138) in 2021. Fertility rates declined in all countries and territories since 1950, with TFR remaining above 2·1—canonically considered replacement-level fertility—in 94 (46·1%) countries and territories in 2021. This included 44 of 46 countries in sub-Saharan Africa, which was the super-region with the largest share of livebirths in 2021 (29·2% [28·7–29·6]). 47 countries and territories in which lowest estimated fertility between 1950 and 2021 was below replacement experienced one or more subsequent years with higher fertility; only three of these locations rebounded above replacement levels. Future fertility rates were projected to continue to decline worldwide, reaching a global TFR of 1·83 (1·59–2·08) in 2050 and 1·59 (1·25–1·96) in 2100 under the reference scenario. The number of countries and territories with fertility rates remaining above replacement was forecast to be 49 (24·0%) in 2050 and only six (2·9%) in 2100, with three of these six countries included in the 2021 World Bank-defined low-income group, all located in the GBD super-region of sub-Saharan Africa. The proportion of livebirths occurring in sub-Saharan Africa was forecast to increase to more than half of the world's livebirths in 2100, to 41·3% (39·6–43·1) in 2050 and 54·3% (47·1–59·5) in 2100. The share of livebirths was projected to decline between 2021 and 2100 in most of the six other super-regions—decreasing, for example, in south Asia from 24·8% (23·7–25·8) in 2021 to 16·7% (14·3–19·1) in 2050 and 7·1% (4·4–10·1) in 2100—but was forecast to increase modestly in the north Africa and Middle East and high-income super-regions. Forecast estimates for the alternative combined scenario suggest that meeting SDG targets for education and contraceptive met need, as well as implementing pro-natal policies, would result in global TFRs of 1·65 (1·40–1·92) in 2050 and 1·62 (1·35–1·95) in 2100. The forecasting skill metric values for the IHME model were positive across all age groups, indicating that the model is better than the constant prediction. Fertility is declining globally, with rates in more than half of all countries and territories in 2021 below replacement level. Trends since 2000 show considerable heterogeneity in the steepness of declines, and only a small number of countries experienced even a slight fertility rebound after their lowest observed rate, with none reaching replacement level. Additionally, the distribution of livebirths across the globe is shifting, with a greater proportion occurring in the lowest-income countries. Future fertility rates will continue to decline worldwide and will remain low even under successful implementation of pro-natal policies. These changes will have far-reaching economic and societal consequences due to ageing populations and declining workforces in higher-income countries, combined with an increasing share of livebirths among the already poorest regions of the world. Bill & Melinda Gates Foundation.

The growing need for food worldwide requires the development of a high-performance, high-productivity, and sustainable agriculture, which implies the introduction of new technologies into monitoring activities related to control and decision-making. In this regard, this paper presents a hierarchical structure based on the collaboration between unmanned aerial vehicles (UAVs) and federated wireless sensor networks (WSNs) for crop monitoring in precision agriculture. The integration of UAVs with intelligent, ground WSNs, and IoT proved to be a robust and efficient solution for data collection, control, analysis, and decisions in such specialized applications. Key advantages lay in online data collection and relaying to a central monitoring point, while effectively managing network load and latency through optimized UAV trajectories and in situ data processing. Two important aspects of the collaboration were considered: designing the UAV trajectories for efficient data collection and implementing effective data processing algorithms (consensus and symbolic aggregate approximation) at the network level for the transmission of the relevant data. The experiments were carried out at a Romanian research institute where different crops and methods are developed. The results demonstrate that the collaborative UAV–WSN–IoT approach increases the performances in both precision agriculture and ecological agriculture.

Background. Systematic reviews are essential tools for evidence-based practice but are often time-consuming. Recent developments in artificial intelligence, including large language models such as ChatGPT-4o, offer potential to support and partially automate some processes. This study aimed to evaluate the performance of ChatGPT-4o in assessing Risk of Bias (RoB) using RoB 2.0 tool and in extracting data from randomised controlled trials (RCTs) on exercise therapy for chronic low back pain.   Materials and Methods. This cross-sectional comparative study included 150 RCTs previously assessed by human reviewers. ChatGPT-4o was tested in two tasks: (1) RoB assessment using a single structured prompt, compared with expert ratings across five domains and overall judgement; (2) data extraction across 34 predefined variables using both simplified and detailed prompts. Human reviewers served as the reference standard. Statistical analysis focused on Cohen’s kappa and overall accuracy, alongside sensitivity, specificity, PPV, NPV, and F1-score.   Results. Agreement between ChatGPT-4o and human reviewers for RoB assessment was low (Cohen’s κ = 0.14), with a tendency to underestimate bias. Sensitivity was 40%, while specificity and PPV were higher for low-risk classifications. For data extraction, ChatGPT-4o showed strong performance, with accuracy above 84% and F1-scores over 90% using both prompt types. Hallucinations were rare (<0.02%). Task duration was reduced from 30-50 minutes (human reviewers) to under 5 minutes with ChatGPT-4o.   Conclusions. While ChatGPT-4o showed limited reliability for RoB assessment, likely due to the interpretative complexity of the task, it performed robustly in data extraction, particularly when guided by well-structured prompts. Its high precision, speed, and low hallucination rate suggest strong potential as a secondary reviewer in systematic review workflows. Nonetheless, its application to evaluative tasks requiring critical judgement remains premature. With further development and proper human oversight, LLMs like ChatGPT-4o may help streamline systematic review processes, especially for labour-intensive, structured data extraction.  

In this paper, we propose an information extraction (IE) system for extracting data records from semi-structured documents on the Deep Web using a promising proposed technique, called Repetitive Subject Pattern. This technique was based on the hypothesis that data records in the web page must have a subject item, and the repetitive pattern of the subject items can be used to identify the boundary of data records. The system consists of four automatic tasks: (1) parsing a sample page to a DOM tree, (2) recognizing a subject string in the DOM tree, (3) using the subject string for identifying the pattern of data records and generating a wrapper, and (4) using the generated wrapper for extracting data records. This approach enables the very flexible wrapper generator; when the automatic process generated the wrong wrapper, user can also provide a new sample subject string for generating better wrapper. As the result, the system can be both semi-supervised and unsupervised system. The experimentation shows that the proposed technique provides the outstanding results in generating the very high quality wrappers, with both recall and precision close to 100 % when tested on a number of datasets.

Background: The extraction of data from the reports of primary studies, on which the results of systematic reviews depend, needs to be carried out accurately. To aid reliability, it is recommended that two researchers carry out data extraction independently. The extraction of statistical data from graphs in PDF files is particularly challenging, as the process is usually completely manual, and reviewers need sometimes to revert to holding a ruler against the page to read off values: an inherently time-consuming and error-prone process. Methods: To mitigate some of the above problems we integrated and customised two existing JavaScript libraries to create a new web-based graphical data extraction tool to assist reviewers in extracting data from graphs. This tool aims to facilitate more accurate and timely data extraction through a user interface which can be used to extract data through mouse clicks. We carried out a non-inferiority evaluation to examine its performance in comparison to standard practice. Results: We found that the customised graphical data extraction tool is not inferior to users’ prior preferred current approaches. Our study was not designed to show superiority, but suggests that there may be a saving in time of around 6 minutes per graph, accompanied by a substantial increase in accuracy. Conclusions: Our study suggests that the incorporation of this type of tool in online systematic review software would be beneficial in facilitating the production of accurate and timely evidence synthesis to improve decision-making.

In a real-world situation produced under COVID-19 scenarios, predicting cryptocurrency returns accurately can be challenging. Such a prediction may be helpful to the daily economic and financial market. Unlike forecasting the cryptocurrency returns, we propose a new approach to predict whether the return classification would be in the first, second, third quartile, or any quantile of the gold price the next day. In this paper, we employ the support vector machine (SVM) algorithm for exploring the predictability of financial returns for the six major digital currencies selected from the list of top ten cryptocurrencies based on data collected through sensors. These currencies are Binance Coin, Bitcoin, Cardano, Dogecoin, Ethereum, and Ripple. Our study considers the pre-COVID-19 and ongoing COVID-19 periods. An algorithm that allows updated data analysis, based on the use of a sensor in the database, is also proposed. The results show strong evidence that the SVM is a robust technique for devising profitable trading strategies and can provide accurate results before and during the current pandemic. Our findings may be helpful for different stakeholders in understanding the cryptocurrency dynamics and in making better investment decisions, especially under adverse conditions and during times of uncertain environments such as in the COVID-19 pandemic.

Surveys on explainable artificial intelligence (XAI) are related to biology, clinical trials, fintech management, medicine, neurorobotics, and psychology, among others. Prognostics and health management (PHM) is the discipline that links the studies of failure mechanisms to system lifecycle management. There is a need, which is still absent, to produce an analytical compilation of PHM-XAI works. In this paper, we use preferred reporting items for systematic reviews and meta-analyses (PRISMA) to present a state of the art on XAI applied to PHM of industrial assets. This work provides an overview of the trend of XAI in PHM and answers the question of accuracy versus explainability, considering the extent of human involvement, explanation assessment, and uncertainty quantification in this topic. Research articles associated with the subject, since 2015 to 2021, were selected from five databases following the PRISMA methodology, several of them related to sensors. The data were extracted from selected articles and examined obtaining diverse findings that were synthesized as follows. First, while the discipline is still young, the analysis indicates a growing acceptance of XAI in PHM. Second, XAI offers dual advantages, where it is assimilated as a tool to execute PHM tasks and explain diagnostic and anomaly detection activities, implying a real need for XAI in PHM. Third, the review shows that PHM-XAI papers provide interesting results, suggesting that the PHM performance is unaffected by the XAI. Fourth, human role, evaluation metrics, and uncertainty management are areas requiring further attention by the PHM community. Adequate assessment metrics to cater to PHM needs are requested. Finally, most case studies featured in the considered articles are based on real industrial data, and some of them are related to sensors, showing that the available PHM-XAI blends solve real-world challenges, increasing the confidence in the artificial intelligence models’ adoption in the industry.