Search Results (70)

A systematic review was conducted to examine interventions designed to reduce the influence of implicit bias on professional judgements, with the aim of identifying strategies relevant to forensic and legal contexts. These decisions are often made under time pressure, ambiguity, and limited information, increasing reliance on intuitive judgement and mental shortcuts that can allow bias to shape how information is evaluated. Eight databases were searched and screened using predefined inclusion criteria. Studies were included if they assessed the behavioural impact of a bias-reduction intervention on decisions made by professionals or mock professionals in forensic, legal, healthcare, educational, or organisational settings. Thirty-eight studies met the inclusion criteria and were analysed. Interventions were mapped by mechanism, delivery format, and decision context. Systemic strategies, such as decision protocols, standardised rubrics, or changes to how information was presented, consistently outperformed individual-level approaches focused on changing attitudes or awareness. Effective interventions typically constrained discretion or embedded structured prompts at the point of judgement. However, most were tested in simulated settings, with limited evidence of long-term or applied effects. The review identifies strategies with the strongest empirical support and highlights those most effective, practical, and transferable to forensic and legal contexts. Full article

In dealing with emergency events, it is very important when making scientific and correct decisions. As an important premise, the creation of information needs is quite essential. Taking earthquakes as a type of unexpected event, this paper constructs a large and model-driven system for automating the generating process of information requirements for earthquake response. This research explores how the different departments interact during an earthquake emergency response, how the information interacts with each other, and how the information requirement process operates. The system is designed from three points of view, building a knowledge base, designing and developing prompts, and designing the system structure. It talks about how computers automatically make info needs for sudden emergencies. During the experimental process, the backbone architectures used were four Large Language Models (LLMs): chatGLM (GLM-4.6), Spark (SparkX1.5), ERNIE Bot (4.5 Turbo), and DeepSeek (V3.2). According to the desired system process, information needs is generated by real-word cases and then they are compared to the gathered information needs by experts. In the comparison process, the “keyword weighted matching + text structure feature fusion” method was used to calculate the semantic similarity. Like true positives, false positives, and false negatives can be used to find differences and calculate metrics like precision and recal. And the F1-score is also computed. The experimental results show that all four LLMs achieved a precision and recall of over 90% in earthquake information extraction, with their F1-scores all exceeding 85%. This verifies the feasibility of the analytical method a chatGLM dopted in this research. Through comparative analysis, it was found that chatGLM exhibited the best performance, with an F1-score of 93.2%. Eventually, Python is used to script these aforementioned processes, which then create complete comparison charts for visual and test result checking. In the course of researching we also use Protege to create the knowledge requirements ontology, so it is easy for us to show and look at it. This research is particularly useful for emergency management departments, earthquake emergency response teams, and those working on intelligent emergency information systems or those focusing on the automated information requirement generation using technologies such as LLMs. It provides practical support for optimizing rapid decision-making in earthquake emergency response. Full article

Background: Systems thinking (ST) is an approach to problem-solving that views systems through a holistic perspective, focusing on the interconnections and relationships between various elements. In healthcare, the World Health Organization’s 2009 report marked a paradigm shift toward ST, prompting the development and use of ST tools to address complex challenges. Despite this, limited attention has been given to ST’s application in healthcare human resource management (HRM). This paper aims to provide a scoping review of ST application in healthcare HRM to explore its value in workforce management. Methods: Following Arksey and O’Malley’s framework, a scoping review was conducted to map how ST has been applied in healthcare HRM. Peer-reviewed articles published between 1999 and December 2024 were identified through Scopus and PubMed, using search terms such as systems thinking, human resources, and workforce. Data were extracted using a structured tool, and findings were analyzed through the lens of the system level of application. Results: The review identified 19 studies from 15 countries, with the majority using qualitative or mixed methods approaches across diverse settings. Core applications were applied at the macro, meso, and micro system levels to address workforce challenges, map feedback loops, identify leverage points, and strengthen stakeholder collaboration. ST was commonly applied at regional and national levels and supported improved workforce planning, policy development, and service coordination. Most studies employed soft systems modeling. Conclusions: This review highlights ST’s potential to enhance HRM by recognizing interdependencies across workforce functions. Findings suggest that ST enables more integrated strategies, promotes collaboration, and supports systemic decision-making. The adoption of ST in healthcare HRM may address persistent workforce challenges, though implementation remains limited by reductionist perspectives and unfamiliarity with ST tools. Full article

Background: Large language models (LLMs) are increasingly considered in dentistry, yet their accuracy in orthodontic radiology remains uncertain. This study evaluated the performance of ChatGPT-4 on questions aligned with current radiology guidelines. Methods: Fifty short, guideline-anchored questions were authored; thirty were pre-selected a priori for their diagnostic relevance. Using the ChatGPT-4 web interface in March 2025, we obtained 30 answers per item (900 in total) across two user accounts and three times of day, each in a new chat with a standardised prompt. Two blinded experts graded all responses on a 3-point scale (0 = incorrect, 1 = partially correct, 2 = correct); disagreements were adjudicated. The primary outcome was strict accuracy (proportion of answers graded 2). Secondary outcomes were partial-credit performance (mean 0–2 score) and inter-rater agreement using multiple coefficients. Results: Strict accuracy was 34.1% (95% CI 31.0–37.2), with wide item-level variability (0–100%). The mean partial-credit score was 1.09/2.00 (median 1.02; IQR 0.53–1.83). Inter-rater agreement was high (percent agreement: 0.938, with coefficients indicating substantial to almost-perfect reliability). Conclusions: In the conditions of this study, ChatGPT-4 demonstrated limited strict accuracy yet substantial reliability in expert grading when applied to orthodontic radiology questions. These findings underline its potential as a complementary educational and decision-support resource while also highlight its present limitations. Its role should remain supportive and informative, never replacing the critical appraisal and professional judgement of the clinician. Full article

Over 150 years, pathology has transformed remarkably, from the humble beginnings of microscopic tissue examination to today’s revolutionary advancements in digital pathology and artificial intelligence (AI) applications. This review briefly retraces the evolution of microscopes and highlights breakthroughs in complementary tools and techniques that laid the foundation for modern surgical pathology, recently expanded into a new dimension with digital pathology. Digital pathology marked a pivotal turning point by addressing the longstanding limitations of conventional microscopy, paving the way for AI integration. AI now revolutionizes pathology workflows, offering unprecedented opportunities for automated diagnostics, enhanced precision, accelerated research, and advanced medical education. Despite widespread consensus on AI as complementary to pathologists, rare studies critically explore the feasibility of a fully autonomous, pathologist-independent diagnostic workflow. Given the rapid advancement of AI, it is timely to examine whether mature AI systems might realistically achieve diagnostic autonomy. Thus, this review uniquely addresses this gap by evaluating the feasibility, limitations, and implications of a disruptive, pathologist-free diagnostic model. This exploration raises critical questions about the evolving role of pathologists in an era increasingly defined by automation. Can pathologists adapt to emerging trends, maintain their central role in patient care, and leverage AI effectively, or will their traditional roles inevitably diminish? Could the continued advancement of AI eventually prompt a return of pathologists to their initial mid-19th century role as scientist scholars, removed from frontline diagnostics? Ultimately, we assess whether AI can independently sustain diagnostic accuracy and decision making without pathologist oversight. Full article

In view of the problems that the track mode accuracy of the automatic steering gear on survey ships cannot meet the requirements of hydrographic survey accuracy and the workload of manual steering is large, an intelligent auxiliary decision-making algorithm based on LSTM and multiple linear regression is proposed. By learning historical track information, marine environment information, historical steering data, hull state data, etc., it provides the helm with auxiliary operation prompt information, such as the command course and its adjustment timing (time range, area), so as to reduce the number of times the helm steers. The effectiveness of the algorithm is verified through sea trials. The results show that the number of steering times is reduced by 45.5% and the number of effective measuring points is increased by 1.5% through the algorithm in this paper. This result confirms that the algorithm can improve the operational efficiency of offshore survey tasks by optimizing human–computer interaction. Full article

Abrupt speed variations and motor start-ups have been pointed out as critical challenges in the framework of fault diagnostics in induction motor drives, namely inter-turn short circuit faults. Generally, abrupt accelerations influence the typical symptoms of the fault, and consequently, the fault detection becomes ambiguous, impacting prompt and effective decision-making. To overcome this issue, this study proposes an inter-turn short-circuit fault diagnostic technique for asymmetrical six-phase induction motor drives operating under both smooth and abrupt motor accelerations. A time–frequency domain spectrogram of the AC component extracted from the q-axis reference current signal serves as a reliable fault indicator. This technique stands out for the compromise between robustness and computational effort using only one control variable accessible in the model predictive control algorithm, thus discarding both voltage and current signals. Experimental tests involving various load torques and fault severities, in transient regimes, were performed to validate the proposed methodology’s effectiveness thoroughly. Full article

Background/Objectives: The integration of AI chatbots in nursing education, particularly in simulation-based learning, is advancing rapidly. However, there is a lack of structured evaluation models, especially to assess AI-generated simulations. This article introduces the AI-Integrated Method for Simulation (AIMS) evaluation framework, a dual-phase evaluation framework adapted from the FAITA model, designed to evaluate both prompt design and chatbot performance in the context of nursing education. Methods: This simulation-based study explored the application of an AI chatbot in an emergency planning course. The AIMS framework was developed and applied, consisting of six prompt-level domains (Phase 1) and eight performance criteria (Phase 2). These domains were selected based on current best practices in instructional design, simulation fidelity, and emerging AI evaluation literature. To assess the chatbots educational utility, the study employed a scoring rubric for each phase and incorporated a structured feedback loop to refine both prompt design and chatbox interaction. To demonstrate the framework’s practical application, the researchers configured an AI tool referred to in this study as “Eval-Bot v1”, built using OpenAI’s GPT-4.0, to apply Phase 1 scoring criteria to a real simulation prompt. Insights from this analysis were then used to anticipate Phase 2 performance and identify areas for improvement. Participants (three individuals)—all experienced healthcare educators and advanced practice nurses with expertise in clinical decision-making and simulation-based teaching—reviewed the prompt and Eval-Bot’s score to triangulate findings. Results: Simulated evaluations revealed clear strengths in the prompt alignment with course objectives and its capacity to foster interactive learning. Participants noted that the AI chatbot supported engagement and maintained appropriate pacing, particularly in scenarios involving emergency planning decision-making. However, challenges emerged in areas related to personalization and inclusivity. While the chatbot responded consistently to general queries, it struggled to adapt tone, complexity and content to reflect diverse learner needs or cultural nuances. To support replication and refinement, a sample scoring rubric and simulation prompt template are provided. When evaluated using the Eval-Bot tool, moderate concerns were flagged regarding safety prompts and inclusive language, particularly in how the chatbot navigated sensitive decision points. These gaps were linked to predicted performance issues in Phase 2 domains such as dialog control, equity, and user reassurance. Based on these findings, revised prompt strategies were developed to improve contextual sensitivity, promote inclusivity, and strengthen ethical guidance within chatbot-led simulations. Conclusions: The AIMS evaluation framework provides a practical and replicable approach for evaluating the use of AI chatbots in simulation-based education. By offering structured criteria for both prompt design and chatbot performance, the model supports instructional designers, simulation specialists, and developers in identifying areas of strength and improvement. The findings underscore the importance of intentional design, safety monitoring, and inclusive language when integrating AI into nursing and health education. As AI tools become more embedded in learning environments, this framework offers a thoughtful starting point for ensuring they are applied ethically, effectively, and with learner diversity in mind. Full article

Background: To assess the accuracy of ChatGPT-4o and OpenAI-o1 in answering refractive surgery questions from the AAO BCSC Self-Assessment Program and to evaluate whether their performance could meaningfully support clinical decision making, we compared the models with 1983 ophthalmology residents and clinicians. Methods: A randomized, questionnaire-based study was conducted with 228 text-only questions from the Refractive Surgery section of the BCSC Self-Assessment Program. Each model received the prompt, “Please provide an answer to the following questions.” Accuracy was measured as the proportion of correct answers and reported with 95 percent confidence intervals. Differences between groups were assessed with the chi-squared test for independence and pairwise comparisons. Results: OpenAI-o1 achieved the highest score (91.2%, 95% CI 87.6–95.0%), followed by ChatGPT-4o (86.4%, 95% CI 81.9–90.9%) and the average score from 1983 users of the Refractive Surgery section of the BCSC Self-Assessment Program (77%, 95% CI 75.2–78.8%). Both language models significantly outperformed human users. The five-point margin of OpenAI-o1 over ChatGPT-4o did not reach statistical significance (p = 0.1045) but could represent one additional correct decision in twenty clinically relevant scenarios. Conclusions: Both ChatGPT-4o and OpenAI-o1 significantly outperformed BCSC Program users, demonstrating a level of accuracy that could augment medical decision making. Although OpenAI-o1 scored higher than ChatGPT-4o, the difference did not reach statistical significance. These findings indicate that the “advanced reasoning” architecture of OpenAI-o1 offers only incremental gains and underscores the need for prospective studies linking LLM recommendations to concrete clinical outcomes before routine deployment in refractive-surgery practice. Full article

Automating candidate shortlisting is a non-trivial task that stands to benefit substantially from advances in artificial intelligence. We evaluate a suite of foundation models such as Llama 2, Llama 3, Mixtral, Gemma-2b, Gemma-7b, Phi-3 Small, Phi-3 Mini, Zephyr, and Mistral-7b for their ability to predict hiring outcomes in both zero-shot and few-shot settings. Using only features extracted from applicants’ submissions, these models, on average, achieved an AUC above 0.5 in zero-shot settings. Providing a few examples similar to the job applicants based on a nearest neighbor search improved the prediction rate marginally, indicating that the models perform competently even without task-specific fine-tuning. For Phi-3 Small and Mixtral, all reported performance metrics fell within the 95% confidence interval across evaluation strategies. Model outputs were interpreted quantitatively via post hoc explainability techniques and qualitatively through prompt engineering, revealing that decisions are largely attributable to knowledge acquired during pre-training. A task-specific MLP classifier trained solely on the provided dataset only outperformed the strongest foundation model (Zephyr in 5-shot setting) by approximately 3 percentage points on accuracy, but all the foundational models outperformed the baseline model by more than 15 percentage points on f1 and recall, underscoring the competitive strength of general-purpose language models in the hiring domain. Full article

Background/Objectives: Chat Generative Pretrained Transformer (ChatGPT) is a useful resource for individuals working in the healthcare field. This paper will include descriptions of several ways in which ChatGPT-4 can achieve greater accuracy in its diagnosis and treatment plans for ulcerative colitis (UC) and Crohn’s disease (CD) by following the guidelines set out by the European Crohn’s and Colitis Organization (ECCO). Methods: The survey, which comprised 102 questions, was developed to assess the precision and consistency of respondents’ responses regarding the UC and CD. The questionnaire incorporated true/false and multiple-choice questions, with the objective of simulating real-life scenarios and adhering to the ECCO guidelines. We employed Likert scales to assess the responses. The inquiries were put to ChatGPT-4 on the initial day, the 15th day, and the 180th day. Results: The 51 true or false items demonstrated stability over a six-month period, with an initial accuracy of 92.8% at baseline, 92.8% on the 15th day, and peaked to 98.0% on the 180th day. This finding suggests a negligible effect size. The accuracy of the multiple-choice questions was initially 90.2% on Day 1, reached its highest point at 92.2% on Day 15, and then decreased to 84.3% on Day 180. However, the reliability of the data was found to be suboptimal, and the impact was deemed negligible. A modest, transient increase in performance was observed at 15 days, which subsequently diminished by 180 days, resulting in negligible effect sizes. Conclusions: ChatGPT-4 demonstrates potential as a clinical decision support system for UC and CD, but its assessment is marked by temporal variability and the inconsistent execution of various tasks. Essential initiatives that should be carried out before involving artificial intelligence (AI) technology in IBD trials are routine revalidation, multi-rater comparisons, prompt standardization, and the cultivation of a comprehensive understanding of the model’s limitations. Full article

Governance plays a critical role at the intersection of disaster risk management (DRM) and climate change (CC). As CC increases the frequency and intensity of disasters, so DRM policies must consider the potential impacts of CC and integrate climate resilience measures. Over the past decade, extreme wildfires in wildland–urban interface (WUI) areas have left devastating effects for local economies, local development, environmental protection, and the continuity of government operations worldwide, prompting all actors to work in the same direction to face its changing context. This systematic review of the literature aims to analyze the research trends on wildfire risk governance in WUI areas during 2021–2024 and to identify the key risk governance determinants, thereby offering a robust foundation to guide technical discussions and support decision-making processes in local development planning, land use regulation, and DRM. The study is based on the application of the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) declaration to allow the identification, selection, analysis, and systematization of 68 articles from the Scopus database through three bibliographic search equations, which were then categorized using the software of text mining and natural language processing NLP software (VantagePoint 15.2) to identify four key pillars that structure extreme wildfire risk governance: political management, development planning, disaster risk management, and resilience management. Within this framework, ten governance determinants are highlighted, encompassing aspects such as regulatory frameworks, institutional coordination, information systems, technical capacities, community engagement, risk perception, financial resources, accountability mechanisms, adaptive planning, and cross-sectoral integration. These findings provide a conceptual basis for strengthening governance approaches in the face of increasing wildfire risk. Full article

Background: Investment decisions in stocks are one of the most complex tasks due to the uncertainty of which stocks will increase or decrease in their values. A diversified portfolio statistically reduces the risk; however, stock choice still substantially influences the profitability. Methods: This work proposes a methodology to automate investment decision recommendations with clear explanations. It utilizes generative AI, guided by prompt engineering, to interpret price predictions derived from neural networks. The methodology also includes the Artificial Intelligence Trust, Risk, and Security Management (AI TRiSM) model to provide robust security recommendations for the system. The proposed system provides long-term investment recommendations based on the financial fundamentals of companies, such as the price-to-earnings ratio (PER) and the net margin of profits over the total revenue. The proposed explainable artificial intelligence (XAI) system uses DeepSeek for describing recommendations and suggested companies, as well as several charts based on Shapley additive explanation (SHAP) values and local-interpretable model-agnostic explanations (LIMEs) for showing feature importance. Results: In the experiments, we compared the profitability of the proposed portfolios, ranging from 8 to 28 stock values, with the maximum expected price increases for 4 years in the NASDAQ-100 and S&P-500, where both bull and bear markets were, respectively, considered before and after the custom duties increases in international trade by the USA in April 2025. The proposed system achieved an average profitability of 56.62% while considering 120 different portfolio recommendations. Conclusions: A t-Student test confirmed that the difference in profitability compared to the index was statistically significant. A user study revealed that the participants agreed that the portfolio explanations were useful for trusting the system, with an average score of 6.14 in a 7-point Likert scale. Full article

The total global economic cost of flood damages between 1990 and 2024 exceeds £790 billion, with over half of these losses attributed to flood damages occurring in the last decade alone. Recent severe flood events have prompted a shift in flood risk management towards probabilistic approaches, leading to the notion that flood risk management is a continuous process of adaptive management. While substantial research has been dedicated towards characterising and quantifying climate model uncertainty, less focus has been directed towards the propagation of this uncertainty into hydraulically modelled systems and adaptive decision making. Recently, the concept of adaptation pathways has gained growing interest as a decision-focused, analytical tool to assess climate adaptation scenarios under uncertainty. This research develops an approach to quantify climate model uncertainty across multiple plausible adaptation scenarios and examines its influence on adaptation pathways using the case study area of Inverurie, Scotland. Uncertainty is quantified using stratified sampling and captured across scenarios, resulting in the identification and development of adaptation pathways within the context of specified flood risk management objectives and identified adaptation tipping points. The findings underscore the critical importance of embracing uncertainty in adaptation pathways to support robust, informed decision making. Full article

Background: Artificial intelligence (AI) and large language models (LLMs) are increasingly used in healthcare, with applications in clinical decision-making and workflow optimization. In head and neck surgery, postoperative rehabilitation is a complex, multidisciplinary process requiring personalized care. This study evaluates the feasibility of using LLMs to generate tailored rehabilitation programs for patients undergoing major head and neck surgical procedures. Methods: Ten hypothetical head and neck surgical clinical scenarios were developed, representing oncologic resections with complex reconstructions. Four LLMs, ChatGPT-4o, DeepSeek V3, Gemini 2, and Copilot, were prompted with identical queries to generate rehabilitation plans. Three senior clinicians independently assessed their quality, accuracy, and clinical relevance using a five-point Likert scale. Readability and quality metrics, including the DISCERN score, Flesch Reading Ease, Flesch–Kincaid Grade Level, and Coleman–Liau Index, were applied. Results: ChatGPT-4o achieved the highest clinical relevance (Likert mean of 4.90 ± 0.32), followed by DeepSeek V3 (4.00 ± 0.82) and Gemini 2 (3.90 ± 0.74), while Copilot underperformed (2.70 ± 0.82). Gemini 2 produced the most readable content. A statistical analysis confirmed significant differences across the models (p < 0.001). Conclusions: LLMs can generate rehabilitation programs with varying quality and readability. ChatGPT-4o produced the most clinically relevant plans, while Gemini 2 generated more readable content. AI-generated rehabilitation plans may complement existing protocols, but further clinical validation is necessary to assess their impact on patient outcomes. Full article