Search Results (6,950)

Intelligent driving cabins operated by artificial intelligence technology are evolving into the third living space. They aim to integrate perception, analysis, decision making, and intervention. By using multimodal biosignal acquisition technologies (flexible sensors and non-contact sensing), it is possible to monitor the physiological indicators of heart rate and blood pressure in real time. Leveraging the benefits of domain controllers in the vehicle and edge computing helps the AI platform reduce data latency and enhance real-time processing capabilities, as well as integrate the cabin’s internal and external data through machine learning. Its aim is to build tailored health baselines and high-precision risk prediction models (e.g., CNN, LSTM). This system can initiate multi-level interventions such as adjustments to the environment, health recommendations, and ADAS-assisted emergency parking with telemedicine help. Current issues consist of sensor precision, AI model interpretation, security of data privacy, and whom to attribute legal liability to. Future development will mainly focus on cognitive digital twin construction, L4/L5 autonomous driving integration, new biomedical sensor applications, and smart city medical ecosystems. Full article

Background/Objectives: High-risk (B3) breast lesions are a heterogeneous group with uncertain malignant potential. Methods: We systematically reviewed and meta-analyzed the ability of artificial-intelligence (AI) models to predict malignant upgrades (a ductal carcinoma in situ or an invasive carcinoma) after biopsy. A comprehensive search of medical and engineering databases through 27 July 2025 identified retrospective studies that developed or validated AI models for upgrade prediction in cohorts with ≥20 B3 lesions and confirmed outcomes at surgical excision or after ≥24 months of follow-up. Results: Three single-center studies (557 lesions, 91 upgrades) met the eligibility criteria. Pooled analysis focused on clinically meaningful operating points rather than raw accuracy metrics. Models tuned for high sensitivity achieved high negative predictive values (pooled 0.95), suggesting reliable identification of lesions suitable for surveillance, but positive predictive values were modest and heterogenous (0.15–1.00), reflecting trade-offs between avoiding missed upgrades and reducing unnecessary excisions. Only two studies reported area-under-the-receiver-operating-characteristic curves, which pooled to 0.72, indicating moderate discrimination. Conclusions: Although limited by small sample sizes and single-center designs, these findings suggest that AI could aid decision-making for B3 lesion management. Prospective multicenter validation and standardized reporting are needed to evaluate clinical utility. Full article

Cloud-based machine learning systems are increasingly used in sectors such as healthcare, finance, and public services, where they influence decisions with significant social consequences. While these technologies offer scalability and efficiency, they raise significant concerns regarding security, privacy, and compliance. One of the central issues is algorithmic bias, which can emerge from data, design choices, or system interactions, and is often amplified when deployed at scale through cloud infrastructures. This study examines the relationship between algorithmic bias, social equity, and cloud-based innovation. Drawing on a survey of public perceptions, we find strong recognition of the risks posed by biased systems, including diminished trust, harm to vulnerable populations, and erosion of fairness. Participants overwhelmingly supported regulatory oversight, developer accountability, and greater transparency in algorithmic decision-making. Building on these findings, this paper proposes measures to integrate fairness auditing, representative datasets, and bias mitigation techniques into cloud security and compliance frameworks. We argue that addressing bias is not only an ethical responsibility but also an essential requirement for safeguarding public trust and meeting evolving legal and regulatory standards. Full article

A virtual power plant (VPP) faces multiple uncertainties and temporal coupled decisions when participating as an independent entity in electricity and green markets. A multi-level electricity–green coupled market framework is constructed for a VPP participating as an independent market entity. To address uncertainties in renewable energy outputs and market prices, a risk management method based on conditional value at risk entropy weight method information gap decision theory (CVaR-EIGDT) is proposed. To address the temporal coupled challenges in VPP participation across multi-level electricity–green coupled markets, a multi-stage rolling decision-making method coordinating annual, monthly, and daily scales is proposed, achieving deep coupling in the decision-making sequence of multi-level electricity–green coupled markets. Results show that the proposed model enables adaptive decision-making under varying risk preferences, with decisions exhibiting strong practical adaptability while balancing real-time adjustments and long-term planning. The multi-level electricity–green coupled market framework enhances VPP profitability and resilience, while the CVaR-EIGDT method effectively improves decision-making efficiency across multi-level electricity–green coupled markets. Full article

Background/Objectives: Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive fibrotic interstitial lung disease with high mortality and limited treatment options. Despite recent therapeutic advances, predicting survival remains challenging. Given the challenge of predicting disease progression in IPF, identifying reliable prognostic markers may support individualized treatment strategies, guide follow-up intensity, and improve clinical decision making. This study aimed to evaluate mortality rates and factors associated with poor prognosis in patients with IPF over a 10-year period at a tertiary care center. Methods: Medical records of 268 patients diagnosed with IPF between 2015 and 2024 were retrospectively reviewed. Demographic characteristics, comorbidities, radiological findings, pulmonary function test results, frequency of exacerbations and hospitalizations, treatment details, and survival outcomes were analyzed. Univariate and multivariate logistic regression analyses were performed to identify predictors of mortality. Results: This study included 268 patients (77.2% male; median age, 72 years). During a median follow-up of 24 months, 44% (n = 118) of patients died. Deceased patients were older (p < 0.001) and had higher rates of coronary artery disease, pulmonary embolism, pulmonary hypertension, and malignancy (all p < 0.05). A definite UIP pattern was more common among deceased patients (71.2% vs. 52.4%, p = 0.02). Acute exacerbations (23.3% vs. 8.1%) and hospitalizations (61.9% vs. 23.3%) were significantly more frequent in this group (p < 0.001). In multivariate analysis, GAP score (OR 11.68, p = 0.001), pulmonary hypertension (OR 15.39, p = 0.02), history of exacerbation (OR 56.2, p = 0.04), baseline FVC (OR 1.10, p = 0.02), mean platelet volume (OR 0.29, p = 0.01), and AST level (OR 1.12, p = 0.04) were independent predictors of mortality. Conclusions: Despite advances in management, IPF continues to carry a high mortality risk. This study represents one of the largest single-center IPF cohorts from our region with long-term real-life follow-up and additionally evaluates laboratory biomarkers such as MPV and AST, which have not been widely investigated as prognostic indicators in IPF. Advanced age, reduced pulmonary function, comorbidities, and acute exacerbations are major prognostic factors. Early recognition and proactive management of these parameters may help improve survival outcomes. Full article

Background: Patient-specific instrumentation (PSI) in total knee arthroplasty represents an increasingly relevant component of personalized surgical planning. As nearly half of orthopedic patients search online for medical information before or after clinical consultation, the quality, accuracy, and readability of publicly available digital resources directly influence patient expectations, shared decision-making, and rehabilitation engagement. This study assessed the content, quality, and readability of online information about PSI in TKA. Methods: Google searches using four predefined PSI-related terms were conducted on 6 March 2025. After applying exclusion criteria, 71 websites were included for evaluation. Websites were categorized as academic or non-academic and analyzed for authorship, reporting of advantages and disadvantages, inaccurate assertions, use of peer-reviewed references, multimedia content, and mention of specific PSI platforms. Website quality was assessed using validated quality evaluation tools (QUEST and JAMA criteria), and readability was evaluated using established readability indices (SMOG, FKGL, and FRE). Results: Academic websites demonstrated significantly higher quality than non-academic sources based on QUEST (25.4 vs. 9.8; p < 0.001) and JAMA criteria (3.7 vs. 1.7; p < 0.001). Disadvantages of PSI were reported in 69.1% of academic sites versus 12.5% of non-academic sites (p < 0.001). Inaccurate claims occurred in 31.3% of non-academic sites but were absent in academic sources (p < 0.001). Peer-reviewed references were present in 81.8% of academic websites and only 12.5% of non-academic sites (p < 0.001). Readability was uniformly poor across all websites, with no significant group differences (mean SMOG 13.5; mean FKGL 11.8; mean FRE 32.4). Conclusions: Online information about PSI in total knee arthroplasty varies widely in transparency and accuracy, with non-academic websites frequently omitting risks or presenting misleading claims. Given the role of individualized implant planning, accessible and evidence-based digital content is essential to support personalized patient education and shared decision-making. Because limited readability restricts patient comprehension and informed participation in personalized orthopedic care, improving the clarity and accessibility of digital patient resources is essential. Full article

Harvest-disrupting rain events (HDREs) are prolonged cloudy–rainy spells during winter wheat maturity that impede harvesting and drying, induce pre-harvest sprouting and grain mould, and threaten food security in the Huang–Huai–Hai Plain (HHHP), China’s core winter wheat region. Using daily meteorological records (1960–2019), remote sensing-derived land-use data and topography, we develop a hazard–exposure–vulnerability framework to quantify HDRE risk and its drivers at 1 km resolution. Results show that HDRE risk has increased markedly over the past six decades, with the area of medium-to-high risk rising from 26.9% to 73.1%. The spatial pattern evolved from a “high-south–low-north” structure to a concentrated high-risk belt in the central–northern HHHP, and the risk centroid migrated from Fuyang (Anhui) to Heze (Shandong), with an overall displacement of 124.57 km toward the north–northwest. GeoDetector analysis reveals a shift from a “humidity–temperature dominated” mechanism to a “sunshine–humidity–precipitation co-driven” mechanism; sunshine duration remains the leading factor (q > 0.8), and its interaction with relative humidity shows strong nonlinear enhancement (q = 0.91). High-risk hot spots coincide with low-lying plains and river valleys with dense winter wheat planting, indicating the joint amplification of meteorological conditions and underlying surface features. The results can support regional decision-making for harvest-season early warning, risk zoning, and disaster risk reduction in the HHHP. Full article

The causal analysis of historical aviation accidents documented in investigation reports is important for the design, manufacture, operation, and maintenance of aircraft. However, given that most accident data are unstructured or semi-structured, identifying and extracting causal information remain labor intensive and inefficient. This gap is further deepened by tasks, such as system identification from component information, that require extensive domain-specific knowledge. In addition, there is a consequential demand for causation pattern analysis across multiple accidents and the extraction of critical causation chains. To bridge those gaps, this study proposes an aviation accident causation and relation analysis framework that integrates prompt engineering with a retrieval-augmented generation approach. A total of 343 real-world accident reports from the NTSB were analyzed to extract causation factors and their interrelations. An innovative causation classification schema was also developed to cluster the extracted causations. The clustering accuracy for the four main causation categories—Human, Aircraft, Environment, and Organization—reached 0.958, 0.865, 0.979, and 0.903, respectively. Based on the clustering results, a causation knowledge graph for aviation accidents was constructed, and by designing a set of safety evaluation indicators, “pilot—decision error” and “landing gear system malfunction” are identified as high-risk causations. For each high-risk causation, critical combinations of causation chains are identified and “Aircraft operator—policy or procedural deficiency/pilot—procedural violation/Runway contamination → pilot—decision error → pilot procedural violation/32 landing gear/57 wings” was identified as the critical causation combinations for “pilot—decision error”. Finally, safety recommendations for organizations and personnel were proposed based on the analysis results, which offer practical guidance for aviation risk prevention and mitigation. The proposed approach demonstrates the potential of combining AI techniques with domain knowledge to achieve scalable, data-driven causation analysis and strengthen proactive safety decision-making in aviation. Full article

This study investigates a large language model driven (LLM) framework for intelligent preprocessing and short-term electricity price forecasting in the Australian National Electricity Market (NEM). By integrating unstructured news features, weather signals, and cyclical calendar variables, the model captures both physical and informational drivers of price volatility. A hybrid approach combining quantile regression with conformal calibration achieves statistically significant improvements in accuracy and uncertainty calibration. The framework demonstrates the potential of integrating LLMs into operational forecasting pipelines to support electricity market decision-making and risk management. Full article

This study proposes a collision-risk assessment framework that combines an interval type-2 fuzzy inference system with Dempster–Shafer evidence theory to more reliably evaluate vessel collision risk under the uncertainty inherent in AIS-based marine navigation data. The fuzzy system models membership-function uncertainty through a footprint of uncertainty and produces time-indexed basic probability assignments that are subsequently combined through a Dempster–Shafer–based temporal integration process. Robust combination rules are incorporated to mitigate the counterintuitive results often produced by classical evidence combination. Furthermore, Lenart’s time-based criterion and Fujii’s spatial safety domain are unified to construct a three-level risk labeling scheme, overcoming the limitations of conventional binary risk classification. Case studies using real AIS data demonstrate improved predictive accuracy and significantly reduced uncertainty, particularly when using the robust symmetric combination rule. Overall, the proposed framework provides a systematic approach for handling structural uncertainty in maritime environments and supports more reliable collision-risk prediction and safer navigational decision-making. Full article

Logistics involves planning and managing resources to meet customer demands. Its effectiveness depends not only on time and process coordination but also on the performance of logistics operators, whose actions directly affect customer satisfaction. Although operational risks are inherent to logistics, customer-oriented service failures are often overlooked in traditional risk assessment. To address this gap, this study proposes an integrated approach that combines a Pareto Diagram and Failure Mode and Effects Analysis (FMEA) within the ISO 31000 risk assessment framework. This structured method enables the identification and prioritization of logistics failures based on customer complaints, thereby supporting data-driven decision-making and continuous service improvement. Applied to a real-world case in a ceramic production line specializing in tableware manufacturing, the method identified and evaluated key logistics failures; particularly those related to late deliveries and damaged goods. Based on these findings, improvement actions were proposed to reduce the recurrence of these issues. This study contributes a structured, practical, and replicable approach for organizations to introduce risk assessment practices and enhance the service quality of logistics management. This study advances the literature by shifting the focus from internal production failures to customer-driven service risks, offering strategic insights for improving reliability and operational performance. Full article

Background: Optimal cerebral protection strategies for acute Stanford type A aortic dissection (aTAAD) surgery remain controversial. This study aimed to evaluate the role of near-infrared spectroscopy (NIRS)-guided monitoring and its association with clinical outcomes. Methods: We retrospectively analyzed 619 patients undergoing aTAAD surgery (Hemi-Arch, Total-Arch, or Arch-Stent procedures). Intraoperative cerebral oxygenation was monitored using NIRS, with the magnitude of desaturation quantified as ΔNIRS. We assessed correlations between ΔNIRS and nasopharyngeal temperature, employed generalized additive models (GAM) to analyze nonlinear relationships with major adverse cardiovascular events (MACE), and used piecewise logistic regression to identify procedure-specific ΔNIRS risk thresholds. Results: ΔNIRS showed a significant positive correlation with lower temperatures in Total-Arch (R = 0.486, p < 0.001) and Arch-Stent (R = 0.216, p < 0.001) groups. GAM analysis revealed a nonlinear, accelerating relationship between higher ΔNIRS and increased log odds of MACE in Hemi-Arch and Total-Arch groups. Procedure-specific ΔNIRS thresholds were identified: 8.5% for Hemi-Arch, 19.6% for Total-Arch, and 20.9% for Arch-Stent. Patients with ΔNIRS above these thresholds had significantly higher rates of stroke and MACE. Conclusions: This study identifies ΔNIRS as a significant, procedure-dependent intraoperative monitoring indicator in aTAAD surgery, and the proposed risk thresholds provide a rationale for real-time NIRS-guided clinical decision-making. Full article

Financial institutions increasingly rely on data-driven decision systems; however, many operational models remain purely predictive, failing to account for confounding biases inherent in observational data. In credit settings characterized by selective treatment assignment, this limitation can lead to erroneous policy assessments and the accumulation of “methodological debt”. To address this issue, we propose an “Estimate → Predict & Evaluate” framework that integrates Double Machine Learning (DML) with practical MLOps strategies. The framework first employs DML to mitigate selection bias and estimate unbiased Conditional Average Treatment Effects (CATEs), which are then distilled into a lightweight Target Model for real-time decision-making. This architecture further supports Off-Policy Evaluation (OPE), creating a “Causal Sandbox” for simulating alternative policies without risky experimentation. We validated the framework using two real-world datasets: a low-confounding marketing dataset and a high-confounding credit risk dataset. While uplift-based segmentation successfully identified responsive customers in the marketing context, our DML-based approach proved indispensable in high-risk credit environments. It explicitly identified “Sleeping Dogs”—customers for whom intervention paradoxically increased delinquency risk—whereas conventional heuristic models failed to detect these adverse dynamics. The distilled model demonstrated superior stability and provided consistent inputs for OPE. These findings suggest that the proposed framework offers a systematic pathway for integrating causal inference into financial decision-making, supporting transparent, evidence-based, and sustainable policy design. Full article

Background/Objectives: Large Language Models (LLMs), including ChatGPT-4 and Gemini, are increasingly incorporated into clinical care; however, their reliability within maternal–fetal medicine (MFM), a high-risk field in which diagnostic and management errors may affect both the pregnant patient and the fetus, remains uncertain. Evaluating the alignment of AI-generated case management recommendations with those of MFM specialists, emphasizing accuracy, agreement, and clinical relevancy. Study Design and Setting: Cross-sectional study with blinded online evaluation (November–December 2024); evaluators were blinded to responder identity (AI vs. human), and case order and response labels were randomized for each evaluator using a computer-generated sequence to reduce order and identification bias. Methods: Twenty hypothetical MFM cases were constructed, allowing standardized presentation of complex scenarios without patient-identifiable data and enabling consistent comparison of AI-generated and human specialist recommendations. Responses were generated by ChatGPT-4, Gemini, and three MFM specialists, then assessed by 22 blinded board-certified MFM evaluators using a 10-point Likert scale. Agreement was measured with Spearman’s rho (ρ) and Cohen’s (κ); accuracy differences were measured with Wilcoxon signed-rank tests. Results: ChatGPT-4 exhibited moderate alignment (mean 6.6 ± 2.95; ρ = 0.408; κ = 0.232, p < 0.001), performing well in routine, guideline-driven scenarios (e.g., term oligohydramnios, well-controlled gestational hypertension, GDMA1). Gemini scored 7.0 ± 2.64, demonstrating effectively no consistent inter-rater agreement (κ = −0.024, p = 0.352), indicating that although mean scores were slightly higher, evaluators varied widely in how they judged individual Gemini responses. No significant difference was found between ChatGPT-4 and clinicians in median accuracy scores (Wilcoxon p = 0.18), while Gemini showed significantly lower accuracy (p < 0.01). Model performance varied primarily by case complexity: agreement was higher in straightforward, guideline-based scenarios and more variable in complex cases, whereas no consistent pattern was observed by gestational age or specific clinical domain across the 20 cases. Conclusions: AI shows promise in routine MFM decision-making but remains constrained in complex cases, where models sometimes under-prioritize maternal–fetal risk trade-offs or incompletely address alternative management pathways, warranting cautious integration into clinical practice. Generalizability is limited by the small number of simulated cases and the use of hypothetical vignettes rather than real-world clinical encounters. Full article

Neurodegenerative synucleinopathies—including Parkinson’s disease, multiple system atrophy, pure autonomic failure, and dementia with Lewy bodies—often feature cardiovascular autonomic dysfunction. Neurogenic orthostatic hypotension (nOH) is common and symptomatic, while neurogenic supine hypertension (nSH) is less frequent but may carry long-term cardiovascular risks. Lifestyle measures are first-line for managing nSH, yet persistent hypertension unresponsive to nonpharmacological strategies presents a treatment dilemma. Limited trial data and unclear guidelines make it difficult to determine when antihypertensive therapy is appropriate. Evidence from studies on hypertension-mediated organ damage (HMOD)—assessed through markers such as carotid intima-media thickness, pulse wave velocity, left ventricular hypertrophy, estimated glomerular filtration rate, and white matter hyperintensities—suggests that nSH, rather than the underlying neurodegenerative disorder, drives vascular, cardiac, renal, and cerebral injury. Therefore, treatment decisions should be individualized. While antihypertensive therapy may help prevent subclinical organ damage, clinicians must balance this benefit against the risk of worsening nOH and further compromising overall prognosis. Full article