All stories

1045 published stories · page 9 of 70

Evidence-backed gain

Explainable and domain-adaptive prediction models for refrigerant charging in air conditioning systems within industrial processes

Accurate prediction of refrigerant deficiency in consumer air conditioning (AC) systems is critical for optimizing energy efficiency and operational stability. However, existing data-driven models often suffer from significant performance degradation due to domain shift across different AC types and a lack of explanatory transparency. To address these challenges, we propose AC-RPX (AC-Refrigerant Prediction eXplainable AI), a unified framework that integrates a Domain Encoder augmented with domain-specific token…

Scientific Reports · Lifestyle

Evidence-backed gain

Methodological Reporting Quality of Artificial Intelligence-Based Orthopedic Studies: A Literature Analysis

Objective We set out to examine how completely artificial intelligence (AI)-based orthopedic studies report their methods. Methods A PubMed search covering 2023-2025 was run with a predefined strategy. Screening of titles, abstracts and full texts left 280 eligible papers, and 200 of these were drawn at random for scoring. Each paper was rated against a six-item framework built from the TRIPOD-AI, STARD-AI and CONSORT-AI guidelines. Results Mean score across the 200 studies was 4.8±0.9. Twenty-eight percent reac…

Health

Evidence-backed gain

Implementation of a passive bin-based perpetual medication inventory model within ambulatory clinics at an academic medical center

Purpose Ambulatory clinics manage high-cost medications with little visibility into quantity or movement, leaving unrealized opportunities for inventory optimization. Automated dispensing cabinets, common in inpatient settings, address this issue but require significant capital investment, forcing clinics into complex workflows to balance demand for high-cost medications with minimizing waste. This study evaluated a passive bin-based inventory model that tracked clinic transactions in real time using light senso…

Business

Evidence-backed problem

Multimodal Graph Neural Networks and Evolutionary Knowledge Fusion for Secure and Explainable Governance in Intelligent IoT Interactive Media Systems

This research proposes a secure, explainable, and context-aware governance framework for blockchain-based digital media contracts in multimodal artificial intelligence-enabled AIoT interactive systems. As digital licensing, NFT copyright management, royalty distribution, and cross-chain content circulation become increasingly embedded in smart media ecosystems, existing contract auditing approaches remain limited by unimodal analysis, weak explainability, black-box decision processes, and insufficient cross-plat…

Policy

Evidence-backed problem

Post-traumatic Psychopathology and Cardiovascular Risk: A Danish Case-Control Study of Sex-Specific Associations

Background There is increasing recognition that trauma exposure and related psychiatric consequences predict cardiovascular disease risk. However, most research has specifically examined post-traumatic stress disorder-despite evidence that a range of psychiatric disorders may follow trauma. We applied machine learning to identify key post-traumatic psychiatric predictors of incident major adverse cardiac and cerebrovascular events (MACCE) in a population-based cohort. Methods We conducted a case-control study of…

Health

Evidence-backed problem

A strategic pathway for the ethical development of AI tools in dementia care

Artificial intelligence (AI) is rapidly entering dementia clinical practice, offering opportunities across the care continuum. However, cognitive decline creates a unique ethical challenge. This perspective article proposes a strategy to ensure the responsible development and deployment of AI tools for dementia. An interdisciplinary workgroup of the Alzheimer's Association Innovation Roundtable synthesized ethical frameworks, regulatory standards, and empirical evidence to generate expert consensus. The result i…

Health

Evidence-backed gain

Artificial intelligence-assisted histopathological diagnosis of endocervical gastric-type adenocarcinoma: a multicenter model development and validation study

Endocervical gastric-type adenocarcinoma (GAS) is one of the most aggressive subtypes of cervical cancer and is frequently underdiagnosed due to morphological ambiguity, leading to delayed diagnosis. Despite the availability of molecular and genomic assays, their high cost, complexity, and limited reproducibility restrict clinical use. This study therefore proposes a highly sensitive artificial intelligence (AI)-assisted diagnostic system for GAS based exclusively on H&E-stained histopathological images. We incl…

Health

Portable Raman spectroscopy coupled with machine learning for rapid identification and source apportionment of plastic particles in aquaculture wastewater

Aquaculture expansion has exacerbated microplastics (MPs) contamination in aquaculture water bodies. MPs readily adsorb heavy metals and organic pollutants to form composite contamination and accumulate through food chains, imposing ecological and human health risks. Conventional detection techniques including microscopic observation, FTIR and Py-GC-MS are limited by low identification accuracy, matrix interference, destructiveness and cumbersome procedures, which cannot support rapid large-scale monitoring. Ram…

Lifestyle

Machine learning-assisted nitrogen-doped carbon dots for Fe<sup>3+</sup> detection in aqueous environments

The concentration of iron ions is a crucial indicator for assessing water quality. In this study, nitrogen-doped carbon dots (NCDs) were synthesized using a microwave-assisted method with citric acid and urea as precursors, thereby establishing a fluorescence sensing platform for the detection of alkaline pH and Fe 3+ . During Fe 3+ detection, the fluorescence intensity of NCDs was specifically quenched as the concentration of Fe 3+ increased, demonstrating good linearity across the ranges of 1-10 µM and 10-100…

Climate

Data-efficient exploration of atomic clusters via uncertainty quantification on complex potential energy surfaces

Machine learning interatomic potentials have become an effective method for exploring complex potential energy surfaces; however, their application to atomic clusters is frequently hindered by the high cost of sampling diverse isomer spaces and the difficulty in ensuring model generalizability across complex energy landscapes. While uncertainty quantification (UQ) offers a pathway to mitigate data scarcity, its efficacy in capturing continuous potential energy surface features and guiding active learning within…

Science

Artificial intelligence-enabled causal estimate of Medicare drug plan integration in cancer care: A doubly robust machine learning instrumental variable analysis

Background Artificial intelligence (AI) methods are increasingly used to strengthen policy evaluation in managed care pharmacy. Among Medicare beneficiaries with cancer, which is one of the most clinically complex and costly populations, prescription drug coverage is obtained through either integrated Medicare Advantage Prescription Drug plans (MA-PDs) or stand-alone Prescription Drug Plans (PDPs). However, causal evidence of plans' impact remains limited because of nonrandom enrollment. Objective To apply an AI…

Health

An informatics framework to harmonize electronic health record medication data for managed care analytics and artificial intelligence applications

Background Artificial intelligence (AI) applications in managed care pharmacy depend on semantically consistent medication data, yet heterogeneous medication identifiers across real-world electronic health records (EHRs) could undermine analytic fidelity and risk propagating classification errors. To enable transportable, reproducible AI tools, methods for harmonizing disparate medication identifiers (eg, National Drug Code [NDC] and Multum drug synonym ID) to standardized vocabularies are required. Objective To…

Health

A pharmacist-overseen, artificial intelligence-enabled model for provider-side prior authorization: From burden to opportunity (PAVE-1)

Prior authorization (PA) imposes substantial administrative burdens on clinicians, contributing to burnout, delayed care, and excess health care spending. Artificial intelligence (AI) is emerging as a tool to automate PA tasks in managed care pharmacy, yet concerns persist regarding transparency, bias, and overreliance on autonomous systems. This is particularly true in payer-deployed AI systems that may deny claims without adequate clinical review. This viewpoint proposes a pharmacist-overseen, AI-enabled syste…

Health

A pharmacist-overseen, artificial intelligence-enabled model for provider-side prior authorization: From burden to opportunity (PAVE-1)

[Artificial intelligence in cardiovascular prevention: a strategic opportunity for risk prediction and early diagnosis]

Cardiovascular diseases remain the leading cause of mortality and morbidity worldwide, with substantial impact in Italy. Cardiovascular prevention is a strategic priority, yet a significant gap persists between evidence-based guideline recommendations and their actual implementation in clinical practice. Artificial intelligence (AI), through machine learning and deep learning models, is emerging as a potentially transformative technology to bridge this gap, enabling more precise, dynamic, and personalized cardio…

Health

[Breast arterial calcifications and cardiovascular risk in women]

Cardiovascular (CV) diseases remain the leading cause of mortality in women and often present as the first clinical manifestation, highlighting the limitations of current risk scores. In this context, breast arterial calcifications (BACs), incidentally detected on screening mammography, are emerging as a potential biomarker of systemic CV risk. This narrative review summarizes the most recent evidence (2023-2026) on the association between BACs and CV outcomes, including observational studies, prospective and re…

Health