Exploring the Impact of Artificial Intelligence and Machine Learning in the Diagnosis and Management of Esthesioneuroblastomas: A Comprehensive Review DOI Open Access

Raj Nath Patel,

Tadas Masys,

Refat Baridi

et al.

Cureus, Journal Year: 2024, Volume and Issue: unknown

Published: June 19, 2024

Esthesioneuroblastomas (ENBs) present unique diagnostic and therapeutic challenges due to their rare complex clinical presentation. In recent years, artificial intelligence (AI) machine learning (ML) have emerged as promising tools in various medical specialties, revolutionizing accuracy, treatment planning, patient outcomes. However, application ENBs remains relatively unexplored. This comprehensive literature review aims evaluate the current state of AI ML technologies ENB diagnosis, radiological histopathological imaging, planning. By synthesizing existing evidence identifying gaps knowledge, this showcase potential benefits, limitations, future directions integrating into multidisciplinary management ENBs.

Language: Английский

Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects DOI Creative Commons
Burak Koçak, Andrea Ponsiglione, Arnaldo Stanzione

et al.

Diagnostic and Interventional Radiology, Journal Year: 2024, Volume and Issue: unknown

Published: July 2, 2024

Although artificial intelligence (AI) methods hold promise for medical imaging-based prediction tasks, their integration into practice may present a double-edged sword due to bias (i.e., systematic errors).AI algorithms have the potential mitigate cognitive biases in human interpretation, but extensive research has highlighted tendency of AI systems internalize within model.This fact, whether intentional or not, ultimately lead unintentional consequences clinical setting, potentially compromising patient outcomes.This concern is particularly important imaging, where been more progressively and widely embraced than any other field.A comprehensive understanding at each stage pipeline therefore essential contribute developing solutions that are not only less biased also applicable.This international collaborative review effort aims increase awareness imaging community about importance proactively identifying addressing prevent its negative from being realized later.The authors began with fundamentals by explaining different definitions delineating various sources.Strategies detecting were then outlined, followed techniques avoidance mitigation.Moreover, ethical dimensions, challenges encountered, prospects discussed.

Language: Английский

Citations

22
Crucial Role of Understanding in Human-Artificial Intelligence Interaction for Successful Clinical Adoption DOI
Seong Ho Park, Curtis P. Langlotz

Korean Journal of Radiology, Journal Year: 2025, Volume and Issue: 26

Published: Jan. 1, 2025

Language: Английский

Citations

1
AI in radiology: From promise to practice − A guide to effective integration DOI

Sanaz Katal,

Benjamin R York, Ali Gholamrezanezhad

et al.

European Journal of Radiology, Journal Year: 2024, Volume and Issue: 181, P. 111798 - 111798

Published: Oct. 20, 2024

Language: Английский

Citations

4
Transforming Pharmacology Education: Insights from the Pharmacology Education Project in the Era of Digital Learning DOI Creative Commons
John L. Szarek, Clare Guilding, Simon Maxwell

et al.

European Journal of Pharmacology, Journal Year: 2025, Volume and Issue: 989, P. 177258 - 177258

Published: Jan. 9, 2025

The IUPHAR Education Section's Pharmacology Project (PEP; www.pharmacologyeducation.org) provides an open-access, peer-reviewed platform to support pharmacology education globally. Launched in 2016, PEP offers a comprehensive range of freely accessible, resources, including extensive topic summaries with links videos, slide sets, and other media curated by pharmacologists catering diverse learners' needs. This paper update on PEP's growth, providing analytics user engagement feedback. averages 20,000 visits per month, peak 50,000 during the COVID-19 pandemic. Engagement rates are approximately 40%, indicating robust interaction content. Feedback from 115 users spanning 31 countries praises quality quantity resources ease navigation through website. Comparisons traditional used highlight advantages accessibility peer review. Examples use provided, emphasizing active self-directed learning methodologies. discussion includes challenges maintaining expanding platform, such as funding content curation, outlines strategies for sustainable development, role that artificial intelligence may play. is valuable resource contemporary plays vital advancing field

Language: Английский

Citations

0
Impact of artificial intelligence bias in medical systems DOI

Naina Yadav,

Ramakant Kumar, Divya Pandey

et al.

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 227 - 243

Published: Jan. 1, 2025

Language: Английский

Citations

0
Advancing personalized digital therapeutics: integrating music therapy, brainwave entrainment methods, and AI-driven biofeedback DOI Creative Commons

典弘 川角

Frontiers in Digital Health, Journal Year: 2025, Volume and Issue: 7

Published: Feb. 25, 2025

Mental health disorders and cognitive decline are pressing global concerns, increasing the demand for non-pharmacological interventions targeting emotional dysregulation, memory deficits, neural dysfunction. This review systematically examines three promising methodologies-music therapy, brainwave entrainment (binaural beats, isochronic tones, multisensory stimulation), their integration into a unified therapeutic paradigm. Emerging evidence indicates that music therapy modulates affect, reduces stress, enhances cognition by engaging limbic, prefrontal, reward circuits. Brainwave entrainment, particularly within gamma frequency range (30-100 Hz), facilitates oscillatory patterns linked to relaxation, concentration, memory, with 40 Hz showing promise enhancement, albeit individual variability. Synchronized stimulation, combining auditory visual inputs at frequencies, has demonstrated potential in enhancing supporting integrity, Alzheimer's disease. However, challenges such as patient response variability, lack of standardization, scalability hinder widespread implementation. Recent research suggests synergistic application these modalities may optimize outcomes leveraging complementary mechanisms. To actualize this, AI-driven biofeedback, enabling real-time physiological assessment individualized adjustments-such tailoring musical complexity, components-emerges solution. adaptive model treatment accessibility consistency while maximizing long-term efficacy. Although early stages, preliminary highlights its transformative reshaping strategies. Advancing this field requires interdisciplinary research, rigorous evaluation, ethical data stewardship develop innovative, patient-centered solutions mental rehabilitation.

Language: Английский

Citations

0
Biases in Artificial Intelligence Application in Pain Medicine DOI Creative Commons
Oranicha Jumreornvong,

A. Pérez,

Brian Malave

et al.

Journal of Pain Research, Journal Year: 2025, Volume and Issue: Volume 18, P. 1021 - 1033

Published: Feb. 1, 2025

Artificial Intelligence (AI) has the potential to optimize personalized treatment tools and enhance clinical decision-making. However, biases in AI, arising from sex, race, socioeconomic status (SES), statistical methods, can exacerbate disparities pain management. This narrative review examines these proposes strategies mitigate them. A comprehensive literature search across databases such as PubMed, Google Scholar, PsycINFO focused on AI applications management sources of biases. Sex racial often stem societal stereotypes, underrepresentation females, overrepresentation European ancestry patients trials, unequal access caused by systemic racism, leading inaccurate assessments misrepresentation data. SES reflect differential healthcare resources incomplete data for lower individuals, resulting larger prediction errors. Statistical biases, including sampling measurement further affect reliability algorithms. To ensure equitable delivery, this recommends employing specific fairness-aware techniques reweighting algorithms, adversarial debiasing, other methods that adjust training minimize bias. Additionally, leveraging diverse perspectives-including insights patients, clinicians, policymakers, interdisciplinary collaborators-can development fair interpretable systems. Continuous monitoring inclusive collaboration are essential addressing harnessing AI's improve outcomes populations.

Language: Английский

Citations

0
Saliency-based metric and FaceKeepOriginalAugment: a novel approach for enhancing fairness and Diversity DOI Creative Commons

Teerath Kumar,

Alessandra Mileo, Malika Bendechache

et al.

Multimedia Systems, Journal Year: 2025, Volume and Issue: 31(2)

Published: March 13, 2025

Language: Английский

Citations

0
Gender Biases within Artificial Intelligence and ChatGPT: Evidence, Sources of Biases and Solutions DOI Creative Commons

Jerlyn Q.H. Ho,

Andree Hartanto,

Andrew Koh

et al.

Computers in Human Behavior Artificial Humans, Journal Year: 2025, Volume and Issue: unknown, P. 100145 - 100145

Published: March 1, 2025

Language: Английский

Citations

0
Evolution of an Artificial Intelligence-Powered Application for Mammography DOI Creative Commons
Yuriy А. Vasilev, Denis А. Rumyantsev, Anton V. Vladzymyrskyy

et al.

Diagnostics, Journal Year: 2025, Volume and Issue: 15(7), P. 822 - 822

Published: March 24, 2025

Background: The implementation of radiological artificial intelligence (AI) solutions remains challenging due to limitations in existing testing methodologies. This study assesses the efficacy a comprehensive methodology for performance and monitoring commercial-grade mammographic AI models. Methods: We utilized combination retrospective prospective multicenter approaches evaluate neural network based on Faster R-CNN architecture with ResNet-50 backbone, trained dataset 3641 mammograms. encompassed functional calibration testing, coupled routine technical clinical monitoring. Feedback from testers radiologists was relayed developers, who made updates model. test comprised 112 medical organizations, representing 10 manufacturers mammography equipment encompassing 593,365 studies. evaluation metrics included area under curve (AUC), accuracy, sensitivity, specificity, defects, assessment scores. Results: results demonstrated significant enhancement model's through collaborative efforts among testers, radiologists. Notable improvements functionality, diagnostic stability. Specifically, AUC rose by 24.7% (from 0.73 0.91), accuracy improved 15.6% 0.77 0.89), sensitivity grew 37.1% 0.62 0.85), specificity increased 10.7% 0.84 0.93). average proportion defects declined 9.0% 1.0%, while score 63.4 72.0. Following 2 years 9 months solution integrated into compulsory health insurance system. Conclusions: multi-stage, lifecycle-based substantial potential software integration practice. Key elements this include robust requirements, continuous updates, systematic feedback collection radiologists,

Language: Английский

Citations

0