Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 92 - 108
Published: Dec. 24, 2024
Language: Английский
Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 473 - 504
Published: Jan. 10, 2025
The utilization of the wearable devices (WDs) that are enhanced by artificial intelligence (AI) can have a notable potential in healthcare. This chapter aimed to provide an overview applications AI-driven WDs enhancing early detection and management virus infections. First, we presented examples highlight capabilities very monitoring infections such as COVID-19. In addition, provided on utility machine learning algorithms analyze large data for signs We also overviewed enable real-time surveillance effective outbreak management. showed how this be achieved via collection analysis diverse WDs' across various populations. Finally, discussed challenges ethical issues comes with virology diagnostics, including concerns about privacy security well issue equitable access.
Language: Английский
Citations
0
The Journal of Critical Care Medicine, Journal Year: 2025, Volume and Issue: 11(1), P. 70 - 77
Published: Jan. 1, 2025
Abstract Introduction Determining the optimal timing for extubation in critically ill patients is essential to prevent complications. Predictive models based on Machine Learning (ML) have proven effective anticipating weaning success, thereby improving clinical outcomes. Aim of study The aimed evaluate predictive capacity five ML techniques, both supervised and unsupervised, applied spontaneous breathing trial (SBT), objective cough measurement (OCM), diaphragmatic contraction velocity (DCV) estimate a favorable outcome SBT patients. Material Methods A post hoc analysis conducted COBRE-US study. included ICU who underwent evaluation SBT, OCM, DCV. Five techniques were applied: unsupervised data training group test group. diagnostic performance each method was determined using accuracy. Results In predicting all methods displayed same accuracy (77.3%) (69.6%). decision trees demonstrated highest accuracy, 89.8% 95.7% other also showed good accuracy: 85.9% 93.5% Conclusions DCV, as input variables through artificial neural networks best performance. This suggests that these can effectively classify are likely succeed during process from mechanical ventilation.
Language: Английский
Citations
0
Artificial Intelligence in Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 103130 - 103130
Published: April 1, 2025
Language: Английский
Citations
0
npj Digital Medicine, Journal Year: 2024, Volume and Issue: 7(1)
Published: Nov. 11, 2024
In the future, large language models (LLMs) may enhance delivery of healthcare, but there are risks misuse. These methods be trained to allocate resources via unjust criteria involving multimodal data - financial transactions, internet activity, social behaviors, and healthcare information. This study shows that LLMs biased in favor collective/systemic benefit over protection individual rights could facilitate AI-driven credit systems.
Language: Английский
Citations
3
Journal of Personalized Medicine, Journal Year: 2024, Volume and Issue: 14(7), P. 703 - 703
Published: June 30, 2024
In the realm of computational pathology, scarcity and restricted diversity genitourinary (GU) tissue datasets pose significant challenges for training robust diagnostic models. This study explores potential Generative Adversarial Networks (GANs) to mitigate these limitations by generating high-quality synthetic images rare or underrepresented GU tissues. We hypothesized that augmenting data pathology models with GAN-generated images, validated through pathologist evaluation quantitative similarity measures, would significantly enhance model performance in tasks such as classification, segmentation, disease detection.
Language: Английский
Citations
2
IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 126043 - 126062
Published: Jan. 1, 2024
The rapid advancement and integration of artificial intelligence (AI) in various domains society have given rise to a complex landscape public concerns. This research endeavors systematically explore these concerns by employing multi-stage methodology that combines large-scale social media data collection from Twitter advanced text analytics. study identifies seven distinct clusters concerns, encompassing privacy security, workforce displacement, existential risks, ethical implications, dependency on AI, misuse lack transparency. To further contextualize findings, the Delphi method was employed gather insights AI ethics experts, providing deeper understanding public's apprehensions. results underscore critical need for addressing foster trust acceptance technologies. comprehensive analysis offers valuable guidance policymakers, developers, stakeholders navigate mitigate multifaceted issues associated with ultimately contributing more informed responsible deployment. By aims pave way ethically sound socially acceptable into society, ensuring benefits can be realized while minimizing potential risks negative impacts. Through this systematic approach, highlights importance continuous monitoring proactive management AI-related sustain confidence promote beneficial innovation.
Language: Английский
Citations
2
Journal of Inflammation Research, Journal Year: 2024, Volume and Issue: Volume 17, P. 5723 - 5740
Published: Aug. 1, 2024
Primary Sjögren's syndrome (pSS) is an autoimmune condition marked by lymphocyte infiltration in the exocrine glands. Our study aimed to identify a novel biomarker for pSS improve its diagnosis and treatment.
Language: Английский
Citations
2
bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown
Published: May 21, 2024
Abstract In the realm of computational pathology, scarcity and restricted diversity genitourinary (GU) tissue datasets pose significant challenges for training robust diagnostic models. This study explores potential Generative Adversarial Networks (GANs) to mitigate these limitations by generating high-quality synthetic images rare or underrepresented GU tissues. We hypothesized that augmenting data pathology models with GAN-generated images, validated through pathologist evaluation quantitative similarity measures, would significantly enhance model performance in tasks such as classification, segmentation, disease detection. To test this hypothesis, we employed a GAN produce eight different The quality was rigorously assessed using Relative Inception Score (RIS) 17.2 ± 0.15 Fréchet Distance (FID) stabilized at 120, metrics reflect visual statistical fidelity generated real histopathological images. Additionally, received an 80% approval rating from board-certified pathologists, further validating their realism utility. used alternative Spatial Heterogeneous Recurrence Quantification Analysis (SHRQA) assess prostate tissue. allowed us make comparison between original context features, which were pathologist’s evaluation. Future work will focus on implementing deep learning evaluate augmented provide more comprehensive understanding utility enhancing workflows. not only confirms feasibility GANs augmentation medical image analysis but also highlights critical role addressing dataset imbalance. refining generative even diverse complex representations, potentially transforming landscape diagnostics AI-driven solutions. CONSENT FOR PUBLICATION All authors have provided consent publication.
Language: Английский
Citations
1
Journal of the American Medical Informatics Association, Journal Year: 2024, Volume and Issue: 31(12), P. 2820 - 2828
Published: July 3, 2024
This study aims to develop machine learning models that provide both accurate and equitable predictions of 2-year stroke risk for patients with atrial fibrillation across diverse racial groups.
Language: Английский
Citations
1
Diagnostics, Journal Year: 2024, Volume and Issue: 14(15), P. 1594 - 1594
Published: July 24, 2024
While machine learning (ML) models hold promise for enhancing the management of acute kidney injury (AKI) in sepsis patients, creating that are equitable and unbiased is crucial accurate patient stratification timely interventions. This study aimed to systematically summarize existing evidence determine effectiveness ML algorithms predicting mortality patients with sepsis-associated AKI. An exhaustive literature search was conducted across several electronic databases, including PubMed, Scopus, Web Science, employing specific terms. review included studies published from 1 January 2000 February 2024. Studies were if they reported on use not written English or insufficient data excluded. Data extraction quality assessment performed independently by two reviewers. Five final analysis, reporting a male predominance (>50%) among Limited race ethnicity available studies, White comprising majority cohorts. The predictive demonstrated varying levels performance, area under receiver operating characteristic curve (AUROC) values ranging 0.60 0.87. Algorithms such as extreme gradient boosting (XGBoost), random forest (RF), logistic regression (LR) showed best performance terms accuracy. findings this show immense ability identify high-risk predict progression AKI early, improve survival rates. However, lack fairness critically ill could perpetuate healthcare disparities. Therefore, it develop trustworthy ensure their widespread adoption reliance both professionals patients.
Language: Английский
Citations
1