Microvascular Research, Journal Year: 2024, Volume and Issue: 157, P. 104762 - 104762
Published: Nov. 8, 2024
Language: Английский
Journal of Clinical Medicine, Journal Year: 2025, Volume and Issue: 14(8), P. 2627 - 2627
Published: April 11, 2025
Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia, associated with significant morbidity, mortality, and healthcare burden. Despite advances in AF management, challenges persist early detection, risk stratification, treatment optimization, necessitating innovative solutions. Artificial intelligence (AI) has emerged as a transformative tool care, leveraging machine learning deep algorithms to enhance diagnostic accuracy, improve prediction, guide therapeutic interventions. AI-powered electrocardiographic screening demonstrated ability detect asymptomatic AF, while wearable photoplethysmography-based technologies have expanded real-time rhythm monitoring beyond clinical settings. AI-driven predictive models integrate electronic health records multimodal physiological data refine stroke anticoagulation decision making. In realm of treatment, AI revolutionizing individualized therapy optimizing management catheter ablation strategies. Notably, AI-enhanced electroanatomic mapping procedural guidance hold promise for improving success rates reducing recurrence. these advancements, integration remains an evolving field. Future research should focus on large-scale validation, model interpretability, regulatory frameworks ensure widespread adoption. This review explores current emerging applications highlighting its potential precision medicine patient outcomes.
Language: Английский
Citations
4
Frontiers in Computational Neuroscience, Journal Year: 2025, Volume and Issue: 19
Published: Feb. 17, 2025
Retinal imaging, used for assessing stroke-related retinal changes, is a non-invasive and cost-effective method that can be enhanced by machine learning deep algorithms, showing promise in early disease detection, severity grading, prognostic evaluation stroke patients. This review explores the role of artificial intelligence (AI) patient care, focusing on imaging integration into clinical workflows. has revealed several microvascular including decrease central artery diameter an increase vein diameter, both which are associated with lacunar intracranial hemorrhage. Additionally, such as arteriovenous nicking, increased vessel tortuosity, arteriolar light reflex, decreased fractals, thinning nerve fiber layer also reported to higher risk. AI models, Xception EfficientNet, have demonstrated accuracy comparable traditional risk scoring systems predicting For diagnosis, models like Inception, ResNet, VGG, alongside classifiers, shown high efficacy distinguishing patients from healthy individuals using imaging. Moreover, random forest model effectively distinguished between ischemic hemorrhagic subtypes based features, superior predictive performance compared characteristics. support vector achieved classification pial collateral status. Despite this advancements, challenges lack standardized protocols modalities, hesitance trusting AI-generated predictions, insufficient data electronic health records, need validation across diverse populations, ethical regulatory concerns persist. Future efforts must focus validating ensuring algorithm transparency, addressing issues enable broader implementation. Overcoming these barriers will essential translating technology personalized care improving outcomes.
Language: Английский
Citations
0
Cancer Medicine, Journal Year: 2025, Volume and Issue: 14(8)
Published: April 1, 2025
To investigate the changes in retinal oxygen kinetics and hemodynamics patients with choroidal melanoma (CM) within 2 years before after iodine-125 plaque radiotherapy (PRT) using a novel noninvasive structure-functional imaging analysis system. A cost-effective system that integrates multimodal structural functional techniques has been used, which allows rapid acquisition of vascular structural, hemodynamic, oxygenation metrics multispectral (MSI) laser speckle contrast (LSCI) techniques. Follow-ups have arranged at time implantation surgery, 1 month, 3 months, 6 12 18 24 months removal. CM PRT demonstrated significant decrease arterial concentration (CO2 a), saturation (SO2 utilization av, CO2 av), metabolism (oxygen extraction fraction, OEF) over time. However, there was no difference SO2 compared healthy controls. Systolic (Time_sr), acceleration index (ATI), resistivity (RI) gradually increase time; ATI RI were significantly higher than those At baseline, mean blood flow velocity (BFVa) (RBFa) eyes control group. BFVa RBFa showed decreasing trend PRT. In addition, some hemodynamic indicators also correlated tumor size, patient gender, age. had changes. Future research should focus on rapidly screening radiation microvascular complications exploring more timely effective interventions to protect visual function patients.
Language: Английский
Citations
0
Journal of Thermal Biology, Journal Year: 2025, Volume and Issue: 130, P. 104133 - 104133
Published: May 1, 2025
Language: Английский
Citations
0
Heliyon, Journal Year: 2024, Volume and Issue: 10(15), P. e35067 - e35067
Published: July 23, 2024
In the study of atrial fibrillation (AF), a prevalent cardiac arrhythmia, utilization artificial intelligence (AI) in diagnostic and therapeutic strategies holds potential to address existing limitations. This research employs bibliometrics objectively investigate hotspots, development trends, issues application AI within AF field, aiming provide targeted recommendations for relevant researchers.
Language: Английский
Citations
3
medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown
Published: April 18, 2024
Abstract Background Cardiovascular risk prediction models based on sociodemographic factors and traditional clinical measurements have received significant attention. With rapid development in deep learning for image analysis the last decade well-known association between micro- macrovascular complications, some recent studies focused of cardiovascular using retinal fundus images. The objective this scoping review is to identify describe images predict markers diseases. Methods We searched MEDLINE Embase peer-reviewed articles 17 November 2023. Abstracts relevant full-text were independently screened by two reviewers. included that used (e.g. blood pressure, coronary artery calcification, intima-media thickness) or diseases (prevalent incident). Studies only predefined characteristics tortuosity, fractal dimension) not considered. Study extracted first author verified senior author. Results are presented descriptive statistics. 24 review, published 2018 Among these, 21 (88%) cross-sectional eight (33%) follow-up with outcome CVD. Five a combination both designs. Most (n=23, 96%) convolutional neural networks process found nine (38%) incorporated four (17%) compared results commonly scores prospective setting. Three these reported improved discriminative performance. External validation was rare (n=5, 21%). Only made their code publicly available. Conclusions There an increasing interest assessment. However, there need more studies, comparisons augmented factors. Moreover, extensive sharing necessary make findings reproducible impactful beyond specific study.
Language: Английский
Citations
1
European Heart Journal - Digital Health, Journal Year: 2024, Volume and Issue: 5(6), P. 660 - 669
Published: Sept. 9, 2024
Abstract Rapid development in deep learning for image analysis inspired studies to focus on predicting cardiovascular risk using retinal fundus images. This scoping review aimed identify and describe images predict markers diseases. We searched MEDLINE Embase 17 November 2023. Abstracts relevant full-text articles were independently screened by two reviewers. included that used the of or diseases (CVDs) excluded only predefined characteristics Study presented descriptive statistics. 24 published between 2018 Among these, 23 (96%) cross-sectional eight (33%) follow-up with clinical CVD outcomes. Seven a combination both designs. Most convolutional neural networks process found nine (38%) incorporated factors prediction four (17%) compared results commonly scores prospective setting. Three these reported improved discriminative performance. External validation models was rare (21%). There is increasing interest assessment some demonstrating improvements prediction. However, more studies, comparisons scores, augmented traditional can strengthen further research field.
Language: Английский
Citations
0
Microvascular Research, Journal Year: 2024, Volume and Issue: 157, P. 104762 - 104762
Published: Nov. 8, 2024
Language: Английский
Citations
0