Journal of the Practice of Cardiovascular Sciences, Год журнала: 2024, Номер 10(3), С. 203 - 204
Опубликована: Сен. 1, 2024
Язык: Английский
Diagnostics, Год журнала: 2024, Номер 14(11), С. 1103 - 1103
Опубликована: Май 26, 2024
Background: Artificial intelligence (AI) can radically change almost every aspect of the human experience. In medical field, there are numerous applications AI and subsequently, in a relatively short time, significant progress has been made. Cardiology is not immune to this trend, fact being supported by exponential increase number publications which algorithms play an important role data analysis, pattern discovery, identification anomalies, therapeutic decision making. Furthermore, with technological development, have appeared new models machine learning (ML) deep (DP) that capable exploring various cardiology, including areas such as prevention, cardiovascular imaging, electrophysiology, interventional many others. sense, present article aims provide general vision current state use cardiology. Results: We identified included subset 200 papers directly relevant research covering wide range applications. Thus, paper presents arithmology, clinical or emergency procedures summarized manner. Recent studies from highly scientific literature demonstrate feasibility advantages using different branches Conclusions: The integration cardiology offers promising perspectives for increasing accuracy decreasing error rate efficiency practice. From predicting risk sudden death ability respond cardiac resynchronization therapy diagnosis pulmonary embolism early detection valvular diseases, shown their potential mitigate feasible solutions. At same limits imposed small samples studied highlighted alongside challenges presented ethical implementation; these relate legal implications regarding responsibility making processes, ensuring patient confidentiality security. All constitute future directions will allow
Язык: Английский
Процитировано
10
Indus journal of bioscience research., Год журнала: 2025, Номер 3(2), С. 213 - 224
Опубликована: Фев. 25, 2025
The increasing rate of cardiovascular diseases (CVDs) has posed a tremendous challenge to their early detection and personalized treatment. This research examines the potential Artificial Intelligence (AI) for management CVDs, in particular whether it can enhance diagnostic accuracy, personalize treatment guidelines, reduce healthcare costs. A quantitative methodology was adopted survey strategy employed collecting primary data from 300 professionals consisting cardiologists, general physicians, AI fields Punjab hospitals Pakistan. questionnaire constructed determine knowledge, experiences, perceptions regarding use services. Data analysis revealed that application had strong correlation with increased success, evident statistically significant chi-square test (p < 0.001). Furthermore, multiple regression AI, together years experience educational history, is an important contributor personalizing plans. results indicate key role making more precise diagnoses improving methods, which ultimately decrease cost patient outcomes. Yet, issues around privacy, transparency, clinician confidence systems must be resolved order widely. Future suggested by study into integration other health technologies ethics using clinical practice.
Язык: Английский
Процитировано
0
Advances in medical technologies and clinical practice book series, Год журнала: 2025, Номер unknown, С. 503 - 530
Опубликована: Фев. 14, 2025
In this study, we develop a hybrid deep learning model for IoMT which is capable of delivering efficient predictive capability. The effectiveness was enhanced through feature selection pipeline using Pearson correlation, chi-square tests, and ExtraTreesClassifier ranking importance. By eliminating redundant attributes transforming categorical data with LabelEncoder, computational efficiency performance are enhanced. integrates CNN, LSTM, GRU layers, augmented by an attention mechanism. CNN component extracts spatial patterns from the input data, while LSTM layers capture temporal sequential dependencies. mechanism further enhances focusing on most relevant features, improving interpretability overall prediction accuracy. proposed demonstrates high level performance, achieving accuracy 98.9% curated dataset.
Язык: Английский
Процитировано
0
Healthcare, Год журнала: 2024, Номер 12(14), С. 1380 - 1380
Опубликована: Июль 10, 2024
Cardiovascular and neurological diseases are a major cause of mortality morbidity worldwide. Such require careful monitoring to effectively manage their progression. Artificial intelligence (AI) offers valuable tools for this purpose through its ability analyse data identify predictive patterns. This review evaluated the application AI in cardiac clinical impact on general population. We reviewed studies cardiological fields. Our search was performed PubMed, Web Science, Embase Cochrane library databases. Of initial 5862 studies, 23 met inclusion criteria. The showed that most commonly used algorithms these fields Random Forest Neural Network, followed by logistic regression Support-Vector Machines. In addition, an ECG-AI algorithm based convolutional neural networks has been developed widely several detection atrial fibrillation with good accuracy. great potential support physicians interpretation, diagnosis, risk assessment disease management.
Язык: Английский
Процитировано
3
medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown
Опубликована: Июнь 30, 2024
Abstract Background and Objectives: Cardiovascular disease (CVD) remains the leading cause of death globally, with an estimated 18.6 million deaths in 2021. E-health interventions have potential to improve CVD management by providing remote monitoring, patient education, support. This updated systematic review meta-analysis aimed synthesize evidence on effectiveness innovative e-health technologies for treatment, including studies published up November 2023. Methods: A comprehensive literature search was conducted MEDLINE, Embase, Cochrane Central Register Controlled Trials, CINAHL, PsycINFO from inception Randomized controlled trials (RCTs) comparing technology usual care or another intervention adults at risk were included. The bias assessed using Collaboration’s tool. outcomes sufficient similar outcomes. For other outcomes, a narrative synthesis performed. certainty each outcome GRADE approach. Findings: Thirty met inclusion criteria, total 10,234 participants. included artificial intelligence, machine learning, wearable devices, mobile health, telehealth, virtual reality, augmented blockchain technology, Internet Things (IoT), big data analytics. blood pressure, cholesterol levels, medication adherence, cardiovascular events, quality life. showed that effective improving pressure (mean difference: -5.7 mmHg; 95% CI: -7.3 -4.1), levels -10.8 mg/dL; -13.9 -7.7), adherence (odds ratio: 1.48; 1.31 1.67). these moderate. indicated also reducing events However, limited, more research is needed. Conclusions: findings this provide robust significantly enhance (CVD). interventions, spanning intelligence (AI), learning (ML), health (mHealth), reality (VR), (AR), analytics, demonstrated substantial improvements key clinical limitations such as variability study design need high-quality RCTs highlight areas further research. In practice, offer promising avenues optimizing strategies.
Язык: Английский
Процитировано
1
Editora Pascal LTDA eBooks, Год журнала: 2024, Номер unknown
Опубликована: Сен. 3, 2024
É com imensa satisfação que apresentamos os Anais do Simpósio de Inteligência Artificial Aplicada à Saúde, um evento reuniu renomados pesquisadores, profissionais e estudantes para discutir avanços, desafios inovações no uso da inteligência artificial (IA) na área saúde. Este simpósio, realizado Centro Universitário Belo Horizonte - UNIBH período 22 23 maio 2024, foi marco significativo a comunidade científica, proporcionando espaço troca conhecimento colaboração entre especialistas diferentes disciplinas.
Процитировано
0
Applied Sciences, Год журнала: 2024, Номер 14(21), С. 10078 - 10078
Опубликована: Ноя. 4, 2024
Electrocardiographic (ECG) R-peak detection is essential for every sensor-based cardiovascular health monitoring system. To validate detectors, comparing the predicted results with reference annotations crucial. This comparison typically performed using tools provided by waveform database (WFDB) or custom methods. However, many studies fail to provide detailed information on validation process. The literature also highlights inconsistencies in reporting window size, a crucial parameter used compare predictions expert distinguish false peaks from true R-peak. Additionally, there need uniformity total number of beats individual collective records widely MIT-BIH arrhythmia database. Thus, we aim review methods various methodologies before their implementation real time. discusses impact non-beat when method, allowable tolerance, effects size deviations, and implications varying numbers skipping segments ECG testing, providing comprehensive guide researchers. Addressing these gaps critical as they can significantly affect validatory outcomes. Finally, conclusion section proposes structured concept future approach, integrate WFDB testing any QRS annotated Overall, this underscores importance complete transparency procedures, which prevents misleading assessments algorithms enables fair methodological comparison.
Язык: Английский
Процитировано
0
Journal of the Practice of Cardiovascular Sciences, Год журнала: 2024, Номер 10(3), С. 203 - 204
Опубликована: Сен. 1, 2024
Язык: Английский
Процитировано
0