The Role of Wearable Devices in Chronic Disease Monitoring and Patient Care: A Comprehensive Review

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

Published: Sept. 8, 2024

Wearable health devices are becoming vital in chronic disease management because they offer real-time monitoring and personalized care. This review explores their effectiveness challenges across medical fields, including cardiology, respiratory health, neurology, endocrinology, orthopedics, oncology, mental health. A thorough literature search identified studies focusing on wearable devices' impact patient outcomes. In wearables have proven effective for hypertension, detecting arrhythmias, aiding cardiac rehabilitation. these enhance asthma continuous of critical parameters. Neurological applications include seizure detection Parkinson's management, with showing promising results improving technology advances thyroid dysfunction monitoring, fertility tracking, diabetes management. Orthopedic improved postsurgical recovery rehabilitation, while help early complication oncology. Mental benefits anxiety detection, post-traumatic stress disorder reduction through biofeedback. conclusion, transformative potential managing illnesses by enhancing engagement. Despite significant improvements adherence outcomes, data accuracy privacy persist. However, ongoing innovation collaboration, we can all be part the solution to maximize technologies healthcare.

Language: Английский

---

AI-Driven Heart Disease Prediction Using Machine Learning and Deep Learning Techniques

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2025, Volume and Issue: 11(2)

Published: April 10, 2025

Heart disease remains a leading cause of mortality worldwide, necessitating early detection and prevention strategies. This study explores machine learning (ML) approaches for predicting heart using patient datasets. Various ML algorithms, including Logistic Regression, Naive Bayes, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree, Random Forest, XGBoost, an Artificial Neural Network (ANN), were implemented to classify presence. The Forest model achieved the highest accuracy 95%. findings demonstrate that can significantly enhance prediction, aiding diagnosis treatment.

Language: Английский

---

Artificial Intelligence in Sports Medicine: Reshaping Electrocardiogram Analysis for Athlete Safety—A Narrative Review

Sports, Journal Year: 2024, Volume and Issue: 12(6), P. 144 - 144

Published: May 26, 2024

Artificial Intelligence (AI) is redefining electrocardiogram (ECG) analysis in pre-participation examination (PPE) of athletes, enhancing the detection and monitoring cardiovascular health. Cardiovascular concerns, including sudden cardiac death, pose significant risks during sports activities. Traditional ECG, essential yet limited, often fails to distinguish between benign adaptations serious conditions. This narrative review investigates application machine learning (ML) deep (DL) ECG interpretation, aiming improve arrhythmias, channelopathies, hypertrophic cardiomyopathies. A literature over past decade, sourcing from PubMed Google Scholar, highlights growing adoption AI medicine for its precision predictive capabilities. algorithms excel at identifying complex patterns, potentially overlooked by traditional methods, are increasingly integrated into wearable technologies continuous monitoring. Overall, offering a comprehensive overview current innovations outlining future advancements, this supports professionals merging screening methods with state-of-the-art technologies. approach aims enhance diagnostic accuracy efficiency athlete care, promoting early more effective through AI-enhanced within PPEs.

Language: Английский

---

Real-Time Myocardial Infarction Detection Approaches with a Microcontroller-Based Edge-AI Device

Sensors, Journal Year: 2024, Volume and Issue: 24(3), P. 828 - 828

Published: Jan. 26, 2024

Myocardial Infarction (MI), commonly known as heart attack, is a cardiac condition characterized by damage to portion of the heart, specifically myocardium, due disruption blood flow. Given its recurring and often asymptomatic nature, there need for continuous monitoring using wearable devices. This paper proposes single-microcontroller-based system designed automatic detection MI based on Edge Computing paradigm. Two solutions are evaluated, Machine Learning (ML) Deep (DL) techniques. The developed algorithms two different approaches currently available in literature, they optimized deployment low-resource hardware. A feasibility assessment their implementation single 32-bit microcontroller with an ARM Cortex-M4 core was examined, comparison terms accuracy, inference time, memory usage detailed. For ML techniques, significant data processing feature extraction, coupled simpler Neural Network (NN) involved. On other hand, second method, DL, employs Spectrogram Analysis extraction Convolutional (CNN) longer time higher utilization. Both methods employ same low power hardware reaching accuracy 89.40% 94.76%, respectively. final prototype energy-efficient capable real-time without connect remote servers or cloud. All performed at edge, enabling NN microcontroller.

Language: Английский

---

A comprehensive review of deep learning-based models for heart disease prediction

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(10)

Published: Aug. 19, 2024

Heart disease (HD) is one of the leading causes death in humans, posing a heavy burden on society, families, and patients. Real-time prediction HD can reduce mortality rates crucial for timely intervention treatment HD. Deep learning (DL)-related methods have higher accuracy real-time performance predicting In this study, we comprehensively compared evaluated contributions limitations DL algorithms, extended deep (ETDL) integrated (integrated DL) algorithms that combine with other technologies The articles considered span period from 2018 to 2023, after rigorous screening, 64 were selected preliminary research. A systematic literature review HDP will provide future researchers comprehensive understanding existing related healthcare industry. Furthermore, it discusses popular datasets employed deploying numerous models. Additionally, reveals open problems or challenges encountered by previous researchers. Notably, most prevalent challenge scarcity large discrete datasets, followed need further improvement

Language: Английский

---

Comparison Between a Single-Lead ECG Garment Device and a Holter Monitor: A Signal Quality Assessment

Journal of Medical Systems, Journal Year: 2024, Volume and Issue: 48(1)

Published: May 27, 2024

Abstract Wearable electronics are increasingly common and useful as health monitoring devices, many of which feature the ability to record a single-lead electrocardiogram (ECG). However, recording ECG commonly requires user touch device complete lead circuit, prevents continuous data acquisition. An alternative approach enable without initiation is embed leads in garment. This study assessed obtained from YouCare (a novel sensorized garment) via comparison with conventional Holter monitor. A cohort thirty patients (age range: 20–82 years; 16 females 14 males) were enrolled monitored for twenty-four hours both devices qualitatively by panel three expert cardiologists quantitatively analyzed using specialized software. Patients also responded survey about comfort compared The was have 70% its signals “Good”, 12% “Acceptable”, 18% “Not Readable”. R-wave, independently recorded monitor, synchronized within measurement error during 99.4% cardiac cycles. In addition, found more comfortable than monitor (comfortable 22 vs. 5 uncomfortable 1 18, respectively). Therefore, quality collected garment-based comparable when signal sufficiently acquired, garment comfortable.

Language: Английский

---

The Power of AI-Assisted Diagnosis

ICST Transactions on e-Education and e-Learning, Journal Year: 2023, Volume and Issue: 8(4), P. e3 - e3

Published: Sept. 6, 2023

The rapid advancements in artificial intelligence (AI) have unleashed a wave of transformative technologies, and one area that has witnessed significant progress is AI-assisted diagnosis healthcare. With the ability to analyze vast amounts medical data, learn from patterns, make accurate predictions, AI systems hold immense potential revolutionize diagnostic process, enabling earlier detection, improved accuracy, personalized treatment recommendations. This review aims explore impact healthcare, specifically focusing on its role assisting physicians with diagnosis, highlighting benefits, challenges, ethical considerations associated integration into clinical practice. Through utilization AI's capabilities, enhancement patient outcomes, optimization resource allocation, reshaping professionals' approaches can be achieved.

Language: Английский

---

Emerging intelligent wearable devices for cardiovascular health monitoring

Nano Today, Journal Year: 2024, Volume and Issue: 59, P. 102544 - 102544

Published: Nov. 8, 2024

Language: Английский

---

Long-Short-Term-Memory-Based Deep Stacked Sequence-to-Sequence Autoencoder for Health Prediction of Industrial Workers in Closed Environments Based on Wearable Devices

Sensors, Journal Year: 2023, Volume and Issue: 23(18), P. 7874 - 7874

Published: Sept. 14, 2023

To reduce the risks and challenges faced by frontline workers in confined workspaces, accurate real-time health monitoring of their vital signs is essential for improving safety productivity preventing accidents. Machine-learning-based data-driven methods have shown promise extracting valuable information from complex data. However, practical industrial settings still struggle with data collection difficulties low prediction accuracy machine learning models due to work environment. tackle these challenges, a novel approach called long short-term memory (LSTM)-based deep stacked sequence-to-sequence autoencoder proposed predicting status spaces. The first step involves implementing wireless acquisition system using edge-cloud platforms. Smart wearable devices are used collect multiple sources, like temperature, heart rate, pressure. These comprehensive provide insights into workers’ within closed space manufacturing factory. Next, hybrid model combining support vector (SVM) constructed anomaly detection. LSTM-based specifically designed learn discriminative features time-series reconstructing input thus generating fused features. then fed one-class SVM, enabling recognition status. effectiveness superiority demonstrated through comparisons other existing approaches.

Language: Английский

---

Reconstructing 12-lead ECG from reduced lead sets using an encoder–decoder convolutional neural network

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 104, P. 107486 - 107486

Published: Jan. 9, 2025

Language: Английский

---