Machine Learning
Studies in this Category
Seismocardiography Pig Hypovolemia Dataset for Signal Quality Indexing and Validated Cardiac Timings
This study provides a high-quality dataset of heart vibrations from pigs, helping researchers develop better tools for tracking heart health using wearable sensors.
Severe aortic stenosis detection using seismocardiography
This study shows that chest vibrations measured by a small device can accurately detect severe heart valve disease, offering a low-cost alternative to traditional tests like echocardiography.
SCG With Your Phone: Diagnosis of Rhythmic Spectrum Disorders in Field Conditions
This study shows that smartphones can reliably monitor heart rhythms using vibrations from the chest, thanks to advanced AI that works even in noisy, real-world conditions.
SEISMIC-HF 1: key findings from AHA24 and implications for remote cardiac monitoring
This study shows that a wearable patch can estimate heart pressure in patients with heart failure as accurately as invasive tests, offering hope for better remote care options.
Fully automated template matching method for ECG-free heartbeat detection in cardiomechanical signals of healthy and pathological subjects
This study developed a new method to detect heartbeats from chest vibrations without needing ECG, showing high accuracy even for patients with heart diseases. It could enable long-term heart monitoring using wearable devices.
Monitoring of respiration and cardiorespiratory interactions from multichannel seismocardiography signals
This study shows that chest vibrations measured by accelerometers can accurately track breathing and heart-lung interactions, regardless of sensor placement. It introduces a new method to analyze these signals for better health monitoring.
Deep Learning Predicts Cardiac Output from Seismocardiographic Signals in Heart Failure
This study shows that wearable sensors using chest vibrations and heart signals can estimate heart function as accurately as invasive tests, offering a safer and more accessible option for heart failure patients.
MSCardio Seismocardiography (SCG) Dataset
This dataset shows how smartphones can record heart vibrations to help researchers study heart health remotely and affordably.
From video to vital signs: a new method for contactless multichannel seismocardiography
This study shows that smartphone videos can track heart vibrations using QR stickers on the chest, offering a low-cost way to monitor heart health and detect issues early, with accuracy comparable to clinical tools.
Estimation of cardiorespiratory fitness in healthy using seismocardiography
This study shows that a chest vibration sensor can accurately measure fitness levels without exercise, offering a simple and affordable way to track heart health.
Non-exercise estimation of peak oxygen uptake in patients with ischaemic heart disease and heart failure using seismocardiography
This study found that a new heart monitoring method using vibrations (SCG) was not accurate enough to estimate fitness levels or track improvements in heart patients after rehabilitation.
Robustness of Persistence Diagrams to Time-Delay for Seismocardiogram Signal Quality Assessment*
This study shows that a new method using persistence diagrams can assess heart vibration signal quality without needing ECG, making it more reliable for wearable heart monitors in noisy environments.
Digital Twin-Based Investigation of Seismocardiogram Sensitivity to Tissue Mechanics and Myocardial Motion
This study shows how personalized computer models based on CT scans can simulate heart vibrations (SCG) and improve non-invasive heart monitoring by accounting for individual anatomy and tissue properties.
The acceptability of a novel seismocardiography device for measuring VO2 max in a workplace setting: a mixed methods approach
This study shows that a new heart vibration device can measure fitness at work more comfortably than exercise tests, but better training for practitioners is needed to make it widely usable.
Deep learning-based beat-to-beat delineation of heart sounds and fiducial points in seismocardiography
This study developed an AI tool that accurately detects key heart vibration points, enabling better heart monitoring for patients with or without heart disease.
Non-Invasive Wearable Technology to Predict Heart Failure Decompensation
This study reviews wearable devices like smartwatches and patches that monitor heart and lung health to predict worsening heart failure. These technologies could help doctors intervene earlier and prevent hospitalizations, but more research is needed to make them reliable and easy to use.
LubDubDecoder: Bringing Micro-Mechanical Cardiac Monitoring to Hearables
This study shows how regular earbuds can monitor heart health by detecting subtle vibrations linked to heartbeats, offering a convenient way to track cardiovascular health daily.
Smartphone-Based Recognition of Heart Failure by Means of Microelectromechanical Sensors
This study shows that smartphones can detect heart failure with high accuracy using built-in motion sensors, offering a simple and non-invasive way to monitor heart health remotely.
A Wavelet-Based Approach for Motion Artifact Reduction in Ambulatory Seismocardiography
This study developed a method to clean heart vibration signals for wearable devices, making them more accurate even during walking, without needing extra sensors like ECG. This could improve heart monitoring in daily life and hospitals.
Extracting Cardiovascular-Induced Chest Vibrations from Ordinary Chest Videos: A Comparative Study
This study shows that smartphone videos can accurately track heart vibrations using advanced computer vision methods, offering a comfortable and non-invasive way to monitor heart health.
Advances in Respiratory Monitoring: A Comprehensive Review of Wearable and Remote Technologies
This study reviews wearable and remote devices for tracking breathing, from chest belts to advanced sensors like fiber optics and radar. These technologies could help monitor respiratory health at home or in clinics, improving care for conditions like asthma and sleep apnea.
Evaluating Seismocardiography as a Non-Exercise Method for Estimating Maximal Oxygen Uptake
This study shows that the Seismofit® device can estimate fitness levels (VO2MAX) without exercise, offering a simpler alternative to traditional lab tests with good accuracy and reliability.
Smartphone-Derived Seismocardiography: Robust Approach for Accurate Cardiac Energy Assessment in Patients with Various Cardiovascular Conditions
This study shows that smartphones can reliably measure heart vibrations to assess cardiac energy, making it easier for patients to monitor their heart health at home.
Deep Learning for identifying systolic complexes in SCG traces: a cross-dataset analysis
This study shows how deep learning can identify heart activity from chest vibrations, even in real-world conditions, by using data from multiple sensors and personalizing the model for each user.
Seismocardiography for Emotion Recognition: A Study on EmoWear with Insights from DEAP
This study shows that a single wearable accelerometer on the chest can track emotions by measuring heart and breathing vibrations, offering a simpler and cheaper way to integrate emotion recognition into daily life.
A deep learning approach to using wearable seismocardiography (SCG) for diagnosing aortic valve stenosis and predicting aortic hemodynamics obtained by 4D flow MRI
This study shows that wearable heart vibration sensors combined with AI can predict blood flow and diagnose aortic valve problems as accurately as advanced MRI scans, offering a cheaper and faster alternative for heart disease screening.
Postural and longitudinal variability in seismocardiographic signals
This study shows that SCG signals, which measure heart vibrations, change with posture but remain stable over time, making them promising for long-term heart monitoring.
Point-of-care aid-to-diagnosis for heart failure using artificial intelligence based on seismocardiography acquired with a smartphone in the emergency department
This study shows that a smartphone app using heart vibrations and AI can help diagnose heart failure quickly and accurately in emergency settings.
Waveform Similarity Analysis Using Graph Mining for the Optimization of Sensor Positioning in Wearable Seismocardiography
This study shows that placing a wearable heart sensor near the mitral valve while lying down gives the most consistent readings, helping improve heart monitoring accuracy for future clinical use.
Cross-Domain Detection of Pulmonary Hypertension in Human and Porcine Heart Sounds
This study shows that heart sound recordings from pigs can help train AI models to detect pulmonary hypertension in humans, offering a non-invasive and accurate alternative to invasive procedures like catheterization.
Synthetic Seismocardiography Signal Generation by a Generative Adversarial Network
Researchers used AI to create realistic heart vibration signals, helping scientists train heart-monitoring systems without needing expensive patient data collection.
Introducing the Electromechanical Risk Factor Score Derived from Seismocardiography for Estimating the Likelihood of Coronary Artery Disease
This study developed a new heart vibration-based score that better detects coronary artery disease, reducing false positives compared to current methods.
Revolutionizing smartphone gyrocardiography for heart rate monitoring: overcoming clinical validation hurdles
This study highlights how smartphone gyroscopes can accurately monitor heart rate, offering a practical and non-invasive alternative to traditional methods like ECG and PPG, even during daily activities.
Accuracy of a Clinical Applicable Method for Prediction of VO2max Using Seismocardiography
This study shows that a chest vibration-based method (SCG) can accurately predict fitness levels (VO2max) in healthy adults, potentially offering a simpler alternative to traditional exercise tests.
Correlation between diastolic seismocardiography variables and echocardiography variables
This study shows that chest vibrations (SCG) can reliably measure heart relaxation, similar to echocardiography, offering a simpler and faster way to monitor heart health at home or in clinics.
Heartbeat Detection in Seismocardiograms with Semantic Segmentation
This study shows that a deep learning model can accurately detect heartbeats from chest vibrations, offering a promising alternative to traditional ECG-based methods for heart monitoring.
Respiratory Modulation of Sternal Motion in the Context of Seismocardiography
This study shows how chest vibrations (SCG) can track breathing and heart activity using a single wearable sensor, paving the way for simpler health monitoring devices.
Toward Wearable Estimation of Tidal Volume via Electrocardiogram and Seismocardiogram Signals
This research shows how a wearable chest patch can estimate lung air volume using heart signals and machine learning, offering a step toward easy, continuous respiratory health monitoring.
Estimation of Changes in Intracardiac Hemodynamics Using Wearable Seismocardiography and Machine Learning in Patients With Heart Failure: A Feasibility Study
This study shows that a wearable patch can track heart pressure changes in heart failure patients, offering a cheaper way to monitor their condition remotely and reduce hospital visits.
BIOWISH: Biometric Recognition using Wearable Inertial Sensors detecting Heart Activity
This research shows how wearable sensors can use heart vibrations to identify people with high accuracy, even weeks after enrollment. It also demonstrates how these sensors can recognize activities like walking or lying down, making them useful for secure health monitoring.
Wearable Seismocardiography‐Based Assessment of Stroke Volume in Congenital Heart Disease
This study shows that a wearable device using chest vibrations and heart signals can estimate blood flow in children with heart defects, offering a way to monitor heart health remotely and affordably.
Computer-Aided Detection of Fiducial Points in Seismocardiography through Dynamic Time Warping
This study shows how advanced algorithms can improve heart monitoring by accurately detecting key heart signals from chest vibrations, helping predict heart failure with over 92% accuracy.
Effect of Normal Breathing and Breath Holding on Seismocardiographic Signals and Heart Rate
This study shows that holding your breath can make heart vibration signals more consistent, which could help improve heart health monitoring techniques.
Enabling Wearable Pulse Transit Time-Based Blood Pressure Estimation for Medically Underserved Areas and Health Equity: Comprehensive Evaluation Study (Preprint)
This study shows that a wearable device can accurately measure blood pressure without a cuff, helping underserved communities monitor hypertension remotely and conveniently.
Detecting Aortic Stenosis Using Seismocardiography and Gryocardiography Combined with Convolutional Neural Networks
This study shows that heart vibrations measured by wearable sensors and analyzed with AI can detect aortic stenosis with over 98% accuracy, offering a simpler alternative to traditional echocardiography.
Determination of Maximal Oxygen Uptake Using Seismocardiography at Rest
This study explores using chest vibrations (SCG) to estimate fitness levels without exercise. While the method shows potential, it needs refinement to match clinical accuracy standards.
Detecting Coronary Artery Disease Using Rest Seismocardiography and Gyrocardiography
This study shows that chest vibrations measured by a wearable sensor can detect heart disease with high accuracy, offering a potential at-home screening tool for coronary artery disease.
The Latest Progress and Development Trend in the Research of Ballistocardiography (BCG) and Seismocardiogram (SCG) in the Field of Health Care
This study reviews how BCG and SCG technologies are being revived to monitor heart and health conditions, with potential applications in sleep and cardiovascular care. It calls for making these technologies more accessible and standardized for everyday use.
Smart Seismocardiography: A Machine Learning Approach for Automatic Data Processing
This research shows how a low-cost sensor and machine learning can track heart vibrations to monitor cardiac health, paving the way for affordable wearable devices.
Advanced Fusion and Empirical Mode Decomposition-Based Filtering Methods for Breathing Rate Estimation from Seismocardiogram Signals
This study shows how heart vibration signals can be used to estimate breathing rate accurately without invasive procedures, using advanced signal processing techniques like EMD and fusion methods.
A Comprehensive Review on Seismocardiogram: Current Advancements on Acquisition, Annotation, and Applications
This study reviews how SCG, a method to measure heart vibrations, is advancing with new sensors and AI to monitor heart health more effectively, even at home. It also highlights challenges like reducing noise in signals during movement.
Seismocardiography: Interpretation and Clinical Application
This research shows how heart vibrations (SCG) can help monitor heart health. It links SCG signals to heart events, tracks therapy effects in heart failure patients, and estimates fitness levels without exercise tests, making heart monitoring simpler and more accessible.
Non-Invasive Wearable Patch Utilizing Seismocardiography for Peri-Operative Use in Surgical Patients
This study shows that a wearable patch can accurately monitor heart function during and after surgery, offering a non-invasive alternative to traditional methods.
High-Accuracy, Unsupervised Annotation of Seismocardiogram Traces for Heart Rate Monitoring
This study shows how chest vibrations can be used to monitor heartbeats accurately without needing traditional ECG sensors, paving the way for wearable heart monitors in daily life.
Contactless Seismocardiography via Deep Learning Radars
This research shows how radar and AI can monitor heart vibrations without physical contact, achieving accuracy similar to clinical ultrasound for detecting key heart movements.
Heart Beat Detection from Smartphone SCG Signals: Comparison with Previous Study on HR Estimation
This study shows that smartphones can accurately detect heartbeats using vibrations from the chest, with improved algorithms achieving near-perfect accuracy.
Performance Analysis of Gyroscope and Accelerometer Sensors for Seismocardiography-Based Wearable Pre-Ejection Period Estimation
This study shows that combining gyroscope and accelerometer data improves heart health monitoring, making wearable devices more accurate for tracking cardiac function.
A Unified Framework for Quality Indexing and Classification of Seismocardiogram Signals
This study shows how a new method can improve the quality and analysis of heart vibration signals, helping detect issues like misplaced sensors with high accuracy. It could make heart monitoring more reliable and automated for patients and clinicians.
Visualization of the Multichannel Seismocardiogram
This study explores ways to visualize chest vibrations caused by heart activity using data from 16 sensors. The methods help researchers better understand how these vibrations relate to heart function.
Recent Advances in Seismocardiography
This study reviews how SCG, a method to measure heart vibrations, is improving with new sensors and AI, showing promise for diagnosing heart conditions like atrial fibrillation and heart failure noninvasively.
Influence of Gravitational Offset Removal on Heart Beat Detection Performance from Android Smartphone Seismocardiograms
This study shows that smartphones can accurately detect heartbeats using vibrations from the chest, even without removing gravitational effects, thanks to advanced signal processing techniques.
Multiclass Classifier based Cardiovascular Condition Detection Using Smartphone Mechanocardiography
This study shows that smartphones can detect heart conditions like AFib and heart attacks using built-in sensors and machine learning, offering a promising tool for global heart health monitoring.
Comprehensive Analysis of Cardiogenic Vibrations for Automated Detection of Atrial Fibrillation Using Smartphone Mechanocardiograms
This study shows that a smartphone can detect atrial fibrillation (AFib) with high accuracy using chest vibrations, making heart monitoring accessible and easy for everyone without extra devices.
Wearable ballistocardiogram and seismocardiogram systems for health and performance
This study shows how wearable sensors can track heart health by measuring vibrations caused by heartbeats, offering a low-cost way to monitor conditions like heart failure and optimize physical performance in challenging environments.
Novel Wearable Seismocardiography and Machine Learning Algorithms Can Assess Clinical Status of Heart Failure Patients
This study shows that a wearable device can track heart failure severity by analyzing chest vibrations during exercise, potentially helping doctors monitor patients remotely and adjust treatments effectively.
Machine Learning Based Classification of Myocardial Infarction Conditions Using Smartphone-Derived Seismo- and Gyrocardiography
Researchers used smartphone sensors to track heart changes in heart attack patients before and after treatment, achieving promising accuracy with machine learning methods.
Determining the Respiratory State From a Seismocardiographic Signal--A Machine Learning Approach
This study shows that chest vibrations from the heart (SCG signals) can predict breathing patterns using advanced machine learning, with neural networks being the most accurate method. This could help monitor breathing and heart health more easily and affordably.
A Machine Learning Approach to Assess the Separation of Seismocardiographic Signals by Respiration
This study shows that machine learning can classify heart vibrations based on breathing patterns, with lung volume proving to be a better grouping method than respiratory phases for reducing signal variability.
Automatic Detection of Seismocardiogram Sensor Misplacement for Robust Pre-Ejection Period Estimation in Unsupervised Settings
This research shows that SCG sensors must be correctly placed on the chest to measure heart function accurately. A machine learning algorithm helps users detect misplacement, improving home-based heart monitoring for heart failure patients.
Universal Pre-Ejection Period Estimation Using Seismocardiography: Quantifying the Effects of Sensor Placement and Regression Algorithms
This study shows that placing heart vibration sensors below the clavicle improves heart function tracking accuracy, and wearable devices can work over thin clothing without losing precision.
A Hidden Markov Model for Seismocardiography
This study shows that heart vibrations can be analyzed using a mathematical model to measure heart rate and other metrics with high accuracy, even using inexpensive sensors at home.
A Cardiac Early Warning System with Multi Channel SCG and ECG Monitoring for Mobile Health
This study shows how wearable sensors can monitor heart health by combining electrical and mechanical heart signals, offering an affordable and reliable early warning system for heart disease.
Accurate and consistent automatic seismocardiogram annotation without concurrent ECG
This study developed a method to analyze heart vibrations without needing ECG data, showing promise for affordable and standalone heart monitoring devices.
Beat-to-beat estimation of LVET and QS2 indices of cardiac mechanics from wearable seismocardiography in ambulant subjects
This study shows that smartphones can accurately detect heartbeats using vibrations from the chest, with improved algorithms achieving near-perfect accuracy.
Estimating Cardiac Stroke Volume from the Seismocardiogram Signal
This study shows that heart vibrations measured on the chest (SCG) can estimate the amount of blood pumped by the heart (stroke volume) almost as accurately as ultrasound methods, using machine learning techniques.
Wearable Seismocardiography
This study shows that wearable devices can use heart vibrations and AI to diagnose aortic valve problems and predict blood flow metrics as accurately as advanced MRI scans, offering a cheaper and faster alternative for heart health monitoring.