A Novel Short-Term Event Extraction Algorithm for Biomedical Signals

Yazdani, Sasan; Fallet, Sibylle; Vesin, Jean‐Marc

doi:10.1109/tbme.2017.2718179

Cited by 49 publications

(43 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This was achieved by detecting a fiducial point (i.e., the R Subject ID www.nature.com/scientificreports www.nature.com/scientificreports/ peak) and then selecting a window of time of 640 ms around the fiducial point, in analogy to 64 and accounting for the sampling frequency. The fiducial point for each heartbeat was detected using a QRS detection algorithm as proposed in 91 . Since the ECG were sampled at 250 Hz, a window of time of 640 ms was isolated counting 160 ECG samples around the R fiducial point (i.e., 60 samples preceding the R peak and 100 samples following the R peak).…”

Section: Methodsmentioning

confidence: 99%

Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG

Porumb

Stranges

Pescapè

et al. 2020

Sci Rep

142

View full text Add to dashboard Cite

Tracking the fluctuations in blood glucose levels is important for healthy subjects and crucial diabetic patients. Tight glucose monitoring reduces the risk of hypoglycemia, which can result in a series of complications, especially in diabetic patients, such as confusion, irritability, seizure and can even be fatal in specific conditions. Hypoglycemia affects the electrophysiology of the heart. However, due to strong inter-subject heterogeneity, previous studies based on a cohort of subjects failed to deploy electrocardiogram (ECG)-based hypoglycemic detection systems reliably. The current study used personalised medicine approach and Artificial Intelligence (AI) to automatically detect nocturnal hypoglycemia using a few heartbeats of raw ECG signal recorded with non-invasive, wearable devices, in healthy individuals, monitored 24 hours for 14 consecutive days. Additionally, we present a visualisation method enabling clinicians to visualise which part of the ECG signal (e.g., T-wave, ST-interval) is significantly associated with the hypoglycemic event in each subject, overcoming the intelligibility problem of deep-learning methods. These results advance the feasibility of a real-time, non-invasive hypoglycemia alarming system using short excerpts of ECG signal.Tracking the fluctuations in the blood glucose level is relevant for both healthy individuals and diabetic patients. High glucose levels (hyperglycemia) result in long-term complications and can damage the kidneys, nerves, blood vessels in the eye and can bring many other complications 14 . Low blood glucose levels (hypoglycemia) may result in acute short-term alterations of health status such as confusion, irritability, palpitations, feeling shaky and sweaty and can even result in severe loss of attention, coma or death 15 . In fact, hypoglycemia can be particularly dangerous during specific activities requiring great attention (e.g. while driving, performing complicated surgeries). Thus, technologies for non-invasive, continuous monitoring of glucose concentration aiming at early-detecting hypoglycemic events are highly required.The most diffuse methods for blood glucose testing consist of analysing a drop of blood resulted from a finger prick. However, this method does not allow continuous monitoring, is invasive, cumbersome, expensive, and it has been demonstrated that it affects patient compliance with the glucose measurements 16 . As an alternative, Continuous Glucose Monitoring Devices (CGMs) can infer the blood glucose levels in real-time based on the glucose in the interstitial fluid. These devices significantly empowered diabetic patients, but still, they present some limitations that make them unattractive for pre-diabetic patients and diabetics. Commercially available CGMs can be worn for a limited number of days, usually between 7 and 14 days. Most of the CGMs require finger prick calibration; some studies reported that the reliability of CGMs is limited 17-19 during low blood glucose level events and they sample from the interstitial fluid whi...

show abstract

Section: Methodsmentioning

confidence: 99%

Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG

Porumb

Stranges

Pescapè

et al. 2020

Sci Rep

142

View full text Add to dashboard Cite

show abstract

“…Heartbeats were first extracted from night-long ECG recordings using a non-linear R-wave detector [13], which works on a filtering technique known as relative energy (Rel-En) and has proven to provide robust results in several applications [14][15][16]. After the extraction of RR-interval time series from night-long ECG recordings one can observe a phenomenon, which within the context of this study is referred to as U-patterns.…”

Section: U-patternsmentioning

confidence: 99%

Analysis of U-Shape Patterns in RR-Interval Time Series During Sleep

Yazdani¹,

Cherqui²,

Bourdillon³

et al. 2018

2018 Computing in Cardiology Conference (CinC)

Self Cite

View full text Add to dashboard Cite

The proposed study investigates a phenomenon, defined as "U-patterns", that takes place in the RR-interval time series during sleep. These patterns are defined as a Ushaped decrease-increase in the RR-intervals, with a duration of 20 to 40 seconds with a minimum decrease of 15% in the local RR-interval mean value. This paper studies statistical characteristics of U-patterns on subjects undergoing sleep deprivation. 15 healthy subjects (7males, 22.1 ± 1.7 yrs.) participated in an experiment over a span of 17 days, in three successive stages. A baseline phase of seven days, during which the subjects slept normally; A sleep deprivation phase of three days, during which they could only sleep three hours per night; Finally, in a 7day recovery phase subjects went back to sleeping normally, as they would in the baseline phase. While sleeping, polysomnographic data was recorded from the participants. U-patterns were extracted and their statistical characteristics were analyzed. Alongside the incidence of these patterns, their depth, duration and area were measured. U-patterns were present in all participating subjects. Moreover, these patterns were recurrent in all RRinterval time series. There was a significant difference in their repetition rate, depth and duration from baseline to sleep-deprivation and recovery. Results show that the characteristics of U-patterns change when subjects are undergoing sleep deprivation, suggesting these patterns can be used to identify patients suffering from sleep disorders.

show abstract

“…[6] UditSatija, Barathram.Ramkumar and M. SabarimalaiManikandan propose a novel signal quality aware IoT-enabled ECG telemetry system for continuous cardiac health monitoring applications. The proposed quality-aware that the ECG monitoring system consists of three modules: ECG signal sensing module; automated signal quality assessment module; and signal-quality aware ECG analysis and a transmission module [16]. Design and development of a light-weight ECG signal quality assessment method for automatically classifying the acquired ECG signal into acceptable or unacceptable class and real-time implementation of proposed IoT-enabled.…”

Section: Literature Surveymentioning

confidence: 99%

Enhancement in the Detection of Atrial Fibrillation Arrhythmia For Health Monitoring System

Sowndarya¹,

Srinivasan²

2019

IJEAT

View full text Add to dashboard Cite

In day to day life, continuous monitoring of medical data is essential for many individuals including patients with severe health risks and elderly people. In this paper, one such system is developed for continuous monitoring of Atrial Fibrillation abnormality. Electrocardiographic (ECG) signal monitoring plays a vital role in the management of patients with atrial fibrillation (AF). Atrial Fibrillation (AF) is a type of abnormality in heart, it causes during the AF electrical discharges in the atrium are rapid and results in an abnormal heartbeat. In this paper, ECG signals taken from the MIT-BIH arrhythmia database. After the signal is acquired, the hybrid filtering technique is used to remove the artifacts. Naturally, the ECG signal gets distorted by different types of artifacts which must be removed from the signal otherwise it will convey incorrect information regarding the patient's heart condition. Efficient LMS and Normalized LMS adaptive filters are computationally used for cancellation of noise. Analyzing functions of the filtered signal is Peak Signal to Noise Ratio (PSNR), Mean Square Normalized Error Performance (MSE), Maximum Square Error (MAXERR), the ratio of Squared Norms (L2RAT). The continuous health statistics will be given to individuals and caretaker in the remote location so that they can take necessary action to prevent from health issues. The paper will provide primitive solutions in the field of telemedicine using continuous health monitoring and medical data analysis of a particular individual.In future work, the ECG sensor will acquire the ECG signal and the acquired signal processed through the classification algorithm for classifying the signal into different categories. The biosensor is a combination of the biological element with the physiochemical transducer to produce an electronic signal which can be further converted, processed and transmitted for data analytics, processing, validation, visualization, interpretation, and data logging.

show abstract

A Novel Short-Term Event Extraction Algorithm for Biomedical Signals

Cited by 49 publications

References 40 publications

Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG

Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG

Analysis of U-Shape Patterns in RR-Interval Time Series During Sleep

Enhancement in the Detection of Atrial Fibrillation Arrhythmia For Health Monitoring System

Contact Info

Product

Resources

About