scispace - formally typeset
Search or ask a question
Journal ArticleDOI

PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals.

TL;DR: The newly inaugurated Research Resource for Complex Physiologic Signals (RRSPS) as mentioned in this paper was created under the auspices of the National Center for Research Resources (NCR Resources).
Abstract: —The newly inaugurated Research Resource for Complex Physiologic Signals, which was created under the auspices of the National Center for Research Resources of the National Institutes of He...
Citations
More filters
Journal ArticleDOI
TL;DR: This survey tries to provide a structured and comprehensive overview of the research on anomaly detection by grouping existing techniques into different categories based on the underlying approach adopted by each technique.
Abstract: Anomaly detection is an important problem that has been researched within diverse research areas and application domains. Many anomaly detection techniques have been specifically developed for certain application domains, while others are more generic. This survey tries to provide a structured and comprehensive overview of the research on anomaly detection. We have grouped existing techniques into different categories based on the underlying approach adopted by each technique. For each category we have identified key assumptions, which are used by the techniques to differentiate between normal and anomalous behavior. When applying a given technique to a particular domain, these assumptions can be used as guidelines to assess the effectiveness of the technique in that domain. For each category, we provide a basic anomaly detection technique, and then show how the different existing techniques in that category are variants of the basic technique. This template provides an easier and more succinct understanding of the techniques belonging to each category. Further, for each category, we identify the advantages and disadvantages of the techniques in that category. We also provide a discussion on the computational complexity of the techniques since it is an important issue in real application domains. We hope that this survey will provide a better understanding of the different directions in which research has been done on this topic, and how techniques developed in one area can be applied in domains for which they were not intended to begin with.

9,627 citations

Journal ArticleDOI
TL;DR: The Medical Information Mart for Intensive Care (MIMIC-III) as discussed by the authors is a large, single-center database comprising information relating to patients admitted to critical care units at a large tertiary care hospital.
Abstract: MIMIC-III ('Medical Information Mart for Intensive Care') is a large, single-center database comprising information relating to patients admitted to critical care units at a large tertiary care hospital. Data includes vital signs, medications, laboratory measurements, observations and notes charted by care providers, fluid balance, procedure codes, diagnostic codes, imaging reports, hospital length of stay, survival data, and more. The database supports applications including academic and industrial research, quality improvement initiatives, and higher education coursework.

4,056 citations

Journal ArticleDOI
TL;DR: Application of fractal analysis may provide new approaches to assessing cardiac risk and forecasting sudden cardiac death, as well as to monitoring the aging process, and similar approaches show promise in assessing other regulatory systems, such as human gait control in health and disease.
Abstract: According to classical concepts of physiologic control, healthy systems are self-regulated to reduce variability and maintain physiologic constancy. Contrary to the predictions of homeostasis, however, the output of a wide variety of systems, such as the normal human heartbeat, fluctuates in a complex manner, even under resting conditions. Scaling techniques adapted from statistical physics reveal the presence of long-range, power-law correlations, as part of multifractal cascades operating over a wide range of time scales. These scaling properties suggest that the nonlinear regulatory systems are operating far from equilibrium, and that maintaining constancy is not the goal of physiologic control. In contrast, for subjects at high risk of sudden death (including those with heart failure), fractal organization, along with certain nonlinear interactions, breaks down. Application of fractal analysis may provide new approaches to assessing cardiac risk and forecasting sudden cardiac death, as well as to monitoring the aging process. Similar approaches show promise in assessing other regulatory systems, such as human gait control in health and disease. Elucidating the fractal and nonlinear mechanisms involved in physiologic control and complex signaling networks is emerging as a major challenge in the postgenomic era.

1,905 citations

Journal ArticleDOI
TL;DR: It is demonstrated that an end-to-end deep learning approach can classify a broad range of distinct arrhythmias from single-lead ECGs with high diagnostic performance similar to that of cardiologists.
Abstract: Computerized electrocardiogram (ECG) interpretation plays a critical role in the clinical ECG workflow1. Widely available digital ECG data and the algorithmic paradigm of deep learning2 present an opportunity to substantially improve the accuracy and scalability of automated ECG analysis. However, a comprehensive evaluation of an end-to-end deep learning approach for ECG analysis across a wide variety of diagnostic classes has not been previously reported. Here, we develop a deep neural network (DNN) to classify 12 rhythm classes using 91,232 single-lead ECGs from 53,549 patients who used a single-lead ambulatory ECG monitoring device. When validated against an independent test dataset annotated by a consensus committee of board-certified practicing cardiologists, the DNN achieved an average area under the receiver operating characteristic curve (ROC) of 0.97. The average F1 score, which is the harmonic mean of the positive predictive value and sensitivity, for the DNN (0.837) exceeded that of average cardiologists (0.780). With specificity fixed at the average specificity achieved by cardiologists, the sensitivity of the DNN exceeded the average cardiologist sensitivity for all rhythm classes. These findings demonstrate that an end-to-end deep learning approach can classify a broad range of distinct arrhythmias from single-lead ECGs with high diagnostic performance similar to that of cardiologists. If confirmed in clinical settings, this approach could reduce the rate of misdiagnosed computerized ECG interpretations and improve the efficiency of expert human ECG interpretation by accurately triaging or prioritizing the most urgent conditions. Analysis of electrocardiograms using an end-to-end deep learning approach can detect and classify cardiac arrhythmia with high accuracy, similar to that of cardiologists.

1,632 citations

Journal ArticleDOI
Leon Glass1
08 Mar 2001-Nature
TL;DR: Molecular and physical techniques combined with physiological and medical studies are addressing questions concerning the dynamics of physiological rhythms and are transforming the understanding of the rhythms of life.
Abstract: Complex bodily rhythms are ubiquitous in living organisms. These rhythms arise from stochastic, nonlinear biological mechanisms interacting with a fluctuating environment. Disease often leads to alterations from normal to pathological rhythm. Fundamental questions concerning the dynamics of these rhythmic processes abound. For example, what is the origin of physiological rhythms? How do the rhythms interact with each other and the external environment? Can we decode the fluctuations in physiological rhythms to better diagnose human disease? And can we develop better methods to control pathological rhythms? Mathematical and physical techniques combined with physiological and medical studies are addressing these questions and are transforming our understanding of the rhythms of life.

1,204 citations

References
More filters
Journal ArticleDOI
Leon Glass1
TL;DR: Any claim for "chaos" based solely on calculation of dimension or Liapunov number must be viewed with extreme skepticism.
Abstract: Any claim for \"chaos\" based solely on calculation of dimension or Liapunov number . . . must be viewed with extreme skepticism . . . Glass and Mackey' (1988) Chaos may provide a healthy flexibility to the heart, brain, and other parts of the body. Poop (1989) . . . many of the earlier demonstrations of chaos in biological data are spurious. Rapp3 (1993) Low dimensional chaos prevails in the intact heart. Elbert et al.^ (1994)

44 citations

Journal ArticleDOI
TL;DR: The "dynamic reorganization" in the allograft rhythm-generating system, seen in the first 100 days, is a manifestation of the adaptive capacity of intrinsic control mechanisms, which may provide a new perspective on principles that constitute homeodynamic regulation.
Abstract: The capacity of self-organized systems to adapt is embodied in the functional organization of intrinsic control mechanisms. Evolution in functional complexity of heart rate variability (HRV) was us...

37 citations

Journal ArticleDOI
TL;DR: Clustering of ventricular ectopy, as measured by the fractal dimension, is observed in patients at increased risk of sudden cardiac death and is related to changes in heart rate and heart rate variability that are consistent with transient increases in cardiac sympathetic tone.
Abstract: Background Fractal geometric analysis of ventricular ectopy yields a fractal dimension, which can range from zero to one and is inversely related to clustering of ventricular premature contractions (VPCs). Low values of this fractal dimension, which reflect significantly nonuniform distributions of ventricular ectopy, are found in patients with life-threatening ventricular arrhythmias and predict adverse outcomes in selected patients with congestive heart failure and with mitral regurgitation. However, the physiological mechanism and correlates of the fractal dimension are unknown. Methods and Results To explore the physiological correlates of clustered ventricular ectopy, we studied 30 patients with a history of sustained ventricular tachycardia or ventricular fibrillation who had inducible sustained monomorphic ventricular tachycardia during electrophysiological study and also underwent drug-free 24-hour ambulatory ECG. In addition to fractal dimension (determined by use of our previously described algorithm), we measured the mean RR interval (±SD) for all sinus beats preceding a sinus beat and for all sinus beats preceding a single VPC and the mean root-mean-square difference (RMSSD) of all windows of 15 successive RR intervals (excluding ectopic beats) preceding a sinus beat and preceding a single VPC. Based on the directional changes of mean RR (a measure of both sympathetic and parasympathetic tone) and of RMSSD (a measure of parasympathetic tone), each patient’s inferred relative sympathetic tone preceding ventricular ectopy was classified as increased, unchanged, or decreased. If these values changed concordantly, relative sympathetic tone was indeterminate. Fractal dimension did not correlate with the mean RR interval, SD of the RR interval, or RMSSD preceding sinus beats or preceding VPCs (all P >.10). In 20 patients, fractal dimension was significantly lower among those with increased relative sympathetic tone (n=14) than those with unchanged or decreased sympathetic tone (n=6, P =.008). Ten patients had indeterminate relative sympathetic tone. Conclusions Clustering of ventricular ectopy, as measured by the fractal dimension, is observed in patients at increased risk of sudden cardiac death. A low fractal dimension (clustered ventricular ectopy) is related to changes in heart rate and heart rate variability that are consistent with transient increases in cardiac sympathetic tone.

16 citations

Journal ArticleDOI
TL;DR: The persuasive argument for sharing and archiving data is that scientists must build on the shoulders of other scientists, that science is cumulative and replicative, and that science must be open.
Abstract: The persuasive argument for sharing and archiving data is that scientists must build on the shoulders of other scientists, that science is cumulative and replicative, and that science must be open. Sharing and archiving data are just a small part of all that is implied by that principle, but it is inextricably part of our obligation as social and behavioral scientists to conduct our work in the open. Only then can others see and understand what we did, and only then will someone have a chance to confirm that we were right, or to prove that we were wrong. Moreover, data archiving and sharing create opportunities for addressing questions not envisioned by the initial investigators. Indeed, by supplementing or pooling archived data, new and original data sets can be created that permit analyses well beyond the purpose or scope of the initial data collection. Of course, the creativity and labor of initial investigators should be protected, and the privacy of research participants must be safeguarded. These protections and safeguards, however, are not antithetical to data archiving and sharing. They simply raise questions about when and how data archiving and sharing should take place. In our view, the benefits of properly archived and shared data for outweigh the potential for harm. As indicated above, this is a perspective shared by several funding agencies of behavioral and social research, including the NIA.

9 citations