88 research outputs found
Uncovering statistical features of bradycardia severity in premature infants using a point process model
No full textPredicting Bradycardia in Preterm Infants Using Point Process Analysis of Heart Rate
No full textObjective: Episodes of bradycardia are common and recur sporadically in preterm infants, posing a threat to the developing brain and other vital organs. We hypothesize that bradycardias are a result of transient temporal destabilization of the cardiac autonomic control system and that fluctuations in the heart rate signal might contain information that precedes bradycardia. We investigate infant heart rate fluctuations with a novel application of point process theory. Methods: In ten preterm infants, we estimate instantaneous linear measures of the heart rate signal, use these measures to extract statistical features of bradycardia, and propose a simplistic framework for prediction of bradycardia. Results: We present the performance of a prediction algorithm using instantaneous linear measures (mean area under the curve = 0.79 ± 0.018) for over 440 bradycardia events. The algorithm achieves an average forecast time of 116 s prior to bradycardia onset (FPR = 0.15). Our analysis reveals that increased variance in the heart rate signal is a precursor of severe bradycardia. This increase in variance is associated with an increase in power from low content dynamics in the LF band (0.04-0.2 Hz) and lower multiscale entropy values prior to bradycardia. Conclusion: Point process analysis of the heartbeat time series reveals instantaneous measures that can be used to predict infant bradycardia prior to onset. Significance: Our findings are relevant to risk stratification, predictive monitoring, and implementation of preventative strategies for reducing morbidity and mortality associated with bradycardia in neonatal intensive care units
Applying Machine Learning Algorithms for Automatic Detection of Swallowing from Sound
No full textLaura F. Santoso participated in this study as a medical student in the Senior Scholars research program at the University of Massachusetts Medical School.Despite the severe consequences of dysfunctional swallowing, there is no simple method of monitoring swallowing outside of clinical settings. People who cannot swallow cannot eat safely, resulting in profound changes in quality of life and risk of death from aspiration pneumonia. A non-invasive swallowing detector may have widespread impact in both clinical care and research. Detection of swallowing from laryngeal sounds could become an ideal assessment tool because sounds are simple to record, quantifiable, and amenable to software analysis. The focus of this paper is to achieve high accuracy binary swallowing detection from sound recordings. A dataset with 2500 swallow sound samples and 1700 mixed laryngeal noise samples from 15 healthy adults was used to train and test three supervised machine learning algorithms. A decision tree, support vector machine (SVM), and neural network trained with the scaled conjugate gradient (SCG) method had areas under the receiver operating characteristic (ROC) curve of 0.970, 0.961, and 0.971 and average accuracies of 93.2 percent, 86.2 percent, and 93.7 percent respectively. While further work needs to be done to further optimize these algorithms and validate their efficacy, these initial results suggest machine learning strategies may be helpful to improve accuracy of swallowing detection
Sensory dysphagia: A case series and proposed classification of an under recognized swallowing disorder
No full textLaura Santoso participated in this study as a medical student as part of the Senior Scholars research program at the University of Massachusetts Medical School.BACKGROUND: Although sensory feedback is a vital regulator of deglutition, it is not comprehensively considered in the standard dysphagia evaluation. Difficulty swallowing secondary to sensory loss may be termed "sensory dysphagia" and may account for cases receiving diagnoses of exclusion, like functional or idiopathic dysphagia. METHODS AND RESULTS: Three cases of idiopathic dysphagia were suspected to have sensory dysphagia. The patients had (1) effortful swallowing, (2) globus sensation, and (3) aspiration. Endoscopic sensory mapping revealed laryngopharyngeal sensory loss. Despite normal laryngeal motor function during voluntary maneuvers, laryngeal closure was incomplete during swallowing. The causes of sensory loss were identified: cranial neuropathy from Chiari malformation, immune-mediated neuronopathy, and nerve damage from prior traumatic intubation. CONCLUSIONS: Sensory loss may cause dysphagia without primary motor dysfunction. Sensory dysphagia should be classified as a distinct form of swallowing motility disorder to improve diagnosis. Increasing awareness and developing appropriate assessment tools may advance dysphagia care
Directions to "Eureka!".
No full textThe process of scientific discovery is presented by David Paydarfar and William J. Schwartz as a tongue-in-cheek flow diagram, as well as a (presumably) more serious set of informal heuristics (or “principles”) (Editorial, 6 Apr., p. 13). I find it somewhat disappointing that the psychology of discovery would be treated in such an informal fashion...</p
Improving heart rate estimation in preterm infants with bivariate point process analysis of heart rate and respiration
No full textAccurate estimation of heart rate dynamics in preterm infants is important for predicting recurrent episodes of severe bradycardia. We hypothesize that estimation of heart rate can be improved by including respiration as a state variable, based on mechanisms that underlie cardio-respiratory coherence. For ten preterm infants, we demonstrate that including respiration as a covariate improves estimation accuracy by an average of 11% across bradycardia severity, and reduces the maximum error by 8%. We also find that cardio-respiratory coherence increases in low frequency content just prior to severe bradycardia. Thus, incorporating respiratory information may improve models of heart rate dynamics and narrow potential features for bradycardia prediction
Flipping Biological Switches: Solving for Optimal Control: A Dissertation
No full textSwitches play an important regulatory role at all levels of biology, from molecular switches triggering signaling cascades to cellular switches regulating cell maturation and apoptosis. Medical therapies are often designed to toggle a system from one state to another, achieving a specified health outcome. For instance, small doses of subpathologic viruses activate the immune system’s production of antibodies. Electrical stimulation revert cardiac arrhythmias back to normal sinus rhythm. In all of these examples, a major challenge is finding the optimal stimulus waveform necessary to cause the switch to flip. This thesis develops, validates, and applies a novel model-independent stochastic algorithm, the Extrema Distortion Algorithm (EDA), towards finding the optimal stimulus. We validate the EDA’s performance for the Hodgkin-Huxley model (an empirically validated ionic model of neuronal excitability), the FitzHugh-Nagumo model (an abstract model applied to a wide range of biological systems that that exhibit an oscillatory state and a quiescent state), and the genetic toggle switch (a model of bistable gene expression). We show that the EDA is able to not only find the optimal solution, but also in some cases excel beyond the traditional analytic approaches. Finally, we have computed novel optimal stimulus waveforms for aborting epileptic seizures using the EDA in cellular and network models of epilepsy. This work represents a first step in developing a new class of adaptive algorithms and devices that flip biological switches, revealing basic mechanistic insights and therapeutic applications for a broad range of disorders.MD/Ph
Assessment of cardio-respiratory interactions in preterm infants by bivariate autoregressive modeling and surrogate data analysis
No full textBackground: Cardio-respiratory interactions are weak at the earliest stages of human development, suggesting that assessment of their presence and integrity may be an important indicator of development in infants. Despite the valuable research devoted to infant development, there is still a need for specifically targeted standards and methods to assess cardiopulmonary functions in the early stages of life. We present a new methodological framework for the analysis of cardiovascular variables in preterm infants. Our approach is based on a set of mathematical tools that have been successful in quantifying important cardiovascular control mechanisms in adult humans, here specifically adapted to reflect the physiology of the developing cardiovascular system.
Methods: We applied our methodology in a study of cardio-respiratory responses for 11 preterm infants. We quantified cardio-respiratory interactions using specifically tailored multivariate autoregressive analysis and calculated the coherence as well as gain using causal approaches. The significance of the interactions in each subject was determined by surrogate data analysis. The method was tested in control conditions as well as in two different experimental conditions; with and without use of mild mechanosensory intervention.
Results: Our multivariate analysis revealed a significantly higher coherence, as confirmed by surrogate data analysis, in the frequency range associated with eupneic breathing compared to the other ranges.
Conclusions: Our analysis validates the models behind our new approaches, and our results confirm the presence of cardio-respiratory coupling in early stages of development, particularly during periods of mild mechanosensory intervention, thus encouraging further application of our approach.Center for Integration of Medicine and Innovative Technology (U.S. Army Medical Research Acquisition Activity Cooperative Agreement W81XWH-07-2-0011)National Institutes of Health (U.S.) (Grant R01-HL084502)National Institutes of Health (U.S.) (Grant R01-DA015644)National Institutes of Health (U.S.) (Grant DP1-OD003646
- …
