Dataset Information

Regression analysis for peak designation in pulsatile pressure signals.

ABSTRACT: Following recent studies, the automatic analysis of intracranial pressure (ICP) pulses appears to be a promising tool for forecasting critical intracranial and cerebrovascular pathophysiological variations during the management of many disorders. A pulse analysis framework has been recently developed to automatically extract morphological features of ICP pulses. The algorithm is able to enhance the quality of ICP signals, to segment ICP pulses, and to designate the locations of the three ICP sub-peaks in a pulse. This paper extends this algorithm by utilizing machine learning techniques to replace Gaussian priors used in the peak designation process with more versatile regression models. The experimental evaluations are conducted on a database of ICP signals built from 700 h of recordings from 64 neurosurgical patients. A comparative analysis of different state-of-the-art regression analysis methods is conducted and the best approach is then compared to the original pulse analysis algorithm. The results demonstrate a significant improvement in terms of accuracy in favor of our regression-based recognition framework. It reaches an average peak designation accuracy of 99% using a kernel spectral regression against 93% for the original algorithm.

SUBMITTER: Scalzo F

PROVIDER: S-EPMC2734262 | biostudies-literature | 2009 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Regression analysis for peak designation in pulsatile pressure signals.

Scalzo Fabien F Xu Peng P Asgari Shadnaz S Bergsneider Marvin M Hu Xiao X

Medical & biological engineering & computing 20090704 9

Following recent studies, the automatic analysis of intracranial pressure (ICP) pulses appears to be a promising tool for forecasting critical intracranial and cerebrovascular pathophysiological variations during the management of many disorders. A pulse analysis framework has been recently developed to automatically extract morphological features of ICP pulses. The algorithm is able to enhance the quality of ICP signals, to segment ICP pulses, and to designate the locations of the three ICP sub ...[more]

PMID: 19578916

Similar Datasets

Project description:Right ventricular failure from increased pulmonary vascular loading is a major cause of morbidity and mortality, yet its modulation by disease remains poorly understood. We tested the hypotheses that, unlike the systemic circulation, pulmonary vascular resistance (R(PA)) and compliance (C(PA)) are consistently and inversely related regardless of age, pulmonary hypertension, or interstitial fibrosis and that this relation may be changed by elevated pulmonary capillary wedge pressure, augmenting right ventricular pulsatile load.Several large clinical databases with right heart/pulmonary catheterization data were analyzed to determine the R(PA)-C(PA) relationship with pulmonary hypertension, pulmonary fibrosis, patient age, and varying pulmonary capillary wedge pressure. Patients with suspected or documented pulmonary hypertension (n=1009) and normal pulmonary capillary wedge pressure displayed a consistent R(PA)-C(PA) hyperbolic (inverse) dependence, C(PA)=0.564/(0.047+R(PA)), with a near-constant resistance-compliance product (0.48±0.17 seconds). In the same patients, the systemic resistance-compliance product was highly variable. Severe pulmonary fibrosis (n=89) did not change the R(PA)-C(PA) relation. Increasing patient age led to a very small but statistically significant change in the relation. However, elevation of the pulmonary capillary wedge pressure (n=8142) had a larger impact, significantly lowering C(PA) for any R(PA) and negatively correlating with the resistance-compliance product (P<0.0001).Pulmonary hypertension and pulmonary fibrosis do not significantly change the hyperbolic dependence between R(PA) and C(PA), and patient age has only minimal effects. This fixed relationship helps explain the difficulty of reducing total right ventricular afterload by therapies that have a modest impact on mean R(PA). Higher pulmonary capillary wedge pressure appears to enhance net right ventricular afterload by elevating pulsatile, relative to resistive, load and may contribute to right ventricular dysfunction.

Project description:BackgroundWe aimed to evaluate a novel method of atrial fibrillation (AF) screening using an iPhone camera to detect and analyze photoplethysmographic signals from the face without physical contact by extracting subtle beat-to-beat variations of skin color that reflect the cardiac pulsatile signal.Methods and resultsPatients admitted to the cardiology ward of the hospital for clinical reasons were recruited. Simultaneous facial and fingertip photoplethysmographic measurements were obtained from 217 hospital inpatients (mean age, 70.3±13.9 years; 71.4% men) facing the front camera and with an index finger covering the back camera of 2 independent iPhones before a 12-lead ECG was recorded. Backdrop and background light intensity was monitored during signal acquisition. Three successive 20-second (total, 60 seconds) recordings were acquired per patient and analyzed for heart rate regularity by Cardiio Rhythm (Cardiio Inc, Cambridge, MA) smartphone application. Pulse irregularity in ?1 photoplethysmographic readings or 3 uninterpretable photoplethysmographic readings were considered a positive AF screening result. AF was present on 12-lead ECG in 34.6% (n=75/217) patients. The Cardiio Rhythm facial photoplethysmographic application demonstrated high sensitivity (95%; 95% confidence interval, 87%-98%) and specificity (96%; 95% confidence interval, 91%-98%) in discriminating AF from sinus rhythm compared with 12-lead ECG. The positive and negative predictive values were 92% (95% confidence interval, 84%-96%) and 97% (95% confidence interval, 93%-99%), respectively.ConclusionsDetection of a facial photoplethysmographic signal to determine pulse irregularity attributable to AF is feasible. The Cardiio Rhythm smartphone application showed high sensitivity and specificity, with low negative likelihood ratio for AF from facial photoplethysmographic signals. The convenience of a contact-free approach is attractive for community screening and has the potential to be useful for distant AF screening.

Project description:Invasive monitoring of pulsatile intracranial pressure can accurately predict shunt response in patients with idiopathic normal pressure hydrocephalus, but may potentially cause complications such as bleeding and infection. We tested how a proposed surrogate parameter for pulsatile intracranial pressure, the phase-contrast magnetic resonance imaging derived pulse pressure gradient, compared with its invasive counterpart. In 22 patients with suspected idiopathic normal pressure hydrocephalus, preceding invasive intracranial pressure monitoring, and any surgical shunt procedure, we calculated the pulse pressure gradient from phase-contrast magnetic resonance imaging derived cerebrospinal fluid flow velocities obtained at the upper cervical spinal canal using a simplified Navier-Stokes equation. Repeated measurements of the pulse pressure gradient were also undertaken in four healthy controls. Of 17 shunted patients, 16 responded, indicating high proportion of "true" normal pressure hydrocephalus in the patient cohort. However, there was no correlation between the magnetic resonance imaging derived pulse pressure gradient and pulsatile intracranial pressure (R = -.18, P = .43). Pulse pressure gradients were also similar in patients and healthy controls (P = .26), and did not differ between individuals with pulsatile intracranial pressure above or below established thresholds for shunt treatment (P = .97). Assessment of pulse pressure gradient at level C2 was therefore not found feasible to replace invasive monitoring of pulsatile intracranial pressure in selection of patients with idiopathic normal pressure hydrocephalus for surgical shunting. Unlike invasive, overnight monitoring, the pulse pressure gradient from magnetic resonance imaging comprises short-term pressure fluctuations only. Moreover, complexity of cervical cerebrospinal fluid flow and -pulsatility at the upper cervical spinal canal may render the pulse pressure gradient a poor surrogate marker for intracranial pressure pulsations.

Dataset Information

Regression analysis for peak designation in pulsatile pressure signals.

Publications

Regression analysis for peak designation in pulsatile pressure signals.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets