Prediction of plasma volume and total hemoglobin mass with machine learning.

Hemoglobin concentration ([Hb]) is used for the clinical diagnosis of anemia, and in sports as a marker of blood doping. [Hb] is however subject to significant variations mainly due to shifts in plasma volume (PV). This study proposes a newly developed model able to accurately predict total hemoglobin mass (Hbmass) and PV from a single complete blood count (CBC) and anthropometric variables in healthy subject. Seven hundred and sixty-nine CBC coupled to measures of Hbmass and PV using a CO-rebreathing method were used with a machine learning tool to calculate an estimation model. The predictive model resulted in a root mean square error of 33.2 g and 35.6 g for Hbmass, and 179 mL and 244 mL for PV, in women and men, respectively. Measured and predicted data were significantly correlated (p < 0.001) with a coefficient of determination (R2 ) ranging from 0.76 to 0.90 for Hbmass and PV, in both women and men. The Bland-Altman bias was on average 0.23 for Hbmass and 4.15 for PV. We herewith present a model with a robust prediction potential for Hbmass and PV. Such model would be relevant in providing complementary data in contexts such as the epidemiology of anemia or the individual monitoring of [Hb] in anti-doping.

Thiol-to-amine cyclization reaction enables screening of large libraries of macrocyclic compounds and the generation of sub-kilodalton ligands.

Macrocyclic compounds are an attractive modality for drug development, but the limited availability of large, structurally diverse macrocyclic libraries hampers the discovery of leads. Here, we describe the discovery of efficient macrocyclization reactions based on thiol-to-amine ligations using bis-electrophiles, their application to synthesize and screen large libraries of macrocyclic compounds, and the identification of potent small macrocyclic ligands. The thiol-to-amine cyclization reactions showed unexpectedly high yields for a wide substrate range, which obviated product purification and enabled the generation and screening of an 8988 macrocycle library with a comparatively small effort. X-ray structure analysis of an identified thrombin inhibitor (K i = 42 ± 5 nM) revealed a snug fit with the target, validating the strategy of screening large libraries with a high skeletal diversity. The approach provides a route for screening large sub-kilodalton macrocyclic libraries and may be applied to many challenging drug targets.

Evaluation of ablation patterns using a biophysical model of atrial fibrillation.

Atrial fibrillation (AF) is the most common form of cardiac arrhythmia. Surgical/Radiofrequency (RF) ablation is a therapeutic procedure that consists of creating lines of conduction block to interrupt AF. The present study evaluated 13 different ablation patterns by means of a biophysical model of the human atria. In this model, ablation lines were abruptly applied transmurally during simulated sustained AF, and success rate, time to AF termination and average beat-to-beat interval were documented. The gold standard Cox's Maze III procedure was taken as reference. The effectiveness of twelve less invasive patterns was compared to it. In some of these incomplete lines (entailing a gap) were simulated. Finally, the computer simulations were compared to clinical data. The results show that the model reproduces observations made in vivo: (1) the Maze III is the most efficient ablation procedure; (2) less invasive patterns should include lines in both right and left atrium; (3) incomplete ablation lines between the pulmonary veins and the mitral valve annulus lead to uncommon flutter; (4) computer simulations of incomplete lines are consistent with clinical results of non-transumural RF ablation. Biophysical modeling may therefore be considered as a useful tool for understanding the mechanisms underlying AF therapies.

Study of atrial arrhythmias in a computer model based on magnetic resonance images of human atria.

The maintenance of multiple wavelets appears to be a consistent feature of atrial fibrillation (AF). In this paper, we investigate possible mechanisms of initiation and perpetuation of multiple wavelets in a computer model of AF. We developed a simplified model of human atria that uses an ionic-based membrane model and whose geometry is derived from a segmented magnetic resonance imaging data set. The three-dimensional surface has a realistic size and includes obstacles corresponding to the location of major vessels and valves, but it does not take into account anisotropy. The main advantage of this approach is its ability to simulate long duration arrhythmias (up to 40 s). Clinically relevant initiation protocols, such as single-site burst pacing, were used. The dynamics of simulated AF were investigated in models with different action potential durations and restitution properties, controlled by the conductance of the slow inward current in a modified Luo-Rudy model. The simulation studies show that (1) single-site burst pacing protocol can be used to induce wave breaks even in tissue with uniform membrane properties, (2) the restitution-based wave breaks in an atrial model with realistic size and conduction velocities are transient, and (3) a significant reduction in action potential duration (even with apparently flat restitution) increases the duration of AF. (c) 2002 American Institute of Physics.

Automatic classification of HITS into artifacts or solid or gaseous emboli by a wavelet representation combined with dual-gate TCD.

BACKGROUND AND PURPOSE: Transcranial Doppler (TCD) can detect high-intensity transient signals (HITS) in the cerebral circulation. HITS may correspond to artifacts or solid or gaseous emboli. The aim of this study was to develop an offline automated Doppler system allowing the classification of HITS. METHODS: We studied 600 HITS in vivo, including 200 artifacts from normal subjects, 200 solid emboli from patients with symptomatic internal carotid artery stenosis, and 200 gaseous emboli in stroke patients with patent foramen ovale. The study was 2-fold, each part involving 300 HITS (100 of each type). The first 300 HITS (learning set) were used to construct an automated classification algorithm. The remaining 300 HITS (validation set) were used to check the validity of this algorithm. To classify HITS, we combined dual-gate TCD with a wavelet representation and compared it with the current "gold standard," the human experts. RESULTS: A combination of the peak frequency of HITS and the time delay makes it possible to separate artifacts from emboli. On the validation set, we achieved a sensitivity of 97%, a specificity of 98%, a positive predictive value (PPV) of 99%, and a negative predictive value (NPV) of 94%. To distinguish between solid and gaseous emboli, where positive refers now to the solid emboli, we used the peak frequency, the relative power, and the envelope symmetry of HITS. On the validation set, we achieved a sensitivity of 89%, a specificity of 86%, a conditional PPV of 89%, and a conditional NPV of 89%. CONCLUSIONS: An automated wavelet representation combined with dual-gate TCD can reliably reject artifacts from emboli. From a clinical standpoint, however, this approach has only a fair accuracy in differentiating between solid and gaseous emboli.

A computer model of human atria with reasonable computation load and realistic anatomical properties.

Atrial fibrillation is the most frequent arrhythmia, provoking discomfort, heart failure and arterial embolisms. The aim of this work is to develop a simplified anatomical computer model of human atria for the study of atrial arrhythmias and the understanding of electrical propagation mechanisms. With the model we propose, up to 40 s of real-time propagation have been simulated on a single-processor computer. The size and the electrophysiological properties of the simulated atria are within realistic values and information about anatomy has been taken into account in a three-dimensional structure. Besides normal sinus beat, pathological phenomena such as flutter and fibrillation have been induced using a programmed stimulation protocol. One important observation in our model is that atrial arrhythmias are a combination of functional and anatomical reentries and that the geometry plays an important role. This virtual atrium can reproduce electrophysiological observations made in humans but with the advantage of showing in great detail how arrhythmias are initiated and sustained. Such details are difficult or impossible to study in humans. This model will serve us as a tool to evaluate the impact of new therapeutic strategies and to improve them.

Rank-order polynomial subband decomposition for medical image compression.

In this paper, the problem of progressive lossless image coding is addressed. A nonlinear decomposition for progressive lossless compression is presented. The decomposition into subbands is called rank-order polynomial decomposition (ROPD) according to the polynomial prediction models used. The decomposition method presented here is a further development and generalization of the morphological subband decomposition (MSD) introduced earlier by the same research group. It is shown that ROPD provides similar or slightly better results than the compared coding schemes such as the codec based on set partitioning in hierarchical trees (SPIHT) and the codec based on wavelet/trellis-coded quantization (WTCQ). Our proposed method highly outperforms the standard JPEG. The proposed lossless compression scheme has the functionality of having a completely embedded bit stream, which allows for data browsing. It is shown that the ROPD has a better lossless rate than the MSD but it has also a much better browsing quality when only a part of the bit stream is decompressed. Finally, the possibility of hybrid lossy/lossless compression is presented using ultrasound images. As with other compression algorithms, considerable gain can be obtained if only the regions of interest are compressed losslessly.

The matching pursuit: a new method of characterizing microembolic signals?

Detection of clinically silent circulating microemboli within cerebral arteries by transcranial Doppler ultrasound (US) is now being widely investigated in the hope of identifying patients at increased risk for stroke. However, the widespread application of embolus detection is still limited in clinical practice because current transcranial Doppler systems have not the required sensitivity and specificity to analyze microembolic signals, particularly to distinguish between gaseous, or solid brain emboli and artefacts. In this work, we proposed to investigate the potential of a new approach for the analysis of microembolic signals via the so-called matching pursuit, which is closely related to wavelet transform and is not subject to the same limitations as the fast Fourier transform. Our preliminary results clearly indicate that matching pursuit is well suited to this task.

Observer of autonomic cardiac outflow based on blind source separation of ECG parameters.

We present a novel method which provides an observer of the autonomic cardiac outflow using heartbeat intervals (RR) and QT intervals. The model of the observer is inferred from qualitative physiological knowledge. It consists in a problem of blind source separation of noisy mixtures which is resolved by a simple and robust algorithm. The robustness of the algorithm has been assessed by numerical simulations in adverse noisy environments. In clinical applications, we have validated the observer on subjects exposed to experimental conditions known to elicit sympathetic or parasympathetic response.

Heart rate dynamics at the onset of ventricular tachyarrhythmias as retrieved from implantable cardioverter-defibrillators in patients with coronary artery disease.

BACKGROUND: The recent availability of implantable cardioverter-defibrillators (ICDs) that record 1024 R-R intervals preceding a ventricular tachyarrhythmia (VTA) provides a unique opportunity to analyze heart rate variability (HRV) before the onset of VTA. METHODS AND RESULTS: Fifty-eight post-myocardial infarction patients with an implanted ICD for recurrent VTA provided 2 sets of 98 heart rate recordings in sinus rhythm: (1) before a VTA and (2) during control conditions. Three subgroups were considered according to the antiarrhythmic (AA) drug regimen. A state of sympathoexcitation was suggested by the significant reduction in HRV before VTA onset compared with control conditions. beta-Blockers and dl-sotalol enhanced HRV in control recordings; nevertheless, HRV declined before VTA independent of AA drugs. A gradual increase in heart rate and decrease in sinus arrhythmia at VTA onset were specific findings of patients who received dl-sotalol. CONCLUSIONS: The peculiar heart rate dynamics observed before VTA onset are suggestive of a state of sympathoexcitation that is independent of AA drugs.

Observer of the human cardiac sympathetic nerve activity using noncausal blind source separation.

We present a novel method for the blind reconstruction of the cardiac sympathetic nerve activity (CSNA) in the low-frequency (LF) band (0.04-0.15 Hz) using only heart rate and arterial blood pressure. The originality of the method consists in the application of blind source separation techniques to obtain an observer of CSNA. We show how this observer can be deduced from a linear model of the cardiovascular system by introduction of the fundamental assumptions about the independence of the cardiac sympathetic an parasympathetic outflow. In cardiovascular applications, the reliability of the observer has been assessed by verification of the fundamental assumption for the given data. A primer qualitative validation has been performed using the muscle sympathetic nerve activity as an indirect indicator of CSNA. Very satisfying and promising results have been obtained. Moreover, we have performed quantitative validations of the observer in various experimental conditions known to elicit selectively cardiac sympathetic or parasympathetic response. The experimental conditions include a supine-to-60 degrees tilt test, indirect sympathetic stimulation/inhibition by medication, and sympathetic stimulation by isometric handgrip. We show that the observer allows to highlight changing levels of the cardiac sympathetic activity in the LF band in all these experimental conditions.

A computer model of cardiac electrical activity for the simulation of arrhythmias.

Modern computer power allows development of models of the heart that may be helpful for the understanding of arrhythmia mechanisms if, based on realistic physiological parameters, such models can display phenomena difficult to study in nature. Therefore, a two-dimensional model of the cardiac tissue has been implemented, where the modeling of each cell is based on membrane ionic channels (Beeler-Reuter and Luo-Rudy models). In addition, an ECG was computed based on the ionic currents simulated. This model allows us to observe the propagation of the action potentials Vm across the cardiac tissue, the evolution of Vm for any of the cardiac cells, and the underlying ionic currents. The computation of the ECG makes it possible to relate this information with an often-used diagnostic tool. Simulations of normal and pathological phenomena such as functional and anatomic reentry have been performed. Our simulation results show that the applied computer model based on ionic currents seems accurate and realistic when compared with biological models and offers a new approach to study the origin, prevention, and termination of arrhythmias.

Robust parameter estimation of intensity distributions for brain magnetic resonance images.

This paper presents two new methods for robust parameter estimation of mixtures in the context of magnetic resonance (MR) data segmentation. The head is constituted of different types of tissue that can be modeled by a finite mixture of multivariate Gaussian distributions. Our goal is to estimate accurately the statistics of desired tissues in presence of other ones of lesser interest. These latter can be considered as outliers and can severely bias the estimates of the former. For this purpose, we introduce a first method, which is an extension of the expectation-maximization (EM) algorithm, that estimates parameters of Gaussian mixtures but incorporates an outlier rejection scheme which allows to compute the properties of the desired tissues in presence of atypical data. The second method is based on genetic algorithms and is well suited for estimating the parameters of mixtures of different kind of distributions. We use this property by adding a uniform distribution to the Gaussian mixture for modeling the outliers. The proposed genetic algorithm can efficiently estimate the parameters of this extended mixture for various initial settings. Also, by changing the minimization criterion, estimates of the parameters can be obtained by histogram fitting which considerably reduces the computational cost. Experiments on synthetic and real MR data show that accurate estimates of the gray and white matters parameters are computed.

Subband modeling of the human cardiovascular system: new insights into cardiovascular regulation.

We present a new approach to cardiovascular analysis based on a well-known signal processing technique, namely, the frequency subband decomposition. The subbands are chosen in accordance with physiological standards: (1) 0-0.04 Hz, (2) 0.04-0.15 Hz, (3) 0.15-0.4 Hz. It is shown that such a pre-processing drastically improves the accuracy of the analysis and introduces a new direction in the understanding of the relationships between cardiovascular signals.

Exponential-type distribution of human muscle sympathetic nerve activity results in an automatic quantification method.

A new burst counting method based on a subject invariant characteristic demonstrates the limits of the actual automatic based methods. The exponential behaviour of the counted bursts in function of a variable threshold highlights a scaling property of the muscle sympathetic nerve activity. From experimental single unit recording results, we deduce the exponential-type (gamma) distribution of instantaneous spiking frequency within multi-unit recordings. We show that integrated muscle sympathetic nerve discharges must be gamma distributed with parameters proportional to the number of neurons in the recording pool and to the integration window width.

Autonomic imbalance assessed by heart rate variability analysis in vasovagal syncope.

In this prospective study, the autonomic modulation of the sinus node of 12 patients (mean age 28 +/- 7 years) suffering from vasovagal syncope (VVS) was compared to that of 11 sex and age matched control patients (mean age 32 +/- 4 years) by analysis of heart rate variability. Spectral indices (low frequency power [Plf], high frequency power [Phf], total power [Pt], sympathovagal balance [LF/HF]) and temporal indices, the mean of all coupling intervals between normal beats (mRR), the standard deviation about the mean (sdRR), the percentage of adjacent R to R intervals differing by more than 50 msec (pNN50), and the root mean square of variations in successive R to R intervals (rMSSD) were compared at baseline and during head-up tilt between and within groups. Baseline results were similar in both groups. During tilt testing, comparison of results between groups revealed only significantly higher sdRR and rMSSD and lower LF/HF ratio in VVS patients. Within VVS patients, comparison of temporal and spectral analysis between baseline and tilt showed a significant increase of most indices (Plf, Phf, Pt, sdRR, and rMSSD) but a comparable LF/HF ratio; in contrast, control patients exhibited only a significant increase of LF/HF ratio. In conclusion, VVS patients who developed vasovagal syncope during head-up tilt demonstrated a nonreciprocal modulation of the sinus node by the autonomic nervous system indicative of a pronounced physiological sympathetic surge along with a paradoxical vagal input to the cardiovascular system.