Can the ROX index predict high-flow nasal cannula failure in children under 2 with lower respiratory tract infection?

OBJECTIVE: This study evaluates the ROX index's accuracy in predicting the success or failure of high-flow nasal cannula (HFNC) therapy in children under 2 years with acute respiratory failure (ARF) from lower respiratory tract infections. METHODS: From January 2018 to 2021 we conducted this multicenter retrospective cohort study, which included patients aged 2-24 months. We aimed to assess HFNC therapy outcomes as either success or failure. The analysis covered patient demographics, diagnoses, vital signs, and ROX index values at intervals from 0 to 48 h after initiating HFNC. We used bivariate analysis, repeated measures ANOVA, multivariate logistic regression, and the area under the receiver operating characteristic (AUC-ROC) curve for statistical analysis. RESULTS: The study involved 529 patients from six centers, with 198 females (37%) and a median age of 9 months (IQR: 3-15 months). HFNC therapy failed in 38% of cases. We observed significant variability in failure rates across different centers and physicians (p < .001). The ROX index was significantly associated with HFNC outcomes at all time points, showing an increasing trend in success cases over time (p < .001), but not in HFNC failure cases. Its predictive ability is limited, with AUC-ROC values ranging from 0.56 at the start to 0.67 at 48 h. CONCLUSION: While the ROX index is associated with HFNC outcomes in children under 2 years, its predictive ability is modest, impacted by significant variability among patients, physicians, and centers. These findings emphasize the need for more reliable predictive tools for HFNC therapy in this patient population.

Long-Term Outcomes of Pharmacoinvasive Strategy Versus Primary Percutaneous Coronary Intervention in ST-Elevation Myocardial Infarction: A Study from Mexico City.

Although primary percutaneous coronary intervention (pPCI) is the treatment of choice in ST-elevation myocardial infarction (STEMI), challenges may arise in accessing this intervention for certain geodemographic groups. Pharmacoinvasive strategy (PIs) has demonstrated comparable outcomes when delays in pPCI are anticipated, but real-world data on long-term outcomes are limited. The aim of the present study was to compare long-term outcomes among real-world patients with STEMI who underwent either PIs or pPCI. This was a prospective registry including patients with STEMI who received reperfusion during the first 12 hours from symptom onset. The primary objective was cardiovascular mortality at 12 months according to the reperfusion strategy (pPCI vs PIs) and major cardiovascular events (cardiogenic shock, recurrent myocardial infarction, and congestive heart failure), and Bleeding Academic Research Consortium type 3 to 5 bleeding events were also evaluated. A total of 799 patients with STEMI were included; 49.1% underwent pPCI and 50.9% received PIs. Patients in the PIs group presented with more heart failure on admission (Killip-Kimbal >I 48.1 vs 39.7, p = 0.02) and had a lower proportion of pre-existing heart failure (0.2% vs 1.8%, p = 0.02) and atrial fibrillation (0.25% vs 1.2%, p = 0.02). No statistically significant difference was observed in cardiovascular mortality at the 12-month follow-up (hazard ratio for PIs 0.74, 95% confidence interval 0.42 to 1.30, log-rank p = 0.30) according to the reperfusion strategy used. The composite of major cardiovascular events (hazard ratio for PIs 0.98, 95% confidence interval 0.75 to 1.29, p = 0.92) and Bleeding Academic Research Consortium type 3 to 5 bleeding rates were also comparable. A low socioeconomic status, Killip-Kimball >2, age >60 years, and admission creatinine >2.0 mg/100 ml were predictors of the composite end point after multivariate analysis. In conclusion, this prospective real-world registry provides additional support that long-term major cardiovascular outcomes and bleeding are not different between patients who underwent PIs versus primary PCI.

Low albumin levels and high impedance ratio as risk factors for worsening kidney function during hospitalization of decompensated heart failure patients.

BACKGROUND: Patients hospitalized for decompensated heart failure (DHF) frequently experience worsening of renal function (WRF), leading to volume overload and resistance to diuretics. OBJECTIVE: To investigate whether albumin levels and whole-body impedance ratio, as an indicator of water distribution, were associated with WRF in patients with DHF. METHODS: A total of 80 patients hospitalized for DHF were consecutively included in the present longitudinal study. WRF during hospitalization was defined as an increase of ≥0.3 mg/dL (≥26.52 µmol/L) or 25% of baseline serum creatinine. Clinical and echocardiographic characteristics were assessed at baseline. Whole-body bioelectrical impedance was measured using tetrapolar and multiple-frequency equipment to obtain the ratio of impedance at 200 kHz to that at 5 kHz. Serum albumin levels were also evaluated. Baseline characteristics were compared between patients with and without deteriorating renal function using a t test or χ(2) test. Subsequently, a logistic regression analysis was performed to obtain the independent variables associated with WRF. RESULTS: The incidence of WRF during hospitalization was 26%. Independent risk factors associated with WRF were low serum albumin (RR=0.11; P=0.04); impedance ratio >0.85 (RR=5.3; P=0.05), systolic blood pressure >160 mmHg (RR=12; P=0.02) and maximum dose of continuous intravenous furosemide required >80 mg/day during hospitalization (RR=5.7, P=0.015). CONCLUSIONS: WRF is frequent in patients with DHF. It results from the inability to effectively regulate volume status because hypoalbuminemia induces water loss from the vascular space (high impedance ratio), and high diuretic doses lower circulatory volumes and reduce renal blood flow, leading to a decline in renal filtration function.

Dynapenia and Sarcopenia in Post-COVID-19 Syndrome Hospitalized Patients Are Associated with Severe Reduction in Pulmonary Function.

BACKGROUND: After hospital discharge, post-COVID-19 syndrome has been observed to be associated with impaired diffusing capacity, respiratory muscle strength, and lung imaging abnormalities, in addition to loss of muscle mass/strength, sarcopenia, and obesity impact exercise tolerance, pulmonary functions, and overall prognosis. However, the relationship between lung function and the coexistence of obesity with low muscle strength and sarcopenia in post-COVID-19 patients remains poorly investigated. Therefore, our aim was to evaluate the association between lung function and the coexistence of obesity with dynapenia and sarcopenia in post-COVID-19 syndrome patients. METHODS: This cross-sectional study included subjects who were hospitalized due to moderate to severe COVID-19, as confirmed by PCR testing. Subjects who could not be contacted, declined to participate, or died before the follow-up visit were excluded. RESULTS: A total of 711 subjects were evaluated; the mean age was 53.64 ± 13.57 years, 12.4% had normal weight, 12.6% were dynapenic without obesity, 8.3% had sarcopenia, 41.6% had obesity, 21.2% had dynapenic obesity, and 3.8% had sarcopenic obesity. In terms of pulmonary function, the dynapenic subjects showed decreases of -3.45% in FEV1, -12.61 cmH2O in MIP, and -12.85 cmH2O in MEP. On the other hand, the sarcopenic subjects showed decreases of -6.14 cmH2O in MIP and -11.64 cmH2O in MEP. The dynapenic obesity group displayed a reduction of -12.13% in PEF. CONCLUSIONS: In post-COVID-19 syndrome, dynapenia and sarcopenia-both with and without obesity-have been associated with lower lung function.

COMPARISON OF THE PREDICTIVE PERFORMANCE OF CARDIOGENIC SHOCK SCORES IN A REAL-WORLD LATIN AMERICA COUNTRY.

ABSTRACT: Background : Mortality in cardiogenic shock (CS) is up to 40%, and although risk scores have been proposed to stratify and assess mortality in CS, they have been shown to have inconsistent performance. The purpose was to compare CS prognostic scores and describe their performance in a real-world Latin American country. Methods : We included 872 patients with CS. The Society for Cardiovascular Angiography and Interventions (SCAI), CARDSHOCK, IABP-Shock II, Cardiogenic Shock Score, age-lactate-creatinine score, Get-With-The-Guidelines Heart Failure score, and Acute Decompensated Heart Failure National Registry scores were calculated. Decision curve analyses were performed to evaluate the net benefit of the different scoring systems. Logistic and Cox regression analyses were applied to construct area under the curve (AUC) statistics, this last one against time using the Inverse Probability of Censoring Weighting method, for in-hospital mortality prediction. Results: When logistic regression was applied, the scores had a moderate-good performance in the overall cohort that was higher AUC in the CARDSHOCK ( c = 0.666). In acute myocardial infarction-related CS (AMI-CS), CARDSHOCK still is the highest AUC (0.68). In non-AMI-CS only SCAI (0.668), CARDSHOCK (0.533), and IABP-SHOCK II (0.636) had statistically significant values. When analyzed over time, significant differences arose in the AUC, suggesting that a time-sensitive component influenced the prediction of mortality. The highest AUC was for the CARDSHOCK score (0.658), followed by SCAI (0.622). In AMI-CS-related, the highest AUC was for the CARDSHOCK score (0.671). In non-AMI-CS, SCAI was the best (0.642). Conclusions : Clinical scores show a time-sensitive AUC, suggesting that performance could be influenced by time and the type of CS. Understanding the temporal influence on the scores could provide a better prediction and be a valuable tool in CS.

Analysis of immortal-time effect in post-infarction ventricular septal defect.

Introduction: Time-fixed analyses have traditionally been utilized to examine outcomes in post-infarction ventricular septal defect (VSD). The aims of this study were to: (1) analyze the relationship between VSD closure/non-closure and mortality; (2) assess the presence of immortal-time bias. Material and methods: In this retrospective cohort study, patients with ST-elevation myocardial infarction (STEMI) complicated by VSD. Time-fixed and time-dependent Cox regression methodologies were employed. Results: The study included 80 patients: surgical closure (n = 26), transcatheter closure (n = 20), or conservative management alone (n = 34). At presentation, patients without VSD closure exhibited high-risk clinical characteristics, had the shortest median time intervals from STEMI onset to VSD development (4.0, 4.0, and 2.0 days, respectively; P = 0.03) and from STEMI symptom onset to hospital arrival (6.0, 5.0, and 0.8 days, respectively; P < 0.0001). The median time from STEMI onset to closure was 22.0 days (P = 0.14). In-hospital mortality rate was higher among patients who did not undergo defect closure (50%, 35%, and 88.2%, respectively; P < 0.0001). Closure of the defect using a fixed-time method was associated with lower in-hospital mortality (HR = 0.13, 95% CI 0.05-0.31, P < 0.0001, and HR 0.13, 95% CI 0.04-0.36, P < 0.0001, for surgery and transcatheter closure, respectively). However, when employing a time-varying method, this association was not observed (HR = 0.95, 95% CI 0.45-1.98, P = 0.90, and HR 0.88, 95% CI 0.41-1.87, P = 0.74, for surgery and transcatheter closure, respectively). These findings suggest the presence of an immortal-time bias. Conclusions: This study highlights that using a fixed-time analytic approach in post-infarction VSD can result in immortal-time bias. Researchers should consider employing time-dependent methodologies.

Gaussian process dynamical models for multimodal affect recognition.

Affective computing systems has a great potential in applications for biofeedback systems and cognitive conductual therapies. Here, by analyzing the physiological behavior of a given subject, we can infer the affective state of an emotional process. Since, emotions can be modeled as dynamic manifestations of these signals, a continuous analysis in the valence/arousal space, brings more information of the affective state related to an emotional process. In this paper we propose a method for dynamic affect recognition from multimodal physiological signals. Our model is based on learning a latent space using Gaussian process latent variable models (GP-LVM), which maps high dimensional data (multimodal physiological signals) in a low dimensional latent space. We incorporate the dynamics to the model by learning the latent representation, with associated dynamics. Finally, a support vector classifier is implemented to evaluate the relevance of the latent space features in the affective recognition process. The results show that the proposed method can efficiently model a physiological time-series and recognize with high accuracy an affective process.

A probabilistic framework based on SLIC-superpixel and Gaussian processes for segmenting nerves in ultrasound images.

We deal with an important problem in the field of anesthesiology known as automatic segmentation of nerve structures depicted in ultrasound images. This is important to aid the experts in anesthesiology, in order to carry out Peripheral Nerve Blocking (PNB). Ultrasound imaging has gained recent interest for performing PNB procedures since it offers a non-invasive visualization of the nerve and the anatomical structures around it. However, the location of these nerves in ultrasound images is a difficult task for the specialist due to the artifacts (i.e. speckle noise) that affect the intelligibility of a given image. In this paper, we present a probabilistic approach based on Simple Linear Iterative Clustering (SLIC-superpixels) and Gaussian processes for automatic segmentation of peripheral nerves. First, we use Graph cuts segmentation to define a region of interest (ROI). Such a ROI is divided into several correlated regions using SLIC-superpixels, then, a nonlinear Wavelet transform is applied as feature extraction stage. Finally, we use a classification scheme based on Gaussian Processes in order to predict the label of each parametrized superpixel (the label can be "nerve" or "background"). The accuracy of the proposed method is measured in terms of the Dice coefficient. Results obtained show performances with a Dice coefficient of 0.6524±0.0085 which brings accurate performances in nerve segmentation processes.

Multi-output Gaussian processes for enhancing resolution of diffusion tensor fields.

Second order diffusion tensor (DT) fields are widely used in several clinical applications: brain fibers connections, diagnosis of neuro-degenerative diseases, image registration, brain conductivity models, etc. However, due to current acquisition protocols and hardware limitations in MRI machines, the diffusion magnetic resonance imaging (dMRI) data is obtained with low spatial resolution (1 or 2 mm3 for each voxel). This issue can be significant, because tissue fibers are much smaller than voxel size. Interpolation has become in a successful methodology for enhancing spatial resolution of DT fields. In this work, we present a feature-based interpolation approach through multi-output Gaussian processes (MOGP). First, we extract the logarithm of eigenvalues (direction) and the Euler angles (orientation) from diffusion tensors and we consider each feature as a separated but related output. Then, we interpolate the features along the whole DT field. In this case, the independent variables are the space coordinates (x, y, z). For this purpose, we assume that all features follow a multi-output Gaussian process with a common covariance matrix. Finally, we reconstruct new tensors from the interpolated eigenvalues and Euler angles. Accuracy of our methodology is better compared to approaches in the state of the art for performing DT interpolation, and it achieves a performance similar to the recently introduced method based on Generalized Wishart processes for interpolation of positive semidefinite matrices. We also show that MOGP preserves important properties of diffusion tensors such as fractional anisotropy.

Automatic segmentation of nerve structures in ultrasound images using Graph Cuts and Gaussian processes.

Peripheral Nerve Blocking (PNB), is a procedure used for performing regional anesthesia, that comprises the administration of anesthetic in the proximity of a nerve. Several techniques have been used with the purpose of locating nerve structures when the PNB procedure is performed: anatomical surface landmarks, elicitation of paresthesia, nerve stimulation and ultrasound imaging. Among those, ultrasound imaging has gained great attention because it is not invasive and offers an accurate location of the nerve and the structures around it. However, the segmentation of nerve structures in ultrasound images is a difficult task for the specialist, since such images are affected by echo perturbations and speckle noise. The development of systems for the automatic segmentation of nerve structures can aid the specialist for locating nerve structures accurately. In this paper we present a methodology for the automatic segmentation of nerve structures in ultrasound images. An initial step is carried out using Graph Cut segmentation in order to generate regions of interest; we then use machine learning techniques with the aim of segmenting the nerve structure; here, a specific non-linear Wavelet transform is used for the feature extraction stage, and Gaussian processes for the classification step. The methodology performance is measured in terms of accuracy and the dice coefficient. Results show that the implemented methodology can be used for automatically segmenting nerve structures.

Peripheral nerve segmentation using Nonparametric Bayesian Hierarchical Clustering.

Several cases related to chronic pain, due to accidents, illness or surgical interventions, depend on anesthesiology procedures. These procedures are assisted with ultrasound images. Although, the ultrasound images are a useful instrument in order to guide the specialist in anesthesiology, the lack of intelligibility due to speckle noise, makes the clinical intervention a difficult task. In a similar manner, some artifacts are introduced in the image capturing process, challenging the expertise of anesthesiologists for not confusing the true nerve structures. Accordingly, an assistance methodology using image processing can improve the accuracy in the anesthesia practice. This paper proposes a peripheral nerve segmentation method in medical ultrasound images, based on Nonparametric Bayesian Hierarchical Clustering. The experimental results show segmentation performances with a Mean Squared Error performance of 1.026 ± 0.379 pixels for ulnar nerve, 0.704 ± 0.233 pixels for median nerve and 1.698 ± 0.564 pixels for peroneal nerve. Likewise, the model allows to emphasize other soft structures like muscles and aqueous tissues, that might be useful for an anesthesiologist.

Automatic assessment of voice quality in the context of multiple annotations.

Approaches to evaluate voice quality include perceptual analysis, and acoustical analysis. Perceptual analysis is subjective and depends mostly on the ability of a specialist to assess a pathology, whereas acoustical analysis is objective, but highly relies on the quality of the so called annotations that the specialist assigns to the voice signal. The quality of the annotations for acoustical analysis depends heavily on the expertise and knowledge of the specialist. We face a scenario where we have annotations performed by several specialists with different levels of expertise and knowledge. Traditional pattern recognition methods employed in acoustical analysis are no longer applicable, since these methods are designed for scenarios where a "ground-truth" label is assigned by the specialist. In this paper, we apply recent developments in machine learning for taking into account multiple annotators for acoustical analysis of voice signals. For the classification step we compare two techniques, one of them based on Gaussian Processes for regression with multiple annotators, and the other is a multi-class Logistic Regression model that measures the annotator performance in terms of sensitivity and specificity. The performance of classifiers is assessed in terms of Cohen's Kappa index. Results show that the multi-annotator classification schemes have better performance when compared to techniques based on a traditional classifier where the true label is estimated from the multiple annotations available using majority voting.

Latent force models for describing transcriptional regulation processes in the embryo development problem for the Drosophila melanogaster.

In the embryo development problem for the Drosophila melanogaster, a set of molecules known as mor-phogens are responsible for the embryo segmentation. These morphogens are encoded by different genes, including the GAP genes, maternal coordination genes and pair-rule genes. One of the maternal coordination genes encodes the Bicoid morphogen, which is the responsible for the development of the Drosophila embryo at the anterior part and for the control and regulation of the GAP genes in segmentation of the early development of the Drosophila melanogaster. The work presented in this document, reports a methodology that tends to integrate mechanistic and data driven based models, aiming at making inference over the mRNA Bicoid from gene expression data at the protein level for the Bicoid morphogen. The fundamental contribution of this work is the description of the concentration gradient of the Bicoid morphogen in the continuous spatio-temporal domain as well as the output regression (gene expression at protein level) using a Gaussian process described by a mechanistically inspired covariance function. Regression results and metrics computed for the Bicoid protein expression both in the temporal and spatial domains, showed outstanding performance with respect to reported experiments from previous studies. In this paper, a correlation coefficient of r = 0.9758 against a correlation coefficient of r = 0.9086 is being reported, as well as a SMSE of 0.0303±0.1512 against a SMSE of 0.1106±0.5090 and finally reporting a MSLL of -1.7036 ± 1.3472 against -1.0151±1.7669.

Sparse representation of MER signals for localizing the Subthalamic Nucleus in Parkinson's disease surgery.

Deep brain stimulation (DBS) of Subthalamic Nucleus (STN) is the best method for treating advanced Parkinson's disease (PD), leading to striking improvements in motor function and quality of life of PD patients. During DBS, online analysis of microelectrode recording (MER) signals is a powerful tool to locate the STN. Therapeutic outcomes depend of a precise positioning of a stimulator device in the target area. In this paper, we show how a sparse representation of MER signals allows to extract discriminant features, improving the accuracy in identification of STN. We apply three techniques for over-complete representation of signals: Method of Frames (MOF), Best Orthogonal Basis (BOB) and Basis Pursuit (BP). All the techniques are compared to classical methods for signal processing like Wavelet Transform (WT), and a more sophisticated method known as adaptive Wavelet with lifting schemes (AW-LS). We apply each processing method in two real databases and we evaluate its performance with simple supervised classifiers. Classification outcomes for MOF, BOB and BP clearly outperform WT and AW-LF in all classifiers for both databases, reaching accuracy values over 98%.

A latent force model for describing electric propagation in deep brain stimulation: a simulation study.

Deep brain stimulation (DBS) is a neurosurgical method used to treat symptoms of movement disorders by implanting electrodes in deep brain areas. Often, the DBS modeling approaches found in the literature assume a quasi-static approximation, and discard any dynamic behavior. Nevertheless, in a real DBS system the stimulus corresponds to a wave that changes as a function of time. It is clear that DBS demands an approach that takes into account the time-varying behavior of the input stimulus. In this work, we present a novel latent force model for describing the dynamic electric propagation occurred during DBS. The performance of the proposed model was studied by simulations under different conditions. The results show that our approach is able to take into account the time variations of the source and the produced field. Moreover, by restricting our model it is possible to obtain solutions for electrostatic formulations, here experimental results were compared with the finite element method. Additionally, our approach allows a solution to the inverse problem, which is a valuable clinical application allowing the appropriate tuning of the DBS device by the expert physician.

Dynamic physiological signal analysis based on Fisher kernels for emotion recognition.

Emotional behavior is an active area of study in the fields of neuroscience and affective computing. This field has the fundamental role of emotion recognition in the maintenance of physical and mental health. Valence/Arousal levels are two orthogonal, independent dimensions of any emotional stimulus and allows an analysis framework in affective research. In this paper we present our framework for emotional regression based on machine learning techniques. Autoregressive coefficients and hidden markov models on physiological signals, based on Fisher Kernels characterization are presented for mapping variable length sequences to new dimension feature vector space. Then, support vector regression is performed over the Fisher Scores for emotional recognition. Also quantitatively we evaluated the accuracy of the proposed model by acomplishing a hold-out cross validation over the dataset. The experimental results show that the proposed model can effectively perform the regression in comparison with static characterization methods.

Unsupervised learning applied in MER and ECG signals through Gaussians mixtures with the Expectation-Maximization algorithm and Variational Bayesian Inference.

Automatic identification of biosignals is one of the more studied fields in biomedical engineering. In this paper, we present an approach for the unsupervised recognition of biomedical signals: Microelectrode Recordings (MER) and Electrocardiography signals (ECG). The unsupervised learning is based in classic and bayesian estimation theory. We employ gaussian mixtures models with two estimation methods. The first is derived from the frequentist estimation theory, known as Expectation-Maximization (EM) algorithm. The second is obtained from bayesian probabilistic estimation and it is called variational inference. In this framework, both methods are used for parameters estimation of Gaussian mixtures. The mixtures models are used for unsupervised pattern classification, through the responsibility matrix. The algorithms are applied in two real databases acquired in Parkinson's disease surgeries and electrocardiograms. The results show an accuracy over 85% in MER and 90% in ECG for identification of two classes. These results are statistically equal or even better than parametric (Naive Bayes) and nonparametric classifiers (K-nearest neighbor).

Feature selection for multimodal emotion recognition in the arousal-valence space.

Emotion recognition is a challenging research problem with a significant scientific interest. Most of the emotion assessment studies have focused on the analysis of facial expressions. Recently, it has been shown that the simultaneous use of several biosignals taken from the patient may improve the classification accuracy. An open problem in this area is to identify which biosignals are more relevant for emotion recognition. In this paper, we perform Recursive Feature Elimination (RFE) to select a subset of features that allows emotion classification. Experiments are carried out over a multimodal database with arousal and valence annotations, and a diverse range of features extracted from physiological, neurophysiological, and video signals. Results show that several features can be eliminated while still preserving classification accuracy in setups of 2 and 3 classes. Using a small subset of the features, it is possible to reach 70% accuracy for arousal and 60% accuracy for valence in some experiments. Experimentally, it is shown that the Galvanic Skin Response (GSR) is relevant for arousal classification, while the electroencephalogram (EEG) is relevant for valence.