Effect of body mass index on exercise capacity following pediatric heart transplantation.

BACKGROUND: Obesity and impaired exercise tolerance following heart transplantation increase the risk of post-transplant morbidity and mortality. The aim of this study was to evaluate the effect of body mass index on markers of exercise capacity in pediatric heart transplant recipients and compare this effect with a healthy pediatric cohort. METHODS: A retrospective analysis of cardiopulmonary exercise test data between 2004 and 2022 was performed. All patients exercised on a treadmill using the Bruce protocol. Inclusion criteria included patients aged 6-21 years, history of heart transplantation (transplant cohort) or no cardiac diagnosis (control cohort) at the time of testing, and a maximal effort test. Patients were further stratified within these two cohorts as underweight, normal, overweight, and obese based on body mass index groups. Two-way analyses of variance were performed with diagnosis and body mass index category as the independent variables. RESULTS: A total of 250 exercise tests following heart transplant and 1963 exercise tests of healthy patients were included. Heart transplant patients across all body mass index groups had higher resting heart rate and lower maximal heart rate, heart rate recovery at 1 min, exercise duration, and peak aerobic capacity (VO2peak). Heart transplant patients in the normal and overweight body mass index categories had higher VO2peak and exercise duration when compared to underweight and obese patients. CONCLUSION: Underweight status and obesity are strongly associated with lower VO2peak and exercise duration in heart transplant patients. Normal and overweight heart transplant patients had the best markers of exercise capacity.

Microbiota-gut-brain axis: the mediator of exercise and brain health.

The brain controls the nerve system, allowing complex emotional and cognitive activities. The microbiota-gut-brain axis is a bidirectional neural, hormonal, and immune signaling pathway that could link the gastrointestinal tract to the brain. Over the past few decades, gut microbiota has been demonstrated to be an essential component of the gastrointestinal tract that plays a crucial role in regulating most functions of various body organs. The effects of the microbiota on the brain occur through the production of neurotransmitters, hormones, and metabolites, regulation of host-produced metabolites, or through the synthesis of metabolites by the microbiota themselves. This affects the host's behavior, mood, attention state, and the brain's food reward system. Meanwhile, there is an intimate association between the gut microbiota and exercise. Exercise can change gut microbiota numerically and qualitatively, which may be partially responsible for the widespread benefits of regular physical activity on human health. Functional magnetic resonance imaging (fMRI) is a non-invasive method to show areas of brain activity enabling the delineation of specific brain regions involved in neurocognitive disorders. Through combining exercise tasks and fMRI techniques, researchers can observe the effects of exercise on higher brain functions. However, exercise's effects on brain health via gut microbiota have been little studied. This article reviews and highlights the connections between these three interactions, which will help us to further understand the positive effects of exercise on brain health and provide new strategies and approaches for the prevention and treatment of brain diseases.

A hybrid statistical morphometry free-form deformation approach to 3D personalized foot-ankle models.

Foot and ankle joint models are widely used in the biomechanics community for musculoskeletal and finite element analysis. However, personalizing a foot and ankle joint model is highly time-consuming in terms of medical image collection and data processing. This study aims to develop and evaluate a framework for constructing a comprehensive 3D foot model that integrates statistical shape modeling (SSM) with free-form deformation (FFD) of internal bones. The SSM component is derived from external foot surface scans (skin measurements) of 50 participants, utilizing principal component analysis (PCA) to capture the variance in foot shapes. The derived surface shapes from SSM then guide the FFD process to accurately reconstruct the internal bone structures. The workflow accuracy was established by comparing three model-generated foot models against corresponding skin and bone geometries manually segmented and not part of the original training set. We used the top ten principal components representing 85 % of the population variation to create the model. For prediction validation, the average Dice similarity coefficient, Hausdorff distance error, and root mean square error were 0.92 ± 0.01, 2.2 ± 0.19 mm, and 2.95 ± 0.23 mm for soft tissues, and 0.84 ± 0.03, 1.83 ± 0.1 mm, and 2.36 ± 0.12 mm for bones, respectively. This study presents an efficient approach for 3D personalized foot model reconstruction via SSM generation of the foot surface that informs bone reconstruction based on FFD. The proposed workflow is part of the open-source Musculoskeletal Atlas Project linked to OpenSim and makes it feasible to accurately generate foot models informed by population anatomy, and suitable for rigid body analysis and finite element simulation.

Integration of diffusion tensor imaging parameters with mesh morphing for in-depth analysis of brain white matter fibre tracts.

Averaging is commonly used for data reduction/aggregation to analyse high-dimensional MRI data, but this often leads to information loss. To address this issue, we developed a novel technique that integrates diffusion tensor metrics along the whole volume of the fibre bundle using a 3D mesh-morphing technique coupled with principal component analysis for delineating case and control groups. Brain diffusion tensor MRI scans of high school rugby union players (n = 30, age 16-18) were acquired on a 3 T MRI before and after the sports season. A non-contact sport athlete cohort with matching demographics (n = 12) was also scanned. The utility of the new method in detecting differences in diffusion tensor metrics of the right corticospinal tract between contact and non-contact sport athletes was explored. The first step was to run automated tractography on each subject's native space. A template model of the right corticospinal tract was generated and morphed into each subject's native shape and space, matching individual geometry and diffusion metric distributions with minimal information loss. The common dimension of the 20 480 diffusion metrics allowed further data aggregation using principal component analysis to cluster the case and control groups as well as visualization of diffusion metric statistics (mean, ±2 SD). Our approach of analysing the whole volume of white matter tracts led to a clear delineation between the rugby and control cohort, which was not possible with the traditional averaging method. Moreover, our approach accounts for the individual subject's variations in diffusion tensor metrics to visualize group differences in quantitative MR data. This approach may benefit future prediction models based on other quantitative MRI methods.

Rethinking running biomechanics: a critical review of ground reaction forces, tibial bone loading, and the role of wearable sensors.

This study presents a comprehensive review of the correlation between tibial acceleration (TA), ground reaction forces (GRF), and tibial bone loading, emphasizing the critical role of wearable sensor technology in accurately measuring these biomechanical forces in the context of running. This systematic review and meta-analysis searched various electronic databases (PubMed, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect) to identify relevant studies. It critically evaluates existing research on GRF and tibial acceleration (TA) as indicators of running-related injuries, revealing mixed findings. Intriguingly, recent empirical data indicate only a marginal link between GRF, TA, and tibial bone stress, thus challenging the conventional understanding in this field. The study also highlights the limitations of current biomechanical models and methodologies, proposing a paradigm shift towards more holistic and integrated approaches. The study underscores wearable sensors' potential, enhanced by machine learning, in transforming the monitoring, prevention, and rehabilitation of running-related injuries.

Mucus-coated, magnetically-propelled fecal surrogate to mimic fecal shear forces on colonic epithelium.

The relationship between the mechanical forces associated with bowel movement and colonic mucosal physiology is understudied. This is partly due to the limited availability of physiologically relevant fecal models that can exert these mechanical stimuli in in vitro colon models in a simple-to-implement manner. In this report, we created a mucus-coated fecal surrogate that was magnetically propelled to produce a controllable sweeping mechanical stimulation on primary intestinal epithelial cell monolayers. The mucus layer was derived from purified porcine stomach mucins, which were first modified with reactive vinyl sulfone (VS) groups followed by reaction with a thiol crosslinker (PEG-4SH) via a Michael addition click reaction. Formation of mucus hydrogel network was achieved at the optimal mixing ratio at 2.5 % w/v mucin-VS and 0.5 % w/v PEG-4SH. The artificial mucus layer possessed similar properties as the native mucus in terms of its storage modulus (66 Pa) and barrier function (resistance to penetration by 1-µm microbeads). This soft, but mechanically resilient mucus layer was covalently linked to a stiff fecal hydrogel surrogate (based on agarose and magnetic particles, with a storage modulus of 4600 Pa). The covalent bonding between the mucus and agarose ensured its stability in the subsequent fecal sliding movement when tested at travel distances as long as 203 m. The mucus layer served as a lubricant and protected epithelial cells from the moving fecal surrogate over a 1 h time without cell damage. To demonstrate its utility, this mucus-coated fecal surrogate was used to mechanically stimulate a fully differentiated, in vitro primary colon epithelium, and the physiological stimulated response of mucin-2 (MUC2), interleukin-8 (IL-8) and serotonin (5HT) secretion was quantified. Compared with a static control, mechanical stimulation caused a significant increase in MUC2 secretion into luminal compartment (6.4 × ), a small but significant increase in IL-8 secretion (2.5 × and 3.5 × , at both luminal and basal compartments, respectively), and no detectable alteration in 5HT secretion. This mucus-coated fecal surrogate is expected to be useful in in vitro colon organ-on-chips and microphysiological systems to facilitate the investigation of feces-induced mechanical stimulation on intestinal physiology and pathology.

Prognostic Value of RV Function Analysis During the Interstage Period in Patients with Hypoplastic Left Heart Syndrome.

Cardiac dysfunction is associated with mortality in children with hypoplastic left heart syndrome (HLHS). We evaluated the ability of qualitative and quantitative RV functional parameters to predict outcomes in HLHS patients. In this retrospective, single-center study, echocardiograms from 3 timepoints (pre-stage 1 palliation, 4-8 weeks post-stage 1 palliation, and pre-Glenn) were analyzed in infants with HLHS. Patients were stratified into two groups based on outcome of transplant-free survival post-Glenn (survivors) versus mortality or transplantation prior to Fontan (non-survivors). Images were retrospectively reviewed to obtain RV global longitudinal strain (RVGLS), RV-free wall strain (RVFWS), fractional area change (FAC), tricuspid annular systolic plane excursion (TAPSE), tissue motion annular displacement of the tricuspid valve (TMAD-TV) and qualitative systolic function assessment during the predetermined timepoints. An equal variance t-test and chi-square were used to determine significant differences and ROC curve analysis was performed to derive optimal cutoff values to predict mortality/transplant. A total of 47 patients met inclusion criteria, of which, 21 patients met composite endpoint. There were no significant differences in any RV functional parameter during the pre- or post-stage 1 palliation timepoints. The absolute values of RVFWS, RVGLS, and TMAD-TV were significantly greater in survivors than non-survivors during the pre-Glenn timepoint. A pre-Glenn RVGLS > -15.6 (AUC 0.79), RVFWS > -18.6 (AUC 0.75), and TMAD-TV < 12.6% (AUC 0.82) were sensitive and specific for predicting death or need for transplantation prior to Fontan completion. RVGLS, RVFWS, and TMAD-TV may help identify higher-risk HLHS patients during the interstage period.

Otolaryngology Care Disparities in American Indian Populations.

Our objectives were to quantify geographical disparities in otolaryngology care access with respect to American Indian (AI) populations and to identify gaps in care. Although increased incidence and mortality rates of ear, nose, and throat (ENT) conditions in AI populations are well documented, few studies address factors contributing to these differential outcomes. We conducted a cross-sectional study of US states with AI areas that either met the population threshold for the American Community Survey annual estimate or annual supplemental estimate. A 2-tailed t test was used to compare the geographic distribution of ENT providers practicing within AI areas against non-AI areas, showing a statistically significant difference (P < .001) in the concentration of providers (0.409 vs 2.233 providers per 100,000 patients). To our knowledge, this is the first study to explore geographic barriers contributing to AI disparities within otolaryngology.

Heart rate detection method based on Ballistocardiogram signal of wearable device：Algorithm development and validation.

Background: Heart rate, as the four vital signs of human body, is a basic indicator to measure a person's health status. Traditional electrocardiography (ECG) measurement, which is routinely monitored, requires subjects to wear lead electrodes frequently, which undoubtedly places great restrictions on participants' activities during the normal test. At present, the boom of wearable devices has created hope for non-invasive, simple operation and low-cost daily heart rate monitoring, among them, Ballistocardiogram signal (BCG) is an effective heart rate measurement method, but in the actual acquisition process, the robustness of non-invasive vital sign collection is limited. Therefore, it is necessary to develop a method to improve the robustness of heart rate monitoring. Objective: Therefore, in view of the problem that the accuracy of untethered monitoring heart rate is not high, we propose a method aimed at detecting the heartbeat cycle based on BCG to accurately obtain the beat-to-beat heart rate in the sleep state. Methods: In this study, we implement an innovative J-wave detection algorithm based on BCG signals. By collecting BCG signals recorded by 28 healthy subjects in different sleeping positions, after preprocessing, the data feature set is formed according to the clustering of morphological features in the heartbeat interval. Finally, a J-wave recognition model is constructed based on bi-directional long short-term memory (BiLSTM), and then the number of J-waves in the input sequence is counted to realize real-time detection of heartbeat. The performance of the proposed heartbeat detection scheme is cross-verified, and the proposed method is compared with the previous wearable device algorithm. Results: The accuracy of J wave recognition in BCG signal is 99.67%, and the deviation rate of heart rate detection is only 0.27%, which has higher accuracy than previous wearable device algorithms. To assess consistency between method results and heart rates obtained by the ECG, seven subjects are compared using Bland-Altman plots, which show no significant difference between BCG and ECG results for heartbeat cycles. Conclusions: Compared with other studies, the proposed method is more accurate in J-wave recognition, which improves the accuracy and generalization ability of BCG-based continuous heartbeat cycle extraction, and provides preliminary support for wearable-based untethered daily monitoring.

The Child Opportunity Index 2.0 and Disparities in Pediatric Cardiorespiratory Fitness.

OBJECTIVE: To evaluate the effect of neighborhood-level characteristics on cardiorespiratory fitness (CRF) via peak oxygen consumption (VO2peak) for healthy pediatric patients. STUDY DESIGN: The institutional cardiopulmonary exercise testing (CPET) database was analyzed retrospectively. All patients aged ≤ 18 years without a diagnosis of cardiac disease and with a maximal effort CPET were included. Patients were divided into three self-identified racial categories: White, Black, and Latinx. The Child Opportunity Index (COI) 2.0 was used to analyze social determinants of health. CRF was evaluated based on COI quintiles and race. Assessment of the effect of COI on racial disparities in CRF was performed using ANCOVA. RESULTS: A total of 1753 CPETs met inclusion criteria. The mean VO2peak was 42.1 ± 9.8 mL/kg/min. The VO2peak increased from 39.1 ± 9.6 mL/kg/min for patients in the very low opportunity cohort to 43.9 ± 9.4 mL/kg/min for patients in the very high opportunity cohort. White patients had higher percent predicted VO2peak compared with both Black and Latinx patients (P < .01 for both comparisons). The racial differences in CRF were no longer significant when adjusting for COI. CONCLUSION: In a large pediatric cohort, COI was associated with CRF. Racial disparities in CRF are reduced when accounting for modifiable risk factors.

Enhancing Knee MR Image Clarity through Image Domain Super-Resolution Reconstruction.

This study introduces a hybrid analytical super-resolution (SR) pipeline aimed at enhancing the resolution of medical magnetic resonance imaging (MRI) scans. The primary objective is to overcome the limitations of clinical MRI resolution without the need for additional expensive hardware. The proposed pipeline involves three key steps: pre-processing to re-slice and register the image stacks; SR reconstruction to combine information from three orthogonal image stacks to generate a high-resolution image stack; and post-processing using an artefact reduction convolutional neural network (ARCNN) to reduce the block artefacts introduced during SR reconstruction. The workflow was validated on a dataset of six knee MRIs obtained at high resolution using various sequences. Quantitative analysis of the method revealed promising results, showing an average mean error of 1.40 ± 2.22% in voxel intensities between the SR denoised images and the original high-resolution images. Qualitatively, the method improved out-of-plane resolution while preserving in-plane image quality. The hybrid SR pipeline also displayed robustness across different MRI sequences, demonstrating potential for clinical application in orthopaedics and beyond. Although computationally intensive, this method offers a viable alternative to costly hardware upgrades and holds promise for improving diagnostic accuracy and generating more anatomically accurate models of the human body.

Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors.

The ankle joint plays a crucial role in gait, facilitating the articulation of the lower limb, maintaining foot-ground contact, balancing the body, and transmitting the center of gravity. This study aimed to implement long short-term memory (LSTM) networks for predicting ankle joint angles, torques, and contact forces using inertial measurement unit (IMU) sensors. Twenty-five healthy participants were recruited. Two IMU sensors were attached to the foot dorsum and the vertical axis of the distal anteromedial tibia in the right lower limb to record acceleration and angular velocity during running. We proposed a LSTM-MLP (multilayer perceptron) model for training time-series data from IMU sensors and predicting ankle joint biomechanics. The model underwent validation and testing using a custom nested k-fold cross-validation process. The average values of the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE) for ankle dorsiflexion joint and moment, subtalar inversion joint and moment, and ankle joint contact forces were 0.89 ± 0.04, 0.75 ± 1.04, and 2.96 ± 4.96 for walking, and 0.87 ± 0.07, 0.88 ± 1.26, and 4.1 ± 7.17 for running, respectively. This study demonstrates that IMU sensors, combined with LSTM neural networks, are invaluable tools for evaluating ankle joint biomechanics in lower limb pathological diagnosis and rehabilitation, offering a cost-effective and versatile alternative to traditional experimental settings.

Sub-volt high-speed silicon MOSCAP microring modulator driven by high-mobility conductive oxide.

Silicon microring modulator plays a critical role in energy-efficient optical interconnect and optical computing owing to its ultra-compact footprint and capability for on-chip wavelength-division multiplexing. However, existing silicon microring modulators usually require more than 2 V of driving voltage (Vpp), which is limited by both material properties and device structures. Here, we present a metal-oxide-semiconductor capacitor microring modulator through heterogeneous integration between silicon photonics and titanium-doped indium oxide, which is a high-mobility transparent conductive oxide (TCO) with a strong plasma dispersion effect. The device is co-fabricated by Intel's photonics fab and our in-house TCO patterning processes, which exhibits a high modulation efficiency of 117 pm/V and consequently can be driven by a very low Vpp of 0.8 V. At a 11 GHz modulation bandwidth where the modulator is limited by the RC bandwidth, we obtained 25 Gb/s clear eye diagrams with energy efficiency of 53 fJ/bit.

Stroke Lesion Segmentation and Deep Learning: A Comprehensive Review.

Stroke is a medical condition that affects around 15 million people annually. Patients and their families can face severe financial and emotional challenges as it can cause motor, speech, cognitive, and emotional impairments. Stroke lesion segmentation identifies the stroke lesion visually while providing useful anatomical information. Though different computer-aided software are available for manual segmentation, state-of-the-art deep learning makes the job much easier. This review paper explores the different deep-learning-based lesion segmentation models and the impact of different pre-processing techniques on their performance. It aims to provide a comprehensive overview of the state-of-the-art models and aims to guide future research and contribute to the development of more robust and effective stroke lesion segmentation models.

Differences in intra-foot movement strategies during locomotive tasks among chronic ankle instability, copers and healthy individuals.

Individuals with chronic ankle instability (CAI) suffer from the resulting sequela of repetitive lateral ankle sprains (LAS), whilst copers appear to cope with initial LAS successfully. Therefore, the aim of this study was to explore the intra-foot biomechanical differences among CAI, copers, and healthy individuals during dynamic tasks. Twenty-two participants per group were included and required to perform cutting and different landing tasks (DL: drop landing; FL: forward jump followed a landing). A five-segment foot model with 8 degrees of freedom was used to explore the intra-foot movement among these three groups. Smaller dorsiflexion angles were found in copers (DL tasks and prelanding task) and CAI (DL and FL task) compared to healthy participants. Copers presented a more eversion position compared to others during these dynamic tasks. During the descending phase of DL task, greater dorsiflexion angles in the metatarsophalangeal joint were found in copers compared to the control group. Joint moment difference was only found in the subtalar joint during the descending phase of FL task, presenting more inversion moments in copers compared to healthy participants. Copers rely on more eversion positioning to prevent over-inversion of the subtalar joint compared to CAI. Further, the foot became more unstable when conducting sport-related movements, suggesting that foot stability seems to be sensitive to the task types. These findings may help in designing and implementing interventions to restore functions of the ankle joint in CAI individuals.

Localised non-metastatic sarcomatoid renal cell carcinoma: a 31-year externally verified study.

OBJECTIVE: To evaluate post-nephrectomy outcomes and predictors of cancer-specific survival (CSS) between patients with localised sarcomatoid renal cell carcinoma (sRCC) and those with Grade 4 RCC (non-sRCC), as most sRCC research focuses on advanced or metastatic disease with limited studies analysing outcomes of patients with localised non-metastatic sRCC. PATIENTS AND METHODS: A total of 564 patients with localised RCC underwent partial or radical nephrectomy between June 1988 to March 2019 for sRCC (n = 204) or World Health Organization/International Society of Urological Pathology Grade 4 non-sRCC (n = 360). The CSS at every stage between groups was assessed. Phase III ASSURE clinical trial data were used to externally validate the CSS findings. The Mann-Whitney U-test and chi-squared test compared outcomes and the Kaplan-Meier method evaluated CSS, overall survival (OS) and recurrence-free survival. Clinicopathological features associated with RCC death were evaluated using Cox proportional hazards regression. RESULTS: The median follow-up was 31.5 months. The median OS and CSS between the sRCC and Grade 4 non-sRCC groups was 45 vs 102 months and 49 vs 152 months, respectively (P < 0.001). At every stage, sRCC had worse CSS compared to Grade 4 non-sRCC. Notably, pT1 sRCC had worse CSS than pT3 Grade 4 non-sRCC. Negative predictors of CSS were sarcomatoid features, non-clear cell histology, positive margins, higher stage (pT3/pT4), and use of minimally invasive surgery (MIS). ASSURE external verification showed worse CSS in patients with sRCC (hazard ratio [HR] 1.63, 95% confidence interval [CI] 1.12-2.36; P = 0.01), but not worse outcomes in MIS surgery (HR 1.39, 95% CI 0.75-2.56; P = 0.30). CONCLUSIONS: Localised sRCC had worse CSS compared to Grade 4 non-sRCC at every stage. Negative survival predictors included positive margins, higher pathological stage, use of MIS, and non-clear cell histology. sRCC is an aggressive variant even at low stages requiring vigilant surveillance and possible inclusion in adjuvant therapy trials.

A Reference Equation for Peak Oxygen Uptake for Pediatric Patients Who Undergo Treadmill Cardiopulmonary Exercise Testing.

Pediatric patients are often referred to cardiopulmonary exercise testing (CPET) laboratories for assessment of exercise-related symptoms. For clinicians to understand results in the context of performance relative to peers, adequate fitness-based prediction equations must be available. However, reference equations for prediction of peak oxygen uptake (VO2peak) in pediatrics are largely developed from field-based testing, and equations derived from CPET are primarily developed using adult data. Our objective was to develop a pediatric reference equation for VO2peak. Clinical CPET data from a validation cohort of 1,383 pediatric patients aged 6 to 18 years who achieved a peak respiratory exchange ratio ≥1.00 were analyzed to identify clinical and exercise testing factors that contributed to the prediction of VO2peak from tests performed using the Bruce protocol. The resultant prediction equation was applied to a cross-validation cohort of 1,367 pediatric patients. Exercise duration, gender, weight, and age contributed to the prediction of VO2peak, generating the following prediction equation: (R2 = 0.645, p <0.001, standard error of the estimate = 6.19 ml/kg/min): VO2peak (ml/kg/min) =16.411+ 3.423 (exercise duration [minutes]) - 5.145 (gender [0 = male, 1 = female]) - 0.121 (weight [kg]) + 0.179 (age [years]). This equation was stable across the age range included in the present study, with differences ≤0.5 ml/kg/min between mean measured and predicted VO2peak in all age groups. In conclusion, this study represents what we believe is the largest pediatric CPET-derived VO2peak prediction effort to date, and this VO2peak prediction equation provides clinicians who perform and interpret exercise tests in pediatric patients with a resource with which to better quantify fitness when CPET is not available.

Reference Values for Cardiorespiratory Fitness in Patients Aged 6 to 18 Years.

OBJECTIVE: To develop reference values for cardiorespiratory fitness, as quantified by peak oxygen uptake (VO2peak) and treadmill time, in patients aged 6 through 18 years referred for cardiopulmonary exercise testing (CPET). STUDY DESIGN: We reviewed a clinical pediatric CPET database for fitness data in children aged 6-18 years with no underlying heart disease. CPET was obtained via the Bruce protocol utilizing objectively confirmed maximal effort via respiratory exchange ratio. Fitness data (VO2peak and treadmill test duration) were analyzed to determine age- and sex-specific reference values for this pediatric cohort. RESULTS: Data from 2025 pediatric CPETs (53.2% female) were included in the analyses. VO2peak increased with age in males, but not females. Treadmill test duration increased with age in both males and females. Fitness was generally higher in males when compared with females in the same age groups. CONCLUSIONS: Our study provides extensive reference values for both VO2peak and total treadmill test time via the Bruce protocol for a pediatric population without known cardiac disease. Furthermore, the inclusion of objectively confirmed maximal exercise effort increases confidence in these findings compared with prior studies in this area. Clinicians performing CPET in pediatric populations can utilize these reference values to characterize test results according to representative peer data.

Brain-Inspired Spatio-Temporal Associative Memories for Neuroimaging Data Classification: EEG and fMRI.

Humans learn from a lot of information sources to make decisions. Once this information is learned in the brain, spatio-temporal associations are made, connecting all these sources (variables) in space and time represented as brain connectivity. In reality, to make a decision, we usually have only part of the information, either as a limited number of variables, limited time to make the decision, or both. The brain functions as a spatio-temporal associative memory. Inspired by the ability of the human brain, a brain-inspired spatio-temporal associative memory was proposed earlier that utilized the NeuCube brain-inspired spiking neural network framework. Here we applied the STAM framework to develop STAM for neuroimaging data, on the cases of EEG and fMRI, resulting in STAM-EEG and STAM-fMRI. This paper showed that once a NeuCube STAM classification model was trained on a complete spatio-temporal EEG or fMRI data, it could be recalled using only part of the time series, or/and only part of the used variables. We evaluated both temporal and spatial association and generalization accuracy accordingly. This was a pilot study that opens the field for the development of classification systems on other neuroimaging data, such as longitudinal MRI data, trained on complete data but recalled on partial data. Future research includes STAM that will work on data, collected across different settings, in different labs and clinics, that may vary in terms of the variables and time of data collection, along with other parameters. The proposed STAM will be further investigated for early diagnosis and prognosis of brain conditions and for diagnostic/prognostic marker discovery.

Utilizing Deep Learning Algorithms for Signal Processing in Electrochemical Biosensors: From Data Augmentation to Detection and Quantification of Chemicals of Interest.

Nanomaterial-based aptasensors serve as useful instruments for detecting small biological entities. This work utilizes data gathered from three electrochemical aptamer-based sensors varying in receptors, analytes of interest, and lengths of signals. Our ultimate objective was the automatic detection and quantification of target analytes from a segment of the signal recorded by these sensors. Initially, we proposed a data augmentation method using conditional variational autoencoders to address data scarcity. Secondly, we employed recurrent-based networks for signal extrapolation, ensuring uniform signal lengths. In the third step, we developed seven deep learning classification models (GRU, unidirectional LSTM (ULSTM), bidirectional LSTM (BLSTM), ConvGRU, ConvULSTM, ConvBLSTM, and CNN) to identify and quantify specific analyte concentrations for six distinct classes, ranging from the absence of analyte to 10 µM. Finally, the second classification model was created to distinguish between abnormal and normal data segments, detect the presence or absence of analytes in the sample, and, if detected, identify the specific analyte and quantify its concentration. Evaluating the time series forecasting showed that the GRU-based network outperformed two other ULSTM and BLSTM networks. Regarding classification models, it turned out signal extrapolation was not effective in improving the classification performance. Comparing the role of the network architectures in classification performance, the result showed that hybrid networks, including both convolutional and recurrent layers and CNN networks, achieved 82% to 99% accuracy across all three datasets. Utilizing short-term Fourier transform (STFT) as the preprocessing technique improved the performance of all datasets with accuracies from 84% to 99%. These findings underscore the effectiveness of suitable data preprocessing methods in enhancing neural network performance, enabling automatic analyte identification and quantification from electrochemical aptasensor signals.