Gait Characterization in Duchenne Muscular Dystrophy (DMD) Using a Single-Sensor Accelerometer: Classical Machine Learning and Deep Learning Approaches.

Differences in gait patterns of children with Duchenne muscular dystrophy (DMD) and typically developing (TD) peers are visible to the eye, but quantifications of those differences outside of the gait laboratory have been elusive. In this work, we measured vertical, mediolateral, and anteroposterior acceleration using a waist-worn iPhone accelerometer during ambulation across a typical range of velocities. Fifteen TD and fifteen DMD children from 3 to 16 years of age underwent eight walking/running activities, including five 25 m walk/run speed-calibration tests at a slow walk to running speeds (SC-L1 to SC-L5), a 6-min walk test (6MWT), a 100 m fast walk/jog/run (100MRW), and a free walk (FW). For clinical anchoring purposes, participants completed a Northstar Ambulatory Assessment (NSAA). We extracted temporospatial gait clinical features (CFs) and applied multiple machine learning (ML) approaches to differentiate between DMD and TD children using extracted temporospatial gait CFs and raw data. Extracted temporospatial gait CFs showed reduced step length and a greater mediolateral component of total power (TP) consistent with shorter strides and Trendelenberg-like gait commonly observed in DMD. ML approaches using temporospatial gait CFs and raw data varied in effectiveness at differentiating between DMD and TD controls at different speeds, with an accuracy of up to 100%. We demonstrate that by using ML with accelerometer data from a consumer-grade smartphone, we can capture DMD-associated gait characteristics in toddlers to teens.

Uncovering the Gut-Liver Axis Biomarkers for Predicting Metabolic Burden in Mice.

Western diet (WD) intake, aging, and inactivation of farnesoid X receptor (FXR) are risk factors for metabolic and chronic inflammation-related health issues ranging from metabolic dysfunction-associated steatotic liver disease (MASLD) to dementia. The progression of MASLD can be escalated when those risks are combined. Inactivation of FXR, the receptor for bile acid (BA), is cancer prone in both humans and mice. The current study used multi-omics including hepatic transcripts, liver, serum, and urine metabolites, hepatic BAs, as well as gut microbiota from mouse models to classify those risks using machine learning. A linear support vector machine with K-fold cross-validation was used for classification and feature selection. We have identified that increased urine sucrose alone achieved 91% accuracy in predicting WD intake. Hepatic lithocholic acid and serum pyruvate had 100% and 95% accuracy, respectively, to classify age. Urine metabolites (decreased creatinine and taurine as well as increased succinate) or increased gut bacteria (Dorea, Dehalobacterium, and Oscillospira) could predict FXR deactivation with greater than 90% accuracy. Human disease relevance is partly revealed using the metabolite-disease interaction network. Transcriptomics data were also compared with the human liver disease datasets. WD-reduced hepatic Cyp39a1 (cytochrome P450 family 39 subfamily a member 1) and increased Gramd1b (GRAM domain containing 1B) were also changed in human liver cancer and metabolic liver disease, respectively. Together, our data contribute to the identification of noninvasive biomarkers within the gut-liver axis to predict metabolic status.

Hierarchical clustering optimizes the tradeoff between compositionality and expressivity of task structures for flexible reinforcement learning.

A hallmark of human intelligence, but challenging for reinforcement learning (RL) agents, is the ability to compositionally generalise, that is, to recompose familiar knowledge components in novel ways to solve new problems. For instance, when navigating in a city, one needs to know the location of the destination and how to operate a vehicle to get there, whether it be pedalling a bike or operating a car. In RL, these correspond to the reward function and transition function, respectively. To compositionally generalize, these two components need to be transferable independently of each other: multiple modes of transport can reach the same goal, and any given mode can be used to reach multiple destinations. Yet there are also instances where it can be helpful to learn and transfer entire structures, jointly representing goals and transitions, particularly whenever these recur in natural tasks (e.g., given a suggestion to get ice cream, one might prefer to bike, even in new towns). Prior theoretical work has explored how, in model-based RL, agents can learn and generalize task components (transition and reward functions). But a satisfactory account for how a single agent can simultaneously satisfy the two competing demands is still lacking. Here, we propose a hierarchical RL agent that learns and transfers individual task components as well as entire structures (particular compositions of components) by inferring both through a non-parametric Bayesian model of the task. It maintains a factorised representation of task components through a hierarchical Dirichlet process, but it also represents different possible covariances between these components through a standard Dirichlet process. We validate our approach on a variety of navigation tasks covering a wide range of statistical correlations between task components and show that it can also improve generalisation and transfer in more complex, hierarchical tasks with goal/subgoal structures. Finally, we end with a discussion of our work including how this clustering algorithm could conceivably be implemented by cortico-striatal gating circuits in the brain.

Focused Treatment of Heart Failure with Reduced Ejection Fraction Using Sacubitril/Valsartan.

The clinical syndrome of heart failure (HF) can be described as the reduced capacity of the heart to deliver blood throughout the body. To compensate for inadequate tissue perfusion, the renin-angiotensin aldosterone system (RAAS) and the sympathetic nervous system (SNS) become activated, resulting in increased blood pressure, heart rate, and blood volume. Consequent activation of the natriuretic peptide system (NPS) typically balances these effects; however, the NPS is unable to sustain compensation for excessive neurohormonal activation over time. Until recently, mortality benefits have been provided to patients with HF only by therapies that target the RAAS and SNS, including angiotensin-converting enzyme inhibitors (ACEIs), angiotensin receptor blockers (ARBs), mineralocorticoid receptor antagonists, and beta-blockers. Sacubitril/valsartan, the first-in-class angiotensin receptor/neprilysin inhibitor (ARNI), targets both the NPS and RAAS to further improve clinical outcomes. This review discusses the focused management of patients with HF with reduced ejection fraction (HFrEF) and suggests changes to current management paradigms. From this assessment, the evidence supports favoring sacubitril/valsartan over ACEIs or ARBs, and this therapy should be used in conjunction with beta-blockers to further decrease morbidity and mortality in patients with HFrEF.

Tornus catheter facilitated recanalization of chronic total occlusions--another niche device for a difficult lesion subset.

One of the last frontiers facing interventionalists is the treatment of chronic total occlusions. Chronic total occlusions (CTO) are present in about one-third of all diagnostic coronary angiograms. Recanalizations of these CTOs have demonstrated a trend towards lower mortality. Unfortunately, use of standard angioplasty equipment has only resulted in a 50-60% success rate.5,6,7 Several recently developed guidewires have increased success rates to 79-90%. Further success in CTO revascularization has been improved by use of novel techniques such as crossing the lesion in a retrograde fashion from collateral vessels. Niche devices such as the Frontrunner CTO catheter (Lumend Inc., Johnson and Johnson, Picataway, NJ) have also facilitated in successful treatment of CTOs. Unfortunately, none of these developments address the issue of deliverability of angioplasty balloons and stents. A newly developed device, the Tornus catheter (Asahi Intech; Abbot Vascular, Redwood City, CA), plays a niche role in the recanalization of this lesion subset. The following contains two case reports which highlight successful revascularization of CTOs with utilization of this new catheter.

Immediate- and short-term outcome following recanalization of long chronic total occlusions (> 50 mm) of native coronary arteries with the Frontrunner catheter.

Thirty percent of diagnostic angiograms have at least 1 chronic total occlusion (CTO). The 10-year survival of patients with a CTO is improved if they have the CTO successfully recanalized. The success of recanalization with conventional wires is 50% and the impact of new technology on recanalization is unknown. This abstract reports a single center experience with one such new device, the Lumend Frontrunner catheter in revascularization of this difficult lesion subset. A consecutive series of 18 patients with CTO's of native coronary arteries were enrolled in this single center, single operator series. The mean age of the CTO was 5.3 years. The indication for attempt at recanalization was ischemia in the territory of the CTO on SPECT imaging. Success was defined as TIMI flow restoration and < 40% residual stenosis. Primary success (defined as TIMI 3 Flow restoration and < 40% residual stenosis) was achieved in 77% of patients. At 30 days and out to 6 months, clinical TVR was 11% (2/18) in this difficult lesion subset. Conventional predictors of failure to recanalize CTOs do not appear to hold true with the use of the Frontrunner catheter. In this small series, dual cusp injections and use of the Microglide catheter appears to correlate with favorable outcomes. Fluoroscopy times and contrast use are high when attempting recanalization of CTOs with this technology.