Latent space arithmetic on data embeddings from healthy multi-tissue human RNA-seq decodes disease modules.

Computational analyses of transcriptomic data have dramatically improved our understanding of complex diseases. However, such approaches are limited by small sample sets of disease-affected material. We asked if a variational autoencoder trained on large groups of healthy human RNA sequencing (RNA-seq) data can capture the fundamental gene regulation system and generalize to unseen disease changes.

FLEX-SMOTE: Synthetic over-sampling technique that flexibly adjusts to different minority class distributions.

Class imbalance is a challenge that affects the prediction rate on a minority class. To remedy this problem, various SMOTEs (synthetic minority over-sampling techniques) have been designed to populate synthetic minority instances. Some SMOTEs operate on the border of a minority class, while others concentrate on the class core.

Benchmark suites instead of leaderboards for evaluating AI fairness.

Benchmarks and leaderboards are commonly used to track the fairness impacts of artificial intelligence (AI) models. Many critics argue against this practice, since it incentivizes optimizing for metrics in an attempt to build the "most fair" AI model. However, this is an inherently impossible task since different applications have different considerations.

DataDesc: A framework for creating and sharing technical metadata for research software interfaces.

The reuse of research software is central to research efficiency and academic exchange. The application of software enables researchers to reproduce, validate, and expand upon study findings. The analysis of open-source code aids in the comprehension, comparison, and integration of approaches.

Privacy of single-cell gene expression data.

The possibility that single-cell gene expression datasets could leak information about individuals' genotypes has been largely unexplored. Walker et al. showed that even noisy genotype predictions derived from these data can be linked to the corresponding genotype profiles with significant accuracy.

Hopfield and Hinton's neural network revolution and the future of AI.

In this opinion piece, the authors, from the fields of artificial intelligence (AI) and psychology, reflect on how the foundational discoveries of Nobel laureates Hopfield and Hinton have influenced their research. They also discuss emerging directions in AI and the challenges that lie ahead for neural networks and machine learning.

Toward a tipping point in federated learning in healthcare and life sciences.

We discuss the real-world application of federated learning (FL) in the healthcare and life sciences industry, noting a tipping point in its adoption beyond academia. Sharing our experiences with multi-hospital and multi-pharma collaborations, we highlight the importance of involving key stakeholders to develop production-grade FL solutions that are fully compliant with stringent privacy and security standards.

Segmentation tracking and clustering system enables accurate multi-animal tracking of social behaviors.

Accurate analysis of social behaviors in animals is hindered by methodological challenges. Here, we develop a segmentation tracking and clustering system (STCS) to address two major challenges in computational neuroethology: reliable multi-animal tracking and pose estimation under complex interaction conditions and providing interpretable insights into social differences guided by genotype information. We established a comprehensive, long-term, multi-animal-tracking dataset across various experimental settings.

A latent transfer learning method for estimating hospital-specific post-acute healthcare demands following SARS-CoV-2 infection.

The long-term complications of COVID-19, known as the post-acute sequelae of SARS-CoV-2 infection (PASC), significantly burden healthcare resources. Quantifying the demand for post-acute healthcare is essential for understanding patients' needs and optimizing the allocation of valuable medical resources for disease management. Driven by this need, we developed a heterogeneous latent transfer learning framework (Latent-TL) to generate critical insights for individual health systems in a distributed research network.

A multi-dimensional approach to the future of digital research infrastructure for systemic environmental science.

Digital research infrastructure (DRI) for environmental science requires significant transformation to support the changing nature of science and utilize digital innovations. Numerous challenges prevent this change yet simultaneously pose exciting principles to drive the future of DRI. This opinion piece details a multi-dimensional approach toward these futures for the environmental community.

Germline de novo alterations of RUNX1T1 in individuals with neurodevelopmental and congenital anomalies.

Runt-related transcription factor 1 translocated to 1 (RUNX1T1; also known as eight-twenty-one [ETO]) encodes a transcription regulator for hematopoietic genes and is well known for its involvement in hematologic malignancies, particularly acute myeloid leukemia (AML). However, its role in congenital disease is less understood. This study provides detailed clinical and molecular information on three cases exhibiting neurodevelopmental and congenital anomalies with germline de novo alterations in RUNX1T1.

Neuromorphic engineering: Artificial brains for artificial intelligence.

Neuromorphic engineering is a research discipline that tries to bridge the gaps between neuroscience and engineering, cognition and algorithms, and natural and artificial intelligence. Neuromorphic engineering promises revolutionary breakthroughs that could rapidly advance our understanding of the brain and pave the way toward more human-like and sustainable artificial intelligence. But first, it will have to find its way out of the laboratory.

Protective effects of exercise on responses to combined social and environmental stress in prairie voles.

The combination of social and environmental stressors significantly influences psychological and physical health in males and females, and contributes to both depression and cardiovascular diseases. Animal models support these findings. Voluntary exercise may protect against some forms of stress; however, the protective effects of exercise against social stressors require further investigation.

Advanced framework for multilevel detection of digital video forgeries.

The rapid expansion of digital media has sparked significant concerns regarding the swift dissemination and potential misuse of forged video content. Existing forgery detection technologies primarily focus on simple forgeries and are still evolving, resulting in a critical gap in the detection of multilevel forgeries, where one forgery is layered over another. This paper presents an innovative framework designed to address this challenge by extracting intricate features from forged frames using attention-augmented convolutional neural networks (AACNNs).

Ischemia Time in Extremity Allotransplantation: A Comprehensive Review.

In response to the widespread occurrence of limb loss and the transformative potential of extremity vascularized composite allotransplantation (VCA), we examine the impact of warm and cold ischemia duration on limb survival and functional recovery. Our insights into warm ischemia are largely derived from relevant literature on replantation and revascularization. Studies indicate that achieving reperfusion within 5 to 6 hours of warm ischemia is critical for limb survival, and within 3 hours for curbing significant functional deficits.

Echography-guided Botulinum Toxin for Moving Ear Syndrome.

Background: Moving Ear Syndrome is a rare hyperkinetic disorder.

Phenomenology Shown: This Video Abstract illustrates typical backward movements of the right ear associated with pain and discomfort in a man with Moving Ear Syndrome.

Educational Value: Moving Ear Syndrome is effectively and safely treatable with EMG-US-guided botulinum toxin injections.

Shaking Up Essential Tremor: Peripheral Devices and Mechanical Strategies to Reduce Tremor.

This review discusses non-pharmacological, non-surgical interventions for action tremor, including essential tremor (ET). We review transcutaneous peripheral nerve stimulation (PNS), a variety of orthotic/mechanical devices, cooling and vibration strategies, and adaptive utensils, most of which are currently available. The PNS section discusses open loop (CALA-Trio) and closed loop systems (Felix™, NeuroAI™ and Motimove® systems).

Morphologic transformation of ferrofluid during micropump driving under field control.

The superiority of ferrofluid pumps in the fields of biomedical, life science, energy, and power research has been experimentally demonstrated. However, the mechanisms underlying the morphological transformations of ferrofluid fusion and separation during pump driving are not completely understood. To bridge the gap between the theory and practical applications of ferrofluid pumps, we employed optical methods to record the dynamic morphological transformation of rotating and fixed ferrofluids under different magnetic field polarities, magnetic field distributions, and ferrofluid mass fractions.

Effects of multidisciplinary therapy on energy balance, inflammation, and metabolic diseases in adolescents with obesity: A narrative review.

Obesity is a consequence of multiple factors, including genetics, lifestyle and nutritional choices, physical activity, sleep duration, screen time, and mood disorders. These behavioral elements can impair the regulation of energy balance and obesity management that link obesity to a constellation of chronic conditions that lead to a high prevalence of cardiometabolic risk factors, metabolic syndrome, and nonalcoholic fatty liver disease. Multidisciplinary therapy is defined as an approach delivered by a multidisciplinary-trained health team covering at least two components of behavior, physical activity/exercise, dietary habits, and/or psychological counseling associated with clinical interventions.

Chatbot Demonstrates Moderate Interrater Reliability in Billing for Hand Surgery Clinic Encounters.

Background: Artificial intelligence offers opportunities to improve the burden of health care administrative tasks. Application of machine learning to coding and billing for clinic encounters may represent time- and cost-saving benefits with low risk to patient outcomes.

Methods: Gemini, a publicly available large language model chatbot, was queried with 139 de-identified patient encounters from a single surgeon and asked to provide the Current Procedural Terminology code based on the criteria for different encounter types.