Radiomics-Based Analysis of Intestinal Ultrasound Images for Inflammatory Bowel Disease: A Feasibility Study.

Background: The increasing adoption of intestinal ultrasound (IUS) for monitoring inflammatory bowel diseases (IBD) by IBD providers has uncovered new challenges regarding standardized image interpretation and limitations as a research tool. Artificial intelligence approaches can help address these challenges. We aim to determine the feasibility of radiomic analysis of IUS images and to determine if a radiomics-based classification model can accurately differentiate between normal and abnormal IUS images. We will also compare the radiomic-based model's performance to a convolutional neural network (CNN)-based classification model to understand which method is more effective for extracting meaningful information from IUS images. Methods: Retrospectively analyzing IUS images obtained during routine outpatient visits, we developed and tested radiomic-based and CNN-based models to distinguish between normal and abnormal images, with abnormal images defined as bowel wall thickness > 3 mm or bowel hyperemia with modified Limberg score ≥ 1 (both are surrogate markers for inflammation). Model performances were measured by area under the receiver operator curve (AUC). Results: For this feasibility study, 125 images (33% abnormal) were analyzed. A radiomic-based model using XG boost yielded the best classifier model with average test AUC 0.98%, 93.8% sensitivity, 93.8% specificity, and 93.7% accuracy. The CNN-based classification model yielded an average testing AUC of 0.75. Conclusions: Radiomic analysis of IUS images is feasible, and a radiomic-based classification model could accurately differentiate abnormal from normal images. Our findings establish methods to facilitate future radiomic-based IUS studies that can help standardize image interpretation and expand IUS research capabilities.

KRAGEN: a knowledge graph-enhanced RAG framework for biomedical problem solving using large language models.

MOTIVATION: Answering and solving complex problems using a large language model (LLM) given a certain domain such as biomedicine is a challenging task that requires both factual consistency and logic, and LLMs often suffer from some major limitations, such as hallucinating false or irrelevant information, or being influenced by noisy data. These issues can compromise the trustworthiness, accuracy, and compliance of LLM-generated text and insights. RESULTS: Knowledge Retrieval Augmented Generation ENgine (KRAGEN) is a new tool that combines knowledge graphs, Retrieval Augmented Generation (RAG), and advanced prompting techniques to solve complex problems with natural language. KRAGEN converts knowledge graphs into a vector database and uses RAG to retrieve relevant facts from it. KRAGEN uses advanced prompting techniques: namely graph-of-thoughts (GoT), to dynamically break down a complex problem into smaller subproblems, and proceeds to solve each subproblem by using the relevant knowledge through the RAG framework, which limits the hallucinations, and finally, consolidates the subproblems and provides a solution. KRAGEN's graph visualization allows the user to interact with and evaluate the quality of the solution's GoT structure and logic. AVAILABILITY AND IMPLEMENTATION: KRAGEN is deployed by running its custom Docker containers. KRAGEN is available as open-source from GitHub at: https://github.com/EpistasisLab/KRAGEN.

Points to consider when initiating clinical investigations in autistic paediatric populations-A White Paper.

Many individuals with autism spectrum disorder (ASD) experience various degrees of impairment in social interaction and communication, restricted, repetitive behaviours, interests/activities. These impairments make a significant contribution to poorer everyday adaptive functioning. Yet, there are no pharmacological therapies to effectively treat the core symptoms of ASD. Since symptoms of ASD likely emerge from a complex interplay of vulnerabilities, environmental factors and compensatory mechanisms during the early developmental period, pharmacological interventions arguably would have the greatest impact to improve long-term outcomes when implemented at a young age. It is essential therefore, that clinical development programmes of investigational drugs in ASD include the paediatric population early on in clinical trials. Such trials need to offer the prospect of direct benefit (PDB) for participants. In most cases in drug development this prospect is supported by evidence of efficacy in adults. However, the effectiveness of treatment approaches may be age-dependent, so that clinical trials in adults may not provide sufficient evidence for a PDB in children. In this white paper, we consolidate recommendations from regulatory guidelines, as well as advice from the Food and Drug Administration, USA (FDA) and the Committee for Human Medicinal Products (CHMP) consultations on various development programmes on: 1) elements to support a PDB to participants in early paediatric clinical trials in ASD, including single-gene neurodevelopment disorders, 2) aspects of study design to allow for a PDB. This white paper is intended to be complementary to existing regulatory guidelines in guiding industry and academic sponsors in their conduct of early paediatric clinical trials in ASD.

Auditory cortical regions show resting-state functional connectivity with the default mode-like network in echolocating bats.

Echolocating bats are among the most social and vocal of all mammals. These animals are ideal subjects for functional MRI (fMRI) studies of auditory social communication given their relatively hypertrophic limbic and auditory neural structures and their reduced ability to hear MRI gradient noise. Yet, no resting-state networks relevant to social cognition (e.g., default mode-like networks or DMLNs) have been identified in bats since there are few, if any, fMRI studies in the chiropteran order. Here, we acquired fMRI data at 7 Tesla from nine lightly anesthetized pale spear-nosed bats (Phyllostomus discolor). We applied independent components analysis (ICA) to reveal resting-state networks and measured neural activity elicited by noise ripples (on: 10 ms; off: 10 ms) that span this species' ultrasonic hearing range (20 to 130 kHz). Resting-state networks pervaded auditory, parietal, and occipital cortices, along with the hippocampus, cerebellum, basal ganglia, and auditory brainstem. Two midline networks formed an apparent DMLN. Additionally, we found four predominantly auditory/parietal cortical networks, of which two were left-lateralized and two right-lateralized. Regions within four auditory/parietal cortical networks are known to respond to social calls. Along with the auditory brainstem, regions within these four cortical networks responded to ultrasonic noise ripples. Iterative analyses revealed consistent, significant functional connectivity between the left, but not right, auditory/parietal cortical networks and DMLN nodes, especially the anterior-most cingulate cortex. Thus, a resting-state network implicated in social cognition displays more distributed functional connectivity across left, relative to right, hemispheric cortical substrates of audition and communication in this highly social and vocal species.

Sex classification of 3D skull images using deep neural networks.

Determining the fundamental characteristics that define a face as "feminine" or "masculine" has long fascinated anatomists and plastic surgeons, particularly those involved in aesthetic and gender-affirming surgery. Previous studies in this area have relied on manual measurements, comparative anatomy, and heuristic landmark-based feature extraction. In this study, we collected retrospectively at Cedars Sinai Medical Center (CSMC) a dataset of 98 skull samples, which is the first dataset of this kind of 3D medical imaging. We then evaluated the accuracy of multiple deep learning neural network architectures on sex classification with this dataset. Specifically, we evaluated methods representing three different 3D data modeling approaches: Resnet3D, PointNet++, and MeshNet. Despite the limited number of imaging samples, our testing results show that all three approaches achieve AUC scores above 0.9 after convergence. PointNet++ exhibits the highest accuracy, while MeshNet has the lowest. Our findings suggest that accuracy is not solely dependent on the sparsity of data representation but also on the architecture design, with MeshNet's lower accuracy likely due to the lack of a hierarchical structure for progressive data abstraction. Furthermore, we studied a problem related to sex determination, which is the analysis of the various morphological features that affect sex classification. We proposed and developed a new method based on morphological gradients to visualize features that influence model decision making. The method based on morphological gradients is an alternative to the standard saliency map, and the new method provides better visualization of feature importance. Our study is the first to develop and evaluate deep learning models for analyzing 3D facial skull images to identify imaging feature differences between individuals assigned male or female at birth. These findings may be useful for planning and evaluating craniofacial surgery, particularly gender-affirming procedures, such as facial feminization surgery.

AI-luminating Artificial Intelligence in Inflammatory Bowel Diseases: A Narrative Review on the Role of AI in Endoscopy, Histology, and Imaging for IBD.

Endoscopy, histology, and cross-sectional imaging serve as fundamental pillars in the detection, monitoring, and prognostication of inflammatory bowel disease (IBD). However, interpretation of these studies often relies on subjective human judgment, which can lead to delays, intra- and interobserver variability, and potential diagnostic discrepancies. With the rising incidence of IBD globally coupled with the exponential digitization of these data, there is a growing demand for innovative approaches to streamline diagnosis and elevate clinical decision-making. In this context, artificial intelligence (AI) technologies emerge as a timely solution to address the evolving challenges in IBD. Early studies using deep learning and radiomics approaches for endoscopy, histology, and imaging in IBD have demonstrated promising results for using AI to detect, diagnose, characterize, phenotype, and prognosticate IBD. Nonetheless, the available literature has inherent limitations and knowledge gaps that need to be addressed before AI can transition into a mainstream clinical tool for IBD. To better understand the potential value of integrating AI in IBD, we review the available literature to summarize our current understanding and identify gaps in knowledge to inform future investigations.

Digital Health Interventions for Heart Failure Management in Underserved Rural Areas of the United States: A Systematic Review of Randomized Trials.

BACKGROUND: Heart failure disproportionately affects individuals residing in rural areas, leading to worse health outcomes. Digital health interventions have been proposed as a promising approach for improving heart failure management. This systematic review aims to identify randomized trials of digital health interventions for individuals living in underserved rural areas with heart failure. METHODS AND RESULTS: We conducted a systematic review by searching 6 databases (CINAHL, EMBASE, MEDLINE, Web of Science, Scopus, and PubMed; 2000-2023). A total of 30 426 articles were identified and screened. Inclusion criteria consisted of digital health randomized trials that were conducted in underserved rural areas of the United States based on the US Census Bureau's classification. Two independent reviewers screened the studies using the National Heart, Lung, and Blood Institute tool to evaluate the risk of bias. The review included 5 trials from 6 US states, involving 870 participants (42.9% female). Each of the 5 studies employed telemedicine, 2 studies used remote monitoring, and 1 study used mobile health technology. The studies reported improvement in self-care behaviors in 4 trials, increased knowledge in 2, and decreased cardiovascular mortality in 1 study. However, 3 trials revealed no change or an increase in health care resource use, 2 showed no change in cardiac biomarkers, and 2 demonstrated an increase in anxiety. CONCLUSIONS: The results suggest that digital health interventions have the potential to enhance self-care and knowledge of patients with heart failure living in underserved rural areas. However, further research is necessary to evaluate their impact on clinical outcomes, biomarkers, and health care resource use. REGISTRATION: URL: https://www.crd.york.ac.uk/prospero/; Unique identifier: CRD42022366923.

Design and Implementation of an Electronic Health Record-Integrated Hypertension Management Application.

BACKGROUND: High blood pressure affects approximately 116 million adults in the United States. It is the leading risk factor for death and disability across the world. Unfortunately, over the past decade, hypertension control rates have decreased across the United States. Prediction models and clinical studies have shown that reducing clinician inertia alone is sufficient to reach the target of ≥80% blood pressure control. Digital health tools containing evidence-based algorithms that are able to reduce clinician inertia are a good fit for turning the tide in blood pressure control, but careful consideration should be taken in the design process to integrate digital health interventions into the clinical workflow. METHODS: We describe the development of a provider-facing hypertension management platform. We enumerate key steps of the development process, including needs finding, clinical workflow analysis, treatment algorithm creation, platform design and electronic health record integration. We interviewed and surveyed 5 Stanford clinicians from primary care, cardiology, and their clinical care team members (including nurses, advanced practice providers, medical assistants) to identify needs and break down the steps of clinician workflow analysis. The application design and development stage were aided by a team of approximately 15 specialists in the fields of primary care, hypertension, bioinformatics, and software development. CONCLUSIONS: Digital monitoring holds immense potential for revolutionizing chronic disease management. Our team developed a hypertension management platform at an academic medical center to address some of the top barriers to adoption and achieving clinical outcomes. The frameworks and processes described in this article may be used for the development of a diverse range of digital health tools in the cardiovascular space.

Comparative arrhythmia patterns among patients on tyrosine kinase inhibitors.

BACKGROUND: Tyrosine kinase inhibitors (TKIs) are widely used in the treatment of hematologic malignancies. Limited studies have shown an association between treatment-limiting arrhythmias and TKI, particularly ibrutinib, a Bruton's tyrosine kinase (BTK) inhibitor. We sought to comprehensively assess the arrhythmia burden in patients receiving ibrutinib vs non-BTK TKI vs non-TKI therapies. METHODS: We performed a retrospective analysis of consecutive patients who received long-term cardiac event monitors while on ibrutinib, non-BTK TKIs, or non-TKI therapy for a hematologic malignancy between 2014 and 2022. RESULTS: One hundred ninety-three patients with hematologic malignancies were included (ibrutinib = 72, non-BTK TKI = 46, non-TKI therapy = 75). The average duration of TKI therapy was 32 months in the ibrutinib group vs 64 months in the non-BTK TKI group (p = 0.003). The ibrutinib group had a higher prevalence of atrial fibrillation (n = 32 [44%]) compared to the non-BTK TKI (n = 7 [15%], p = 0.001) and non-TKI (n = 15 [20%], p = 0.002) groups. Similarly, the prevalence of non-sustained ventricular tachycardia was higher in the ibrutinib group (n = 31, 43%) than the non-BTK TKI (n = 8 [17%], p = 0.004) and non-TKI groups (n = 20 [27%], p = 0.04). TKI therapy was held in 25% (n = 18) of patients on ibrutinib vs 4% (n = 2) on non-BTK TKIs (p = 0.005) secondary to arrhythmias. CONCLUSIONS: In this large retrospective analysis of patients with hematologic malignancies, patients receiving ibrutinib had a higher prevalence of atrial and ventricular arrhythmias compared to those receiving other TKI, with a higher rate of treatment interruption due to arrhythmias.

Opportunities to Increase Science of Diversity and Inclusion in Clinical Trials: Equity and a Lack of a Control.

The United States witnessed a nearly 4-fold increase in personal health care expenditures between 1980 and 2010. Despite innovations and obvious benefits to health, participants enrolled in clinical trials still do not accurately represent the racial and ethnic composition of patients nationally or globally. This lack of diversity in cohorts limits the generalizability and significance of results among all populations and has deep repercussions for patient equity. To advance diversity in clinical trials, robust evidence for the most effective strategies for recruitment of diverse participants is needed. A major limitation of previous literature on clinical trial diversity is the lack of control or comparator groups for different strategies. To date, interventions have focused primarily on (1) community-based interventions, (2) institutional practices, and (3) digital health systems. This review article outlines prior intervention strategies across these 3 categories and considers health policy and ethical incentives for substantiation before US Food and Drug Administration approval. There are no current studies that comprehensively compare these interventions against one another. The American Heart Association Strategically Focused Research Network on the Science of Diversity in Clinical Trials represents a multicenter, collaborative network between Stanford School of Medicine and Morehouse School of Medicine created to understand the barriers to diversity in clinical trials by contemporaneous head-to-head interventional strategies accessing digital, institutional, and community-based recruitment strategies to produce informed recruitment strategies targeted to improve underrepresented patient representation in clinical trials.

Development of a compact NMR system to measure pO2 in a tissue-engineered graft.

Cellular macroencapsulation devices, known as tissue engineered grafts (TEGs), enable the transplantation of allogeneic cells without the need for life-long systemic immunosuppression. Islet containing TEGs offer promise as a potential functional cure for type 1 diabetes. Previous research has indicated sustained functionality of implanted islets at high density in a TEG requires external supplementary oxygen delivery and an effective tool to monitor TEG oxygen levels. A proven oxygen-measurement approach employs a 19F oxygen probe molecule (a perfluorocarbon) implanted alongside therapeutic cells to enable oxygen- and temperature- dependent NMR relaxometry. Although the approach has proved effective, the clinical translation of 19F oxygen relaxometry for TEG monitoring will be limited by the current inaccessibility and high cost of MRI. Here, we report the development of an affordable, compact, and tabletop 19F NMR relaxometry system for monitoring TEG oxygenation. The system uses a 0.5 T Halbach magnet with a bore diameter (19 cm) capable of accommodating the human arm, a potential site of future TEG implantation. 19F NMR relaxometry was performed while controlling the temperature and oxygenation levels of a TEG using a custom-built perfusion setup. Despite the magnet's nonuniform field, a pulse sequence of broadband adiabatic full-passage pulses enabled accurate 19F longitudinal relaxation rate (R1) measurements in times as short as ∼2 min (R1 vs oxygen partial pressure and temperature (R2 > 0.98)). The estimated sensitivity of R1 to oxygen changes at 0.5 T was 1.62-fold larger than the sensitivity previously reported for 16.4 T. We conclude that TEG oxygenation monitoring with a compact, tabletop 19F NMR relaxometry system appears feasible.

Electrophysiological mapping of the epicardium via 3D-printed flexible arrays.

Cardiac electrophysiology mapping and ablation are widely used to treat heart rhythm disorders such as atrial fibrillation (AF) and ventricular tachycardia (VT). Here, we describe an approach for rapid production of three dimensional (3D)-printed mapping devices derived from magnetic resonance imaging. The mapping devices are equipped with flexible electronic arrays that are shaped to match the epicardial contours of the atria and ventricle and allow for epicardial electrical mapping procedures. We validate that these flexible arrays provide high-resolution mapping of epicardial signals in vivo using porcine models of AF and myocardial infarction. Specifically, global coverage of the epicardial surface allows for mapping and ablation of myocardial substrate and the capture of premature ventricular complexes with precise spatial-temporal resolution. We further show, as proof-of-concept, the localization of sites of VT by means of beat-to-beat whole-chamber ventricular mapping of ex vivo Langendorff-perfused human hearts.