Citations

Abstract Background Delirium is often underdiagnosed in clinical practice and is not routinely coded for billing. While manual chart review can identify delirium, it is labor-intensive and impractical for large-scale studies. Natural language processing (NLP) can analyze unstructured text in electronic health records (EHRs) to extract meaningful clinical information. Methods To support national integration of NLP for EHR-based delirium identification across different institutions, we launched the Delirium Interest Group within the national Evolve to Next-Gen Accrual to Clinical Trials (ENACT) NLP Working Group. This paper outlines our initial efforts to standardize, evaluate, and translate an NLP-based delirium detection model into the i2b2/ENACT platform. Results Multisite contextual inquiry identified several key challenges, including variations in local screening practices (eg, tools used, documentation frequency, and quality control), the need for harmonized definitions in the context of EHRs, and the complexity of modeling temporal logic. Multisite NLP evaluation revealed variable performance degradation driven by differences in delirium screening practices, clinical documentation patterns and semantics, and note syntactic structures. Conclusion Our work represents an important first step toward enabling scalable and standardized NLP-based delirium detection across institutions. By engaging diverse institutions through the ENACT NLP Working Group, we identified shared challenges and site-specific variations that impact model implementation and performance. Our collaborative approach enabled the development of a more robust framework for delirium identification across heterogeneous EHR systems. Future efforts will build on this foundation to enhance the validity, usability, and translational impact of delirium detection.

Abstract Objective: Electronic Health Record (EHR) data are critical for advancing translational research and AI technologies. The ENACT network offers access to structured EHR data across 57 CTSA hubs. However, substantial information is contained in clinical narratives, requiring natural language processing (NLP) for research. The ENACT NLP Working Group was formed to make NLP-derived clinical information accessible and queryable across the network. Methods: We established the ENACT NLP Working Group with 13 sites selected based on criteria including clinical notes access, IT infrastructure, NLP expertise, and institutional support. We divided sites into five focus groups targeting clinical tasks within disease contexts. Each focus group consisted of two development sites and two validation sites. We extended the ENACT ontology to standardize NLP-derived data and conducted multisite evaluations using the Open Health Natural Language Processing (OHNLP) Toolkit. Results: The working group achieved 100% site retention and deployed NLP infrastructure across all sites. We developed and validated NLP algorithms for rare disease phenotyping, social determinants of health, opioid use disorder, sleep phenotyping, and delirium phenotyping. Performance varied across sites (F1 scores 0.53–0.96), highlighting data heterogeneity impacts. We extended the ENACT common data model and ontology to incorporate NLP-derived data while maintaining Shared Health Research Informatics NEtwork (SHRINE) compatibility. Conclusion: This demonstrates feasibility of deploying NLP infrastructure across large, federated networks. The focus group approach proved more practical than general-purpose approaches. Key lessons include the challenge of data heterogeneity and importance of collaborative governance. This work also provides a foundation that other networks can build on to implement NLP capabilities for translational research.

Accurate diagnosis of gastrointestinal (GI) diseases typically requires invasive procedures or imaging studies that pose the risk of various post-procedural complications or involve radiation exposure. Bowel sounds (BSs), though typically described during a GI-focused physical exam, are highly inaccurate and variable, with low clinical value in diagnosis. Interpretation of the acoustic characteristics of BSs, i.e., using a phonoenterogram (PEG), may aid in diagnosing various GI conditions non-invasively. Use of artificial intelligence (AI) and improvements in computational analysis can enhance the use of PEGs in different GI diseases and lead to a non-invasive, cost-effective diagnostic modality that has not been explored before. The purpose of this work was to develop an automated AI model, You Only Listen Once (YOLO), to detect prominent bowel sounds that can enable real-time analysis for future GI disease detection and diagnosis. A total of 110 2-minute PEGs sampled at 44.1 kHz were recorded using the Eko DUO® stethoscope from eight healthy volunteers at two locations, namely, left upper quadrant (LUQ) and right lower quadrant (RLQ) after IRB approval. The datasets were annotated by trained physicians, categorizing BSs as prominent or obscure using version 1.7 of Label Studio Software®. Each BS recording was split up into 375 ms segments with 200 ms overlap for real-time BS detection. Each segment was binned based on whether it contained a prominent BS, resulting in a dataset of 36,149 non-prominent segments and 6435 prominent segments. Our dataset was divided into training, validation, and test sets (60/20/20% split). A 1D-CNN augmented transformer was trained to classify these segments via the input of Mel-frequency cepstral coefficients. The developed AI model achieved area under the receiver operating curve (ROC) of 0.92, accuracy of 86.6%, precision of 86.85%, and recall of 86.08%. This shows that the 1D-CNN augmented transformer with Mel-frequency cepstral coefficients achieved creditable performance metrics, signifying the YOLO model’s capability to classify prominent bowel sounds that can be further analyzed for various GI diseases. This proof-of-concept study in healthy volunteers demonstrates that automated BS detection can pave the way for developing more intuitive and efficient AI-PEG devices that can be trained and utilized to diagnose various GI conditions. To ensure the robustness and generalizability of these findings, further investigations encompassing a broader cohort, inclusive of both healthy and disease states are needed.

Abstract In comparative effectiveness research (CER), ensuring internal, construct, and external validity is crucial. Internal validity determines whether observed outcomes are causally linked to an intervention; construct validity assesses whether a study measures what it intends to; and external validity relates to generalizability in routine practice. Double-blind randomized trials optimize internal validity by minimizing bias and confounding, while construct validity is strengthened through pre-specified protocols and standardized data collection. However, controlled conditions limit external validity. Pragmatic RCTs improve generalizability but may compromise internal validity due to open-label designs. Observational CER studies—including observational studies following the target trial emulation framework—offer broader external validity and feasibility in less time and at lower cost. However, due to lack of random assignment, these studies are susceptible to measured and unmeasured confounding. Several techniques help mitigate these concerns, including a detailed pre-specified protocol, tools such as propensity score matching to balance measured confounders, falsification endpoint testing for assessing the presence of unmeasured confounders, and quasi-experimental designs (including instrumental variable analysis), which may be able to address both. Pre-specified sensitivity analyses and triangulation with complementary data sources further enhance robustness. Construct validity in observational CER depends on accurate patient profiling and validated computational phenotypes for identifying patients, exposures, and outcomes. Thoughtful study design and analytic rigor are essential for balancing these validity considerations. This brief review highlights these issues with examples from thrombosis research.

The differentiation of naive CD8+ T cells into effector or memory populations requires dynamic remodeling of cellular metabolism and proteome composition. In a recent study published in Nature Immunology, Sinclair et al offer critical insights into the role of autophagy, particularly mitophagy, in regulating these processes during CD8+ T cell differentiation. Autophagy, a conserved catabolic mechanism, is traditionally associated with cellular homeostasis and survival during nutrient deprivation. In contrast, Sinclair et al reveal that, in the immune system, autophagy is not simply a survival mechanism but a fine-tuned regulator of CD8+ T cell metabolism and function, fine-tuning CD8+ T cell effector vs quiescence choices.

Abstract P2x purinoreceptor 7 (P2RX7), an ATP-gated ion channel, is known to play pivotal roles in the progression of Alzheimer’s disease (AD), although its cell type-specific pathological mechanisms have yet to be elucidated. Here, we show that genetic deletion of P2rx7 mitigates brain atrophy, tau accumulation and cognitive impairment in PS19 tauopathy mice. Specific deletion of P2rx7 in microglia, but not astrocytes, significantly suppresses tau propagation from the entorhinal cortex to CA1 in the hippocampus, an early event in AD pathology. Single-cell (sc)-RNA sequencing of mouse brains revealed specific P2rx7 expression in microglia, inducing inflammatory changes accompanied by elevated extracellular vesicles (EVs) secretion in PS19 mice. Brain-derived EVs (BDEVs) proteome demonstrated that P2RX7 increases EV cargo loading of tau and mitochondrial molecules in BDEVs from PS19 mice, which was further validated by single-molecule super-resolution. Notably, following the injection of BDEVs isolated from PS19 mice with or without P2rx7 deficiency, the microglial transcriptome of recipient mice revealed enriched DNA-sensing and type II interferon signaling in response to BDEVs from PS19 mice, which was diminished in the group injected with P2rx7-deficient BDEVs. Thus, our results indicate that P2RX7 regulates EV-mediated tau and mitochondrial transfer and inflammatory activation in microglia with increased EV secretion, thereby contributing to tauopathy and neurodegeneration, highlighting the therapeutic potential of targeting the P2RX7-EV axis in AD.

SUMMARY Tau aggregates propagate through the brain in a prion-like manner in Alzheimer’s disease (AD) and other tauopathies, but the molecular identity and functional partners of the seeding-competent Tau species remain poorly defined. Here, we present an unbiased proteomic profiling of a high-molecular-weight (HMW) Tau-seed isolated from AD patient brains. We contrast this interactome with that of a biochemically similar, seeding-incompetent HMW-Tau species from age-matched healthy controls. Despite comprising less than 5% of total Tau in the brain, Tau-seed associates with a distinct set of proteins enriched in synaptic, mitochondrial, and vesicle-trafficking functions. Cross-species functional screening in Drosophila and mouse models identifies interactors that modulate Tau toxicity and seeding. Spatially resolved analysis of postmortem AD brains reveals heterogenous co-deposition of these proteins with Tau aggregates, suggesting functionally distinct Tau-seed complexes. Together, this dataset provides a framework for understanding selective Tau-seed toxicity and identifies candidate regulators of Tau propagation with therapeutic potential.

Abstract We have previously reported the therapeutic effect of depletion and regeneration of endogenous microglia on autism spectrum disorder-like behaviors in offspring from the dams under maternal immune activation (MIA) by dampening their neuritogenic activation. Here we show a long-lasting pathological effect by MIA, leading to abnormal behaviors in offspring mice in a sex-specific manner at 3 months of age. MIA was induced by injecting Polyinosinic:polycytidylic acid [Poly(I:C)] at 10mg/kg at E9.5 with preselected dams based on the immunoreactivity to low-dose Poly(I:C) injection. MIA offspring show impairments in sociability, repetitive behavior, and spatial working and associative memories in both sexes, whereas only male offspring show social novelty deficit. MIA has no effect on anxiety-like behavior nor sensori-motor or locomotor activity. Administering colony stimulating factor receptor (CSF1R) inhibitor in young adult MIA offspring regenerates microglia and ameliorates sociability deficits in males and spatial working and associative memory impairments in both sexes without effect on social novelty impairments. Transcriptomic analysis of prefrontal cortex and hippocampal tissues reveals MIA and sex-specific pathways and highlights potential key genes involved in the corrective effect of microglial regeneration in MIA offspring. Our results underscore the potential of the sex-specific therapeutic applications of CSF1R inhibitor for MIA-related social and cognitive disorders.