76555 research outputs found
Sort by
Neural network analysis as a novel skin outcome in a trial of belumosudil in patients with systemic sclerosis.
Full text linkBACKGROUND: The modified Rodnan skin score (mRSS), a measure of systemic sclerosis (SSc) skin thickness, is agnostic to inflammation and vasculopathy. Previously, we demonstrated the potential of neural network-based digital pathology applied to SSc skin biopsies as a quantitative outcome. Here, we leverage deep learning and histologic analyses of clinical trial biopsies to decipher SSc skin features \u27seen\u27 by artificial intelligence (AI).
METHODS: Adults with diffuse cutaneous SSc ≤ 6 years were enrolled in an open-label trial of belumosudil [a Rho-associated coiled-coil containing protein kinase 2 (ROCK2) inhibitor]. Participants underwent serial mRSS and arm biopsies at week (W) 0, 24 and 52. Two blinded dermatopathologists scored stained sections (e.g., Masson\u27s trichrome, hematoxylin and eosin, CD3, α-smooth muscle actin) for 16 published SSc dermal pathological parameters. We applied our deep learning model to generate QIF signatures/biopsy and obtain \u27Fibrosis Scores\u27. Associations between Fibrosis Score and mRSS (Spearman correlation), and between Fibrosis Score and mRSS versus histologic parameters [odds ratios (OR)], were determined.
RESULTS: Only ten patients were enrolled due to early study termination, and of those, five had available biopsies due to fixation issues. Median, interquartile range (IQR) for mRSS change (0-52 W) for the ten participants was -2 (-9-7.5) and for the five with biopsies was -2.5 (-11-7.5). The correlation between Fibrosis Score and mRSS was R = 0.3; p = 0.674. Per 1-unit mRSS change (0-52 W), histologic parameters with the greatest associated changes were (OR, 95% CI, p-value): telangiectasia (2.01, [(1.31-3.07], 0.001), perivascular CD3 + (0.99, [0.97-1.02], 0.015), and % of CD8 + among CD3 + (0.95, [0.89-1.01], 0.031). Likewise, per 1-unit Fibrosis Score change, parameters with greatest changes were (OR, p-value): hyalinized collagen (1.1, [1.04 - 1.16], \u3c 0.001), subcutaneous (SC) fat loss (1.47, [1.19-1.81], \u3c 0.001), thickened intima (1.21, [1.06-1.38], 0.005), and eccrine entrapment (1.14, [1-1.31], 0.046).
CONCLUSIONS: Belumosudil was associated with non-clinically meaningful mRSS improvement. The histologic features that significantly correlated with Fibrosis Score changes (e.g., hyalinized collagen, SC fat loss) were distinct from those associated with mRSS changes (e.g., telangiectasia and perivascular CD3 +). These data suggest that AI applied to SSc biopsies may be useful for quantifying pathologic features of SSc beyond skin thickness
From gene modules to gene markers: an integrated AI-human approach selects CD38 to represent plasma cell-associated transcriptional signatures.
Full text linkBACKGROUND: Knowledge-driven prioritization of candidate genes derived from large-scale molecular profiling data for targeted transcriptional profiling assays is challenging due to the vast amount of biomedical literature that needs to be harnessed. We present a workflow leveraging Large Language Models (LLMs) to prioritize candidate genes within module M12.15, a plasma cell-associated module from the BloodGen3 repertoire, by integrating knowledge-driven prioritization with data-driven analysis of transcriptome profiles.
METHODS: The workflow involves a two-step process: (1) high-throughput screening using LLMs to score and rank the 17 genes of module M12.15 based on six predefined criteria, and (2) prioritization employing high-resolution scoring and fact-checking, with human experts validating and refining AI-generated scores.
RESULTS: The first step identified five candidate genes (CD38, TNFRSF17, IGJ, TOP2A, and TYMS). Following human-augmented LLM scoring and fact checking, as part of the second step, CD38 and TNFRSF17 emerged as the top candidates. Next, transcriptome profiling data from three datasets was incorporated in the workflow to assess expression levels and correlations with the module average across various conditions and cell types. It is on this basis that CD38 was prioritized as the top candidate, with TNFRSF17 and IGJ identified as promising alternatives.
CONCLUSION: This study introduces a systematic framework that integrates LLMs with human expertise for gene prioritization. Our analysis identified CD38, TNFRSF17, and IGJ as the top candidates within the plasma cell-associated module M12.15 from the BloodGen3 repertoire, with their relative rankings varying systematically based on specific evaluation criteria, from plasma cell biology to therapeutic relevance. This criterion-dependent ranking demonstrates the ability of the framework to perform nuanced, multi-faceted evaluations. By combining knowledge-driven analysis with data-driven metrics, our approach provides a balanced and comprehensive method for biomarker selection. The methodology established here offers a reproducible and scalable approach that can be applied across diverse biological contexts and extended to analyze large module repertoires
The BIM deletion polymorphism potentiates the survival of leukemia stem and progenitor cells and impairs response to targeted therapies.
No full textOne sixth of human cancers harbor pathogenic germline variants, but few studies have established their functional contribution to cancer outcomes. Here, we developed a humanized mouse model harboring a common East Asian polymorphism, the BIM deletion polymorphism (BDP), which confers resistance to oncogenic kinase inhibitors through generation of non-apoptotic splice isoforms. However, despite its clear role in mediating bulk resistance in patients, the BDP\u27s role in cancer stem and progenitor cells, which initiate disease and possess altered BCL-2 rheostats compared to differentiated tumor cells, remains unknown. To study the role of the BDP in leukemia initiation, we crossed the BDP mouse into a chronic myeloid leukemia (CML) model. We found that the BDP greatly enhanced the fitness of CML cells with a three-fold greater competitive advantage, leading to more aggressive disease. The BDP conferred almost complete resistance to cell death induced by imatinib in CML stem and progenitor cells (LSPCs). Using BH3 profiling, we identified a novel therapeutic vulnerability of BDP LSPCs to MCL-1 antagonists, which we confirmed in primary human LSPCs, and in vivo. Our findings demonstrate the impact of human polymorphisms on the survival of LSPCs and highlight their potential as companion diagnostics for tailored therapies
CT-derived fat density as a predictor of cause-specific mortality in patients undergoing TAVI: Findings from a large registry subanalysis.
Full text linkTranscatheter aortic valve implantation (TAVI) is increasingly performed in older and frailer patients with severe aortic stenosis. Pre-procedural computed tomography (CT) scans at the third lumbar vertebra (CTL3) can estimate overall patient survival after TAVI [1, 2]. This subanalysis investigated whether CTL3 parameters can predict specific causes of death, potentially allowing for more tailored post-operative therapy
RSNA 2023 Abdominal Trauma AI Challenge: Review and Outcomes.
No full textPurpose To evaluate the performance of the winning machine learning models from the 2023 RSNA Abdominal Trauma Detection AI Challenge. Materials and Methods The competition was hosted on Kaggle and took place between July 26 and October 15, 2023. The multicenter competition dataset consisted of 4274 abdominal trauma CT scans, in which solid organs (liver, spleen, and kidneys) were annotated as healthy, low-grade, or high-grade injury. Studies were labeled as positive or negative for the presence of bowel and mesenteric injury and active extravasation. In this study, performances of the eight award-winning models were retrospectively assessed and compared using various metrics, including the area under the receiver operating characteristic curve (AUC), for each injury category. The reported mean values of these metrics were calculated by averaging the performance across all models for each specified injury type. Results The models exhibited strong performance in detecting solid organ injuries, particularly high-grade injuries. For binary detection of injuries, the models demonstrated mean AUC values of 0.92 (range, 0.90-0.94) for liver, 0.91 (range, 0.87-0.93) for splenic, and 0.94 (range, 0.93-0.95) for kidney injuries. The models achieved mean AUC values of 0.98 (range, 0.96-0.98) for high-grade liver, 0.98 (range, 0.97-0.99) for high-grade splenic, and 0.98 (range, 0.97-0.98) for high-grade kidney injuries. For the detection of bowel and mesenteric injuries and active extravasation, the models demonstrated mean AUC values of 0.85 (range, 0.74-0.93) and 0.85 (range, 0.79-0.89), respectively. Conclusion The award-winning models from the artificial intelligence challenge demonstrated strong performance in the detection of traumatic abdominal injuries on CT scans, particularly high-grade injuries. These models may serve as a performance baseline for future investigations and algorithms
Clearance of p21 highly expressing senescent cells accelerates cutaneous wound healing.
No full textWhile senescent cells have detrimental roles in several contexts, they are highly heterogeneous. p16 highly expressing senescent cells have been reported to exert beneficial functions in wound healing. Here we use Xenium spatial transcriptomics to identify a distinct p21 highly expressing senescent population induced on wounding, with a pro-inflammatory profile. We find that clearing p21 highly expressing cells expedites wound closure and is partially mediated by NF-κB inhibition, thus enhancing our understanding of the multifaceted functions of senescence in tissue remodeling
Repeated Measures Latent Dirichlet Allocation for Longitudinal Microbiome Analysis
No full textTopic modeling algorithms generally examine a set of documents, referred to as a corpus in Natural Language Processing (NLP), and analyze the words observed in a document to uncover themes that run through each document in a collection. In the microbiome framework, they are used to identify co-occurring microbial species and reveal hidden patterns or relationships within the microbial communities. Longitudinal microbiome data analysis provides a robust framework for studying microbiome compositions over time. By collecting multiple samples from the same individuals at different time points, researchers can capture the temporal variation within an individual’s microbiome and evaluate its impact on the subjects’ health status during each of their visits. This paper extends the Latent Dirichlet Allocation (LDA) modeling technique to a repeated measures framework. We propose Repeated Measures Latent Dirichlet Allocation (RM-LDA) where each document (subject) is assumed to be a collection of multiple sub-documents (visits associated with a given subject). In this study, we examine microbiome data on subjects making multiple visits to a medical facility to provide data on their microbiome counts. Our model allows us to analyze hidden patterns in the microbiome data over multiple visits, estimate the latent topic correlation structure within each subject, and study their association with the individual’s health status over each visit
Ethical Frameworks for Data-Driven Environmental Health Studies in the AI Era.
Full text linkThe rapid advancement of environmental sensing technologies and artificial intelligence (AI) has ushered in a new era of data-driven environmental health research, especially for the rapid development of exposomics. This surge in data collection and analysis capabilities brings unprecedented opportunities for scientific discovery, but also raises critical ethical concerns. Data ethics, the moral framework guiding data management, has become crucial for environmental researchers. The proliferation of advanced instruments, low-cost sensors, and digitalized knowledge has led to an explosion of environmental data. Concurrently, AI models can now derive complex patterns from these vast data sets without traditional hypothesis testing and features extraction, revolutionizing investigations into environmental health issues. However, these advancements bring challenges. Regulations like the EU’s General Data Protection Regulation (GDPR) have set new standards for data protection, highlighting the need for robust ethical frameworks in environmental health research. This study aims to explore key ethical considerations in data-driven environmental health studies, focusing on three main areas: data collection, analysis, and sharing. We propose a checklist of ethical guidelines for researchers, building upon existing frameworks. By addressing these ethical challenges, we can promote responsible data practices that maximize the benefits of AI and big data while maintaining scientific integrity and protecting individual privacy
Replacing non-biomedical concepts improves embedding of biomedical concepts.
Full text linkEmbeddings are semantically meaningful representations of words in a vector space, commonly used to enhance downstream machine learning applications. Traditional biomedical embedding techniques often replace all synonymous words representing biological or medical concepts with a unique token, ensuring consistent representation and improving embedding quality. However, the potential impact of replacing non-biomedical concept synonyms has received less attention. Embedding approaches often employ concept replacement to replace concepts that span multiple words, such as non-small-cell lung carcinoma, with a single concept identifier (e.g., D002289). Also, all synonyms of each concept are merged into the same identifier. Here, we additionally leveraged WordNet to identify and replace sets of non-biomedical synonyms with their most common representatives. This combined approach aimed to reduce embedding noise from non-biomedical terms while preserving the integrity of biomedical concept representations. We applied this method to 1,055 biomedical concept sets representing molecular signatures or medical categories and assessed the mean pairwise distance of embeddings with and without non-biomedical synonym replacement. A smaller mean pairwise distance was interpreted as greater intra-cluster coherence and higher embedding quality. Embeddings were generated using the Word2Vec algorithm applied to a corpus of 10 million PubMed abstracts. Our results demonstrate that the addition of non-biomedical synonym replacement reduced the mean intra-cluster distance by an average of 8%, suggesting that this complementary approach enhances embedding quality. Future work will assess its applicability to other embedding techniques and downstream tasks. Python code implementing this method is provided under an open-source license
Comparative genomics reveals common diversity and adaptation to harsh environments in the Arabian Peninsula indigenous chickens.
Full text linkIdentifying genomic regions under selection is crucial for comprehending the evolutionary history of the domestic chicken. Arabian Peninsula (AP) indigenous chickens are mostly found outdoors, being reared alongside other livestock for production purposes. These birds show high resilience to extreme temperatures (hot and cold), typical of the desert environment. The selection pressures responsible for unique local adaptations in these birds remain largely unidentified. Here, we aimed to investigate the genome diversity and structure of 15 indigenous chicken populations including 13 populations from the AP (n = 5), Ethiopia (n = 6), and the People\u27s Republic of China (n = 2). We also included two commercial chicken populations, Fayoumi (selected for heat tolerance) and Chantecler (known for its cold tolerance). Principal component (PC) analysis separated all the populations based on their geographic areas of origin. PC1 separates the Ethiopian populations from the Chinese and AP populations, while PC2 separates the AP populations from the Chantecler, and the Ethiopian populations from the Dulong and Chantecler. The genome-wide signatures of analyses identified many candidate regions under positive selection. They include genes that may be associated with thermotolerance. These are involved in energy balance and metabolism (SUGCT, HECW1, MMADHC), cells apoptosis (APP, SRBD1, NTN1, PUF60, SLC26A8, DAP, SUGCT), angiogenesis (RYR2, LDB2, SOX5), skin protection to solar radiation (FZD10, BCO2, WNT5B, COL6A2, SIRT1) as well as growth (NELL1). Our findings suggest that Arabian chicken populations have a distinct gene pool polymorphism in relation to their adaptation to the harsh climatic environments of the AP