In response to the high false positive rate of traditional Low-Dose Computed Tomography (LDCT) in diagnosing pulmonary malignant nodules, this study aimed to investigate the effectiveness of scoring of blood-based non-invasive biological metabolite detection combined with artificial intelligent scoring of non-invasive imaging in the clinical diagnosis of Pulmonary Nodules (PNs). In this retrospective study, risk scoring was performed in patients positive for pulmonary nodules and subsequently, PNs were sampled by invasive procedures for pathological examinations. The pathological classification was used as the gold standard, and statistical and machine learning methods showed, that in 210 patients (23 benign PN and 187 malignant PN), the risk score of Metabonomics, radiomics, and multi-omics had different levels of performance in different risk groups based on various predictive models. The Area Under the receiver operating Characteristic Curve (AUC) of the multi-omics model was 0.823. The present results indicate that a multi-omics model is more effective than a single model in the non-invasive diagnosis of pulmonary malignant nodules.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.clinsp.2025.100599 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Species level and SNP profiling of skin microbiome improve the specificity in identifying forensic fluid and individual.
Forensic Sci Int Genet
March 2025
Guangzhou Key Laboratory of Forensic Multi-Omics for Precision Identification, School of Forensic Medicine, Southern Medical University, Guangzhou, Guangdong 510515, China. Electronic address:
Human skin possesses individual and body fluid-specific microbial signatures potentially useful for forensic identification. Previous studies mostly attribute individuals based on the relative abundance of microbiota at single time point, however fluctuations in taxonomy and phylogenetic structure may cause this to be unreliable. In this study, we assessed the skin microbiome of individuals at consecutive time-point from fingers, palm, arm and forehead sites using full-length 16S rRNA gene sequencing.
View Article and Find Full Text PDFCancer gene identification through integrating causal prompting large language model with omics data-driven causal inference.
Brief Bioinform
March 2025
School of Artificial Intelligence, Jilin University, 3003 Qianjin Street, Changchun 130012, Jilin Province, China.
Identifying genes causally linked to cancer from a multi-omics perspective is essential for understanding the mechanisms of cancer and improving therapeutic strategies. Traditional statistical and machine-learning methods that rely on generalized correlation approaches to identify cancer genes often produce redundant, biased predictions with limited interpretability, largely due to overlooking confounding factors, selection biases, and the nonlinear activation function in neural networks. In this study, we introduce a novel framework for identifying cancer genes across multiple omics domains, named ICGI (Integrative Causal Gene Identification), which leverages a large language model (LLM) prompted with causality contextual cues and prompts, in conjunction with data-driven causal feature selection.
View Article and Find Full Text PDFTerahertz (THz) waves, a novel type of radiation with quantum and electronic properties, have attracted increasing attention for their effects on the nervous system. Spatial working memory, a critical component of higher cognitive function, is coordinated by brain regions such as the infralimbic cortex (IL) region of the medial prefrontal cortex and the ventral cornu ammonis 1 (vCA1) of hippocampus. However, the regulatory effects of THz waves on spatial working memory and the underlying mechanisms remain unclear.
View Article and Find Full Text PDFNew trends in supportive care of head and neck cancers.
Curr Opin Oncol
February 2025
Department of Biomedical Sciences, Humanitas University, Pieve Emanuele.
Purpose Of Review: Supportive care plays a vital role in the management of head and neck cancer (HNC) patients, as the disease often affects a frail and older population that is treated with multiple strategies and is associated with severe symptoms. We will focus on mucositis, dermatitis, dysphagia, pain, cachexia, and infections, as they are among the most common and challenging symptoms encountered.
Recent Findings: Efforts have focused on multiomics approaches to decipher the complex biological pathways that drive symptom onset and treatment-related toxicities, with the aim of developing novel therapeutic strategies.
Integrative analysis of gene expression and chromatin dynamics multi-omics data in mouse models of bleomycin-induced lung fibrosis.
Epigenetics Chromatin
March 2025
State Key Laboratory of Cell Differentiation and Regulation, Henan International Joint Laboratory of Pulmonary Fibrosis, Henan Center for Outstanding Overseas Scientists of Organ Fibrosis, Pingyuan Laboratory, College of Life Science, Henan Normal University, 46 Jianshe Road, Xinxiang, Henan, 453007, China.
Background: Pulmonary fibrosis is a relentless and ultimately fatal lung disorder. Despite a wealth of research, the intricate molecular pathways that contribute to the onset of PF, especially the aspects related to epigenetic modifications and chromatin dynamics, continue to be elusive and not fully understood.
Methods: Utilizing a bleomycin-induced pulmonary fibrosis model, we conducted a comprehensive analysis of the interplay between chromatin structure, chromatin accessibility, gene expression patterns, and cellular heterogeneity.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!