Serum untargeted metabolomics reveal metabolic alteration of non‐small cell lung cancer and refine disease detection

Abstract

This study was performed to characterize the metabolic alteration of non–small‐cell lung cancer (NSCLC) and discover blood‐based metabolic biomarkers relevant to lung cancer detection. An untargeted metabolomics‐based approach was applied in a case–control study with 193 NSCLC patients and 243 healthy controls. Serum metabolomics were determined by using an ultra high performance liquid chromatography–tandem mass spectrometry (UHPLC‐MS/MS) method. We screened differential metabolites based on univariate and multivariate analysis, followed by identification of the metabolites and related pathways. For NSCLC detection, machine learning was employed to develop and validate the model based on the altered serum metabolite features. The serum metabolic pattern of NSCLC was definitely different from the healthy condition. In total, 278 altered features were found in the serum of NSCLC patients comparing with healthy people. About one‐fifth of the abundant differential features were identified successfully. The altered metabolites were enriched in metabolic pathways such as phenylalanine metabolism, linoleic acid metabolism, and biosynthesis of bile acids. We demonstrated a panel of 10 metabolic biomarkers which representing excellent discriminating capability for NSCLC discrimination, with a combined area under the curve (AUC) in the validation set of 0.95 (95% CI: 0.91–0.98). Moreover, this model showed a desirable performance for the detection of NSCLC at an early stage (AUC = 0.95, 95% CI: 0.92–0.97). Our study offers a perspective on NSCLC metabolic alteration. The finding of the biomarkers might shed light on the clinical detection of lung cancer, especially for those cancers in an early stage in Chinese population.

Novel multiclass classification machine learning approach for the early-stage classification of systemic autoimmune rheumatic diseases

“…ML, a computational analytical approach, is gaining rapid prominence in the realm of biomedicine. 32 33 In the context of rheumatology, the integration of ML is witnessing a gradual upsurge, with numerous studies leveraging ML techniques to classify patients with SARDs based on diverse data sources encompassing medical records, 34 35 imaging data, 36 biometric measurements 37 and gene expression profiles. 18 20 38 The modelling indicators of these ML models primarily encompass clinical symptoms, which are relatively subjective, as well as a diverse array of complex laboratory indicators, and even biologically intricate indicators that are challenging to obtain, such as genetic polymorphisms.…”

Comprehensive analysis of the metabolomics and transcriptomics uncovers the dysregulated network and potential biomarkers of Triple Negative Breast Cancer

“…It has been proved that, metabolic dysregulation is linked to therapy response and clinical outcome across various cancer types and may impact the tumorigenesis, progression, and prognosis of BC via pathways related to angiogenesis, anti-apoptosis, mitogenesis, chronic in ammation, increased visceral fat reserves, and other cancer-associated adipokines. [22][23][24][25]. This study aims to identify more reliable and speci c serum markers for diagnosing TNBC using a metabolomic approach.…”

Metabolomics Analysis and Diagnosis of Lung Cancer: Insights from Diverse Sample Types

“…The sensitivity of the support vector machine model was 83%, and the specificity was 89%, indicating that the overall diagnostic accuracy was high. Pathway analysis found that the most significant disturbances in lung cancer patients occurred in the phenylalanine, linoleic acid, and bile acid metabolism pathways 71 .…”