Machine learning of serum metabolic patterns encodes early-stage lung adenocarcinoma

Abstract

Early cancer detection greatly increases the chances for successful treatment, but available diagnostics for some tumours, including lung adenocarcinoma (LA), are limited. An ideal early-stage diagnosis of LA for large-scale clinical use must address quick detection, low invasiveness, and high performance. Here, we conduct machine learning of serum metabolic patterns to detect early-stage LA. We extract direct metabolic patterns by the optimized ferric particle-assisted laser desorption/ionization mass spectrometry within 1 s using only 50 nL of serum. We define a metabolic range of 100-400 Da with 143 m/z features. We diagnose early-stage LA with sensitivity~70-90% and specificity~90-93% through the sparse regression machine learning of patterns. We identify a biomarker panel of seven metabolites and relevant pathways to distinguish early-stage LA from controls (p < 0.05). Our approach advances the design of metabolic analysis for early cancer detection and holds promise as an efficient test for low-cost rollout to clinics.

Nanocomposite‐Based Matrices in Laser Desorption/Ionization Mass Spectrometry for Small‐Molecule Analysis

“…[20] Firstly, the matrix should have low thermal conductivity to retain heat energy produced by laser irradiation in the substrate. [17] Secondly, well electrical conductivity is necessary; therefore, matrix material does not interfere with the electric signal. [21] Thirdly, it requires an excellent light absorption at the MS laser wavelength (e. g., 337 nm, 355 nm), which can better absorb the laser energy and transfer it to the analyte.…”

“…Hence, an ideal matrix material for small molecule detection needs to have these essential characteristics [20] . Firstly, the matrix should have low thermal conductivity to retain heat energy produced by laser irradiation in the substrate [17] . Secondly, well electrical conductivity is necessary; therefore, matrix material does not interfere with the electric signal [21] .…”

“…[7,16] In addition, essential characteristics, such as low thermal conductivity, high electrical conductivity, and high surface area to volume ratio, may further improve LDI efficiency. [17] Despite substantial progress in matrix material design, the matrix performance of these materials with single structure and simple morphology is far from ideal when applied in complex systems. In parallel, composite nanomaterials have received intense interest from research groups globally due to their multi-function and high ionization efficiency.…”

“…The ideal inorganic nanomaterials as matrix enjoy high stability under vacuum conditions, high light absorption, and low degree of fragmentation from self‐dissociation [7,16] . In addition, essential characteristics, such as low thermal conductivity, high electrical conductivity, and high surface area to volume ratio, may further improve LDI efficiency [17] . Despite substantial progress in matrix material design, the matrix performance of these materials with single structure and simple morphology is far from ideal when applied in complex systems.…”

Artificial intelligence and its future potential in lung cancer screening

“…Early detection of cancer plays a significant role in the course of all forms of cancer. Quickly detective, non-invasive, and a high performing method must be available ideally to screen early stages of lung cancer (Huang et al, 2020[ 14 ]). Artificial intelligence allows radiologists to efficiently manage the data load of lung cancer screening using computed tomography (Randerath et al, 2020[ 31 ]).…”