Detection of Lung Cancer by Plasma Lipids

Detection of Early-stage Lung Cancer Using Machine Learning and Plasma Metabolomics

Status

Completed

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT04287712

Acronym

ELAID

Enrollment

558

Registered

2020-02-27

Start date

2018-12-13

Completion date

2020-05-20

Last updated

2020-06-04

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Early-Stage Lung Cancer

Keywords

Early-Stage Lung Cancer, Plasma Metabolomics, Lipids, Machine Learning

Brief summary

There are no reliable blood-based tests currently available for early-stage lung cancer diagnosis. We try to establish a highly accurate method for detecting early-stage lung cancer by combining machine learning with untargeted and targeted metabolomics .

Detailed description

All plasma lipids were first detected by untargeted metabolomics methods and 9 feature lipids of early-stage lung cancer were selected by support vector machine algorithm. Then, a targeted metabolomics method was developed to detect the 9 lipids quantitatively based on multiple reaction monitoring mode. Finally, a detection model was established based on the 9 lipids.

Interventions

DIAGNOSTIC_TESTPlasma lipids

Plasma lipids were detected by an Ultimate 3000 ultra-high-performance liquid chromatography (UHPLC) system coupled with Q-Exactive MS (Thermo Scientific) . Then a detection model was built based on plasma lipids using machine learning algorithm.

Study design

Observational model

COHORT

Time perspective

PROSPECTIVE

Eligibility

Sex/Gender

ALL

Age

18 Years to No maximum

Healthy volunteers

Yes

Inclusion criteria

1. pulmonary nodules or opacity 2. plan to receive surgery

Exclusion criteria

1. history of other malignancies 2. received anti-cancer treatment (chemotherapy, radiotherapy, targeted therapy, etc.) before surgery

Design outcomes

Primary

Measure	Time frame	Description
Plasma Lipids	All samples were detected together after participants recruitment and sample collection. All samples were detected within 18 months from sample collection.	A detection model based on 9 lipids were developed, including 3 lysophosphatidylcholines, 5 phosphatidylcholines, and a triglyceride. The 9 lipids were detected by targeted metabolomics by mass spectrometry.

Countries

China

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026