Detection of Early-stage Lung Cancer Using Machine Learning and Plasma Metabolomics
Trial Snapshot
- Phase
- Not Applicable
- Status
- Completed
- Enrollment
- 558
- Locations
- 1
- Primary Endpoint
- Plasma Lipids
Study Overview
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.
Study Design
- Study Type
- Observational
- Observational Model
- Cohort
- Time Perspective
- Prospective
Eligibility Criteria
- Ages
- 18 Years to — (Adult, Older Adult)
- Sex
- All
- Accepts Healthy Volunteers
- Yes
Inclusion Criteria
- •pulmonary nodules or opacity
- •plan to receive surgery
Exclusion Criteria
- •history of other malignancies
- •received anti-cancer treatment (chemotherapy, radiotherapy, targeted therapy, etc.) before surgery
Outcomes
Primary Outcomes
Plasma Lipids
Time Frame: 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.
Secondary Outcomes
No secondary outcomes reported
Investigators
Jun Wang
Prof
Peking University People's Hospital