Chinese scientists develop AI-assisted tool to detect early-stage lung cancer

BEIJING -- Chinese scientists have developed an Artificial Intelligence (AI) assisted testing tool to detect early-stage lung cancer.
The study published on Thursday in the journal Science Translational Medicine described the Lung Cancer Artificial Intelligence Detector that may play a part in the early detection of lung cancer or large-scale screening of high-risk cancer populations.
Scientists from Peking University performed single-cell RNA sequencing of different early-stage lung cancers and found that the fat metabolism turns abnormal in different cell types.
Then they recruited a cohort of 311 participants including 171 early-stage non-small cell lung cancer patients and 140 healthy people to analyze lipid-related molecules in their plasma.
Using a machine-learning algorithm, the scientists selected nine lipids that are deemed most important for early-stage cancer detection and built the AI-assisted detection model, according to the study.
In a lung cancer screening cohort of 1,036 participants undergoing routine CT exams at a hospital in Beijing, and a clinical cohort containing 109 lung cancer patients, the detector has reached an accuracy of over 90 percent, the study said.
Most of the participants diagnosed with lung cancer were non-smokers with stage one tumors, according to the study.
Yin Yuxin, the paper's co-author and a professor from the School of Basic Medical Sciences of Peking University said the new detection strategy is helpful for the early diagnosis, auxiliary diagnosis, or population screening of many tumor diseases.
In 2021, Yin and his collaborators developed AI-assisted tumor metabolism detection methods for pancreatic cancer and esophageal cancer.
- Shanghai certifies 30 regional HQs of multinationals
- Shanghai plans extensive promotional of high-growth enterprises
- Hainan launches International Talent Club
- Nvidia founder and CEO Jensen Huang says he loves competition
- Evidence of inhuman atrocities
- New guideline aims to impart skills training to 30m people by 2027