Blood-Based Test Uses Lipid Profiles to Detect Early-Stage Lung Cancer

A new study published in Science Translational Medicine on Feb. 2 suggests that the combined use of blood lipid profiles and artificial intelligence may be effective in detecting early-stage lung cancer. The study comes from a Chinese research team that found a link between altered blood lipid levels and early-stage lung cancer, which they then used to create a mass spectrometry-based blood lipid test called the Lung Cancer Artificial Intelligence Detector (LCAID) v2.0.

The Diagnostic Challenge

Lung cancer is the leading cause of cancer death. Early detection significantly increases the chances of survival. Unfortunately, lung cancer is usually diagnosed at a late stage when the survival rate is extremely low. One problem is the general lack of recognized symptoms associated with early-stage lung cancer. Moreover, the current method used to detect early lung cancer lesions, low-dose spiral CT imaging, is expensive. It also involves radiation hazards. All of this makes CT imaging unsuitable for widespread screening of the general population and repeat testing. A blood-based test would be far better suited for these purposes. While liquid biopsy type blood tests are utilized, they are used to assess the genetic characteristics of tumors to inform patient treatment at the late stages. However, there are currently no reliable blood-based tests for early-stage lung cancer diagnosis.

The LCAID v2.0 Study

There have been a number of promising efforts to develop such an assay, including the new project undertaken by researchers from Peking University People’s Hospital. The team used 10x Genomics’ droplet-based technology to perform single-cell RNA sequencing to profile metabolism-related transcriptional features across nearly 26,700 individual cells isolated from five patients awaiting treatment for non-small cell lung cancer (NSCLC) tumors. They then compared the profiles to new and published scRNA-seq profiles on 55,860 individual cells from eight healthy lung samples. The researchers identified shifts in lipid metabolism in the NSCLCs, finding that lipid metabolism was broadly dysregulated in different cell types, with glycerophospholipid metabolism as the most altered lipid metabolism–related pathway. They then performed a series of untargeted lipidomic analyses on blood plasma samples from individuals with or without lung cancer. The team then used high-performance liquid chromatography-mass spectrometry profiling and support vector machine algorithm on blood samples from 171 people who had early-stage NSCLC and a control group of 140 unaffected individuals. In so doing, they identified nine different lipids with apparent ties to early-stage lung cancer. They then analyzed the set with additional data for 550 more samples.

The Findings

The researchers found that the LCAID v.2.0 set had 100 percent specificity in an initial validation cohort made up of 139 persons (99 of whom did have cancer and 40 of whom did not). They then assessed the approach using samples collected from 1,036 participants in a low-dose computed tomography lung cancer screening program run by a local hospital along with prospective samples from 109 individuals. The results: Sensitivity of 90 percent for detecting early-stage lung cancer, and a specificity of 92 percent. LCAID v2.0 “performs well in the case of early-stage lung cancer detection,” the researchers concluded. “This study demonstrates the potential application of LCAID v2.0 for lipidomics-based large-scale population screening, in particularly for populations with high risk of lung cancer,” wrote study co-authors Yuxin Yin and Jun Wang.

Takeaway

Once dismissed as nothing but a pipe dream, the concept of early-stage lung cancer blood tests has come a long way since a 2018 breakthrough study from the American Society of Clinical Oncology suggesting its feasibility. The LCAID v2.0 is the just one of the recent set of promising projects advancing blood-based early-stage lung cancer detection.