Revolutionary Multi-Cancer Early Detection Test Offers Affordable Screening Tool for LMICs

By LabMedica International staff writers
Posted on 20 Jun 2023

Image: The blood-based pan cancer early detection test utilizes NGS and AI (Photo courtesy of Freepik)

Cancer claimed almost 10 million lives globally last year, with a majority of the cases detected too late for effective treatment. While early screening tests for cancer can save lives, these clinically validated tests only cover a few types, such as lung, colon, liver, breast, cervix, and prostate cancers, and their detection rates and specificity are limited. Conventional cancer screening technologies often prove unsuitable for low- and middle-income countries (LMICs) due to their cost, complexity, and reliance on substantial medical infrastructure. Now, a ground-breaking multi-cancer early detection (MCED) test, driven by artificial intelligence (AI) technology, could potentially save numerous lives by identifying cancer at earlier stages. The MCED test could revolutionize early cancer detection in LMICs.

OncoSeek developed by SeekIn Inc. (Shenzhen, China) is an MCED test based on the analysis of protein tumor markers (PTMs). It can simultaneously detect characteristic tumor markers for different types of cancers. Utilizing AI, the test can differentiate between individuals with cancer and those without by calculating a probability of cancer (POC) index. This calculation is based on the plasma levels of seven PTMs, as well as the gender and age of the subjects. With only a blood draw required at screening sites, OncoSeek is both affordable and accessible, making it a sustainable option in LMICs.

A recent study showed that OncoSeek considerably reduces the rate of false positives compared to traditional clinical methods. The study involved nearly 10,000 participants from China and the United States, consisting of 1,959 cancer patients and 7,423 healthy individuals. Each participant had one tube of peripheral blood collected for the detection of seven specific proteins using a standard clinical electrochemiluminescence immunoassay analyzer. After PTMs were quantified, OncoSeek, using AI, distinguished cancer patients from non-cancer individuals, calculated the POC index and predicted the possible affected tissue of origin (TOO) for those with detected cancer signals in blood.

The test demonstrated a sensitivity of 51.7%, and a specificity of 92.9%, resulting in an overall accuracy of 84.3%, with a sensitivity of 49.5% in stage I and II patients. For the detection of nine common cancer types, which account for approximately 59.2% of annual global cancer deaths, sensitivities ranged from 37.1% to 77.6%. The overall accuracy of TOO prediction in true positives is 66.8%, which could be a helpful tool in clinical diagnostic workups. OncoSeek, offering a non-invasive, efficient, and cost-effective solution for MCED, received CE-IVD Mark approval in September 2022.

Related Links:
SeekIn Inc.