On November 10, 2023 SeekIn Inc., a leader in blood-based pan-cancer early detection and monitoring technology, reported the validation studies consisting of one retrospective cohort and one prospective cohort that evaluate SeekInCare’s ability to detect cancer patients and predict the tissue of origin with one tube of blood (Press release, SeekIn, NOV 10, 2023, View Source [SID1234637472]). The results demonstrate the performance of SeekInCare with the consistent results among the two cohorts in ~2,400 cancer patients and non-cancer individuals. SeekInCare achieved overall 65.5% sensitivity at 97.9% specificity in the retrospective studies and 60.0% sensitivity at 96.1% specificity in the prospective cohort study, respectively, which is best-in-class in blood-based multi-cancer early detection (MCED). The findings were presented at the 20th ICGC Workshop and 7th ARGO Meeting in New York.

Schedule your 30 min Free 1stOncology Demo!
Discover why more than 1,500 members use 1stOncology™ to excel in:

Early/Late Stage Pipeline Development - Target Scouting - Clinical Biomarkers - Indication Selection & Expansion - BD&L Contacts - Conference Reports - Combinatorial Drug Settings - Companion Diagnostics - Drug Repositioning - First-in-class Analysis - Competitive Analysis - Deals & Licensing

                  Schedule Your 30 min Free Demo!

"Recent studies have demonstrated that blood-based multi-cancer early detection approaches may hold promise for identifying asymptomatic cancer patients from general population. However, most studies only exploit a single aspect of cancer hallmarks, which is challenging to achieve highly sensitive results because cancer is a heterogenous disease," said Mao Mao, MD, PhD, Founder and CEO of SeekIn. "For example, our OncoSeek test for multi-cancer early detection was designed with seven protein tumor markers. With the assistance of artificial intelligence (AI), the sensitivity of OncoSeek was 51.7% at 92.9% specificity. While OncoSeek significantly reduced false positive rates comparing with traditional methods, we believe sensitivity can be further improved when more omics data are included. And this is how SeekInCare was conceived."

SeekInCare was developed using proprietary AI- and big data-driven algorithm to distinguish cancer patients from non-cancer individuals by calculating cancer risk score (CRS) incorporating copy number aberrations (CNAs), fragment size (FS), end motifs and oncogenic viruses via shallow whole genome sequencing (sWGS) from cell-free DNA (cfDNA), and seven plasma tumor markers (PTMs), and to predict the possible affected tissue of origin (TOO) for those who have been detected with cancer signals in blood. SeekInCare’s performance was well-demonstrated by the overall 65.5% sensitivity at 97.9% specificity in the retrospective study and 60.0% sensitivity at 96.1% specificity in the prospective study. A critical attribute of a blood-based multi-cancer detection test is the ability to localize the TOO to direct the diagnostic workup. The overall accuracy of two most possible organs SeekInCare achieved was 85.4%, improved by 20.0% from OncoSeek.

"In addition to the performance improvement of SeekInCare in TOO prediction comparing with OncoSeek, significant improvements were also observed in major metrics such as sensitivity, specificity and accuracy. Unlike OncoSeek designed for low- and middle-income countries, SeekInCare enables us to provide a more sensitive and specific multi-cancer detection solution to the regions with purchasing power and high demands of advanced cancer screening," said Dr. Mao. "More importantly, comparing with the results of both retrospective and prospective studies from GRAIL and Exact Sciences, SeekInCare showed higher sensitivities with similar specificities."

The excellent consistency of validation results from both retrospective and prospective studies established SeekInCare’s clinical feasibility. With these achievements, SeekIn is planning for future investigation of SeekInCare’s clinical utility as a large-scale cancer screening test in average-risk populations.