Abstract C127: Oncoseek 2.0: Enhanced-sensitivity blood test for multi-cancer early detection

Abstract Background: Early cancer detection improves survival and reduces treatment costs. We previously developed OncoSeek, an AI-powered cost-effective ($25 reagent cost) multi-cancer early detection (MCED) test integrating seven protein tumor markers (PTMs) and clinical data, demonstrating 58.4% sensitivity, 92.0% specificity, and 70.6% tissue-of-origin accuracy in several clinical studies (n=15,122). This study aimed to enhance OncoSeek by incorporating three additional PTMs to improve detection in prostate, lung and various squamous cell carcinomas especially, upgrading it to version 2.0 ($31), and to validate its improved sensitivity. Methods: The same OncoSeek algorithm was used to develop OncoSeek 2.0. A retrospective cohort was conducted to validate OncoSeek 2.0's MCED performance and assess sensitivity improvements, involving 585 cancer patients and 355 non-cancer individuals. Plasma/serum PTM levels were analyzed, and probability of cancer (POC) indexes were calculated to distinguish cancer patients from non-cancer individuals. Results: OncoSeek 2.0 outperformed OncoSeek 1.0, achieving an AUC of 0.895 (vs. 0.849 for 1.0). At 90.1% specificity, sensitivity increased from 74.7% to 80.3% for 15 cancer types, which collectively account for accounting for 76.5% of global cancer-related mortality in the United States. Among these cancers, only five (breast, cervix, colorectum, lung, and prostate) have screening methods recommended by the United States Preventive Services Task Force (USPSTF). For the remaining 10 cancers without USPSTF-recommended screening (bile duct, endometrium, esophagus, gallbladder, head and neck, liver, lymphoma, ovary, pancreas, and stomach), OncoSeek 2.0 achieved a sensitivity of 86.4% at 90.1% specificity. Moreover, OncoSeek 2.0 showed substantial stage-specific sensitivity improvements over OncoSeek 1.0, especially for early-stage cancers: stage I sensitivity increased from 38.9% to 55.6%, stage II from 55.2% to 65.5%, stage III from 62.7% to 71.1%, and stage IV from 87.2% to 88.7%. Conclusion: OncoSeek 2.0 achieved a 7.5% increase in overall sensitivity for all stages, with significant improvements in early-stage cancers: stage I and stage II sensitivities increased 42.9% and 20.5%, respectively. These findings suggest that OncoSeek 2.0 could become a valuable tool for multi-cancer early detection, especially for cancers lacking established screening guidelines. Citation Format: Mao Mao, Shen Shen. Yong, Chang yin. yin, Wu Wei, Li shi. yong, Xing ping. ping, Ding chen. yu, Zhu dan. dan, Xu qing. xia. Oncoseek 2.0: Enhanced-sensitivity blood test for multi-cancer early detection [abstract]. In: Proceedings of the 18th AACR Conference on the Science of Cancer Health Disparities; 2025 Sep 18-21; Baltimore, MD. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2025;34(9 Suppl):Abstract nr C127.

Authors

Institutions

Publication Details

Journal
Cancer Epidemiology Biomarkers & Prevention
Published
2025-09-18
DOI
https://doi.org/10.1158/1538-7755.disp25-c127
Primary Topic
Radiomics and Machine Learning in Medical Imaging
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Abstract C127: Oncoseek 2.0: Enhanced-sensitivity blood test for multi-cancer early detection

Yong Shen, Wu Wei, Xu Ping, Yong Li et al.
Cancer Epidemiology Biomarkers & Prevention
Radiomics and Machine Learning in Medical Imaging
article

Abstract C127: Oncoseek 2.0: Enhanced-sensitivity blood test for multi-cancer early detection

Yong Shen, Wu Wei, Xu Ping, Yong Li, Dan Zhang, Mao Mao, Yin Chang, Xin Xia, D. Yu
article en

Abstract

Abstract Background: Early cancer detection improves survival and reduces treatment costs. We previously developed OncoSeek, an AI-powered cost-effective ($25 reagent cost) multi-cancer early detection (MCED) test integrating seven protein tumor markers (PTMs) and clinical data, demonstrating 58.4% sensitivity, 92.0% specificity, and 70.6% tissue-of-origin accuracy in several clinical studies (n=15,122). This study aimed to enhance OncoSeek by incorporating three additional PTMs to improve detection in prostate, lung and various squamous cell carcinomas especially, upgrading it to version 2.0 ($31), and to validate its improved sensitivity. Methods: The same OncoSeek algorithm was used to develop OncoSeek 2.0. A retrospective cohort was conducted to validate OncoSeek 2.0's MCED performance and assess sensitivity improvements, involving 585 cancer patients and 355 non-cancer individuals. Plasma/serum PTM levels were analyzed, and probability of cancer (POC) indexes were calculated to distinguish cancer patients from non-cancer individuals. Results: OncoSeek 2.0 outperformed OncoSeek 1.0, achieving an AUC of 0.895 (vs. 0.849 for 1.0). At 90.1% specificity, sensitivity increased from 74.7% to 80.3% for 15 cancer types, which collectively account for accounting for 76.5% of global cancer-related mortality in the United States. Among these cancers, only five (breast, cervix, colorectum, lung, and prostate) have screening methods recommended by the United States Preventive Services Task Force (USPSTF). For the remaining 10 cancers without USPSTF-recommended screening (bile duct, endometrium, esophagus, gallbladder, head and neck, liver, lymphoma, ovary, pancreas, and stomach), OncoSeek 2.0 achieved a sensitivity of 86.4% at 90.1% specificity. Moreover, OncoSeek 2.0 showed substantial stage-specific sensitivity improvements over OncoSeek 1.0, especially for early-stage cancers: stage I sensitivity increased from 38.9% to 55.6%, stage II from 55.2% to 65.5%, stage III from 62.7% to 71.1%, and stage IV from 87.2% to 88.7%. Conclusion: OncoSeek 2.0 achieved a 7.5% increase in overall sensitivity for all stages, with significant improvements in early-stage cancers: stage I and stage II sensitivities increased 42.9% and 20.5%, respectively. These findings suggest that OncoSeek 2.0 could become a valuable tool for multi-cancer early detection, especially for cancers lacking established screening guidelines. Citation Format: Mao Mao, Shen Shen. Yong, Chang yin. yin, Wu Wei, Li shi. yong, Xing ping. ping, Ding chen. yu, Zhu dan. dan, Xu qing. xia. Oncoseek 2.0: Enhanced-sensitivity blood test for multi-cancer early detection [abstract]. In: Proceedings of the 18th AACR Conference on the Science of Cancer Health Disparities; 2025 Sep 18-21; Baltimore, MD. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2025;34(9 Suppl):Abstract nr C127.

Cancer Epidemiology Biomarkers & PreventionVol. 34(9_Supplement)
BioClinica (United States) (US), DermResearch (United States) (US), Henan Cancer Hospital (CN)
Openalex Percentile: Top 62%
Radiomics and Machine Learning in Medical Imaging
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.