The Science Behind the Test

OneTest Overview

OneTest is a new cancer risk test using a panel of tumor biomarker tests with an algorithm to help identify cancer risk in generally healthy people.  Depending on gender, a blood specimen is analyzed for six or seven FDA approved tumor biomarkers which may be elevated when cancer is present, even in early stages of development.  To calculate an individual’s cancer risk, OneTest employs machine-learning algorithms which incorporate the results of these blood tests along with your individual information, such as age and gender, which can further improve test accuracy compared to testing tumor biomarkers individually.

Testing of tumor markers is performed at the 20/20 GeneSystems’ CLIA laboratory using Roche Cobas e411 platform. FDA approved Roche’s IVD reagent kits are used according to manufacturer specifications. Results of individual tumor marker tests are used to calculate a risk score using machine learning proprietary algorithm and generate a patient report. The OneTest report provides the following information to the patient: 1) the individual 5 (males) or 6 (females) biomarker levels, an overall cancer risk score calculated using a machine learning algorithm, and for those at high risk, the organ systems (e.g. gastrointestinal, genitourinary, etc.) in which primary tumor is likely originated.

 

Tumor Markers for Screening

Tumor markers in blood have the potential to detect cancers at the early stages while patients are still asymptomatic. For patients who see physicians regularly (e.g. for an annual check-up) blood is usually drawn at or prior to an annual visit and analyzed for a panel of markers of general health (e.g. cholesterol, liver enzymes, etc.) to which tests for tumor markers could easily be (and in some countries already have been) added. Over the years, a number of tumor markers have been identified for different types of cancer. However, only a handful of protein tumor marker immunoassays have been developed and approved by the US-FDA for clinical use [1]. Unfortunately, to date, no single tumor marker (except for PSA and its utility has now been questioned) has demonstrated significantly high levels of specificity or sensitivity to warrant routine use in the general early detection of cancer. To address the limitations of individual biomarkers, numerous academic and industry scientific studies have demonstrated that the combination of established biomarkers into optimized multi-biomarker panels provide increased diagnostic accuracy, making such panels an improved cancer detection tool [2-6].

 

Tests based on panels of markers perform better due to differences in cancer subtype etiology leading to differential expression of the markers, inherent variation of marker levels by different patients and/or increased levels of sensitivity and specificity achieved by combining low-level changes in multiple markers to indicate cancer presence at an earlier stage. Several panels have been clinically approved including OVA1 for ovarian cancer detection [7, 8] and phi for prostate cancer screening [9, 10] which have achieved increased levels of sensitivity and specificity.

OneTest Tumor Marker Panels

OneTest is a panel of 5 or 6 tumor markers:

Male panel: AFP, CEA, CA19-9, CYFRA21-1, PSA

Female panel: AFP, CEA, CA19-9, CYFRA21-1, CA125, CA15-3

CEA: Carcinoembryonic antigen (CEA) is a protein associated primarily with diseases of the colon as well as other organs of the gastrointestinal tract. The marker is also associated with breast and lung cancer. It is approved for use in the management (monitoring) of patients with colorectal cancer.

CA 15-3: CA 15-3 (Cancer Antigen 15-3) is the breast cancer marker.
High rates can also apply to other cancers: colon, stomach, kidney, lung, ovary, uterus, pancreas, and liver.

CA 19-9: CA 19-9 (Cancer Antigen 19-9) is a protein associated primarily with colorectal cancer as well as pancreas cancer, stomach cancer, and bile duct cancer. It is approved for use in the monitoring of patients with pancreatic cancer.

CA 125: Serum CA 125 (Cancer Antigen 125) protein values are useful for monitoring the course of disease in patients with invasive epithelial ovarian cancer. Persistently rising CA 125 values may be associated with malignant disease. CA 125 value greater than or equal to 35 U/mL was found to be indicative of the presence of residual tumor. Elevated levels of CA 125 are also found in cancer of the endometrium and fallopian tubes. It is also elevated in serum of some patients with lung cancer.

AFP: AFP (Alpha-1-Fetoprotein (AFP) is a liver associated protein that is generally elevated in liver disease including viral hepatitis, cirrhosis of the liver and liver cancer as well as testicular and ovarian cancers. It is often used to monitor cancer progression.

CYFRA 21-1: Fragments of Cytokeratin-19 (CYFRA 21-1) are associated with lung cancers, head and neck cancer and breast cancers, but are also elevated in a number of benign conditions. CYFRA 21-1 is approved for use in monitoring progression of lung cancers. CYFRA 21-1 can also be used in uterine cancer, esophagus cancer, bladder cancer.

Tumor Markers for Cancer Detection

Tumor proteins in blood have the potential to detect cancers at the early stages while patients are still asymptomatic. For patients who see physicians regularly (e.g. for an annual check-up) blood is usually drawn at or prior to an annual visit and analyzed for a panel of markers of general health (e.g. cholesterol, liver enzymes, etc.) to which tests for tumor markers could easily be (and in some countries already have been) added. Over the years a number of tumor markers have been identified for different types of cancer. However only a handful of protein tumor marker immunoassays have been developed and approved by the US-FDA for clinical use [1]. Unfortunately, to date no single tumor marker (except for PSA and its utility has now been questioned) has demonstrated significantly high levels of specificity or sensitivity to warrant routine use in the general early detection of cancer. To address the limitations of individual biomarkers, numerous academic and industry scientific studies have demonstrated that the combination of established biomarkers into optimized multi-biomarker panels provide increased diagnostic accuracy, making such panels an improved cancer detection tool [2-6].

Tests based on panels of markers perform better due to differences in cancer subtype etiology leading to differential expression of the markers, inherent variation of marker levels by different patients and/or increased levels of sensitivity and specificity achieved by combining low level changes in multiple markers to indicate cancer presence at an earlier stage. Several panels have been clinically approved including OVA1 for ovarian cancer detection [7, 8] and phi for prostate cancer screening [9, 10] which have achieved increased levels of sensitivity and specificity.

  1. Ludwig JA,Weinstein JN Biomarkers in cancer staging, prognosis and treatment selection Nat Rev Cancer. 2005 Nov;5(11):845-56.
  2. Cohen JD, Li L, Wang Y, et al. Detection and localization of surgically resectable cancers with a multi-analyte blood test. Science 2018; 359:926.
  3. Nolen B, Brand R, Prosser D, Velikokhatnaya L, Allen P, et al. Prediagnostic Serum Biomarkers as Early Detection Tools for Pancreatic Cancer in a Large Prospective Cohort Study. PLoS ONE 2014, 9 (4). e94928.
  4. Molina R, Marrades R, Auge J, et al. Assessment of a Combined Panel of six Serum Tumor Markers for Lung Cancer. Am J Respir Crit Care Med (2015) October. Doi: 10.1164/rccm.201404-0603oc.
  5. Anderson GL, McIntosh M, Wu L, et al. Assessing Lead Time of Selected Ovarian Cancer Biomarkers: A Nested Case–Control Study.JNCI Journal of the National Cancer Institute. 2010;102(1):26-38. doi:10.1093/jnci/djp438.
  6. Cohen JD el al., “Combined circulating tumor DNA and protein biomarker-based liquid biopsy for the earlier detection of pancreatic cancers, PNAS (2017). pnas.org/cgi/doi/10.1073/pnas.1704961114
  7. Moore RG, Miller MC, Disilvestro P, et al. Evaluation of the diagnostic accuracy of the risk of ovarian malignancy algorithm in women with a pelvic mass.Obstet Gynecol. 2011;118:280–28
  8. Montagnana M,Benati MDanese E. Circulating biomarkers in epithelial ovarian cancer diagnosis: from present to future perspective. Ann Transl Med. 2017 Jul;5(13):276. doi: 10.21037/atm.2017.05.13.
  9. Filella X, Giménez N. Evaluation of [-2] proPSA and Prostate Health Index (phi) for the detection of prostate cancer: a systematic review and meta-analysis. Clin Chem Lab Med 2013; 51:729.
  10. Loeb S, Catalona WJ. The Prostate Health Index: a new test for the detection of prostate cancer Ther Adv Urol.2014 Apr; 6(2): 74–77. doi: 10.1177/1756287213513488

Importance of Serial Testing

Currently the 20/20’s OneTest algorithms are derived from measurements of a single serum sample. However, there is now evidence that the levels of CA-125 and CEA, as well as several other tumor proteins, rise sharply over time in pre-diagnostic, serially drawn samples from patients subsequently found to have ovarian, pancreatic cancers and prostate [11-15]. For example, the ROCA algorithm derived from 2 prospective trials on ovarian cancer increased the sensitivity of CA-125 from 58.0% based on a standard cutoff to 89.4% using a longitudinally derived algorithm [11].

A further development of our screening algorithm will be to compare marker velocity, changes in marker levels over time, rather than static or simply threshold levels of a given biomarker. The ability to modify our algorithms with longitudinal data from cancer patients has the potential to significantly improve test performance.

  1. Menon U, Ryan A, Kalsi J, et al. Risk algorithm using serial biomarker measurements doubles the number of screen-detected cancers compared with a single-threshold rule in the United Kingdom Collaborative Trial of Ovarian Cancer Screening. J Clin Oncol 2015; 33: 2062–71.
  2. Skates S, Menon U, MacDonald N, Rosenthal A, Oram D, Knapp R, and Jacobs I. Calculation of the Risk of Ovarian Cancer From Serial CA-125 Values for Preclinical Detection in Postmenopausal Women. J Clin Oncol. 2003; 21:206s-210s.
  3. Menon U, Gentry-Maharaj A, Hallett R, et al: Sensitivity and specificity of multimodal and ultrasound screening for ovarian cancer, and stage distribution of detected cancers: results of the prevalence screen of the UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS). Lancet Oncol; 10: 327- 40, 2009.
  4. Nolen B, Brand R, Prosser D, Velikokhatnaya L, Allen P, et al. Prediagnostic Serum Biomarkers as Early Detection Tools for Pancreatic Cancer in a Large Prospective Cohort Study. PLoS ONE 2014, 9 (4). e94928.
  5. Tuma RS. Measuring the Importance of PSA Velocity . JNCI: Journal of the National Cancer Institute, Volume 103, Issue 6, 16 March 2011, Pages 454–461

“Machine learning” algorithms

Machine Learning is a form of artificial intelligence (AI) in which a computer system has the ability to continually process and incorporate new data and thus fine tune its output over time. Because the algorithm used to combine and interpret patient biomarker levels with relevant clinical factor data is derived from machine learning, this algorithm is amenable to periodic review and redefinition. While the current algorithm is fixed on the basis of rigorous studies performed to date, 20/20 GeneSystems, Inc. is committed to the performance of regular review of the algorithm as the existing patient dataset grows. By providing 20/20 GeneSystems, Inc. with outcome data from patient follow-up subsequent to the OneTest , real-world experiences can inform further development and fine-tuning of the OneTest algorithm and continuously improve the accuracy of the test.

 

No products in the cart.