print Print Back Back

Multianalyte Assays With Algorithmic Analyses for Predicting Risk of Type 2 Diabetes

Policy Number: MP-562

Latest Review Date: August 2021

Category: Laboratory

Policy Grade: Effective February 18, 2015: Active Policy but no longer scheduled for regular literature reviews and updates


The use of multianalyte panels with algorithmic analysis (MAAA) for the prediction of Type II diabetes is considered investigational.


Multianalyte assay with algorithm analysis (MAAA) tests have been developed to predict diabetes risk. The PreDx® Diabetes Risk Score (DRS) is an MAAA that is intended to predict the five-year risk of Type II diabetes via a composite of seven serum biomarkers that are combined via a proprietary algorithm to generate a risk score. The proposed use of this technology is to identify patients at greater risk of developing Type II diabetes and to potentially target preventive interventions at patients with the highest risk.

There are a variety of known factors that predict risk of Type II diabetes. The most direct are measures of glucose metabolism, such as fasting glucose, oral glucose tolerance testing (OGTT), and hemoglobin A1C (HgA1C). For patients with impaired fasting glucose or impaired glucose tolerance, there is a high rate of progression to diabetes. Approximately 10% of these patients will progress to diabetes each year, and by ten years more than 50% will have progressed to diabetes.

Other risk factors for Type II diabetes include family history, ethnicity, lifestyle factors, dietary patterns, and numerous different laboratory parameters. A history of diabetes in the immediate family has long been recognized as one of the strongest predictors of diabetes. A sedentary lifestyle, cigarette smoking, and dietary patterns that include sweetened foods and beverages have all been positively associated with the development of diabetes. In addition, there are numerous non-glucose laboratory parameters that are associated with the risk of diabetes. These include inflammatory markers, lipid markers, measures of endothelial dysfunction, sex hormones, and many others.

Formal risk prediction instruments have combined clinical, laboratory, and genetic information to improve and refine upon the predictive ability of single factors. Many different formal risk prediction models have been developed. These models vary in the number and type of factors examined, and in the intended use of the instrument.

In general, the available models have been shown to have good predictive ability, but most of them have not been externally validated. There is some evidence that directly compares the predictive accuracy of different measures, but there is insufficient comparative research to determine the optimal model. There is evidence that different models have different accuracy depending on the population tested. Also, relatively simple models have performed similarly to more complex models, and genetic information seems to add little over readily available clinical and metabolic parameters.

The PreDx® Diabetes Risk Score™ (Tethys Bioscience® Inc., Emeryville, CA) is a commercially available MAAA that is intended to determine the five-year risk of developing Type II diabetes. The risk score is based on seven biomarkers that are obtained by a peripheral blood draw: 1) HgA1C, 2) Glucose, 3) Insulin, 4) C-reactive protein, 5) Ferritin, 6) Adiponectin, 7) Interleukin-2 receptor alpha. The results of these biomarkers are combined with age and gender to produce a quantitative risk score that varies from zero to ten. Results are reported as the absolute five-year risk of developing Type II diabetes and the relative risk compared with age and gender matched controls.


This policy is updated with review of literature through August 30, 2021.

Summary of Evidence

The evidence is insufficient to determine whether MAAAs (including PreDx® risk score) can improve patient outcomes by targeting preventive interventions to patients who will benefit most. One study evaluated changes in cardiovascular risk factors in patients whose physicians used the PreDx® risk score, but there are no published studies that evaluate use of the risk score to target preventive interventions. The evidence is insufficient to determine the comparative accuracy of the PreDx® with other formal prediction models for diabetes.

There is a paucity of well-designed clinical trials/studies to prove the clinical utility of the use of MAAAs to generate a diagnostic risk score for clinical applications. There is a need for additional evidence based research in a wider variety of patient populations to prove the usefulness of this technology. Therefore, use of MAAAs to predict diabetes risk, including but not limited to the PreDx® diabetes risk score, is considered investigational.

Practice Guidelines and Position Statements

There are no clinical practice guidelines that specifically address the use of diabetes risk scores such as the PreDx® score. However, there are a number of clinical practice guidelines that address screening for diabetes in high-risk individuals. These guidelines specify that screening is performed by glucose-based measurements, either by fasting glucose, oral glucose tolerance test, or HgA1C. None of the available guidelines discuss use of a risk score as a replacement for glucose-based screening measures.

U.S. Preventive Services Task Force Recommendations

The U. S. Preventative Services Task Force (USPSTF) published guidelines on screening for diabetes in adults in 2008. The following recommendations was made for screening:

  • Screening for Type II diabetes in asymptomatic adults with sustained blood pressure (either treated or untreated) greater than 135/80 mm Hg (Grade B recommendation)
  • The current evidence is insufficient to assess the balance of benefits and harms of routine screening for Type II diabetes in asymptomatic adults with blood pressure of 135/80 mm Hg or lower (I statement – insufficient evidence)


Diabetes Risk, PreDx Diabetes Risk Score, PreDx DRS, Pre-Dx, MAAA, diabetes, multianalyte panels with algorithmic analyses


The biomarkers included in the PreDx® Diabetes Risk Score are not subject to U.S. Food and Drug Administration approval. Laboratories performing these tests are subject to Clinical Laboratory Improvement Amendment standards for laboratory testing.


Coverage is subject to member’s specific benefits. Group specific policy will supersede this policy when applicable.

ITS: Home Policy provisions apply.

FEP contracts: FEP does not consider investigational if FDA approved and will be reviewed for medical necessity. Special benefit consideration may apply. Refer to member’s benefit plan.


CPT Codes:


Endocrinology (Type II diabetes), biochemical assays of seven analytes (glucose, HbA1c, insulin, hs-CRP, adiponectin, ferritin, interleukin 2-receptor alpha), utilizing serum or plasma, algorithm reporting a risk score


  1. Abbasi A, Peelen LM, Corpeleijn E et al. Prediction models for risk of developing Type II diabetes: systematic literature search and independent external validation study. BMJ 2012; 345:e5900.
  2. American Diabetes Association. Standards of Medical Care in Diabetes—2014. Diabetes Care 2014; 37(Supplement 1):S14-S80.
  3. Balkau B, Lange C, Fezeu L et al. Predicting diabetes: clinical, biological, and genetic approaches: data from the Epidemiological Study on the Insulin Resistance Syndrome (DESIR). Diabetes Care 2008; 31(10):2056-61.
  4. Blonde L. State of diabetes care in the United States. Am J Manag Care 2007; 13 Suppl 2:S36-40.
  5. Chen L, Magliano DJ, Balkau B et al. Maximizing efficiency and cost-effectiveness of Type II diabetes screening: the AusDiab study. Diabet Med 2011; 28(4):414-23.
  6. Colon-Franco J. Mainstream Clinical Adoption of Multianalyte Assays with Algorithmic Analyses. August 12, 2019. Accessed October 3, 2019.
  7. Colón-Franco JM, et al, Current and Emerging Multianalyte Assays with Algorithmic Analyses—Are Laboratories Ready for Clinical Adoption?, Clinical Chemistry, 2018; 64: 64-6
  8. Deberneh HM, Kim I. Prediction of Type 2 Diabetes Based on Machine Learning Algorithm. Int J Environ Res Public Health. 2021 Mar 23; 18(6):3317.
  9. Diabetes Prevention Program Research G, Knowler WC, Fowler SE et al. 10-year follow-up of diabetes incidence and weight loss in the Diabetes Prevention Program Outcomes Study. Lancet 2009; 374(9702):1677-8
  10. Fox CS, Pencina MJ, Meigs JB et al. Trends in the incidence of Type II diabetes mellitus from the 1970s to the 1990s: the Framingham Heart Study. Circulation 2006; 113(25):2914-8.
  11. Griffin SJ, Little PS, Hales CN et al. Diabetes risk score: towards earlier detection of Type II diabetes in general practice. Diabetes Metab Res Rev 2000; 16(3):164-71.
  12. IOM (Institute of Medicine). 2011. Clinical Practice Guidelines We Can Trust. Washington, DC: The National Academies Press.
  13. Kengne AP, Beulens JW, Peelen LM, et al. Non-invasive risk scores for prediction of type II diabetes (EPIC-InterAct): a validation of existing models. Lancet Diabetes Endocrinol. Jan 2014;2(1):19-2
  14. Knowler WC, Barrett-Connor E, Fowler SE et al. Reduction in the incidence of type II diabetes with lifestyle intervention or metformin. N Engl J Med 2002; 346(6):393-403.
  15. Kohaar I, Petrovics G, and Srivastava S, A Rich Array of Prostate Cancer Molecular Biomarkers: Opportunities and Challenges, Int. J. Mol. Sci. 2019; 20, 1813
  16. Kolberg JA, Jorgensen T, Gerwien RW et al. Development of a Type II diabetes risk model from a panel of serum biomarkers from the Inter99 cohort. Diabetes Care 2009; 32(7):1207-12.
  17. Liu S, Tinker L, Song Y et al. A prospective study of inflammatory cytokines and diabetes mellitus in a multiethnic cohort of postmenopausal women. Arch Intern Med 2007; 167(15):1676-85.
  18. Lyssenko V, Jorgensen T, Gerwien RW et al. Validation of a multi-marker model for the prediction of incident Type II diabetes mellitus: combined results of the Inter99 and Botnia studies. Diab Vasc Dis Res 2012; 9(1):59-67.
  19. Mainous AG, 3rd, Baker R, Koopman RJ et al. Impact of the population at risk of diabetes on projections of diabetes burden in the United States: an epidemic on the way. Diabetologia 2007; 50(5):934-40.
  20. Meigs JB, Hu FB, Rifai N et al. Biomarkers of endothelial dysfunction and risk of Type II diabetes mellitus. JAMA 2004; 291(16):1978-86.
  21. Mohan V, Goldhaber-Fiebert JD, Radha V et al. Screening with OGTT alone or in combination with the Indian diabetes risk score or genotyping of TCF7L2 to detect undiagnosed Type II diabetes in Asian Indians. Indian J Med Res 2011; 133:294-9.
  22. Noble D, Mathur R, Dent T et al. Risk models and scores for Type II diabetes: systematic review. BMJ 2011; 343.
  23. Orozco LJ, Buchleitner AM, Gimenez-Perez G et al. Exercise or exercise and diet for preventing Type II diabetes mellitus. Cochrane Database Syst Rev 2008; (3):CD003054.
  24. Padwal R, Majumdar SR, Johnson JA et al. A systematic review of drug therapy to delay or prevent Type II diabetes. Diabetes Care 2005; 28(3):736-44.
  25. Rowe MW, Bergman RN, Wagenknecht LE et al. Performance of a multi-marker diabetes risk score in the Insulin Resistance Atherosclerosis Study (IRAS), a multi-ethnic US cohort. Diabetes Metab Res Rev 2012; 28(6):519-26.
  26. Schwarz PE, Li J, Lindstrom J et al. Tools for predicting the risk of Type II diabetes in daily practice. Horm Metab Res 2009; 41(2):86-97.
  27. Shah BR, Cox M, Inzucchi SE et al. A quantitative measure of diabetes risk in community practice impacts clinical decisions: The PREVAIL initiative. Nutr Metab Cardiovasc Dis 2013.
  28. Shai I, Jiang R, Manson JE et al. Ethnicity, obesity, and risk of Type II diabetes in women: a 20-year follow-up study. Diabetes Care 2006; 29(7):1585-90.
  29. Turner KA and Algeciras-Schimnich A, Multianalyte Assays With Algorithmic Analysis in Women’s Health, Clinical Laboratory News, July 2018
  30. U. S. Preventive Services Task Force. Screening for Type II diabetes mellitus in adults: U.S. Preventive Services Task Force recommendation statement. Ann Intern Med 2008; 148(11):846-54.
  31. Urdea M, Kolberg J, Wilber J et al. Validation of a multimarker model for assessing risk of Type II diabetes from a five-year prospective study of 6784 Danish people (Inter99). J Diabetes Sci Technol 2009; 3(4):748-55.
  32. Zhang L, Zhang Z, Zhang Y, et al. Evaluation of Finnish Diabetes Risk Score in screening undiagnosed diabetes and prediabetes among U.S. adults by gender and race: NHANES 1999-2010. PLoS One. 2014; 9(5):e97865.


Medical Policy Panel, February 2014

Medical Policy Group, September 2014 (1): New policy, previously only listed on Investigational Listing; remains investigational

Medical Policy Administration Committee, September 2014

Available for comment September 16 through October 31, 2014

Medical Policy Panel, February 2015

Medical Policy Group, February 2015 (6): 2015 Updates to Description, Key Points and References; retiring policy effective February 18, 2015; no change to policy statement.

Medical Policy Group, October 2019 (9): Updates to Description, Key Points, and References. Added key words: MAAA, diabetes, multianalyte panels with algorithmic analyses. No change to policy statement.

Medical Policy Group, August 2021 (9): Updates to References, Description, Key Points. Policy statement updated to remove “not medically necessary,” no change to policy intent.

This medical policy is not an authorization, certification, explanation of benefits, or a contract. Eligibility and benefits are determined on a case-by-case basis according to the terms of the member’s plan in effect as of the date services are rendered. All medical policies are based on (i) research of current medical literature and (ii) review of common medical practices in the treatment and diagnosis of disease as of the date hereof. Physicians and other providers are solely responsible for all aspects of medical care and treatment, including the type, quality, and levels of care and treatment.

This policy is intended to be used for adjudication of claims (including pre-admission certification, pre-determinations, and pre-procedure review) in Blue Cross and Blue Shield’s administration of plan contracts.

The plan does not approve or deny procedures, services, testing, or equipment for our members. Our decisions concern coverage only. The decision of whether or not to have a certain test, treatment or procedure is one made between the physician and his/her patient. The plan administers benefits based on the member’s contract and corporate medical policies. Physicians should always exercise their best medical judgment in providing the care they feel is most appropriate for their patients. Needed care should not be delayed or refused because of a coverage determination.

As a general rule, benefits are payable under health plans only in cases of medical necessity and only if services or supplies are not investigational, provided the customer group contracts have such coverage.

The following Association Technology Evaluation Criteria must be met for a service/supply to be considered for coverage:

1. The technology must have final approval from the appropriate government regulatory bodies;

2. The scientific evidence must permit conclusions concerning the effect of the technology on health outcomes;

3. The technology must improve the net health outcome;

4. The technology must be as beneficial as any established alternatives;

5. The improvement must be attainable outside the investigational setting.

Medical Necessity means that health care services (e.g., procedures, treatments, supplies, devices, equipment, facilities or drugs) that a physician, exercising prudent clinical judgment, would provide to a patient for the purpose of preventing, evaluating, diagnosing or treating an illness, injury or disease or its symptoms, and that are:

1. In accordance with generally accepted standards of medical practice; and

2. Clinically appropriate in terms of type, frequency, extent, site and duration and considered effective for the patient’s illness, injury or disease; and

3. Not primarily for the convenience of the patient, physician or other health care provider; and

4. Not more costly than an alternative service or sequence of services at least as likely to produce equivalent therapeutic or diagnostic results as to the diagnosis or treatment of that patient’s illness, injury or disease.