Subject Matter Panel and Contractor Advisory Committee (CAC) Meeting on June 26th, 2019
A panel of subject matter experts and CAC members from CGS, Wisconsin Physicians Services, Noridian, and Palmetto GBA was convened on June 26th, 2019 over the phone. While only invited experts and CAC members could speak, interested members of the public who registered could listen. The full recording is also available.19 Subject matter experts on the panel included the list below. Included members may have additional titles and positions to those listed.
Mary Relling, Chair, Pharmaceutical Dept. St. Jude Children's Research Hospital
John Greden, Founder and Executive Director, University of Michigan Comprehensive Depression Center
Annette Taylor, AVP, LabCorp, Co-Business Lead, Pharmacogenomics
Stuart Scott, Associate, Associate Professor, Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai
The panel generally agreed that pharmacogenomics testing generally speaking has the ability to provide clinically utile information that allows treating clinicians to select and dose particular medications appropriately. Pharmacogenomic testing (presumably for genes associated with pharmacokinetic pathways) was described as being analogous to measuring renal function with a serum creatinine prior to dosing renally cleared medications. The panel generally agreed that single gene testing and multi- gene panels (as defined at the top of this LCD) for particular genes has role in medication dosing and selection. The panel members did not specifically recommend or support the use of any one combinatorial pharmacogenomics test over another. There was general agreement that combinatorial pharmacogenomics tests with a proprietary algorithm not available for public review required independent evidence establishing their validity and utility. Additionally, a comment was made that CYP2C19 and CYP2D6 testing would most likely be the appropriate comparator in a clinical study to determine if a combinatorial pharmacogenomics test provides information that improves outcomes more than single gene or multi-gene panels. While it was not discussed by the panel, a manuscript submitted by Dr. Black did a retrospective comparison (using statistical modelling rather than a direct comparison) of GeneSight to single gene testing.20 This study suggested that combinatorial testing predicts poor antidepressant response and outcomes better than single gene testing. Two gene panels were not considered.
A CAC member commented that pharmacogenomics testing is becoming increasingly common, and it should not be restricted by provider type.
Additional Expert Input
In addition to the panel, a number of experts who were unable to attend provided written correspondence. These included the following:
John Logan Black, Co-Director, Personalized Genomics Laboratory, Department of Laboratory Medicine and Pathology, Mayo Clinic
To summarize, Dr. Black’s comment generally agreed with the comments of the panel. He indicated support for the use of genetics in guiding pharmacologic treatment, referencing guidelines from CPIC and the FDA. He also provided references to a number of peer-reviewed studies which have been reviewed in this LCD. As regards combinatorial testing, he noted that evidence does support their use, though he also noted that it “is unclear is whether the power of combinatorial pharmacogenomics is driven by a few genes or if it is absolutely due to the combinatorial effects.” He indicated that for panel testing, he would recommend a minimum panel in psychiatry consisting of CYP2C9, CYP2C19, CYP2D6, HLA-A*31:01 and HLA-B*15:02.
Jose DeLeon, Professor, Psychiatry, University of Kentucky
Dr. de Leon’s comments largely agree with the panel’s comments as well, though he specifically noted the clinical utility of HLA-B*15:02 in any patient of Asian ancestry before starting carbamazepine, and for CYP2D6 and CYP2C19 genes for some antidepressants and some antipsychotics. Additionally, Dr. de Leon also indicated his belief that the evidence did not support the use of GeneSight. Notably, he indicated the importance of CYP2D6 and CYP2C19 and questioned the testing of other CYPs. He also noted that the GUIDED study (reviewed above) “further demonstrated that the study results were negative and the authors had to use secondary outcomes to try to demonstrate that a negative study had positive results.”
Bruce Cohen - Director of the Program for Neuropsychiatric Research at McLean Hospital and Harvard Medical School
Dr. Cohen’s comments are summarized below.
Limitations of pharmacogenomics testing
A number of opinion leaders and experts representing multiple provider types have articulated how pharmacogenomics can be used, and how it might drive prescribing decisions, other thought leaders have called into question the utility of pharmacogenomics or specific tests in pharmacogenomics. Notably, the American Psychiatric Association, which is one of the largest organizations in the country representing treating clinicians with medication prescribing authority has to date published no position statement, guideline, or evidentiary interpretation.
The Food and Drug Administration (FDA) has published a document raising concerns about pharmacogenomics testing.21 The document notes: “…the relationship between DNA variations and the effectiveness of antidepressant medication has never been established.’’ It goes on to state as a recommendation to providers
If you are using, or considering using, a genetic test to predict a patient's response to specific medications, be aware that for most medications, the relationship between DNA variations and the medication's effects has not been established.
However, the document also notes:
There are a limited number of cases for which at least some evidence does exist to support a correlation between a genetic variant and drug levels within the body, and this is described in the labeling of FDA cleared or approved genetic tests and FDA approved medications. The FDA authorized labels for these medical products may provide general information on how DNA variations may impact the levels of a medication in a person's body, or they may describe how genetic information can be used in determining therapeutic treatment, depending on the available evidence.
A manuscript examining the metascience of pharmacogenomics testing and providing an accompanying viewpoint reviewed 10 clinical studies of pharmacogenomics in psychiatry and found that none of them were blinded and used a protocol-based comparison.22 The authors point to two evidence-based protocols that are freely available and could have been used, STAR*D and the Texas Medication Algorithm Project. As the authors state early on:
Simply put, MDD [Major Depressive Disorder] is determined by a large number of genes, and, except in rare cases, no single gene or limited gene set, even those for drug metabolism and drug targets, determines more than a few percent of the risk of illness or course of treatment.
The STAR*D study included 2,876 subjects with major depressive disorder from multiple institutions.10,23,24 In this study all participants started with citalopram as the initial treatment and may have advanced through additional levels of treatment up to level 4. If a subject did not respond at a given level, that subject was then advanced to the next level of treatment, which included alternative treatments instead of or in addition to the treatment the patient was on.
Dr. Bruce M. Cohen, the Director of the Program for Neuropsychiatric Research at McLean Hospital and Harvard Medical School, who submitted indicated that current pharmacogenetic tests offer no clear clinical value over freely available and well-established protocols for drug selection with a reference to a number of recent documents.21,22 He also pointed out that, should a clinician be unsure about drug choice, a psychiatry consultation costs substantially less money than pharmacogenetic testing.
