Search Results

The GlutenID Celiac Genetic Health Risk Test uses qualitative genotyping to detect clinically relevant variants in genomic DNA isolated from salva collected from individuals 18 years of age or older with ORAcollect Dx OCD-100 for the purpose of reporting and interpreting Genetic Health Risks (GHR).

The GlutenID Celiac GHR Test is indicated for reporting of one variant associated with the HLA-DQ2.5 haplotype, one variant associated with the HLA-DQ8 haplotype, one variant associated with the HLA-DQ7 haplotype, and three variants associated with the HLA-DQ2.2 haplotype. The report describes if a person has variants linked to haplotypes associated with an increased risk for developing celiac disease, but it does not describe a person's overall risk of developing celiac disease. This report is most relevant for people of European descent.

Not Found

I apologize, but the provided text from the FDA 510(k) clearance letter for the "GlutenID Celiac Genetic Health Risk Test" does not contain the detailed information necessary to answer your request about acceptance criteria and the study proving the device meets them.

The letter is a formal notification of clearance, confirming that the device is substantially equivalent to legally marketed predicate devices. It discusses regulatory matters such as:

• The trade name and regulation details.
• General controls provisions and additional controls for Class II/III devices.
• Applicable regulations like Quality System (QS), Medical Device Reporting (MDR), and Unique Device Identification (UDI).
• Contact information for the FDA.
• The Indications for Use statement.

The document does NOT include information on:

• A table of acceptance criteria and reported device performance.
• Sample sizes for test sets, their provenance, or whether they were retrospective/prospective.
• Number of experts, their qualifications, or adjudication methods for ground truth.
• Whether a multi-reader multi-case (MRMC) comparative effectiveness study was performed or its effect size.
• Whether standalone (algorithm-only) performance was assessed.
• The type of ground truth used (e.g., expert consensus, pathology, outcomes data).
• Sample size for the training set or how its ground truth was established.

This kind of detailed study information is typically found in the 510(k) submission itself, often in a more extensive "Summary of Safety and Effectiveness" or a dedicated study report, which is not part of this specific FDA clearance letter.

Therefore, I cannot fulfill your request based solely on the provided text.

Ask a specific question about this device

The AlphaID™ At Home Genetic Health Risk Service uses qualitative genotyping to detect clinically relevant genetic variants associated with alpha-1 antitrypsin deficiency (AATD) in genomic DNA isolated from human saliva collected from individuals ≥ 18 years with ORAcollect Dx OCD-100.014 for the purpose of reporting and interpreting Genetic Health Risks (GHR).

This Service is indicated for reporting 14 genetic variants in the SERPINA1 gene: PIS; PIM procida; PIM malton; PIS iiyama; PIQ0 granite falls; PIQ0 west; PIQ0 bellingham; PIF; PIQ0 mattawa; PIQ0 clayton, and PI*M heerlen. The report describes if a person is at an increased risk of developing either liver disease linked to AATD. The report does not describe a person's overall risk of developing lung and/or liver disease. AATD is more common in persons of European descent.

The AlphaID™ At Home Genetic Health Risk Service (AlphaID At Home) uses qualitative genotyping to detect clinically relevant genetic variants associated with alphal-antitrypsin deficiency (AATD) and provides a report describing if a person is at risk of developing either lung and/or liver disease linked to AATD. This Service is direct-to-consumer and intended for an Over-the Counter (OTC) use.

The AlphaID™ At Home Genetic Health Risk Service is composed by AlphaID™ At Home Saliva Collection kit for human saliva sample collection (ORAcollect®·Dx OCD-100.014), A1AT Genotyping Test for the genetic analysis and detection of genetic variants associated with alpha-1 antitrypsin deficiency (AATD), and AlphaID™ At Home Genetic Health Risk Service website and result portal software to provide the contents and the procedure to order and use the over the counter (OTC) Service.

A consumer's saliva is self-collected using custom version ORAcollect Dx (model OCD-100.014) device manufactured by DNA Genotek, Inc (See K212745) which consists of collection tube containing a stabilizing buffer solution. Once the sample is collected, it is shipped to Clinical Laboratory Improvement Amendments (CLIA)-certified laboratory for processing.

Human DNA from the saliva sample is isolated and processed with the A1AT Genotyping Test device (K211115) that provides results on 14 genetic variants in the SERPINA / gene: PIS; PIZ; PIM procida; PIM malton; PIS iiyama; PIO0 granite falls: PIO0 west: PIO0 bellingham: PIF; PIP lowell; PIO0 mattawa; PIQ0 clayton, and PI*M heerlen.

Briefly, genomic DNA extracted from human saliva is amplified and biotinylated by multiplex PCR and PCR products are denatured and hybridized to oligonucleotide probes coupled to color-coded beads. Hybridized DNA is labeled with a fluorescent conjugate and the resulting signal is detected with a Luminex® 200™ system. Raw fluorescence data is processed with the A1AT Genotyping Test ANALYSIS SOFTWARE to provide allelic variant genotypes, which are subsequently converted into associated alleles, based on current scientific evidence. Additionally, the software application also provides the type of Genetic Health Risk Report associated with the identified alleles, which is subsequently used as the basis for the generation of personalized reports by the AlphaID™ At Home Genetic Health Risk Service website and result portal.

Depending on the specific variant combination detected, the AlphaID™ At Home Genetic Health Risk Service provides the individuals' genetic health risk for developing lung and liver disease linked to AATD. Personalized reports, in an easy-to-understand format are generated for each consumer that provide results of the testing performed.

Here's a breakdown of the acceptance criteria and study information for the AlphaID™ At Home Genetic Health Risk Service, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

• Increased risk: >80% development.
• Slightly at Increased risk: 20-80% development.
• Not likely at increased risk:

Ask a specific question about this device

The 23andMe Personal Genome Service (PGS) uses qualitative genotyping to detect select clinically relevant variants in genomic DNA isolated from human saliva collected from individuals ≥18 years for the purpose of reporting and interpreting genetic health risks, including the 23andMe PGS Genetic Health Risk Report for Hereditary Prostate Cancer (HOXB13-Related). The 23andMe PGS Genetic Health Risk Report for Hereditary Prostate Cancer (HOXB13- Related) is indicated for reporting of the G84E variant in the HOXB13 gene. The report describes if a person has the G84E variant and if a male is at increased risk for prostate cancer. The variant included in this report is most common in people of European descent. The test report does not describe a person's overall risk of developing any type of cancer, and the absence of a variant tested does not rule out the presence of other variants that may be cancer-related. This test is not a substitute for visits to a healthcare provider for recommended screenings or appropriate follow-up and should not be used for diagnosis, to determine any treatments or medical interventions.

The 23andMe Personal Genome Service (PGS) is an over-the-counter (direct-to-consumer), DNA testing service that provides information and tools for consumers to learn about and explore their DNA.

The 23andMe Personal Genome Service (PGS) is a currently marketed, non-invasive genetic information service that combines qualitative genotyping data covering genetic ancestry, traits, and certain heritable health conditions from a single multiplex assay with descriptive information derived from peer reviewed, published genetic research studies. It is a home use, over-thecounter (direct-to-consumer) DNA testing service intended to provide information and tools for consumers to learn about and explore their DNA.

Customer saliva is self-collected using the Oragene-Dx® Device manufactured by DNA Genotek, Inc. (previously cleared for carrier screening indications under K141410, and the same collection kit used to generate performance data for DEN140044, DEN160026, DEN170046, K182784, DEN180028, and K193492, which consists of a sealable collection tube containing a stabilizing buffer solution. Once the sample is collected, it is shipped to one of our Clinical Laboratory Improvement Amendments (CLIA) certified laboratories for testing.

DNA is isolated from the saliva and tested in a multiplex assay using a customized genotyping beadchip, and off the shelf reagents and instrumentation manufactured by Illumina. The multiplex assay simultaneously tests for more than 500,000 variants, including those for the previously authorized indications, as well as for the indications proposed herein.

Raw data is generated using Illumina GenomeStudio software, and then sent to 23andMe. The data is then analyzed using 23andMe's proprietary Coregen software, where a genotype is determined for each tested SNP. The results for certain of these SNPs are used to generate personalized reports for the customer that provide information about the detected genotype.

Personalized reports are generated for each user that provide results of the testing performed. These reports tell the user which genetic health risk variant(s) have been detected in their sample and provide information about the disease associated with the variant(s). If no variant was detected, that information is also provided. The personalized reports are designed to present scientific concepts to users in an easy-to-understand format. The reports provide scientifically valid information about the risks associated with the presence of a particular variant. The reports are designed to help users understand the meaning of their results and any appropriate actions that may be taken based on their results.

The modified components of the Personal Genome Service included in this 510(k) submission are new labeling to include (a) one new variant to be reported, and (b) the qualitative reporting of one's Genetic Health Risk for Hereditary Prostate Cancer (HOXB13-Related).

Engineering drawings, schematics, etc. of Genetic Health Risk Report for Hereditary Prostate Cancer (HOXB13-Related) are not applicable to this device.

The provided document describes the acceptance criteria and study proving the device meets these criteria for the 23andMe PGS Genetic Risk Report for Hereditary Prostate Cancer (HOXB13-Related).

Here's the breakdown of the information requested:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes Used for the Test Set and Data Provenance

• Accuracy/Method Comparison Study:
  • Sample Size: Not explicitly stated as a number, but "Saliva samples were selected from the 23andMe customer biobank, based on their predetermined genotype and minimum volume required for testing." This implies a varied sample size based on the availability of specific genotypes.
  • Data Provenance: From the "23andMe customer biobank" and "approved contract laboratory sites." The origin of the customers is not specified beyond "23andMe customer" which is a US-based company, suggesting primarily US data. The study was retrospective, using pre-existing samples from the biobank.
• Precision Study:
  • Sample Size: "DNA samples were selected based on their confirmed genotypes, and were obtained from the 23andMe biobank." Not an explicit number.
  • Data Provenance: From the "23andMe biobank." Implies primarily US data, retrospective.
• DNA Input Study:
  • Sample Size: "DNA samples were obtained from the 23andMe biobank based on their listed genotypes." Not an explicit number.
  • Data Provenance: From the "23andMe biobank." Implies primarily US data, retrospective.
• Interfering Substance Study (referenced from DEN140044):
  • Sample Size: Over 35,000 sample replicates.
  • Data Provenance: Not explicitly stated for this particular study, but given it's for a US regulatory submission by a US company, it's highly likely to be US data, retrospective.
• Labeling Comprehension Study (referenced from DEN160026):
  • Sample Size: Not explicitly stated.
  • Data Provenance: Not explicitly stated, but also likely US data.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

• Ground Truth Method: For the analytical studies (Method Comparison, Precision, DNA Input), the ground truth for genotyping was established by bi-directional Sanger sequencing.
• Number/Qualifications of Experts: The document does not specify the number or qualifications of experts involved in performing or interpreting the Sanger sequencing results to establish the "truth." It only states that sequencing was performed "by an approved supplier" and that the sequencing results were "considered to be 'truth.'"

4. Adjudication Method for the Test Set (e.g., 2+1, 3+1, none)

• The document does not describe any human adjudication method for establishing the ground truth from Sanger sequencing. It implies that the sequencing results themselves were directly taken as ground truth without further expert consensus or adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No MRMC or comparative effectiveness study involving human readers (e.g., radiologists) with or without AI assistance was performed or described. This device is a direct-to-consumer genetic test, not an imaging-based AI diagnostic tool.
• The closest concept is the "Labeling Comprehension" study, which assesses how well consumers understand the report. It indicates that the report and educational materials were effective in communicating relevant concepts for safe use. This is a measure of user comprehension, not human reader improvement with AI assistance.

6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Yes, the performance studies (Accuracy, Precision, DNA Input, Interfering Substance) represent a standalone evaluation of the genotyping assay, which is essentially the "algorithm" or technical process of the device. The accuracy and precision figures are "algorithm only" performance metrics, as they compare the device's genotype calls directly against Sanger sequencing as the ground truth.

7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)

• For the analytical performance studies (Accuracy, Precision, DNA Input), the ground truth for specific genetic variants (genotype) was established by bi-directional Sanger sequencing.
• For the clinical performance, the document refers to "published studies of variant frequencies in various populations and the results of analytical studies" and "allele frequencies in the 23andMe customer database." This relies on established scientific literature and aggregated anonymized real-world data rather than individual outcomes or pathology reports.

8. The Sample Size for the Training Set

• The document primarily describes validation studies (test sets) for the analytical performance of the device. It does not provide information about a separate "training set" sample size for developing the genotyping assay or the underlying "Coregen software." The genotyping method described relies on physical beadchip arrays and established principles of DNA analysis, not on a machine learning model that would typically have a distinct training phase with a dedicated dataset.
• The "Customer biobank" is used for selecting samples for the performance studies, which may implicitly reflect data used in the development or refinement of their overall genotyping process, but it's not explicitly defined as a separate 'training set' for an AI model.

9. How the Ground Truth for the Training Set Was Established

• As mentioned above, the document does not elaborate on a distinct "training set" with established ground truth in the context of an AI/ML model for this genetic test. The "Coregen software" analyzes raw data from the beadchip, and its accuracy is validated against Sanger sequencing. The development process of this proprietary software, and any data used to "train" it (if it involves statistical modeling beyond simple rule-based interpretation of genotyping signals), is not detailed in terms of ground truth establishment.

Ask a specific question about this device

The Helix Genetic Health Risk App (HRA) uses qualitative genotyping to detect clinically relevant variants in genomic DNA isolated from human saliva collected from individuals ≥18 years with Oragene®Dx OGD-610 for the purpose of reporting and interpreting Genetic Health Risks (GHR):

The Helix Genetic Health Risk App (HRA) for late-onset Alzheimer's disease is indicated for reporting of the e2/e2, e2/e3, e2/e4 and e4/e4 genotypes in the APOE gene. The report describes if a person's genetic result is associated with an increased or decreased risk of developing late-onset Alzheimer's disease. The e2 and e4 variants included in this report are found and have been studied in many ethnicities. Detailed risk estimates have been studied the most in people of European descent.

The Helix Genetic Health Risk App (HRA) is to be used with the Helix Laboratory Platform.

The Helix Genetic Health Risk App is an over-the-counter (direct-to-consumer), DNA testing service that provides information and tools for consumers to learn about and explore their DNA.

The Helix Genetic Health Risk App is a currently marketed, non-invasive genetic information service that combines qualitative genotyping data indicate for late-onset Alzheimer's disease for reporting of the e2/e2, e2/e3, e2/e4, e3/e3, e3/e4 and e4/e4 genotypes in the APOE gene with descriptive information derived from peer reviewed, published genetic research studies. It is a home use, over-the-counter (direct-to-consumer) DNA testing service intended to provide information and tools for consumers to learn about and explore their DNA. Customer saliva is selfcollected using the FDA cleared Oragene®·Dx OGD-610 saliva collection kit manufactured by DNA Genotek, Inc. (K192920), which consists of a sealable collection tube containing a stabilizing buffer solution. Once the sample is collected, it is shipped to the CLIA-certified and College of American Pathologists (CAP) -accredited Helix laboratory for testing.

DNA is isolated from the saliva and tested using Helix's proprietary whole exome sequencing assay authorized under DEN190035 in the Helix laboratory. The genomic DNA is processed and sequenced using next generation sequencing (NGS) reagents and instrumentation manufactured by Illumina. The sequencing data is analyzed using Helix's proprietary software, where the genetic variants of interest are determined. All samples must pass Helix's stringent quality control metrics prior to analysis. Samples that do not pass quality thresholds will undergo re-sequencing and/or sample re-collection.

The genetic variant results are used to generate personalized reports that provide information about the detected genotype for the customer. These reports tell the user which genotype has/have been detected in their sample and provide information on the risk of disease associated with the genotype. If no genotype was determined, that information is also provided. The personalized reports are designed to present scientific concepts to users in an easy-tounderstand format. The reports provide scientifically valid information about the risks associated with the presence of a particular genetic variant. The reports are designed to help users understand the meaning of their results and any appropriate actions that may be taken based on their results.

Ask a specific question about this device

The AncestryDNA Factor V Leiden Genetic Health Risk Test for Hereditary Thrombophilia uses qualitative genotyping to detect clinically relevant variants in genomic DNA isolated from human saliva collected from individuals 18 years and older with the AncestryDNA Saliva Collection Kit for the purpose of reporting and interpreting Genetic Health Risks (GHR).

The AncestryDNA Factor V Leiden Genetic Health Risk Report for Hereditary Thrombophilia is indicated for reporting of the Factor V Leiden variant in the F5 gene. This report describes if a person has variants associated with a higher risk of developing harmful blood clots, but it does not describe a person's overall risk of developing harmful blood clots. This test is most relevant for people of European descent.

A user's saliva is self-collected using the AncestryDNA Saliva Collection Kit, which consists of a sealable collection tube containing a stabilizing buffer solution. Once the sample is collected, it is shipped to one of two Clinical Laboratory Improvement Amendments (CLIA) certified laboratories for processing.

DNA is isolated from the saliva, quantified, and tested in a multiplex assay using a customized genotyping chip and instrumentation manufactured by Illumina. The multiplex assay simultaneously tests for more than 500,000 variants, including those for the indication proposed herein.

The raw data is generated using Illumina GenomeStudio software, and then sent to Ancestry Genomics (the Manufacturer). The data are analyzed using the Manufacturer's proprietary GHR software, and a genotype is determined for each tested variant. The results for the Factor V Leiden variant are used to generate personalized reports for users that provide information about the disease associated with the detected variant.

Personalized reports are generated for each user that provide results of the testing performed. These reports tell the user which variant(s) has/have been detected in their sample and provide information on the risk of disease associated with the variant(s). If no variant was detected, that information is also provided. The personalized reports are designed to present scientific concepts to users in an easy-to-understand format. The reports provide scientifically valid information about the risks associated with the presence of a particular variant. The reports are designed to help users understand the meaning of their results and any appropriate actions that may be taken based on their results.

Here is a summary of the acceptance criteria and the study that proves the device meets the acceptance criteria, based on the provided text:

Acceptance Criteria and Reported Device Performance

Study Details

2. Sample Size and Data Provenance (Test Set):

• Reproducibility/Precision:
  • Total replicates: 2,340 genotyping events (combining all replicates from Lab 1, Lab 2, inter-laboratory, by site/operator team, by site/instrument, and by site/reagent lot).
  • Donors: 9 donors with known Factor V Leiden genotypes (3 homozygous common, 3 heterozygous, 3 homozygous rare).
  • Provenance: Samples were collected using AncestryDNA Saliva Collection Kits (SCKs) and tested at two CLIA-certified laboratories (Lab 1 and Lab 2). The study was prospective in nature for data collection.
• Analytical Sensitivity:
  • Saliva Study: 15 donors (5 homozygous common, 5 heterozygous, 5 homozygous rare). 450 replicates tested.
  • Cell Line Study: 4 cell lines. 216 data points per cell line for dilutions, and 855 blank replicates.
  • Provenance: Saliva samples collected using Oragene® Dx Collection Device and AncestryDNA SCK. Cell lines. Data collected prospectively for the study.
• Interfering Substances (Endogenous):
  • Donors: 10 saliva donors. 450 initial genotyping attempts (3 replicates for each of 10 donors per interferent + 30 control replicates).
  • Provenance: Saliva samples collected using Oragene® Dx Collection Device. Data collected prospectively for the study.
• Interfering Substances (Exogenous):
  • Donors: 10 non-smokers and 10 smokers. 594 data points.
  • Provenance: Saliva samples collected using AncestryDNA SCKs. Data collected prospectively for the study.
• Interfering Substances (Microbial):
  • Cell Lines: 6 human cell lines (4 homozygous common, 1 heterozygous, 1 homozygous rare). 432 genotyping results.
  • Provenance: Human cell lines. Data collected prospectively for the study.
• Accuracy / Method Comparison:
  • Donors: 209 donors with known Factor V Leiden genotypes (73 homozygous common, 69 heterozygous, 67 homozygous rare). 198 samples passed QC.
  • Provenance: Saliva samples collected using Oragene Dx Ogd-500.001 (OGD) and AncestryDNA SCK. Data collected prospectively for comparison.
• User Comprehension (Study 1):
  • Participants: 378 individuals (N=96, N=86, N=106, N=90 for each of four study arms).
  • Provenance: Participants were recruited from the U.S. matching demographics for education, age, sex/gender, and race/ethnicity, and geographic diversity across four U.S. Census regions. Performed in-person. Prospective study.
• User Comprehension (Study 2):
  • Participants: 213 individuals (N=103 for "1 Variant", N=110 for "Result Not Determined").
  • Provenance: Participants were recruited from the U.S., matching demographics and geographic diversity as in Study 1. Performed via live televideo interviews. Prospective study.

3. Number of Experts and Qualifications for Ground Truth (Test Set):
For analytical studies (Reproducibility, Analytical Sensitivity, Interfering Substances, Accuracy/Method Comparison), the ground truth for Factor V Leiden genotype was primarily established using bi-directional sequencing analysis at a third-party laboratory. The specific qualifications of the experts performing the bi-directional sequencing were not detailed in the provided text.

For User Comprehension Studies, the materials were reviewed by a Certified Genetic Counselor to confirm that the materials met specific criteria for explaining test concepts.

4. Adjudication Method (Test Set):
The text does not explicitly describe an adjudication method like 2+1 or 3+1 for the analytical studies. Instead, direct comparison was made between the device's genotype calls and the ground truth established by bi-directional sequencing. Any discrepancies would presumably be investigated, though the method is not detailed. For User Comprehension studies, a questionnaire was administered by a trained interviewer/moderator to assess comprehension.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not performed. This device is a genetic health risk test (an in vitro molecular diagnostic system), not an imaging device typically associated with MRMC studies in the context of human reader performance improvements with AI.

6. Standalone Performance:
Yes, standalone performance (algorithm only) was done. The studies described (reproducibility, analytical sensitivity, interfering substances, and accuracy/method comparison) evaluate the performance of the device itself (AncestryDNA Factor V Leiden GHR Test) in determining genotype status, independent of human interpretation of raw data. The "AncestryDNA GHR software" processes data from the instrumentation and generates the final analytical genotype information for each sample, which is then used to generate personalized reports.

7. Type of Ground Truth Used (Test Set):
The primary ground truth used for determining the Factor V Leiden genotype in analytical studies was bi-directional sequencing analysis.

8. Sample Size for the Training Set:
The document does not explicitly specify a "training set" sample size for the AncestryDNA Factor V Leiden Genetic Health Risk Test in the context of its 510(k) submission. For molecular diagnostic systems like this, the "training" aspect often refers to the development and optimization of the assay and software algorithms. The document instead focuses on analytical validation studies (test sets) for device performance. If the AncestryDNA GHR software performs certain control checks and analyses (as described in section "P. SYSTEM DESCRIPTION" - "Software"), the underlying algorithms would have been developed and potentially "trained" or optimized during the device's development phase, but specific training set sizes are not provided.

9. How the Ground Truth for the Training Set was Established:
Since a specific training set sample size is not explicitly mentioned for the reported studies, the method for establishing ground truth for a training set is also not detailed. However, for any developmental work or optimization, it is highly probable that the ground truth would have been established using bi-directional sequencing or other highly accurate, established reference methods, similar to how the ground truth for the test sets was established.

Ask a specific question about this device

The 23andMe Personal Genome Service (PGS) Test uses qualitative genotyping to detect the following clinically relevant variants in genomic DNA isolated from human saliva collected from individuals ≥18 years with the Oragene Dx model OGD-500.001 for the purpose of reporting and interpreting Genetic Health Risks (GHR):

The 23andMe PGS Genetic Health Risk Report for Hereditary Thrombophilia is indicated for reporting of the Factor V Leiden variant in the F5 gene, and the Prothrombin G20210A variant in the F2 gene. This report describes if a person has variants associated with a higher risk of developing harmful blood clots, but it does not describe a person's overall risk of developing harmful blood clots. This test is most relevant for people of European descent.

The 23andMe PGS Genetic Health Risk Report for Alpha-1 Antitrypsin Deficiency is indicated for reporting of the PIZ and PIS variants in the SERPINA1 gene. This report describes if a person has variants associated with AAT deficiency and a higher risk for lung or liver disease, but it does not describe a person's overall risk of developing lung or liver disease. This test is most relevant for people of European descent.

The 23andMe PGS Genetic Health Risk Report for Late-onset Alzheimer's Disease is indicated for reporting of the £4 variant in the APOE gene. The report describes if a person's genetic result is associated with an increased risk of developing Late-onset Alzheimer's Disease, but it does not describe a person's overall risk of developing Alzheimer's Disease. The £4 variant included in this report is found and has been studied in many ethnicities. Detailed risk estimates have been studied the most in people of European descent.

The 23andMe PGS Genetic Health Risk Report for Parkinson's Disease is indicated for reporting of the G2019S variant in the LRRK2 gene and the N370S variant in the GBA gene. The report describes if a person's genetic result is associated with an increased risk of developing Parkinson's disease, but it does not describe a person's overall risk of developing Parkinson's disease. The test is most relevant for people of European, Ashkenazi Jewish, and North African Berber descent.

The 23andMe PGS Genetic Health Risk Report for Gaucher Disease Type 1 is indicated for reporting of the N370S, 84GG, and V394L variants in the GBA gene. This report describes if a person has variants associated with an increased risk for developing symptoms of Gaucher Disease Type 1, but it does not describe a person's overall risk of developing Gaucher Disease Type 1. This test is most relevant for people of Ashkenazi Jewish descent.

The 23andMe PGS Genetic Health Risk Report for Factor XI Deficiency is indicated for reporting of the variants F283L. E117X. IVS14+1G>A in the F11 gene. This report describes if a person has a variant associated with Factor XI deficiency and the potential for a higher risk of excessive bleeding following trauma or surgery, but it does not describe a person's overall risk for excessive bleeding. This test is most relevant for people of Ashkenazi Jewish descent.

The 23andMe PGS Genetic Health Risk Report for Celiac Disease is indicated for reporting of a variant associated with the HLA-DQ2.5 haplotype. The report describes if a person has a haplotype associated with an increased risk of developing celiac disease, but it does not describe a person's overall risk for developing celiac disease. This report is most relevant for people of European descent.

The 23andMe PGS Genetic Health Risk Report for Glucose-6-Phosphate-Dehydrogenase Deficiency is indicated for reporting of the Val68Met variant in the G6PD gene. This report describes if a person has a variant associated with G6PD deficiency and a higher risk for episodes of anemia, but it does not describe a person's overall risk of developing anemia. This test is most relevant for people of African descent.

The 23andMe PGS Genetic Health Risk Report for Hereditary Hemochromatosis is indicated for reporting of the C282Y and H63D variants in the HFE gene. This report describes if a person has variants associated with hereditary hemochromatosis and a higher risk for iron overload, but it does not describe a person's overall risk of developing iron overload. This report is most relevant for people of European descent.

The 23andMe PGS Genetic Health Risk Report for Early-Onset Primary Dystonia (DYT1/TOR1A-Related) is indicated for reporting of the deltaE302/303 variant in the DYT1 gene. This report describes if a person has variants associated with a higher risk for early-onset primary dystonia, but it does not describe a person's overall risk of developing dystonia. This report is most relevant for people of Ashkenazi Jewish descent.

The 23andMe PGS is a currently-marketed, non-invasive genetic information service that combines qualitative genotyping data covering genetic ancestry, traits, and certain heritable health conditions from a single multiplex assay with descriptive information derived from peer reviewed, published genetic research studies. It is a direct-toconsumer, over-the-counter, non-diagnostic, DNA genetic testing service intended to provide information and tools for individual users.

A user's saliva is self-collected using the Oragene-Dx device manufactured by DNA Genotek, Inc. (previously cleared under K141410), which consists of a sealable collection tube containing a stabilizing buffer solution. Once the sample is collected, it is shipped to one of two Clinical Laboratory Improvement Amendments (CLIA)-certified laboratories for processing.

DNA is isolated from the saliva and tested in a multiplex assay using a customized genotyping chip and instrumentation manufactured by Illumina. The multiplex assay simultaneously tests for more than 500,000 variants, including those for the indications proposed herein.

The raw data is generated using Illumina GenomeStudio software, and then sent to 23andMe (the Manufacturer). The data are analyzed using the Manufacturer's proprietary Coregen software, and a genotype is determined for each tested variant. The results for certain of these variants are used to generate personalized reports for users that provide information about the diseases associated with the detected variant.

Personalized reports are generated for each user that provide results of the testing performed. These reports tell the user which variant(s) has/have been detected in their sample and provide information on the risk of disease associated with the variant(s). If no variant was detected, that information is also provided. The personalized reports are designed to present scientific concepts to users in an easy-to-understand format. The reports provide scientifically valid information about the risks associated with the presence of a particular variant. The reports are designed to help users understand the meaning of their results and any appropriate actions that may be taken based on their results.

Acceptance Criteria and Device Performance Study for 23andMe Personal Genome Service (PGS) Genetic Health Risk Test

The 23andMe Personal Genome Service (PGS) Genetic Health Risk Test is a qualitative in vitro molecular diagnostic system for detecting genetic variants associated with various diseases. The regulatory approval details the acceptance criteria and performance study results.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for analytical performance (Precision/Reproducibility, Limit of Detection, and Accuracy) are derived from the Special Controls outlined in 21 CFR 866.5950, specifically paragraph (b)(3)(iii)(J).

• PA (CC|CC) = 100% (95% CI: 94.7% to 100%)
• PA (CT|CT) = 100% (95% CI: 94.7% to 100%)
• PA (TT|TT) = 100% (95% CI: 94.6% to 100%)
  Hereditary Thrombophilia (Prothrombin G20210A F2):
• PA (GG|GG) = 100% (95% CI: 94.7% to 100%)
• PA (AG|AG) = 100% (95% CI: 94.6% to 100%)
• PA (AA|AA) = 100% (95% CI: 94.5% to 100%)
  Alpha-1 Antitrypsin Deficiency (PI*Z SERPINA1):
• PA (CC|CC) = 100% (95% CI: 94.8% to 100%)
• PA (CT|CT) = 100% (95% CI: 94.7% to 100%)
• PA (TT|TT) = 100% (95% CI: 94.7% to 100%)
  Alpha-1 Antitrypsin Deficiency (PI*S SERPINA1):
• PA (TT|TT) = 100% (95% CI: 94.4% to 100%)
• PA (AT|AT) = 100% (95% CI: 94.7% to 100%)
• PA (AA|AA) = 100% (95% CI: 94.7% to 100%)
  Late-onset Alzheimer's Disease (APOE s4):
• PA (TT|TT) = 100% (95% CI: 98.8% to 100%)
• PA (CT|CT) = 99.2% (95% CI: 95.7% to 99.9%)
• PA (CC|CC) = 100% (95% CI: 96.3% to 100%)
  Parkinson's Disease (G2019S LRRK2):
• PA (GG|GG) = 100% (95% CI: 86.7% to 100%)
• PA (AG|AG) = 100% (95% CI: 93% to 100%)
• PA (AA|AA) = 100% (95% CI: 51.0% to 100%)
  Parkinson's Disease (N370S GBA):
• PA (TT|TT) = 100% (95% CI: 86.7% to 100%)
• PA (CT|CT) = 100% (95% CI: 94% to 100%)
• PA (CC|CC) = 100% (95% CI: 87.1% to 100%)
  Gaucher Disease Type 1 (N370S GBA):
• PA (TT|TT) = 100% (95% CI: 86.7% to 100%)
• PA (CT|CT) = 100% (95% CI: 94% to 100%)
• PA (CC|CC) = 100% (95% CI: 87.1% to 100%)
  The Manufacturer affirmed that comparison studies for other variants (84GG, V394L in GBA; F283L, E117X, IVS14+1G>A in Factor XI; HLA-DQA1 for Celiac Disease; Val68Met in G6PD; C282Y, H63D in HFE; deltaE302/303 in DYT1) were completed with identical study design, acceptance criteria, and results as the reported variants, including 100% accuracy for all valid calls. |
  | Precision/Reproducibility | The percentage of samples that failed quality control must be indicated (i.e., the total number of sample replicates for which a sequence variant cannot be called (no calls) or that fail sequencing quality control criteria divided by the total number of replicates tested). (b)(3)(iii)(J)(2) | General: All analytical performance studies met the pre-determined acceptance criteria.
  Factor V Leiden: 98.0% correct calls, 2.01% FQCs (0.04% anticipated 2 FQCs).
  Prothrombin G20210A: 98.1% correct calls, 1.85% FQCs (0.03% anticipated 2 FQCs).
  PI*Z SERPINA1: 98.4% correct calls, 1.63% FQCs (0.03% anticipated 2 FQCs).
  PI*S SERPINA1: 98.2% correct calls, 1.76% FQCs (0.03% anticipated 2 FQCs).
  APOE s4: 98.5% correct calls, 1.54% FQCs (0.02% anticipated 2 FQCs).
  G2019S LRRK2: 98.5% correct calls, 1.54% FQCs (0.02% anticipated 2 FQCs).
  N370S GBA (Parkinson's): 96.2% correct calls, 3.81% FQCs (0.15% anticipated 2 FQCs).
  N370S GBA (Gaucher): 97.5% correct calls, 3.12% FQCs (0.10% anticipated 2 FQCs).
  All valid calls in these studies were 100% correct at both sites. The Manufacturer affirmed that reproducibility studies were completed for all other listed variants (84GG, V394L in GBA; F283L, E117X, IVS14+1G>A in Factor XI; HLA-DQA1 for Celiac Disease; Val68Met in G6PD; C282Y, H63D in HFE; deltaE302/303 in DYT1) with identical study design, acceptance criteria, and results. |
  | Limit of Detection (LoD) | Data must be provided demonstrating the minimum amount of DNA that will enable the test to perform correctly in 95 percent of runs. (b)(3)(iii)(J)(5) | The LoD study yielded 100% correct genotype calls for all samples and all reagent lots tested at sample DNA concentrations of 5, 15, and 50 ng/uL. The study passed LoD acceptance criteria at 5 ng/uL. Manufacturer claimed LoD of 15 ng/uL.
  The Manufacturer affirmed that LoD studies were completed for all other listed variants (84GG, V394L in GBA; F283L, E117X, IVS14+1G>A in Factor XI; HLA-DQA1 for Celiac Disease; Val68Met in G6PD; C282Y, H63D in HFE; deltaE302/303 in DYT1) with identical study design, acceptance criteria, and results. |
  | User Comprehension | The user study must meet predefined primary endpoint criteria, including a minimum of a 90 percent or greater overall comprehension rate (i.e., selection of the correct answer) for each comprehension concept. (b)(3)(iii)(M)(4)(vi) | The overall comprehension score for all concepts across all test reports studied was greater than 90%. For the G6PD Deficiency report scenario ("1 Variant Detected"), the report-specific comprehension score was 73.3%, which the Manufacturer mitigated with planned labeling changes in the FAQ section. |

2. Sample Sizes and Data Provenance for Test Set

Test Set for Analytical Accuracy (Comparison to Sanger Bidirectional Sequencing):

• Hereditary Thrombophilia (Factor V Leiden): 68 Homozygous Common (CC), 68 Heterozygous (CT), 67 Homozygous Rare (TT) samples. Total = 203.
• Hereditary Thrombophilia (Prothrombin G20210A): 68 Homozygous Common (GG), 67 Heterozygous (AG), 66 Homozygous Rare (AA) samples. Total = 201.
• Alpha-1 Antitrypsin Deficiency (PI*Z SERPINA1): 70 Homozygous Common (CC), 68 Heterozygous (CT), 69 Homozygous Rare (TT) samples. Total = 207.
• Alpha-1 Antitrypsin Deficiency (PI*S SERPINA1): 65 Homozygous Common (TT), 68 Heterozygous (AT), 69 Homozygous Rare (AA) samples. Total = 202.
• Late-onset Alzheimer's Disease (APOE s4): 316 Homozygous Common (TT), 126 Heterozygous (CT), 101 Homozygous Rare (CC) samples with correct calls. (Total raw samples: 320 TT, 129 CT, 106 CC, including those with "no calls" or "invalid"). Total = 555.
• Parkinson's Disease (G2019S LRRK2): 25 Homozygous Common (GG), 51 Heterozygous (AG), 4 Homozygous Rare (AA) samples. Total = 80.
• Parkinson's Disease (N370S GBA): 25 Homozygous Common (TT), 60 Heterozygous (CT), 26 Homozygous Rare (CC) samples. Total = 111.
• Gaucher Disease Type 1 (N370S GBA): 25 Homozygous Common (TT), 60 Heterozygous (CT), 26 Homozygous Rare (CC) samples. Total = 111.
• Other variants: For Gaucher Disease Type 1 (84GG, V394L), Factor XI Deficiency (F283L, E117X, IVS14+1G>A), Celiac Disease (HLA-DQA1), G6PD Deficiency (Val68Met), Hereditary Hemochromatosis (C282Y, H63D), and Early-Onset Primary Dystonia (deltaE302/303), the manufacturer affirmed that comparison studies were completed with the same design, acceptance criteria, and results as the explicitly detailed studies, testing wild-type, heterozygous, and homozygous samples where applicable, adhering to minimum sample size requirements (e.g., at least 20 unique samples for common genotypes, 3 for rare heterozygous, 3-20 for rare homozygous based on frequency).

Data Provenance: Saliva samples were selected from the 23andMe customer biobank based on their predetermined genotype. The data origin is not explicitly stated geographically, but it is indicated that genotype frequencies are considered for "individuals of European descent," "Ashkenazi Jewish descent," "North African Berber descent," "African descent," "South Asian," and "East Asian" depending on the variant, implying a diverse customer base. The samples are retrospective, as they were chosen from an existing biobank.

3. Number of Experts and Qualifications for Ground Truth

No external experts were explicitly mentioned for establishing the ground truth of the genetic variants in the test set. The ground truth for the test set was established by Sanger bidirectional sequencing, which is considered the "gold standard" for genetic variant determination. This method is an intrinsic, highly accurate laboratory technique, rather than requiring expert consensus interpretation.

4. Adjudication Method for the Test Set

Not applicable. The ground truth was established by Sanger bidirectional sequencing, an objective laboratory method, which means there was no human adjudication process involved for the genetic variant calls.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No MRMC comparative effectiveness study was performed in the context of human readers improving with or without AI assistance. This device is a direct-to-consumer genetic test for detecting specific variants, not an AI-assisted diagnostic imaging or interpretation tool.

6. Standalone (Algorithm-Only) Performance Study

Yes, the analytical performance studies (Accuracy, Precision/Reproducibility, Limit of Detection) represent the standalone performance of the 23andMe PGS device. The device's genotyping results were compared directly against the gold standard (Sanger bidirectional sequencing) without human intervention in the interpretation of the device's output for genetic calls.

7. Type of Ground Truth Used

The type of ground truth used for the analytical performance studies (accuracy, LoD) was Sanger bidirectional sequencing, which is a highly accurate molecular biology laboratory method for DNA sequencing, serving as the "truth" for genetic variants. This is an objective laboratory measure, not expert consensus, pathology, or outcomes data.

8. Sample Size for the Training Set

The document does not explicitly mention a "training set" in the context of machine learning or AI algorithm development for genetic variant detection. The methodologies described are for analytical validation of a qualitative genetic test. The robustness of the test is demonstrated through extensive reproducibility and accuracy studies using defined sets of samples (both cell lines and customer biobank samples).

For the analytical performance studies (Precision/Reproducibility and Limit of Detection), a range of sample sizes were used:

• Precision/Reproducibility for Hereditary Thrombophilia (Factor V Leiden): 10 DNA samples (3 wild type, 2 heterozygous, 1 homozygous rare, repeated multiple times) used for 1890 replicates.
• Precision/Reproducibility for Hereditary Thrombophilia (Prothrombin G20210A): 10 DNA samples (3 wild type, 1 heterozygous, 1 homozygous rare, repeated multiple times) used for 1620 replicates.
• Precision/Reproducibility for Alpha-1 Antitrypsin Deficiency (PI*Z SERPINA1): 8 DNA samples (2 wild type, 1 heterozygous, 1 homozygous rare, repeated multiple times) used for 1350 replicates.
• Similar numbers of DNA samples and replicates were used for other variants in the reproducibility studies.
• Limit of Detection: Samples were diluted to three different DNA concentrations (5, 15, and 50 ng/uL) and genotyped. The text does not specify the number of individual donor samples used for LoD beyond "each sample was diluted," implying the same initial set of samples used for accuracy/precision.

9. How the Ground Truth for the Training Set Was Established

As mentioned above, a "training set" in the conventional machine learning sense for algorithm development is not explicitly described. The ground truth for the samples used in the analytical validation studies (which could be considered analogous to a "development/test set" for a traditional assay) was established through bidirectional Sanger sequencing, performed by an independent laboratory. This external, highly accurate, and objective method served as the reference standard for confirming the genotypes of the samples used in the performance evaluations.

Ask a specific question about this device