FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

The BD MAX™ Enteric Viral Panel performed on the BD MAX System, is an automated in vitro diagnostic test for the direct qualitative detection and differentiation of enteric viral pathogens. The BD MAX™ Enteric Viral Panel detects nucleic acids from

. Norovirus GI & GII
. Rotavirus A
. Adenovirus F40/41
. Sapovirus (genogroups I, II, IV, V)
. Human Astrovirus (hAstro)

Testing is performed on unpreserved soft to diarrheal or Cary-Blair preserved stool specimens from symptomatic patients with suspected acute gastroenteritis or colitis. The test is performed directly on the specimen, utilizing real-time polymerase chain reaction (PCR) for the amplification of relevant gene target DNA/RNA. The test utilizes fluorogenic gene-specific hybridization probes for the detection of the amplified DNA.

This test is intended for use, in conjunction with clinical presentation, laboratory findings, and epidemiological information, as an aid in the differential diagnosis of Norovirus GI & GII, Rotavirus A, Adenovirus F40/41, Sapovirus (genogroups I, II, IV, V), and Astrovirus infections. Results of this test should not be used as the sole basis for diagnosis, treatment, or other patient management decisions. Positive results do not rule out co-infection with other organisms that are not detected by this test, and may not be the sole of patient illness. Negative results in the setting of clinical illness compatible with gastroenteritis may be due to infection by pathogens that are not detected by this test or non-infectious causes such as ulcerative colitis, irritable bowel syndrome, or Crohn's disease.

Device Description

Norovirus GI & GII
Rotavirus A
Adenovirus F40/41
Sapovirus (genogroups I, II, IV, V) .
. Human Astrovirus (hAstro)

The BD MAX™ System and the BD MAX™ Enteric Viral Panel is run with the instrument with associated hardware and accessories, disposable microfluidic cartridges, master mixes, unitized reagent strips, extraction reagents, and sample buffer tubes. The instrument automates sample preparation including target lysis, DNA/RNA extraction and concentration, reagent rehydration, and target nucleic acid amplification and detection using real-time PCR. The assay includes a Sample Processing Control (SPC) that is present in the Extraction Tube. The SPC monitors DNA/RNA extraction steps, thermal cycling steps, reagent integrity and the presence of inhibitory substances. The BD MAX™ System software automatically interprets test result may be called as POS (Positive), NEG (Negative), or UNR (Unresolved) for each of the assay's targets, based on the amplification status of the target and of the Sample Processing Control. IND (Indeterminate) or INC (Incomplete) results are due to BD MAXTM System failure.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

BD MAX™ Enteric Viral Panel Study Analysis

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" as a single table with target metrics. Instead, the performance characteristics (Precision, Reproducibility, Analytical Sensitivity, Clinical Performance) define the acceptable levels for the device. I will infer the acceptance criteria from the reported performance and standard expectations for such devices.

Acceptance Criteria (Inferred)	Reported Device Performance (BD MAX™ Enteric Viral Panel)
Precision (Within-laboratory):	Norovirus: TN: 100%, LP: 100%, MP: 100%
Rotavirus: TN: 99.5%, LP: 100%, MP: 100%
Adenovirus: TN: 100%, LP: 100%, MP: 100%
Sapovirus: TN: 100%, LP: 100%, MP: 100%
Astrovirus: TN: 100%, LP: 100%, MP: 100%
Moderate Positive (MP): ≥2 to ≤3x LoD; 100% agreement with expected results	Met for all targets.
*Low Positive (LP): ≥1 to 25% v/v. RotaTeq vaccine yielded positive, as expected. No other reportable interference was found.
Minimal interference from common biological and chemical substances found in stool.	Met. Specific interfering substances are identified and characterized, which is standard for such assays. The RotaTeq vaccine positive is expected given its viral load.
Carryover/Cross-Contamination:	Test: Alternating high positive and negative samples.
Performance: 2 out of 108 negative samples produced a positive result.
Low rate of carryover between samples.	Met. The documented low rate (2/108) indicates acceptable performance in a highly sensitive assay, especially given the high viral loads tested.
Mixed Infection/Competitive Interference:	Test: Low positive target spiked in presence of high concentrations of other targets.
Performance: All organisms corresponding to their respective simulated mixed infection preparations were successfully detected.
Ability to detect low levels of targets in the presence of high levels of other pathogens.	Met. The assay demonstrated successful detection in competitive environments.
Freeze/Thaw:	Test: Up to 3 freeze/thaw cycles for specimens at varied LoD levels.
Performance: 100% positive proportion for all enteric viral targets, both preserved and unpreserved.
Stability of samples after multiple freeze/thaw cycles.	Met. The device maintains performance after 3 freeze/thaw cycles.
Clinical Performance (Positive Percent Agreement - PPA and Negative Percent Agreement - NPA):	Norovirus (Prospective Fresh): Cary-Blair: PPA 92.5%, NPA 99.2%; Unpreserved: PPA 90.7%, NPA 99.6%
Rotavirus (Prospective Fresh): Cary-Blair: PPA 100%, NPA 99.2%; Unpreserved: PPA 100%, NPA 99.9%
Adenovirus (Prospective Fresh): Cary-Blair: PPA 93.8%, NPA 100%; Unpreserved: PPA 80.0%, NPA 99.9% (supplemented with 100% for contrived specimens)
Sapovirus (Prospective Fresh): Cary-Blair: PPA 87.8%, NPA 99.0%; Unpreserved: PPA 80.0%, NPA 99.9%
hAstrovirus (Prospective Fresh): Cary-Blair: PPA 93.5%, NPA 99.9%; Unpreserved: PPA 93.3%, NPA 99.7%
Retrospective results also show high agreement, generally exceeding prospective results due to selection for positive cases.
High PPA and NPA against reference method for all targets in both fresh and preserved stool specimens.	Met. The device demonstrates high agreement rates for all targets across different specimen types and origins, with 95% CIs generally supporting statistical significance. Any lower PPA values for certain targets are often supplemented or discussed within the context of prevalence or specific challenges.
Non-Reportable Rate:	Final Unresolved Rate: Cary-Blair: 0.1%, Unpreserved: 1.0%
Final Indeterminate Rate: Cary-Blair: 0.1%, Unpreserved: 0.0%
Final Incomplete Rate: Cary-Blair: 0.1%, Unpreserved: 0.0%
Combined Final Total Rate: 0.6%
Low rates of unresolved, indeterminate, and incomplete results after repeat testing.	Met. Very low final non-reportable rates are demonstrated.

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

Clinical Test Set Sample Size:
- Total Enrolled Specimens: 2239
  - 1873 Prospective specimens (1055 Cary-Blair preserved, 818 unpreserved)
  - 366 Retrospective specimens (136 Cary-Blair preserved, 230 unpreserved)
- Total Compliant Specimens (after exclusions): 2148
Data Provenance:
- Country of Origin: Not explicitly stated, but described as a "multi-site investigational study" involving "six (6) geographically diverse clinical centers" within the US (implied by FDA submission and 21 CFR references).
- Retrospective or Prospective: Both.
  - Prospective: Specimens (1873) collected as part of routine patient care from symptomatic patients with suspected acute gastroenteritis or colitis.
  - Retrospective: Specimens (366) with historical results, confirmed by an alternate PCR assay and bi-directional sequencing.

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

The document does not specify the number of experts used to establish ground truth or their qualifications.
The "reference method" for prospective specimens was described as "a combination of two (2) sets of alternate PCRs and bi-directional sequencing for one (1) PCR." For retrospective specimens, "historical results were recorded at the collection site" and then "confirmed using an alternate PCR assay and bi-directional sequencing." This implies laboratory personnel or molecular diagnostics experts, but no specific number or experience level is mentioned.

4. Adjudication Method for the Test Set

The document describes a "discrepant analysis" for clinical performance.
- For Norovirus, Rotavirus, Sapovirus, and Human Astrovirus, discordant results between the BD MAX device and the initial reference method were subjected to further testing, often using the BioFire FilmArray™ Gastrointestinal Panel. For example, for Norovirus Cary-Blair preserved specimens, 7/7 specimens that were BD MAX positive and RM negative were tested with FilmArray™, and 4/7 tested positive with FilmArray™. Similarly, 6/6 specimens that were BD MAX negative and RM positive were tested with FilmArray™ and tested negative with FilmArray™.
This suggests a 2+1 adjudication method, where if the initial reference method and the investigational device disagree, a third method (FilmArray™ in this case) is used to adjudicate the true positive/negative status. If the third method agrees with the investigational device, the investigational device's result is considered correct, and vice versa.

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done.
This device is an automated in vitro diagnostic test that produces a qualitative result (positive/negative) for viral pathogens. It is not an imaging device or a decision support system that would typically involve human readers interpreting results with or without AI assistance. The performance is assessed against a reference laboratory method, not human interpretation.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance)

Yes, the performance study primarily focuses on standalone (algorithm only) performance.
The device is an automated system for nucleic acid detection. "The BD MAX™ System software automatically interprets test result may be called as POS (Positive), NEG (Negative), or UNR (Unresolved) for each of the assay's targets." While human operators load samples and review results, the core diagnostic decision is made by the automated system. The clinical performance data reflects this automated output.

7. The Type of Ground Truth Used

Clinical Ground Truth: For prospective specimens, the ground truth was established by a "combination of two (2) sets of alternate PCRs and bi-directional sequencing for one (1) PCR."
Retrospective Ground Truth: For retrospective specimens, ground truth was based on "historical results" which were "confirmed using an alternate PCR assay and bi-directional sequencing."
Adjudication: For discordant results, an additional reference method (BioFire FilmArray™ Gastrointestinal Panel) was used for discrepant analysis, thereby contributing to the final ground truth determination.
This means the ground truth is primarily based on expert laboratory methods (molecular diagnostics/PCR and sequencing), which is standard for detecting viral nucleic acids.

8. The Sample Size for the Training Set

The document does not explicitly mention a separate "training set" or its size in the context of the clinical validation study.
For in vitro diagnostic devices based on molecular assays, "training" typically refers to the assay development and optimization phases rather than a distinct, labeled dataset for machine learning model training as seen in AI/ML applications. The analytical studies (LoD, inclusivity, specificity, interference) represent the extensive work undertaken during assay development to ensure robust performance.

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

Since a separate "training set" in the AI/ML sense is not explicitly described, the concept of establishing ground truth for it is not directly applicable here.
However, during the development and optimization of the BD MAX™ Enteric Viral Panel (analogous to "training"), ground truth would have been established through:
- Characterized strains: Using well-defined viral isolates and quantified nucleic acid standards.
- Spiked samples: Creating samples with known concentrations of target organisms in negative matrices.
- Reference laboratory methods: Using established gold-standard PCRs, sequencing, or culture methods to verify the presence and quantity of pathogens in control samples.

Summary

Regulation Number and Section

§ 866.3990 Gastrointestinal microorganism multiplex nucleic acid-based assay.

(a)
Identification. A gastrointestinal microorganism multiplex nucleic acid-based assay is a qualitativein vitro diagnostic device intended to simultaneously detect and identify multiple gastrointestinal microbial nucleic acids extracted from human stool specimens. The device detects specific nucleic acid sequences for organism identification as well as for determining the presence of toxin genes. The detection and identification of a specific gastrointestinal microbial nucleic acid from individuals exhibiting signs and symptoms of gastrointestinal infection aids in the diagnosis of gastrointestinal infection when used in conjunction with clinical evaluation and other laboratory findings. A gastrointestinal microorganism multiplex nucleic acid-based assay also aids in the detection and identification of acute gastroenteritis in the context of outbreaks.(b)
Classification. Class II (special controls). The special controls are set forth in FDA's guideline document entitled: “Class II Special Controls Guideline: Gastrointestinal Microorganism Multiplex Nucleic Acid-Based Assays for Detection and Identification of Microorganisms and Toxin Genes from Human Stool Specimens.” For availability of the guideline document, see § 866.1(e).