What happened
The diagnostics company bioMérieux makes VITEK MS, a mass spectrometer that identifies bacteria and yeasts grown from patient specimens. Its software sorts each spectrum into 1300 bins and classifies the bin scores with the Advanced Spectrum Classifier, a supervised machine learning algorithm. In a prospective study in five US clinical microbiology laboratories, staff tested fresh isolates from patient cultures. Molecular sequencing, with other tests where needed, gave the reference identification. FDA reviewers report a correct single identification for 87.5% (6184/7068) of isolates. Counting results with more than one choice within the correct genus, 6614 of 7068 were correct. A single wrong identification occurred in 0.8% of isolates, and 3.2% received no identification. FDA granted the De Novo request on 21 August 2013. The reviewers name faster identification as the main benefit, which may lead to appropriate antibiotics sooner. The study measured accuracy and did not measure time to result or patient outcomes.
Sources
-
Regulatory document, by authors with no tie to the system.
U.S. Food and Drug Administration, Center for Devices and Radiological Health. Evaluation of Automatic Class III Designation (De Novo) for VITEK MS (K124067 / DEN130013): decision summary. Granted 2013-08-21.
The following performance characteristics were obtained by testing fresh strains from patient cultures, including Gram-positive bacteria, Gram- negative bacteria and yeasts, in five clinical microbiology laboratories in the United States, comparing VITEK®MS identification to a reference identification determined by molecular sequencing
Details
AI system
- Reported configuration
-
VITEK MS V2.0 Knowledge Base
- Workflow
-
Operators at each site were trained in slide preparation and passed a proficiency panel before the study. The classifier compared each spectrum with the reference species in the V2.0 Knowledge Base.
Follow-up
- Conditions for replication
-
The organism belongs to a species claimed in the knowledge base. Laboratories read results with other clinical and laboratory findings and run confirmatory tests where the labeling requires them.
Entry details
- Sector
-
Healthcare.
- Purpose
-
BioMérieux built VITEK MS to identify microorganisms cultured from human specimens, as an aid in diagnosing bacterial and yeast infections.
Not yet checked: model, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.
Cite this record
Peter H. Vartanian. (2026). VITEK MS named bacteria and yeasts from patient cultures in five labs (AIBD-0787). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0787.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)