(184 days)
The RAPIDPoint 500 system is intended for in vitro diagnostic use and is designed to provide the determination in whole blood for the following parameters:
- Partial pressure of carbon dioxide .
- Partial pressure of oxygen .
- . pH
- Sodium .
- Potassium .
- lonized calcium .
- Chloride .
- Glucose .
- Total hemoglobin and fractions: fO2Hb, fCOHb, fMetHb, fHHb .
- Neonatal bilirubin .
- . Lactate
This test system is intended for use in point of care or laboratory settings.
Lactate. Lactic acid measurements that evaluate the acid-base status are used in the diagnosis and treatment of lactic acidosis (abnormally high acidity of the blood).
Lactate (Lac) is a new parameter offered on the RAPIDPoint 500 (RP500) blood gas system. The RP500 system is a point-of-care and laboratory testing blood gas analyzer and currently measures a variety of parameters that have been previously cleared. Enabling the lactate measurement is accomplished through software design changes introduced in Software Version 2.0 and requires the use of a RAPIDPoint 500 Measurement Cartridge. No hardware or mechanical changes were needed.
Here's a breakdown of the acceptance criteria and study information for the RAPIDPoint® 500 System for Lactate measurement:
Device: RAPIDPoint® 500 System with Lactate (Lac) Test
Predicate Device: Siemens Healthcare Diagnostics RAPIDLab 1265
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Coefficient of determination (r²) value > 0.90 (when compared to predicate device) | The coefficient of determination (r²) value was within the acceptance criteria (>0.90) when combining results from the external evaluation for a total of over 140 samples. |
2. Sample Size and Data Provenance for Test Set
- Sample Size: Over 140 samples.
- Data Provenance:
- Country of Origin: Not explicitly stated.
- Retrospective or Prospective: The "external evaluation study included testing at multiple point-of-care sites with intended use whole blood samples," suggesting these were likely prospectively collected samples in a real-world setting.
3. Number of Experts and Qualifications for Ground Truth of Test Set
- Number of Experts: Not applicable. The ground truth was established by comparison to a predicate device, not by expert consensus on diagnoses.
- Qualifications of Experts: Not applicable.
4. Adjudication Method for Test Set
- Adjudication Method: Not applicable. The ground truth was established by comparison to a predicate device, not by expert review requiring adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? No. This device is an in vitro diagnostic (IVD) measurement system, not an imaging or diagnostic aid that relies on human interpretation. The study focused on the analytical performance of the device against a predicate, not on how it assists human readers.
- Effect size of how much human readers improve with AI vs. without AI assistance: Not applicable.
6. Standalone (Algorithm Only) Performance Study
- Was a standalone study done? Yes. The "internal evaluation study entailed testing concentrations of lactate in whole blood across the reporting range." This, along with the external evaluation comparing the device to the predicate, represents the standalone performance of the RAPIDPoint® 500 system's lactate measurement. It is an automated system; there is no human-in-the-loop performance component in the measurement process itself.
7. Type of Ground Truth Used
- Type of Ground Truth: Comparison to a predicate device (Siemens Healthcare Diagnostics RAPIDLab 1265). The performance of the new device was evaluated against the established performance of the legally marketed predicate device.
8. Sample Size for Training Set
- The document does not explicitly state a separate "training set" sample size in the context of machine learning or AI. The RAPIDPoint 500 system uses an amperometric method based on enzyme kinetics, not a machine learning algorithm that requires a separate training phase with a labeled dataset in the traditional sense. The lactate measurement is "accomplished through software design changes introduced in Software Version 2.0," which implies traditional software development and verification rather than machine learning model training.
- The "internal evaluation study entailed testing concentrations of lactate in whole blood across the reporting range" would serve as part of the validation and verification of the system's analytical performance, which is analogous to testing, but not "training" in an ML context.
9. How Ground Truth for Training Set Was Established
- Not applicable in the context of a machine learning training set, as the device's measurement is based on a defined electrochemical method, not a trained AI model. The accuracy of the "ground truth" for calibrating and verifying the system during development (if any specific calibration data is considered) would be based on reference methods or traceable standards for lactate concentration. The document mentions "software development life cycle including software requirements specifications, risk management report, and overall verification and validation results," indicating traditional software engineering practices rather than AI specific training.
§ 862.1450 Lactic acid test system.
(a)
Identification. A lactic acid test system is a device intended to measure lactic acid in whole blood and plasma. Lactic acid measurements that evaluate the acid-base status are used in the diagnosis and treatment of lactic acidosis (abnormally high acidity of the blood).(b)
Classification. Class I (general controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 862.9.