(15 days)
The Neonatal Bilirubin assay is used for the quantitation of bilirubin in human neonate serum or plasma. Measurements of bilirubin (total and unbound) in newborn infants are used to aid in indicating the risk of bilirubin encephalopathy (kernicterus).
Neonatal Bilirubin is an in vitro diagnostic assay for the quantitative determination of bilirubin in human neonate serum or plasma. The Neonatal Bilirubin assay is a clinical chemistry assay which uses a differential wavelength method. The absorbance of bilirubin, measured at 444 and 548 nm, is directly proportional to the bilirubin concentration in serum or plasma. Measurement at a secondary wavelength (548 nm) is used to correct for any hemoglobin present in the sample.
The provided 510(k) summary describes a new in vitro diagnostic assay, Neonatal Bilirubin, and demonstrates its substantial equivalence to a previously cleared device, the A-GENT® Neonatal Bilirubin assay (K880743). The study is entirely focused on chemical assay performance rather than AI/ML algorithms. Therefore, many of the requested categories related to AI/ML device studies (such as MRMC, human readers, ground truth methodology involving experts, and training/test set sample sizes in the context of imaging) are not applicable.
Here's an analysis of the available information:
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria are implied by the comparison to the predicate device, K880743, demonstrating "substantially equivalent" performance. The specific quantitative acceptance criteria for each performance characteristic are not explicitly stated as numerical cut-offs but are indicated by "acceptable correlation" and "similar" results to the predicate.
| Performance Characteristic | Acceptance Criteria (Implied) | Reported Device Performance (Neonatal Bilirubin Assay) |
|---|---|---|
| Correlation Coefficient | Acceptable correlation with predicate (K880743) | 0.9995 (vs. K880743) |
| Slope | Acceptable (vs. K880743) | 0.941 (vs. K880743) |
| Y-intercept | Acceptable (vs. K880743) | 0.275 mg/dL (vs. K880743) |
| Total %CV (Level 1) | Acceptable precision | 3.3% |
| Total %CV (Level 2) | Acceptable precision | 3.5% |
| Linearity | Linear across relevant range | Up to 51.11 mg/dL |
| Limit of Quantitation (Sensitivity) | Appropriate for intended use | 0.04 mg/dL |
| Assay Range | Similar to predicate | Minor difference from predicate |
2. Sample Size for Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated for the "comparative performance studies." The document mentions "two levels of control material" for precision studies but does not specify the number of samples or replicates.
- Data Provenance: Not specified (e.g., country of origin, retrospective or prospective).
3. Number of Experts Used to Establish Ground Truth and Qualifications
- N/A. This is a chemical assay, and the "ground truth" for the comparative study is the performance of the predicate device (K880743) on clinical samples. No expert adjudication or interpretation of images/clinical scenarios is involved.
4. Adjudication Method for the Test Set
- N/A. As this is a chemical assay, there is no need for expert adjudication. The comparison is between the quantitative results of the new device and the predicate device.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No. An MRMC study is not applicable for this type of in vitro diagnostic device, which is a quantitative chemical assay. It does not involve human readers interpreting clinical cases with or without AI assistance.
6. Standalone (Algorithm Only) Performance Study
- Yes, in the context of an in vitro diagnostic assay. The "Performance Characteristics" section details the standalone performance of the Neonatal Bilirubin assay itself (precision, linearity, limit of quantitation) and its correlation with the predicate device. There is no "human-in-the-loop" for this type of device's core function (quantitative measurement).
7. Type of Ground Truth Used
- Reference device performance / Clinical results. The "ground truth" for the comparative study is the quantitative results obtained from the predicate device, A-GENT® Neonatal Bilirubin assay, on the ABBOTT SPECTRUM Series II™ System. For precision, linearity, and sensitivity, the "ground truth" is the expected chemical behavior and analytical performance of the assay itself, verified through laboratory testing.
8. Sample Size for the Training Set
- N/A. This is not an AI/ML device that requires a training set in the typical sense. Development of a chemical assay involves extensive R&D and optimization, but not "training data" for an algorithm.
9. How Ground Truth for the Training Set Was Established
- N/A. See point 8.
§ 862.1113 Bilirubin (total and unbound) in the neonate test system.
(a)
Identification. A bilirubin (total and unbound) in the neonate test system is a device intended to measure the levels of bilirubin (total and unbound) in the blood (serum) of newborn infants to aid in indicating the risk of bilirubin encephalopathy (kernicterus).(b)
Classification. Class I.