(122 days)
Lumipulse® G Risk of Ovarian Malignancy Algorithm (ROMA®) is a qualitative serum and plasma (lithium heparin or dipotassium EDTA) test that combines the results of Lumipulse G CA 1251 and menopausal status into a numerical score.
Lumipulse G ROMA is intended to aid in assessing whether a premenopausal woman who presents with an ovarian adnexal mass is at high or low likelihood of finding malignancy on surgery. Lumipulse G ROMA is indicated for women who meet the following criteria: over age 18; ovarian adnexal mass present for which surgery is planned, and not yet referred to an oncologist. Lumipulse G ROMA must be interpreted in conjunction with an independent clinical and radiological assessment. The test is not intended as a screening or stand-alone diagnostic assay.
PRECAUTION: Lumipulse G ROMA should not be used without an independent clinical /radiological evaluation and is not intended to be a screening test or to determine whether a patient should proceed to surgery. Incorrect use of Lumipulse G ROMA carries the risk of unnecessary testing, surgery, and/or delayed diagnosis.
Lumipulse GROMA is a qualitative serum and plasma test that combines the results of 2 analytes, HE4 (Lumipulse G HE4) and CA125 (Lumipulse G CA 125 II) and menopausal status into a numerical score between 0.00 and 10.00. The premenopausal status must be based on ovarian function determined with information available from clinical evaluation and medical history.
The test system consists of Lumipulse G HE4, Lumipulse G CA 125 II, the Lumipulse G ROMA Calculator Tool and the LUMIPULSE G1200 System. The LUMIPULSE G1200 System is not capable of calculating the ROMA score. The immunoassays are performed according to the directions detailed in each product insert.
Both Lumipulse G HE4 and Lumipulse G CA 125 Il are previously 510(k) cleared Class II devices (K151378 and K142895 respectively). The Lumipulse G HE4 assay is a chemiluminescent enzyme immunoassay (CLEIA) for the quantitative determination of HE4 antigen in human serum and plasma (lithium heparin or dipotassium EDTA) on the LUMIPULSE G System. The assay is to be used as an aid in monitoring recurrence or progressive disease in patients with epithelial ovarian cancer. Serial testing for patient HE4 assay values should be used in conjunction with other clinical methods used for monitoring ovarian cancer. Lumipulse G CA 125 II assay is a chemiluminescent enzyme immunoassay (CLEIA) for the quantitative determination of CA125 in human serum and plasma (sodium heparin, lithium heparin, or dipotassium EDTA) on the LUMPULSE G System. The assay is to be used as an aid in monitoring recurrence or progressive disease in patients with ovarian cancer. Serial testing for patient CA125 assay values should be used in conjunction with other clinical methods used for monitoring ovarian cancer.
Lumipulse G ROMA scores (numerical score from 0.00 -10.00) for both premenopausal and postmenopausal women are calculated using the Lumipulse G ROMA Calculator Tool to indicate a low likelihood or high likelihood for finding malignancy on surgery using the value of the 2 immunoassays (Lumipulse G HE4 and Lumipulse G CA125II).
Here’s a summary of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) submission for Lumipulse G ROMA:
1. Table of Acceptance Criteria and Reported Device Performance
The submission does not explicitly state "acceptance criteria" in a quantitative manner for clinical performance in the way usually seen for AI/ML devices (e.g., minimum sensitivity or specificity targets). Instead, it demonstrates substantial equivalence to a predicate device and provides performance metrics (sensitivity, specificity, PPV, NPV) for direct disease detection and adjunctive use with Initial Cancer Risk Assessment (ICRA).
Given that the purpose of the submission is to demonstrate "substantial equivalence" to a predicate device, the implied acceptance criterion for clinical performance is that the Lumipulse G ROMA's performance should be comparable or non-inferior to the predicate device and demonstrate utility for its intended use. For analytical performance, the acceptance criteria are typically met by demonstrating acceptable precision, linearity, analytical specificity, and method comparison to the predicate. The clinical study results presented are the "reported device performance."
| Category | Acceptance Criteria (Implied / Demonstrated) | Reported Device Performance (Lumipulse G ROMA) |
|---|---|---|
| Clinical Performance | Substantial Equivalence to Predicate (ROMA (HE4 EIA + ARCHITECT CA 125 II)) and Utility for Intended Use: To demonstrate aid in assessing high or low likelihood of malignancy in ovarian adnexal mass for pre/postmenopausal women, with acceptable sensitivity, specificity, PPV, and NPV. | For Stratification into High/Low Likelihood of Malignancy (EOC only): |
| Premenopausal: Sensitivity 100.0% (9/9), Specificity 74.9% (167/223), PPV 13.8% (9/65), NPV 100.0% (167/167) | ||
| Postmenopausal: Sensitivity 92.1% (35/38), Specificity 77.6% (111/143), PPV 52.2% (35/67), NPV 97.4% (111/114) |
Adjunctive Use with ICRA (All Malignancies & LMP):
Combined Premenopausal & Postmenopausal: Sensitivity 88.1%, Specificity 67.5%, PPV 38.3%, NPV 96.1%
(Statistically significant improvement in NPV from 93.1% (ICRA alone) to 96.1% (Adjunctive)). |
| Method Comparison | Strong correlation with the predicate device for both premenopausal and postmenopausal women. | Premenopausal Women (n=53): Correlation Coefficient (r) = 0.9977, Intercept (-0.004), Slope (1.005)
Postmenopausal Women (n=115): Correlation Coefficient (r) = 0.9953, Intercept (-0.103), Slope (0.999) |
| Matrix Comparison | Equivalence between serum and K2 EDTA plasma samples. | Premenopausal (n=86): y= 1.001(x) - 0.072; r=0.9983
Postmenopausal (n=86): y= 1.004(x) - 0.058; r=0.9988 |
| Precision (Lot-to-Lot)| Acceptable %CV for ROMA scores across different lots. | Overall Total %CV for Premenopausal ROMA: 4.6% (Panel 1) to 0.0% (Panel 6)
Overall Total %CV for Postmenopausal ROMA: 2.4% (Panel 1) to 0.1% (Panel 6) |
| Reproducibility (Site-to-Site) | Acceptable %CV for ROMA scores across different sites. | Overall Total %CV for Premenopausal ROMA: 8.1% (Panel 1) to 0.1% (Panel 6)
Overall Total %CV for Postmenopausal ROMA: 5.2% (Panel 1) to 0.2% (Panel 6) |
| Analytical Specificity| Minimal interference from common endogenous interferents. | Mean Percent (%) Difference for all tested interferents (Free Bilirubin, Conjugated Bilirubin, Triglycerides, Hemoglobin, Total Protein, Immunoglobulin G, Biotin, HAMA, Rheumatoid Factor) was within a range of -2% to +1% for both pre- and post-menopausal ROMA scores. |
2. Sample Sizes and Data Provenance for Test Set (Clinical Study)
- Sample Size: A total of 450 women were evaluable in the clinical study test set.
- Premenopausal: 244
- Postmenopausal: 206
- Data Provenance: The study was described as a prospective, multi-center, blinded clinical trial. The specific country of origin is not mentioned in the provided text.
3. Number of Experts and Qualifications for Ground Truth (Clinical Study)
- Number of Experts: Not explicitly stated as a count of individual experts.
- Qualifications: "An initial cancer risk assessment (ICRA) was completed by a non-gynecological oncologist". The specific years of experience or board certifications are not provided.
- Ground Truth for Clinical Study: Histopathology reports collected after surgery were the definitive ground truth for malignancy.
4. Adjudication Method for the Test Set
- The text describes the clinical trial as "blinded," implying that those interpreting the Lumipulse G ROMA results were blinded to the initial cancer risk assessment (ICRA) and histopathology, and vice-versa for the ICRA.
- Adjudication Method: Not explicitly detailed beyond the "blinded" nature and the use of histopathology as the definitive truth. There is no mention of a 2+1 or 3+1 type of expert consensus for the initial clinical assessment.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The study evaluated the adjunctive use of Lumipulse G ROMA with Initial Cancer Risk Assessment (ICRA). This is a form of comparative effectiveness study involving human readers (non-gynecological oncologists) with and without the device.
- Effect Size (Improvement with AI vs. without AI assistance):
- The study showed a statistically significant improvement in the Negative Predictive Value (NPV) when Lumipulse G ROMA was used adjunctively with ICRA.
- NPV for classifying benign patients into the low likelihood group increased from 93.1% (ICRA alone) to 96.1% (Adjunctive). This represents a 3% absolute increase in NPV.
- Other metrics for adjunctive use compared to ICRA alone:
- Sensitivity increased from 72.6% to 88.1%
- Specificity decreased from 84.2% to 67.5%
- PPV decreased from 51.3% to 38.3%
6. Standalone (Algorithm Only) Performance
- Yes, a standalone performance was done. The sections titled "Use of Lumipulse G ROMA for stratification into low likelihood and high likelihood groups for finding malignancy on surgery" and "The performance of Lumipulse G ROMA for stratification into low likelihood and high likelihood groups for premenopausal and postmenopausal women with epithelial ovarian cancer (EOC) only" directly present the performance of the Lumipulse G ROMA algorithm in isolation.
- The results are presented for premenopausal and postmenopausal women separately, and for all cancer and LMP tumors combined.
7. Type of Ground Truth Used
- For the clinical study, the definitive ground truth was histopathology reports collected after surgery. This is considered a high-quality, objective ground truth.
8. Sample Size for the Training Set
- The submission does not explicitly mention a separate training set for the Lumipulse G ROMA algorithm itself.
- The ROMA algorithm's equation (Predictive Index for premenopausal and postmenopausal women) and clinical cut-offs (1.31 and 2.77) are identical to the predicate device (ROMA (HE4 EIA + ARCHITECT CA 125 II) K103358). This suggests that the algorithm itself was likely developed and validated previously, and this submission focuses on the performance of the Lumipulse G HE4 and Lumipulse G CA125II assays within the established ROMA framework. The provided study serves as a clinical validation for the proposed device using these specific assays.
9. How the Ground Truth for the Training Set Was Established
- Given that the algorithm and its cut-offs appear to be directly adopted from the predicate device and its previous development, the specific details of how the original training set for the ROMA algorithm's ground truth was established are not provided in this document.
- For the assays themselves (Lumipulse G HE4 and CA125II), which are previously cleared devices, their calibration and standardization would have been established against reference materials, but this isn't a "training set" for the algorithm.
§ 866.6050 Ovarian adnexal mass assessment score test system.
(a)
Identification. An ovarian/adnexal mass assessment test system is a device that measures one or more proteins in serum or plasma. It yields a single result for the likelihood that an adnexal pelvic mass in a woman, for whom surgery is planned, is malignant. The test is for adjunctive use, in the context of a negative primary clinical and radiological evaluation, to augment the identification of patients whose gynecologic surgery requires oncology expertise and resources.(b)
Classification. Class II (special controls). The special control for this device is FDA's guidance document entitled “Class II Special Controls Guidance Document: Ovarian Adnexal Mass Assessment Score Test System.” For the availability of this guidance document,see § 866.1(e).(c)
Black box warning. Under section 520(e) of the Federal Food, Drug, and Cosmetic Act these devices are subject to the following restriction: A warning statement must be placed in a black box and must appear in all advertising, labeling, and promotional material for these devices. That warning statement must read: