(137 days)
The bone density estimates from the SXA 3000™ can be used as an aid to physicians in determining fracture risk, based on their comparison to estimates for people without bone related disease, who have the same gender and ethnic background as the patient.
The Norland OsteoAnalyzerTM Model SXA 3000TM X-Ray Bone Densitometer (SXA 3000TM) can be used whenever it is desirable to do a bone assessment of the os calcis (heel). Bone assessments are of interest in many medical disciplines such as nephrology, endocrinology, rheumatology, gynecology, etc. The SXA 3000TM scans the heel using the industry standard SXA pencil beam technology and provides BMC, Area, BMD, T-Score, and Z-Score values. A scan takes about three minutes and the patient dose is less than 1.5 mRem. The SXA 3000TM provides fracture risk assessment based on the World Health Organization (WHO) criteria for relating the bone density test to fracture risk assessment and disease diagnosis. In general, this assessment states that patients with T-Scores from +1 to -1 are considered to be normal; T-Scores from -1 to -2.5 are considered to have low bone mass and an increased risk of fracture; and T-Scores below -2.5 are considered to be osteoporotic with a high risk of fracture.
The provided text describes a 510(k) summary for a "Fracture Risk Assessment Capability for the Norland SXA 3000™ Bone Densitometer." However, it does not contain information about specific acceptance criteria, a study proving device performance against those criteria, sample sizes for test/training sets, expert qualifications, or adjudication methods. Instead, it focuses on the device's description, classification, and regulatory approval based on substantial equivalence to a predicate device.
The core of the document, the "510k Summary," primarily outlines the device's intended use and claim of "Safety and Effectiveness" by stating: "This Fracture Risk Assessment Capability for the SXA 3000™ is comparable to fracture risk assessment capabilities in use with other bone densitometers in the industry. No new safety or effectiveness issues are raised with this capability." This indicates a reliance on the existing regulatory framework for bone densitometers and the predicate device (K973104), rather than a specific de novo study with acceptance criteria and performance metrics described in typical AI/ML device submissions.
Therefore, most of the requested information cannot be extracted from this document.
Here's a breakdown of what can and cannot be answered based on the provided text:
1. A table of acceptance criteria and the reported device performance
- Cannot be provided. The document does not specify quantitative acceptance criteria or report specific performance metrics for the device. The claim for "Safety and Effectiveness" is based on comparability to predicate devices, not on meeting predefined performance thresholds in a distinct study.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Cannot be provided. The document does not describe a test set or any study involving patient data to validate the device's performance. The approval is based on substantial equivalence.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
- Cannot be provided. No test set or ground truth establishment process is described in the document.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Cannot be provided. No test set or adjudication process is described in the document.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- Cannot be provided. This device is a bone densitometer providing quantitative measurements (T-Scores, Z-Scores), not an AI-assisted diagnostic tool that would typically involve human reader improvement studies. The document does not describe any MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- The device itself is a standalone measurement device. The "Fracture Risk Assessment Capability" for the SXA 3000™ Bone Densitometer functions by providing T-Scores and Z-Scores based on bone density measurements, which are then interpreted by clinicians according to WHO criteria. It's an algorithm embedded in the device to calculate these scores, and its "performance" is implicitly tied to the accuracy and precision of the underlying bone density measurement, which is not detailed here in terms of a standalone study. However, it's not an AI algorithm in the contemporary sense that would have a "standalone performance" study against a human baseline for interpretation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Cannot be explicitly provided from the document. The device outputs T-Scores and Z-Scores, which are compared against "estimates for people without bone related disease." The ground truth for these reference populations is implicitly established by epidemiological studies and clinical consensus, as reflected in the WHO criteria mentioned. However, the document does not detail how the ground truth was established for "testing" this specific device's fracture risk assessment capability.
8. The sample size for the training set
- Cannot be provided. The document does not describe a training set for an algorithm in the context of AI/ML. The device's calculations are based on established physical principles of X-ray attenuation and statistical models for T-Scores/Z-Scores derived from reference populations.
9. How the ground truth for the training set was established
- Cannot be provided. As above, no training set is described in the context of AI/ML. The "ground truth" for the reference data used to define T-scores and Z-scores would be established through large-scale population studies that measure bone mineral density in healthy individuals, often with age, gender, and ethnicity stratification, as referenced by the mention of WHO criteria.
Essentially, this 510(k) summary is from 1998, predating much of the modern regulatory framework and expectations for AI/ML device submissions, which typically involve detailed performance studies. Its approval is based on substantial equivalence to an existing (predicate) device, making most of the requested performance-study-specific details inapplicable or not available within this document.
§ 892.1170 Bone densitometer.
(a)
Identification. A bone densitometer is a device intended for medical purposes to measure bone density and mineral content by x-ray or gamma ray transmission measurements through the bone and adjacent tissues. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.