PIXI BONE DENSITOMETER by LUNAR CORP.

The provided text is a 510(k) summary for the LUNAR PIXI Bone Densitometer. It discusses the device's technical characteristics and claims comparability to predicate devices. However, it does not include a study that defines explicit acceptance criteria and then presents results showing the device meets those criteria.

Instead, the document focuses on demonstrating that the PIXI device's performance metrics (BMD estimation correlation, in vitro precision, and in vivo precision) are "comparable" to previously cleared devices. It does not set a specific threshold or target value that the PIXI must meet to be considered acceptable.

Therefore, I cannot fulfill your request for a table of acceptance criteria and reported device performance, nor can I provide details about the study proving it meets acceptance criteria, because such information is not present in the provided text.

Here's what can be extracted based on the information given, highlighting the missing elements:

1. A table of acceptance criteria and the reported device performance

Acceptance Criteria (Not Explicitly Stated as Criteria)	Reported Device Performance
BMD Estimation Correlation	r = 0.998 (with actual density of calcium hydroxyapatite pellets)
Average Short Term Precision (%CV) In Vitro	0.68 %
Average Short Term Precision (%CV) In Vivo (Forearm)	1.5 %
Average Short Term Precision (%CV) In Vivo (Os Calcis)	1.97 %
Radiation Exposure	20 mrem (higher than predicate, but low compared to max permissible for extremities)

Missing Information:

Explicit, quantitative acceptance criteria (e.g., "BMD correlation must be > 0.99", "In vivo precision must be < 1.0%"). The document only states "correlate highly" and "comparable to those shown on previously cleared devices."

Regarding the Study and Other Details:

The provided text does not describe a specific study designed to prove the device meets acceptance criteria in the way you've outlined. It presents technical specifications and performance metrics that are stated to be "comparable" to predicate devices. Therefore, I cannot answer questions 2 through 9 definitively as that level of detail about a specific study is not available in the given text.

However, based on the inference from the text, here's what we can deduce about how the performance was likely assessed, along with a clear statement of what is missing:

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Missing: The text does not provide details on sample size, data provenance, or whether the study for these precision and correlation figures was retrospective or prospective.
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)
- Missing: This information is not provided. The "ground truth" for BMD estimation correlation was "actual density of calcium hydroxyapatite pellets," which wouldn't involve human experts in the typical clinical assessment sense. For in vivo precision, the "ground truth" is typically the repeated measurements from the device itself on the same individual.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Missing: Not applicable as the data presented (correlation, precision) does not appear to involve an adjudication process as described.
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
- Missing/Not Applicable: This is a bone densitometer, an imaging device that measures BMD, not an AI-assisted diagnostic tool that human readers would interpret. Therefore, an MRMC study related to human reader improvement with AI is not relevant to this device's context.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Partially Applicable: The performance metrics (correlation, precision) are inherent to the device itself. While a human technologist operates it, the results presented are "standalone" in the sense that they reflect the device's measurement capabilities.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- For BMD estimation correlation: "actual density of calcium hydroxyapatite pellets." This is a phantom/calibration standard-based ground truth.
- For In vitro/In vivo precision: The ground truth is the consistency of the device's own measurements on repeated scans.
8. The sample size for the training set
- Missing: The text does not mention a "training set" as it would for a machine learning algorithm. This device is a densitometer, not a learning algorithm that requires training data in that sense.
9. How the ground truth for the training set was established
- Missing/Not Applicable: As above, this concept doesn't directly apply to this type of device. The device's calibration and accuracy would be established through physical standards and known-density phantoms.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the word "LUNAR" in large, bold, black letters. The font is sans-serif and appears to be a blocky, slightly rounded style. The letters are closely spaced, creating a solid, impactful visual. The background is plain white, which makes the word stand out.

APR 1 6 1997

313 W. BELTLINE HIGHWAY

MADISON, WI 53713

(608) 274-2663

K970224

510(k) SUMMARY OF SAFETY AND EFFECTIVENESS 10.0

This summary of safety and effectiveness information is submitted in accordance with the requirements of 21 CFR 807.92(c).

Contact Person:	Kenneth D. BurokerLUNAR Corporation313 West Beltline HighwayMadison, WI 53713
Phone:	(608) 288-6460
Fax:	(608) 274-0853
Date:	January 17, 1997
Device/Trade Name:	PIXI Bone Densitometer
Common Name:	Bone Densitometer
Classification Name:	Bone Densitometer21CFR 892.1170
Predicate Device:	Osteon Osteoanalyzer510 (k) K891582Norland pDEXA

DESCRIPTION OF THE DEVICE: 10.1

The PIXI Bone provides an estimation of Bone Mineral Density (BMD in g/cm2) for the regions of the forearm and heel (os calcis).

SUMMARY OF TECHNICAL CHARACTERISTICS 10.2

The PIXI® Bone Densitometer requires a 5 second exposure, with a total exposure dose of 20 mrem. The radiation exposure of 20 mrem is higher than that for the predicate devices but remains low compared to the maximum permissible dose for extremities. The BMD estimations correlate highly (r= 0.998 ) with the actual density of calcium hydroxyapatite pellets. The average short term precision (%CV) in vitro was 0.68 %. The average short term precision (%CV) in vivo is 1.5% for forearm BMD, and 1.97 % for Os Calcis BMD. These values are comparable to those shown on previously cleared devices.

{1}------------------------------------------------

CONCLUSION 10.3

The results from the PIXI bone densitometer are comparable to previously registered devices which demonstrate similar precision. No new safety and effectiveness questions are raised with the PIXI Bone Densitometer

Signed Kenneth D. Buroker ___________________________________________________________________________________________________________________________________________________________ Printed Name Director, Regulatory Affairs ... . . . . Title ,144

Summary of Safety, Effectiveness Page 2 of 2

Regulation Number and Section

§ 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.