(173 days)
Femoral neck BMD and clinical risk factors are used to estimate the patient's 10year risk of hip fracture and 10-year risk of fracture using the World Health Organization (WHO) algorithm (FRAX™). The physician may use the 10-year percent probability of fracture, along with the physician's knowledge of patient history, and apply medical expertise and best practice clinical judgment po the obtained 10-year percent probability results to determine if therapeutic intervention is necessary.
Software option for Bone Densitometers
The provided document, Koro7// Hologic: 10-year Fracture Risk Questionnaire Option 510(k) Premarket Notification, is a 510(k) summary for a software option for bone densitometers. It focuses on demonstrating substantial equivalence to predicate devices rather than providing detailed acceptance criteria and a study report as typically found in a clinical trial or performance study.
Therefore, many of the requested elements regarding acceptance criteria, study design, sample sizes, expert qualifications, and ground truth establishment are not present in this type of regulatory submission. The 510(k) process primarily relies on demonstrating that a new device is as safe and effective as a legally marketed predicate device, often without requiring new clinical performance studies if substantial equivalence can be shown through other means (e.g., comparison of technical characteristics, performance claims).
Based on the provided text, here's what can be extracted and what is not available:
1. Table of Acceptance Criteria and Reported Device Performance
Not explicitly provided in the 510(k) summary.
A 510(k) summary typically focuses on substantial equivalence to a predicate device rather than detailing specific performance acceptance criteria and a comprehensive study report with quantitative results. The submission states: "The Hologic 10-year Fracture Risk Questionnaire option is substantially equivalent to the presently marketed predicate devices... and no new safety or efficacy questions are raised." This statement itself implies that the device's performance is deemed acceptable because it is equivalent to approved devices.
The "performance" described is that the software uses "Femoral neck BMD and clinical risk factors... to estimate the patient's 10-year risk of hip fracture and 10-year risk of fracture using the World Health Organization (WHO) algorithm (FRAX™)." The acceptance is that it correctly implements this established algorithm.
2. Sample size used for the test set and the data provenance
Not provided. This information would typically be found in a detailed performance study report, which is not part of this 510(k) summary. The FRAX™ algorithm itself was developed and validated on various cohorts, but this submission is about the software's implementation of that algorithm, not a re-validation of FRAX™.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable/Not provided. This device implements an existing algorithm (FRAX™). The "ground truth" for the algorithm itself would have been established during its development and validation by the WHO, likely involving extensive epidemiological studies and expert consensus. For this 510(k), the "truth" is the correct implementation of the algorithm.
4. Adjudication method for the test set
Not applicable/Not provided. No explicit test set or adjudication method is described in this 510(k) summary.
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
Not applicable/Not provided. This device is a software option that calculates fracture risk using an existing algorithm. It does not involve "human readers" interpreting images assisted by AI in the traditional sense of an MRMC study. The output is a risk score for a physician to use, not an AI-assisted diagnostic read.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, implicitly. The device itself is a standalone algorithm that calculates the 10-year fracture risk based on input data (Femoral neck BMD and clinical risk factors). The output is a quantitative risk percentage. The submission states, "The physician may use the 10-year percent probability of fracture...to determine if therapeutic intervention is necessary." This indicates the algorithm provides its output independently, which is then used by a human. The "performance" of the algorithm is its accurate calculation of the FRAX™ score, but the 510(k) does not include a detailed "standalone performance study" report.
7. The type of ground truth used
Algorithm-based calculation. The "ground truth" for this device's performance is the accurate implementation and calculation of the 10-year fracture risk according to the "World Health Organization (WHO) algorithm (FRAX™)". The FRAX™ algorithm itself was developed based on extensive epidemiological data and patient outcomes to predict fracture risk. For the regulatory approval of this software option, the ground truth would be that the software correctly computes the FRAX™ score given appropriate inputs, consistent with how the original FRAX™ tool would calculate it.
8. The sample size for the training set
Not applicable/Not provided. This device implements an existing, published algorithm (FRAX™). It's not a machine learning model requiring a new training set. The "development" data for the FRAX™ algorithm itself would have involved large, multi-national cohorts, but that's distinct from this specific device's approval process.
9. How the ground truth for the training set was established
Not applicable/Not provided. As stated above, this is about implementing an existing algorithm, not training a new model. The ground truth for the FRAX™ algorithm's development was established through longitudinal studies observing fracture outcomes in large populations.
§ 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.