(89 days)
The KKT device is to be used in the aid of management of chronic pain due to non-congenital defects. The device can be used as part of a series of steps in the patient. The procedure involves the use of diagnostic imaging that quantifies the misalignment of vertebrae. The treatment is then administered using the KKT device to deliver impulses at a precise vector. Spinalytics is a software application which facilitates treatment using the KKT device.
Spinalytics provides an interface to manage the patient information stored in a central database. Spinalytics facilitates measuring angles and distances of relevant sketal structures in a patient, by providing the practitioner with an interface to mark the position of these structures directly on digitized X-Rays. Spinalytics then calculates standard treatment protocol parameters which can be sent directly to the KKT device. Spinalytics is an optional accessory to the KKT device and does not change the intended use of the device.
Spinalytics Application is an optional software accessory to the KKT device which facilitates the calculation of the treatment parameters, which were previously calculated manually. Qualified personnel may generate, review, verify, approve, print and export the treatment plan prior to patient treatment. Spinalytics Application also communicates directly with the KKT Device to seamlessly enter the treatment parameters into the device. The clinicians may still enter their own parameters in the Spinalytics Application which meet their own treatment and clinical protocols, if they choose.
The Spinalytics Application software is installed on a computer near the KKT Device. It can be installed on any commercial grade PC that meets the minimum hardware and operating system requirements. The computer and the KKT Device communicate over a USB cable.
Here's a breakdown of the requested information based on the provided text, focusing on the acceptance criteria and the study that proves the device meets those criteria:
1. Table of Acceptance Criteria and Reported Device Performance
The provided text does not explicitly define a table of specific numerical acceptance criteria (e.g., minimum accuracy percentages, sensitivity, specificity) for the Spinalytics software's performance in measuring angles and distances. Instead, the acceptance is broadly stated in terms of meeting software specifications and passing validation.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Device performs as intended according to Software Design Specifications. | "The software was tested against the established Software Design Specifications for each of the test plans to assure the device performs as intended. The testing results support that all the software specifications have met the acceptance criteria of each module and interaction of processes." |
| Data calculations are verified as correct. | "software validation testing has been conducted to verify data calculations." |
| Accurate information for a specific patient/X-ray. | "software testing has been conducted to verify correct information for a specific patient/X-ray." |
| All software specifications met. | "The testing results support that all the software specifications have met the acceptance criteria of each module and interaction of processes." |
| Safe operation. | "The Spinalytics device passed all testing and supports the claims of substantial equivalence and safe operation." |
| Hazard analysis completed and risks mitigated. | "The device Hazard analysis was completed, and risk control implemented to mitigate identified hazards." |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: The document does not specify a numerical sample size for the test set used in the software verification and validation. It broadly mentions "specific patient/X-ray" data without quantifying the number of patients or X-rays.
- Data Provenance: Not explicitly stated. The nature of the device (measuring angles/distances on X-rays) suggests the data would be X-ray images, but their origin (country, retrospective/prospective collection) is not mentioned.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
The document does not explicitly state the number of experts used or their qualifications for establishing ground truth for the test set. It mentions that the software facilitates measurements that were "previously calculated manually" or information "inputted by the physician," but it doesn't describe an expert-led ground truth establishment process for the validation.
4. Adjudication Method for the Test Set
The document does not describe any formal adjudication method (e.g., 2+1, 3+1) used for the test set. The focus is on software verification and validation against design specifications and calculations.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not reported or performed. The document states: "There was no human clinical testing required to support the medical device as the indications for use is equivalent to the predicate device."
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
The evaluation described is essentially a standalone (algorithm only) performance study, focusing on the software's ability to accurately calculate parameters based on user input. The software "facilitates measuring angles and distances" by "providing the practitioner with an interface to mark the position of these structures directly on digitized X-Rays." This means the algorithm's performance is on the calculation after a human marks the points. The validation was conducted to "verify data calculations" and ensure "correct information for a specific patient/X-ray" based on these calculations.
7. Type of Ground Truth Used
The ground truth for the device's performance appears to be expert-defined manual calculations/measurements and established software design specifications. The software is validated to generate "correct information" and "verify data calculations," implying comparison to what would be considered correct through manual analysis or pre-defined rules. The text mentions that the software automates calculations that were "previously calculated manually."
8. Sample Size for the Training Set
The document does not provide any information about a training set or its sample size. This is typical for a rule-based or calculation-based software accessory that does not employ machine learning models requiring a specific training phase.
9. How the Ground Truth for the Training Set Was Established
Since no training set is mentioned (as the software appears to be calculation-based rather than machine learning), this question is not applicable.
N/A