(350 days)
Medacta MyPAO surgical planning report is intended to provide users with patient's pre-operative information and an estimation of the post-operative parameters after the realignment of the acetabulum following the osteotomy. It is intended to be used for the pre-operative planning phase of Peri-Acetabular Osteotomy surgeries and it consists of a report in .pdf format elaborated on the basis of Patient's Anatomical Data derived from the CT scan of the patient. The planning report is generated through a validated internal Medacta Manufacturing software and with a highly specialized engineering manual landmark selection.
The Medical Device, in accordance with a written prescription of the Surgeon, is intended for the specific patient for which the case is created. Medacta MyPAO surgical planning is intended to be used on a skeletally mature population for which a PAO surgery is required.
MyPAO uses the patients' CT scan to segment the patient's bones in order to provide the surgeons with a report (MyPAO Surgical Planning Report) with some parameters of interest that can be used to properly plan the peri-acetabular osteotomy (PAO) and the manual repositioning of the acetabulum during standard PAO procedures. Specifically, the MyPAO Planning Report includes all the relevant preoperative anatomic data of the patient's hip, a proposal of the repositioning of the acetabulum, following the manual osteotomy, and a calculation of the expected postoperative results in relation to the anatomical reference data.
The MyPAO Planning Report device provides pre-operative information and estimated post-operative parameters for acetabular realignment following osteotomy in Peri-Acetabular Osteotomy (PAO) surgeries. The device itself is a PDF report generated from a patient's CT scan using Medacta Manufacturing software and manual landmark selection by specialized engineers.
Here's an analysis of the acceptance criteria and study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Intra-observer variability for chosen Hip Dysplasia parameters | Intraclass Correlation Coefficients (ICC) analysis revealed excellent intra-observer agreement (> 0.9 for both parameters, with 95% CI > 0.9). All differences between paired measurements were less than ±5°. |
| Inter-observer variability for chosen Hip Dysplasia parameters | Intraclass Correlation Coefficients (ICC) analysis revealed excellent inter-observer agreement (> 0.9 for both parameters, with 95% CI > 0.9). All differences between paired measurements were less than ±5°. |
| All test results met established acceptance criteria. | All stated performance measures met the criteria. |
2. Sample Size for Test Set and Data Provenance
- Sample Size: The document states "different PAO cases" were used for the measurements repeatability test but does not specify the exact number of cases.
- Data Provenance: Not explicitly stated. However, given it's for pre-operative planning, it would imply patient CT scans. The document does not mention the country of origin or if it was retrospective or prospective data.
3. Number of Experts and Qualifications for Ground Truth
- Number of Experts: The study did not use "experts" to establish ground truth in the traditional sense of independent clinical review. Instead, human operators performed the measurements. The study evaluated the repeatability of these measurements done by Medacta operators.
- Qualifications of Experts: The measurements were performed by "Medacta operators who have been specifically trained for this purpose." No further details on their specific qualifications (e.g., years of experience, professional certifications) are provided.
4. Adjudication Method for the Test Set
- Adjudication Method: Not applicable in the context of this study. The study focused on the intra- and inter-observer agreement of measurements made by operators, rather than an adjudication of a device output against a reference standard established by multiple experts. The "ground truth" was effectively the measurements themselves, and the variability was assessed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study: No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted. The study evaluated the consistency of measurements made by operators using the MyPAO software, not the effectiveness of the AI or assistance for human readers in a diagnostic capacity.
6. Standalone Performance Study (Algorithm only without human-in-the-loop performance)
- Standalone Performance Study: The MyPAO Planning Report is not a standalone AI algorithm in the traditional sense. The report generation involves "a highly specialized engineering manual landmark selection" by trained Medacta operators. Therefore, the performance described (repeatability of measurements) inherently includes human-in-the-loop interaction. There's no mention of an algorithm-only performance evaluation separate from human input.
7. Type of Ground Truth Used
- Type of Ground Truth: The "ground truth" for the repeatability study was not an independent clinical gold standard like pathology or outcome data. Instead, it was the measurements of two specific parameters relevant to Hip Dysplasia, as performed by trained Medacta operators using the MyPAO software. The study aimed to show the consistency (repeatability) of these measurements.
8. Sample Size for the Training Set
- Sample Size: The document does not provide any information regarding the sample size used for the training set of the validated internal Medacta Manufacturing software.
9. How the Ground Truth for the Training Set was Established
- Ground Truth for Training Set: The document does not describe how the ground truth for the training set (if any, for the "validated internal Medacta Manufacturing software") was established. It only mentions that the report is "elaborated on the basis of Patient's Anatomical Data derived from the CT scan of the patient" and generated through "a validated internal Medacta Manufacturing software and with a highly specialized engineering manual landmark selection." This implies that the 'validation' might refer to internal company processes rather than external ground-truth establishment.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).