(179 days)
hipEOS software is indicated to be used for assisting healthcare professionals in preoperative planning of total hip arthroplasty (THA). The software allows for overlaying of 3D/2D hip implant models on radiological images or 3D reconstruction of bone, and includes tools for performing measurements on the image or 3D model of bones and for selecting and positioning the hip implant models. Clinical judgments and experience are required to properly use the software.
hipEOS 3.0 allows surgeons to perform preoperative surgical planning of hip surgeries in case of Total Hip Arthroplasty (THA). The software provides surgical tools for the implantation of a Total Hip Prosthesis. This software can be used to plan interventions using implants from different manufacturers. The images displayed are x-rays from EOS System (EOS Imaging) and 3D model of the hip from sterEOS Workstation (EOS Imaging), hipEOS also displays preoperative parameters and updated values of parameters after planning. It exports a planning report containing the planning parameters: model, size and position of implants. hipEOS is accessible on any computer via ONEFIT Management System (Class I device -Product code LMD - 510(k) Exempt) that provides a secure internet interface and storage through authentication mechanisms.
The provided text does not contain detailed acceptance criteria or a comprehensive study report with the requested specifications. The "Performance Data" section merely states that "Software verification and validation testing were conducted and documentation was provided," and the software was deemed a "moderate" level of concern. It does not elaborate on the specific acceptance criteria, performance metrics, or the study design.
Therefore, I cannot fulfill your request for the information outlined in bullet points 1 through 9 based solely on the provided text. The document is a 510(k) summary, which typically provides a high-level overview rather than a detailed scientific study report.
To answer your request, I would need a more detailed performance study report or verification and validation documentation for the hipEOS 3.0 device.
Here's what I can extract from the provided text, and where information is missing:
1. A table of acceptance criteria and the reported device performance
- Missing Information: The document does not specify any quantitative acceptance criteria (e.g., accuracy thresholds, precision targets) or present a table of reported device performance against such criteria. It generally states that the device is "as safe and effective as its predicates."
2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Missing Information: The document does not mention the sample size used for any test set or provide details on data provenance (country of origin, retrospective/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 Information: The document does not describe how ground truth was established for a test set, nor does it specify the number or qualifications of any experts involved in such a process.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Missing Information: No information is provided regarding an adjudication method for a test set.
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 Information: The document does not mention an MRMC comparative effectiveness study or any effect size related to human reader improvement with or without AI assistance. The device is for "assisting healthcare professionals" in planning, implying human-in-the-loop, but performance data for this interaction is not detailed.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Partial Information / Implication: The device is described as "assisting healthcare professionals," implying a human-in-the-loop context. However, the software performs "measurements on the image or 3D model" and "selecting and positioning the hip implant models," which are functions of the algorithm. The document doesn't explicitly state whether a standalone performance evaluation of these specific automated tasks was conducted, nor does it provide results if it was. The "Performance Data" section is generic.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- Missing Information: No information is provided on the type of ground truth used for any evaluations.
8. The sample size for the training set
- Missing Information: The document does not mention a training set or its sample size.
9. How the ground truth for the training set was established
- Missing Information: No information is provided on how ground truth was established for a training set.
§ 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).