(210 days)
The StealthConnect® System is web-based software to remotely access the StealthStation® Cranial software for viewing, stereotactic surgery planning and collaborating by trained professionals such as physicians, technologists and nurses.
The StealthConnect® system has not been validated for primary diagnostic reading of Digital Imaging and Communications in Medicine (DICOM) images.
The StealthConnect® Remote Viewing, Planning and Collaboration System is an accessory to the StealthStation® System. It provides a web- based client interface to securely access encrypted storage of DICOM-compliant images via a LAN, and/or the internet using general-purpose computers, and by one or more authorized people. It provides for communication, storage, reformating, and display of DICOM 3.0 compliant image data derived from various sources including CT and MRI. In addition, the system provides access to the surgical planning aspects of StealthStation® software, and can be used to set or review surgical plans for stereotactic surgeries that are compatible with and can be transferred to a StealthStation® System or any DICOM-compliant PACS system.
StealthConnect® is not to be used for mammography.
The StealthConnect™ System enables web clients on users' computers to interact with a version of the existing StealthStation Cranial planning software that is running on a cloud-based server. The StealthConnect System enables Secure remote access for one or more authorized users simultaneously, with each accessing different patients (multi-user concurrent planning sessions) via the server-based cranial software using a web browser on user-supplied, general-purpose client computers. A safe environment to access, control, and share images on a secure Health Insurance Portability and Accountability Act (HIPAA) and Health Information Technology for Economic and Clinical Health Act (HITECH) compliance-ready infrastructure. Authorization and access control, which is provided by integration with the user facility's Lightweight Directory Access Protocol (LDAP) or Windows Active Directory (AD) credentialing system (single sign on).
The Medtronic StealthConnect Remote Viewing, Planning and Collaboration System is a web-based software designed to remotely access the StealthStation Cranial software for viewing, stereotactic surgery planning, and collaboration by trained professionals.
Here's the breakdown of the acceptance criteria and the study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance:
The document primarily focuses on establishing substantial equivalence to predicate devices rather than defining explicit numerical acceptance criteria for a new clinical performance claim. Instead, the "acceptance" is demonstrated through comparative testing against established predicate performance.
| Acceptance Criteria (Demonstrated through Equivalence) | Reported Device Performance (StealthConnect System) |
|---|---|
| Intended Use: Remote viewing, stereotactic surgery planning, and collaboration for trained professionals. Not for primary diagnostic reading or mammography. | Meets this intended use, providing remote access to StealthStation Cranial software functionalities for viewing, planning, and collaboration. Not validated for primary diagnostic reading of DICOM images and not to be used for mammography. |
| System Accuracy (for planning components): Comparable to StealthStation Cranial v 3.0. | Mean Accuracy Values: Positional Error - 1.60mm, Trajectory Error - 0.95 degrees. (These are compared against the predicate's reported 1.65mm and 0.68 degrees respectively). |
| Usability: Meets IEC 62366 requirements. | Usability Testing was conducted in accordance with IEC 62366, demonstrating that usability and human factors requirements were adequately met. |
| Software Functionality: Software and hardware requirements are met, and software performs as intended. Functional equivalence to ResolutionMD's PureWeb component. | Software Verification and Validation testing verified that software and hardware requirements are met and software performs as intended. Functional testing of the PureWeb component demonstrated equivalent functionality to the predicate. |
| Display Effectiveness: Images sufficient for the same level of stereotactic surgical planning as predicate (StealthStation with Cranial v 3.0 software). | Display Effectiveness testing showed that images provided by StealthConnect System are sufficient for the same level of stereotactic surgical planning as provided by the predicate. |
| Security/Cybersecurity: Encrypts data in transit and at rest. | Encrypts data in transit using TLS 1.2 and at rest using AES-256 with dedicated hardware key storage. |
| DICOM Compatibility: Provides communication, storage, reformatting, rendering, and display of DICOM 3.0 compliant image data. | Handles DICOM 3.0 compliant image data from various sources (CT, MRI), importing/exporting to/from its cloud-based patient database. |
| Remote Access: Capable of secure remote access. | Enables secure remote access for authorized users via a web browser, compatible with LAN and/or internet. |
| Collaboration: Supports online collaboration. | Uses PureWeb to share medical image data for online collaboration. |
| Concurrent User Sessions: Supports multiple concurrent user sessions. | Enables 5 users to simultaneously log on and access multiple patient data for stereotactic planning. |
| 2D/3D Viewing: Provides 2D and 3D viewing capabilities comparable to StealthStation Cranial v 3.0. | Provides the same 2D and 3D viewing features as Cranial v 3.0, including volume rendering and interactive controls. |
| Programming Language: Uses C++/Javascript/HTML5. | C++/Javascript/HTML5. |
| Imaging Modalities: Supports X-Ray, MR, and Nuclear Medicine based imaging. | Supports X-Ray, MR, and Nuclear Medicine based imaging. |
| Scanner Interface Technology: Network Connectivity, CD, DVD, USB, DICOM Import/Export. | Supports Network Connectivity, CD, DVD, USB, DICOM Import/Export. |
| Registration Features: Supports various registration types (Exam-to-Exam, Stereotactic Localizer, StarFix Bone Anchor). | Provides Exam-to-Exam Registration (Identity Merge, Manual Merge, Automatic Merge), Stereotactic Localizer Registration, and StarFix Bone Anchor Registration. |
| User Authorization and Authentication: Requires user authentication and log-on capabilities. | Requires user authentication and log-on capabilities, integrating with hospital credentialing systems (LDAP/AD). |
2. Sample Sizes Used for the Test Set and Data Provenance:
The document does not specify precise sample sizes (e.g., number of cases or patients) for the "test set" in the context of a typical AI/ML study. The performance testing described suggests a verification and validation approach rather than a large-scale clinical test set.
- Test Set Sample Size: Not explicitly stated as a number of cases or patients. The tests are described as "laboratory and simulated use settings."
- Data Provenance: Not explicitly stated (e.g., country of origin). Given Medtronic's presence and the FDA 510(k) submission, it is highly likely the testing was conducted in the US or under US-equivalent standards. The testing was performed in "laboratory and simulated use settings," implying synthetic or internal data, or potentially clinical data within Medtronic's environment, but not specified. The study is retrospective in nature as it is a verification and validation of a device's performance against pre-established requirements or predicate device performance, not a prospective trial to gather new efficacy data.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
The document does not mention the use of experts to establish a "ground truth" in the typical sense for a diagnostic device. The device is for planning and collaboration, not primary diagnosis. The accuracy and display effectiveness testing would likely have used quantitative measurements or comparisons against the predicate device's output, rather than expert consensus on a diagnostic outcome. For instance, the "Accuracy testing for planning components" would compare the StealthConnect's output (e.g., calculated positional/trajectory error) to the known/expected values or those of the predicate device, not against expert labels of medical conditions.
4. Adjudication Method for the Test Set:
Not applicable. Since there's no mention of expert readers assessing "ground truth" for diagnostic outcomes, there's no adjudication method described.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:
No, a MRMC comparative effectiveness study was not done. The document describes verification and validation testing, including "Display Effectiveness testing" to show sufficiency for planning, and accuracy testing comparative to the predicate, but not a study to quantify human reader improvement with AI assistance. The device is an accessory for planning and collaboration, not an AI diagnostic tool intended to assist human readers in image interpretation for primary diagnosis.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done:
Yes, in a way. The "performance testing" described (e.g., "Accuracy testing for planning components" and "Functional testing of the PureWeb component") assessed the device's functional performance independently of human interaction, as it aimed to verify that the software and its components perform as intended. However, the device's overall intended use inherently involves human interaction (professionals using it for viewing, planning, and collaboration). There isn't a direct "standalone diagnostic performance" report as typically seen for AI image analysis algorithms.
7. The Type of Ground Truth Used:
The "ground truth" for this device's performance assessment appears to be:
- Predicate Device Performance: For accuracy (e.g., positional and trajectory error) and display effectiveness, the performance was compared to the predicate StealthStation Cranial v 3.0.
- Design Requirements/Specifications: The testing was conducted to ensure the product performs "as intended according to the outlined design requirements."
- Established Industry Standards: Usability testing was conducted in accordance with IEC 62366.
- Functional Equivalence: For components like PureWeb, the "ground truth" was its known functionality as part of the ResolutionMD predicate.
There is no mention of pathology or outcomes data being used for ground truth.
8. The Sample Size for the Training Set:
Not applicable. The document describes a traditional software verification and validation process for a medical device that established substantial equivalence to predicate devices. It does not describe an AI/Machine Learning model that required a "training set." The "PureWeb component" mentioned is a primary component of a predicate device (ResolutionMD), implying it's a developed software part, not an AI model that undergoes training on data.
9. How the Ground Truth for the Training Set Was Established:
Not applicable. As stated above, there is no indication that this device developed or utilized an AI/Machine Learning model that required a training set or associated ground truth labeling.
§ 882.4560 Stereotaxic instrument.
(a)
Identification. A stereotaxic instrument is a device consisting of a rigid frame with a calibrated guide mechanism for precisely positioning probes or other devices within a patient's brain, spinal cord, or other part of the nervous system.(b)
Classification. Class II (performance standards).