(122 days)
The in-room scan application is a planning and information system the necessary functions required for planning and controlling scans of supported SIEMENS CT scanners. It allows users to work in close proximity to the scanner.
The in-room scan application runs on standard information technology hardware and software, utilizing the standard information technology operating systems and user interface. Communication and data exchange are done using special protocols.
Scan&GO is a stand-alone optional planning and information software designed to perform the necessary functions required for planning and controlling of the workflow of supported SIEMENS CT scanners. Scan&GO can be operated on a Siemens provided tablet or a commercially available tablet that meets certain minimum technical requirements. It allows users to work in close proximity to the scanner and the patient. Specifically Scan&GO allows control/display of the following software interactions via a wireless tablet that meets certain minimum requirements:
- Selection of patients
- Selection of pre-defined protocols
- Scan parameter display
- Patient table position display and gantry tilt parameter display
- Tools and instruction message area. Patient table position planning area
- Physiological data display
- Patient data display (e.g. date of birth, name)
- Display of acquired topogram and tomogram images
- Finalization of exam (close patient)
- NOTE: Scan&GO does not support storage of images. Additionally, Scan&GO cannot trigger a scan or radiation release.
The primary function of Scan&GO is to provide a simplified view of the workstation with a synchronous view of the CT scanner (i.e. functionality that occurs on the console can be viewed on the tablet and vice versa). The standard planning and information controls cleared for the respective CT scanners will also be available for those scanners.
The provided text describes Siemens' Scan&GO device and its performance, primarily focusing on its substantial equivalence to a predicate device (SOMATOM Drive, K161196) rather than presenting a standalone study with detailed acceptance criteria and performance metrics.
Based on the information, here's a breakdown of the requested points:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria in a table format for Scan&GO's performance as a diagnostic or outcome-related device (which is expected given its function as a planning and information system for CT scanners). Instead, the acceptance criteria are generally qualitative and refer to meeting software specifications, safety standards, and demonstrating substantial equivalence to the predicate device.
| Acceptance Criteria Category | Reported Device Performance (Scan&GO) |
|---|---|
| Software Specifications | All software specifications have met the acceptance criteria based on verification and validation testing. |
| Safety and Effectiveness | Demonstrated continued conformance with special controls for medical devices containing software. Risk analysis completed, risk controls implemented to mitigate identified hazards. Testing supports claims of substantial equivalence. Device labeling contains necessary cautions and warnings for safe and effective use. |
| Non-Clinical Performance | Non-clinical tests (integration and functional) were conducted. Performance data demonstrates continued conformance with special controls. Comparable to predicate device using the same test methods. |
| Conformance to Standards | Conforms to ISO 14791, IEC 62304, IEC60601, NEMA XR-25, NEMA XR-26, NEMA XR-29, 21 CFR 1020.30, and 21 CFR 1020.33 (for SW functionality only). Electrical safety (60601-2-44) conducted (e.g., SCAN&GO initializes READY STATE). |
| Cybersecurity | Conforms to Cybersecurity requirements (preventing unauthorized access, modifications, misuse, or unauthorized use of information). |
| Wireless Coexistence | Measures taken to address wireless coexistence. Testing included Co-Channel, Adjacent Channel, RF Interference, and Separation Distance/Location. Designed with dynamic frequency selection and transmission power control (802.11h). Ensured wireless communications actively transmitting without interference. |
| Clinical Use (Simulated/External) | Internal Clinical Use Test (CT scanner customer environment simulated in Siemens Test Cabins, with customers/clinical expertise). External Clinical Use Test (CT scanner tested in clinic/hospital with selected customers). All tests met pre-determined acceptance criteria. |
| Functional Equivalence to Predicate | Provides simplified view of workstation; synchronous view of CT scanner. Controls/displays similar software interactions (patient selection, protocols, scan parameters, table position, physiological data, acquired images, exam finalization). Workflow comparable to predicate device. |
| Hardware Technical Requirements | Supports detached commercially available tablets meeting certain minimum technical requirements (Windows operating platform) comparable to the predicate's affixed proprietary tablet. |
| Software Interface Compatibility | Connects to CT scanner via a mobile interface to software platform SOMARIS/10, comparable to the predicate's SOMARIS/7. No impact on safety and effectiveness due to software platform difference. |
| Connection to Scanner | Wi-Fi connection (same function, no impact on safety/effectiveness as predicate's hardware connection/wireless for interventional module; always connected, starts/stops with scanner). |
| User Interface (Mobile vs. Affixed) | Mobile tablet (subject device) comparable to predicate's affixed touch panel. No hardware buttons on subject device's tablet. |
2. Sample Size Used for the Test Set and the Data Provenance
The document does not specify a quantitative "sample size" in terms of number of patient cases or studies for the non-clinical or clinical use tests.
- Test Set Description: The "test set" for performance evaluation consisted of:
- Verification and validation testing of software.
- Non-clinical tests (integration and functional).
- Dosimetry and imaging performance analysis of phantom images.
- Wireless coexistence testing (Co-Channel, Adjacent Channel, RF Interference, Separation Distance/Location).
- Clinical use testing: "Internal Clinical Use Test" (simulated customer environment, typically with customers with clinical expertise) and "External Clinical Use Test" (in clinic/hospital with selected customers before rollout).
- Data Provenance:
- The non-clinical and internal clinical use tests were conducted internally by Siemens.
- External clinical use tests were conducted in actual clinic/hospital environments.
- The data is prospective in the sense that it was generated specifically for the verification and validation of the Scan&GO device during its development and pre-market submission. The country of origin for the internal tests would be Germany (where Siemens Healthcare GmbH is located) and potentially the US for Siemens Medical Solutions USA, Inc. The external tests would be at selected customer sites (countries not specified).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and the Qualifications of Those Experts
The document does not specify a "ground truth" established by experts in the traditional sense of diagnostic accuracy. Scan&GO is a control/planning application, not a diagnostic one.
- For the "Internal Clinical Use Test," it mentions inviting "customers with clinical expertise which perform tests." The exact number and specific qualifications (e.g., radiologist with X years of experience) are not provided.
- For the "External Clinical Use Test," it mentions performing tests with "selected customer" in a clinic/hospital environment. Again, specific numbers or qualifications are not provided.
4. Adjudication Method for the Test Set
The document does not describe an adjudication method for the test set, as this typically applies to studies where multiple readers interpret images against a ground truth. Given that Scan&GO is a CT scanner control/planning application, such a method would not be directly applicable to its core function. The acceptance criteria for the clinical use tests were "pre-determined" and met, suggesting an evaluation of functionality and workflow rather than diagnostic agreement.
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
No MRMC comparative effectiveness study was mentioned. Scan&GO is not an AI-powered diagnostic assistance tool for human readers; it's a mobile interface for controlling a CT scanner and managing its workflow. Therefore, the concept of "how much human readers improve with AI vs without AI assistance" is not relevant to this device.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, the primary evaluation of Scan&GO's performance appears to be analogous to a standalone evaluation of its software functionality and system integration. The software itself, running on a tablet, performs its designated tasks (patient selection, protocol display, scan parameter display, etc.). The "non-clinical testing" and "verification and validation" would largely fall under this category, assessing if the algorithm (software) performs according to its specifications and established standards without human interpretation of its outputs in a diagnostic context. The "customer use testing" then assesses its usability and functional performance in a simulated/real clinical environment with human operators.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
For Scan&GO, the "ground truth" is not in terms of disease presence or absence. Instead, the ground truth relates to:
- Functional correctness: Does the application accurately display information from the CT scanner? Does it correctly execute commands like patient and protocol selection?
- Adherence to specifications: Does the software meet its documented requirements?
- Compliance with standards: Does the device conform to relevant safety, electrical, and cybersecurity standards?
- Workflow efficiency and usability: Is the mobile workflow effective and convenient for operators in a clinical setting?
This "ground truth" was established through internal engineering verification and validation, adherence to regulatory standards, and feedback from clinical "customers/experts" during simulated and external use tests.
8. The Sample Size for the Training Set
Scan&GO is described as a "planning and information system" and "optional software interaction and control component." It is not presented as a machine learning or AI-driven diagnostic device that would require a "training set" of data in the typical sense for model development. Therefore, a training set was not applicable or specified in the document. Its development likely followed traditional software engineering practices.
9. How the Ground Truth for the Training Set Was Established
As no training set was specified for an AI/ML model, this question is not applicable.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.