(58 days)
MOSAIQ® is an oncology information system used to manage workflows for treatment planning and delivery. It supports information flow among healthcare facility personnel and can be used wherever radiotherapy and/or chemotherapy are prescribed.
Users can configure MOSAIQ® for Medical Oncology use, Radiation Oncology use, or the two together. It lets users:
- · Assemble electronic patient charts and treatment plans, order diagnostic tests, and prescribe medications.
- Generate and keep medication formulary lists and calculate applicable medication dosages for medical oncology.
- Import, view, annotate, adjust, enhance, manage and archive images.
- Compare radiation treatment plans and evaluate dose coverage.
- Design leaf plans for operation with radiotherapy treatment machines that have multileaf . collimators.
- . Make sure radiation treatment plans imported from treatment planning systems agree with treatment machine constraints. MOSAIQ® reads actual settings from the treatment machine through the machine communication interface. It compares these settings with predefined values. If a mismatch occurs between the planned values and the actual machine settings, the system warns the user.
- View reference images to setup treatment. MOSAIQ® refers to predefined settings to . help treatment machine setup, and communicates patient and machine setup instructions.
- Record actual delivered radiation values in an electronic chart to track treatment. .
MOSAIQ® is not intended for use in diagnosis. Medical oncology dose calculation functions are designed for use with patients 18 years or older only.
MOSAIQ is a multi-functional, integrated software suite that forms a comprehensive electronic oncology management system for medical and radiation oncology facilities. For both medical and radiation oncology users, MOSAIQ provides image-enabled electronic patient charting and record management as well as medical transcription and billing functionality. For radiation oncology users, it also includes the ability to import and export radiation treatment plan information, the ability to plan multileaf collimator (MLC) shapes, and verify and record treatment setup and delivery.
This Premarket Notification addresses the addition of the "Evaluate" module, which calculates and displays dose volume histograms (DVHs) for the purpose of review and evaluation of radiation treatment plans.
Here's an analysis of the provided text regarding the acceptance criteria and study for the MOSAIQ Oncology Information System:
It's important to note that this document is a 510(k) Premarket Notification summary for software, specifically an Oncology Information System (MOSAIQ). Such notifications primarily focus on demonstrating substantial equivalence to a predicate device and usually involve software verification and validation, not clinical trials in the sense of demonstrating diagnostic accuracy or efficacy in a patient population. Therefore, many of the typical acceptance criteria and study components you'd expect for an AI/algorithm-based diagnostic device will not be present.
Based solely on the provided text, many of the requested categories (especially those related to clinical performance, ground truth, and expert evaluation) are not applicable or not reported as they would be for a typical AI diagnostic device.
Acceptance Criteria and Reported Device Performance
The document doesn't explicitly state quantitative performance-based acceptance criteria for a "device" in the sense of an AI algorithm producing a measurement or diagnosis. Instead, the "device" is an information system, and its acceptance criteria are implicitly tied to the successful completion of non-clinical verification and validation testing, ensuring it functions as designed and meets safety requirements.
| Acceptance Criteria Category | Description from Document (or N/A) | Reported Device Performance |
|---|---|---|
| Functional Requirements | The system successfully performs its stated functions, including assembling patient charts, managing treatment plans, calculating dosages (for medical oncology, 18+ patients only), importing/viewing/managing images, comparing radiation plans, designing leaf plans, verifying treatment machine settings against planned values, alerting users to mismatches, viewing reference images for setup, and recording delivered radiation values. (Implicit, based on "DESCRIPTION OF THE PRODUCT" and "Indications for Use"). Specific to this submission: The "Evaluate" module calculates and displays dose volume histograms (DVHs) for review and evaluation of radiation treatment plans. | "MOSAIQ passed testing and was deemed safe and effective for its intended use." (Implies all functions operate as intended and meet requirements). The "Evaluate" module was added, implying it passed its specific verification. |
| Safety Requirements | The system safely manages workflows without causing harm. Specifically, for the record and verify function (major level of concern), it detects potential mismatches between planned and actual machine settings and alerts the user. Risks are mitigated. (Implicit, based on "LEVEL OF CONCERN," "SUMMARY OF NON-CLINICAL TESTING"). | "tests to ensure that risk mitigations function as intended" were executed and passed. "MOSAIQ passed testing and was deemed safe and effective for its intended use." |
| System Reliability/Stability | The software operates consistently and without critical failures. (Implicit in general software testing). | Over 100 test procedures executed, including exploratory, new functionality, risk mitigation, and regression tests, without indicating failures that prevented acceptance. |
| Performance (e.g., speed) | Not explicitly stated in terms of quantitative operational performance metrics (e.g., specific response times). | N/A (Not reported or not a specific focus for this type of submission). |
| Accuracy (e.g., calculation) | Not explicitly stated with quantitative targets. For medical oncology dosage, it "calculates applicable medication dosages." For radiation treatment plan verification, it "reads actual settings...compares these settings with predefined values. If a mismatch occurs...the system warns the user." The "Evaluate" module "calculates and displays dose volume histograms (DVHs)." (Implicit: these calculations are accurate). | The system passed testing, implying that calculations and comparisons function correctly as designed. |
| Usability | Not explicitly detailed in the provided summary (though generally part of software development). | N/A (Not reported). |
| Substantial Equivalence | The device is substantially equivalent to predicate devices (MOSAIQ K120067 and Mobile MIM K112930) in intended use, safety, and effectiveness. | The FDA reviewed the 510(k) and determined the device is substantially equivalent, noting concurrence by the Division of Radiological Health. |
Study Details: MOSAIQ Oncology Information System
This submission focuses on software validation rather than a clinical study evaluating diagnostic performance.
-
Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective):
- Test Set Description: "Bench testing was performed... using simulated clinical workflows and ad hoc testing where appropriate, with actual patient data."
- Sample Size: Not specified for the "actual patient data" used within the bench testing. The total number of test procedures was "Over 100."
- Data Provenance: "actual patient data" implies retrospective, but no country of origin is mentioned.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not specified.
- Qualifications: Not specified. For software verification and validation, "ground truth" would typically be defined by engineering specifications, expected outputs, and clinical input from subject matter experts (e.g., oncologists, physicists, dosimetrists) who validate the functional correctness of the system rather than establishing a diagnostic truth for patient cases.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not applicable as this was not a human reader study requiring adjudication of interpretations. The "adjudication" would be through verifying test procedure results against expected outcomes defined during the software development lifecycle.
-
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 done. The document explicitly states: "Clinical trials were not performed as part of the development of this product." and "Clinical testing on patients is not advantageous in demonstrating substantial equivalence or safety and effectiveness of the device."
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, in a sense. The non-clinical testing was focused on the software's ability to perform its functions independently ("algorithm only") under simulated conditions, but the device's intended use is with a human in the loop, as an information system for workflow management and to warn users. The testing verified the software's functional correctness.
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- The "ground truth" for this type of software would be based on:
- Functional Specifications/Requirements: The software must perform according to its design documents.
- Clinical Domain Knowledge: Accuracy of calculations (e.g., dosage, DVHs) and correctness of comparisons (e.g., planned vs. actual machine settings) would be validated against established medical/physics principles and expected clinical outcomes.
- Expected Outputs: For test cases, the correct output (e.g., a specific DVH curve, a warning message for a mismatch) would be predefined and compared to the software's actual output.
- The "ground truth" for this type of software would be based on:
-
The sample size for the training set:
- No "training set" in the context of machine learning was mentioned or indicated. This is a rule-based/deterministic software system, not an AI/ML-based system that requires training data.
-
How the ground truth for the training set was established:
- Not applicable, as there was no machine learning training set mentioned.
§ 892.5050 Medical charged-particle radiation therapy system.
(a)
Identification. A medical charged-particle radiation therapy system is a device that produces by acceleration high energy charged particles (e.g., electrons and protons) intended for use in radiation therapy. This generic type of device may include signal analysis and display equipment, patient and equipment supports, treatment planning computer programs, component parts, and accessories.(b)
Classification. Class II. When intended for use as a quality control system, the film dosimetry system (film scanning system) included as an accessory to the device described in paragraph (a) of this section, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.