Search Results

The device is indicated for use for applying ink to the skin to identify the margins for radiation therapy. The device is intended to be used in clinical settings by Radiotherapy professionals.

The Comfort Marker 2.0 is an application system for placing reference marks on or in patient's skin to facilitate set-up for radiation therapy treatment. The device includes the following components:

• 1. Battery powered control unit with pen
• 2. Main powered docking station with adapter and
• 3. Safety needle (single use, sterile)

Mode of operation: To achieve the intended use, the device uses a safety needle (shown in figure 2). This actuation is achieved by a longitudinal movement of the driving rod inside the pen. The driving mechanism comprises electromagnetic coils, switched on and off by the controller for generating magnetic fields. Hereby, the distance moved by the driving rod can be controlled precisely by controlling the amount of applied energy. The driving device comprises a guiding mechanism arranged for allowing only movement of the driving rod along the longitudinal direction. The actual distance travel is measured with a measuring coil and used to control the desired depth setting. The system contains a mechanical end stop in the safety needle to ensure that the needle will not protrude more than 1 mm. The docking station is used to recharge the control unit.

The provided text describes the "Comfort Marker 2.0," a device for applying ink to the skin to identify margins for radiation therapy. It details the device's technical aspects, regulatory information, and summary of non-clinical/bench studies and a limited clinical study.

However, the Acceptance Criteria and the study proving the device meets those criteria are primarily focused on the physical and functional aspects of the device itself (e.g., needle penetration, material compatibility, sterility, electrical safety, software validation, and the durability/visibility of the marks), rather than a diagnostic AI system with associated performance metrics like sensitivity, specificity, or reader improvement.

Thus, the requested table and MRMC study details are not directly applicable in the typical sense for a diagnostic AI system using image analysis. The "study that proves the device meets the acceptance criteria" refers to the various bench tests and the limited human volunteer study that validate the device's physical performance, safety, and the persistence of the applied marks.

Nonetheless, I will extract the closest equivalents to "acceptance criteria" and "device performance" from the provided text and present them as requested, acknowledging the difference in context from an AI diagnostic device.

Acceptance Criteria and Reported Device Performance

Given that this is a physical device for marking, the "acceptance criteria" are derived from the performance tests and regulatory requirements for safety and functionality. The "reported device performance" refers to the results of these tests as stated in the document.

Table 1: Acceptance Criteria (as inferred from tests) and Reported Device Performance

2. Sample size used for the test set and the data provenance

• Test Set (Clinical Study): "(b) (4) healthy human volunteers" participated in the study. The specific number is redacted, but indicated as a count of men and women (e.g., "10 (4) men and " women").
• Data Provenance: The study was conducted in a radiotherapy preparation room. The country of origin is not explicitly stated for the data itself, but the sponsor is from the Netherlands ("Medical Precision B.V. Zwolle Netherlands") and the ink used was Accu-Tatt® "in the United States of America". The study seems to be prospective, as it involved actively recruiting and following up with volunteers over 12 weeks.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Ground Truth Establishment (Clinical Study): The document states: "The procedure was performed in a radiotherapy preparation room by a radiotherapy technician." and "The reference points were marked according to the Comfort Marker 2.0 instructions for use."
• Expert Qualifications: The assessment of mark visibility, migration, and clearance was likely done by the "radiotherapy professional" mentioned in the description of expected use and assessment. Their specific qualifications (e.g., years of experience, independent adjudication) are not detailed in the provided text. No formal expert panel for ground truth generation (as for an AI diagnostic device) is described.

4. Adjudication method for the test set

• Adjudication Method: Not applicable in the context of this device's clinical study. The study involved placement, observation, and documentation of the marks. There is no mention of multiple readers or an adjudication process for subjective interpretation of results, as there would be for a diagnostic imaging study.

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

• MRMC Study: No, an MRMC comparative effectiveness study was not done. This is a physical marking device, not an AI diagnostic system. There is no AI component assisting human readers for interpretation, hence no "effect size of how much human readers improve with AI vs without AI assistance" can be calculated or is relevant to this submission.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

• Standalone Performance: Not applicable directly as this is not an AI algorithm. The closest equivalent would be the bench testing, which evaluates the device's mechanical and electrical performance characteristics in a "standalone" fashion (without human interaction beyond operating the device). For instance, puncture rate, penetration depth, electrical safety, and software functionality tests are "algorithm only" in the sense that they assess the device's inherent functional capabilities.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

• Type of Ground Truth (Clinical Study): The ground truth for the clinical study was qualitative observation and documentation of physical attributes:
  • Visibility: "well defined reference points," "clearly visible."
  • Migration: "did not show any migration."
  • Duration: "faded away at week 12," "no impact on clinical treatment was observed" (outcomes related to the mark's utility rather than direct patient outcomes).
  • The assessment was based on direct observation by a "radiotherapy technician" and potentially other "radiotherapy professionals." It's best described as clinical observation/assessment by trained personnel rather than a formal expert consensus or pathology.

8. The sample size for the training set

• Training Set Sample Size: Not applicable. This is a physical device, not a machine learning model. Therefore, no "training set" in the context of AI model development exists.

9. How the ground truth for the training set was established

• Ground Truth for Training Set Establishment: Not applicable, as there is no AI training set.

Ask a specific question about this device