(133 days)
The Respisens system is intended to monitor patient motion in real time during radiotherapy. In particular, the system is intended to monitor breath hold and to detect undesirable patient motion. Monitoring respiratory motion during breath hold is essential in ensuring patient safety. The system warns the operator when breath hold is not maintained properly. Verifying that the patient stays completely still during treatment is also fundamental. The system can detect patient movement and warn the operator when necessary.
The Respisens system monitors patient motion in real time during radiotherapy. The system is based on a transmitter/receiver that measures distance. When placed on the patient's thorax or abdomen, the system tracks breathing and thus helps monitoring and securing breath hold manoeuvres. If placed on a motionless part of the patient, it helps verify immobility. The underlying technology is a magnetic distance sensor that is capable of measuring movements with high sensitivity.
The Respisens system is composed of a Respisens measurement module and an Interface Box, their accessories, and a user interface software. The Respisens measurement module drives the sensor. The Interface Box is the control core of the system. It sits in the control room and handles the communication with the PC, the calculation of the time lag in signal display introduced by the PC, the detection of the status of the radiation beam, and the alarms.
Here's an analysis of the provided text regarding the Respisens device's acceptance criteria and studies, organized by your requested points:
The provided text for K092845 is a 510(k) summary and FDA clearance letter. It is important to note that 510(k) summaries often focus on demonstrating substantial equivalence to predicate devices rather than exhaustive clinical trial data with predefined acceptance criteria. Clinical trial data like those requested are often detailed in separate, more comprehensive study reports submitted to the FDA, but only a summary is included in the 510(k) public document.
Based on the provided text, the level of detail for some of your requested points is limited.
Acceptance Criteria and Device Performance
The 510(k) summary does not explicitly list quantitative acceptance criteria in a table format. Instead, it states that "Performance data have been submitted to show that the device achieves its intended use and performs comparably to predicate devices." This implies that the acceptance criteria were implicitly met by demonstrating comparable performance to the predicate devices (RPM Respiratory Gating system and Active Breathing Coordinator - ABC system) for the defined intended uses.
The "reported device performance" is qualitative and relies on the comparison to predicate devices, rather than specific numerical metrics.
Table 1: Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Inferred from Intended Use and Comparison to Predicates) | Reported Device Performance (as stated in 510(k) summary) |
|---|---|
| 1. Monitor patient motion in real time during radiotherapy. | "The Respisens system monitors patient motion in real time during radiotherapy." (Device Description) |
| 2. Monitor breath hold. | "Intended to monitor breath hold..." (Intended Use) |
| "Monitoring respiratory motion during breath hold is essential in ensuring patient safety." (Intended Use) | |
| "The system warns the operator when breath hold is not maintained properly." (Intended Use) | |
| 3. Detect undesirable patient motion. | "Intended... to detect undesirable patient motion." (Intended Use) |
| "Verifying that the patient stays completely still during treatment is also fundamental. The system can detect patient movement and warn the operator when necessary." (Intended Use) | |
| 4. Comparable performance to predicate devices (RPM Respiratory Gating & ABC). | "Performance data have been submitted to show that the device achieves its intended use and performs comparably to predicate devices." (Technological Characteristics and Nonclinical Testing) |
| "The Respisens system is similar in intended use, layout, and performance characteristics to the predicate devices. The differences that exist between the devices do not raise new issues of safety or effectiveness." (Summary of Substantial Equivalence) | |
| 5. Differences in sensing technologies do not adversely affect safety/effectiveness. | "The Respisens system has been the subject of nonclinical testing to demonstrate that the differences, in particular in sensing technologies, do not adversely affect the safety or effectiveness of the device." (Technological Characteristics and Nonclinical Testing) |
Study Information
The 510(k) summary refers to "nonclinical testing" and "performance data" but does not describe a detailed study with the specific parameters you've requested. It implies a comparative approach to predicate devices.
-
Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):
The 510(k) summary does not specify a sample size for a test set or data provenance (country/retrospective/prospective). It generally mentions "nonclinical testing" and "performance data," which often refer to bench testing and engineering verification/validation rather than human subject clinical studies requiring extensive test set details. -
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):
This information is not provided in the 510(k) summary. Given the nonclinical nature of the testing mentioned, it's unlikely that expert-established ground truth on human cases, as typically seen in image analysis or diagnostic AI studies, was a primary component of this submission. The ground truth would likely refer to physical measurements of motion or breath hold. -
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
Not applicable or not described. The provided text does not describe a study involving expert adjudication of cases, which is common for studies evaluating diagnostic accuracy with human interpretation. -
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 is mentioned. The device's function is to monitor and warn, not to assist human readers in interpreting medical images or making diagnostic decisions. It's a real-time motion monitor, not an AI diagnostic assistant. -
If a standalone (i.e. algorithm only without human-in-the loop performance) was done:
The device itself, Respisens, operates as a standalone system for monitoring and warning. The "nonclinical testing" and "performance data" would have evaluated the algorithm's performance in detecting motion and breath hold without human intervention in the detection process, but rather with humans as operators receiving the warnings. The summary states, "The Respisens system is composed of a Respisens measurement module and an Interface Box, their accessories, and a user interface software," indicating it functions independently to generate its output. -
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
Based on the device's function (real-time motion monitoring, breath hold detection), the ground truth for "nonclinical testing" would likely involve:- Controlled physical measurements: Using phantoms or mechanical systems to simulate patient motion and breath hold, and independently measuring the actual movement to compare against the Respisens output.
- Reference standard measurement devices: Comparing Respisens's real-time measurements against an established, highly accurate motion tracking system.
This precise detail is not available in the summary.
-
The sample size for the training set:
This information is not provided. The 510(k) summary outlines verification and validation activities, but does not detail a machine learning training process or corresponding training set size. While the device utilizes a "magnetic distance sensor" and "user interface software," it's not explicitly described as an AI/ML device in the sense of requiring a large-scale training set for learning complex patterns. Its function seems more based on established physical principles and signal processing. -
How the ground truth for the training set was established:
Not applicable, as a training set for an AI/ML model is not described. If there were internal thresholds or calibration data used, these likely would have been established through engineering measurements and specifications rather than human-expert consensus on cases.
§ 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.