Search Results

The p.d software is used by radiation therapy professionals to assist in the design, manufacturing, and quality assurance testing of various radiation therapy devices used for cancer patients. The p.d software performs three distinct, primary functions which each are described below.

1. The p.d software takes a design of a compensating filter from a Treatment Planning System and converts the Treatment Planning System compensator filter files into a .decimal file format. This file can then be electronically submitted to .decimal through the software, so that we can manufacture the device.
2. The p.d software can design a beam shaping and compensating filters based on Treatment Planning System and other user supplied data. The device designs for compensating filters will be transferred back into the Treatment Planning System for final dose verification before devices are ordered and used for patient treatment.
3. The p.d software can perform quality assurance testing of the physical characteristics of treatment devices using data from various types of scanned images, including computed tomography images.

The .decimal p.d device is a software application that will enable users of various radiation treatment planning systems (TPS) to design, measure, and order beam shaping and modulating devices used in the delivery of various types of radiotherapy, including photon, electron, and particle therapy. The input from the treatment planning systems to the p.d product is generally received in DICOM file format. but other vendor specific or generic file formats are also utilized. p.d will also provide a simplified radiation dose calculator for the purpose of improving its ability to accurately create/modify patientspecific radiation beam modifying devices without the need for iteration with other treatment planning systems. However, all modulating devices will have final dose verification performed in a commissioned Treatment Planning System before devices are used for patient treatment. Additionally, the p.d software contains tools for analyzing scanned image data that aids users in performing quality assurance measurement and testing of radiotherapy devices.

The provided text describes the p.d 5.1 software, a device used in radiation therapy. However, it does not contain the detailed information required to fully answer your request regarding acceptance criteria and a specific study proving the device meets them. This document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a performance study with detailed acceptance criteria.

While the document indicates some testing was done, it doesn't provide the specifics you're asking for. Here's what can be inferred and what's missing:

1. A table of acceptance criteria and the reported device performance

Missing Information: The document does not provide a table of acceptance criteria with specific quantitative thresholds or reported device performance metrics. The testing described is more qualitative and focused on comparing to predicate devices and general software validation.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

Missing Information:

• Sample Size: Not specified.
• Data Provenance: Not specified. The document mentions "hospital-based testing partners" but doesn't detail the origin or nature of the data used in validation.
• Retrospective/Prospective: Not specified.

3. 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)

Missing Information: The document does not specify the number or qualifications of experts used for establishing ground truth in the test set. It mentions "Clinically oriented validation tests were written and executed by .decimal personnel and hospital-based testing partners," but this doesn't detail specific expert involvement for ground truth adjudication.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Missing Information: The document does not describe any specific adjudication method for establishing ground truth for the test set.

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

Missing Information:

• MRMC Study: No MRMC comparative effectiveness study is mentioned.
• Effect Size: Not applicable, as no MRMC study was described. The focus is on demonstrating substantial equivalence of the software's functionality to existing tools. This device is an aid to radiation therapy professionals, not an AI to improve human reader performance in a diagnostic context.

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

Information Available (Inferred): The testing seems to have been primarily standalone, focusing on the software's ability to perform its functions (design filters, convert files, perform QA measurements) and comparing its output to predicate devices. The document states "Clinical testing was not performed... since testing can be performed such that no human subjects are exposed to risk." This suggests the validation was primarily of the software's internal logic and output, rather than its performance in conjunction with a human user in a clinical setting with real patient outcomes.

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

Information Available: The ground truth for the validation tests was established by:

• Comparing results to those of known predicate devices (p.d software version 5.0 and Eclipse TPS).
• Performing quality assurance measurements on devices of known quality.

This implies a form of "reference standard" or "known truth" derived from established systems and manufactured devices, rather than clinical pathology or patient outcomes.

8. The sample size for the training set

Not Applicable/Missing Information: The document describes software validation and verification, not the training of a machine learning model. Therefore, there is no "training set" in the context of AI/ML. If the "p.d software" incorporates algorithms that are based on machine learning, this information is not provided. The phrasing "using nearly identical algorithms and processes" to the predicate software suggests it's more of a deterministic software rather than a trained AI model.

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

Not Applicable/Missing Information: As there's no mention of a training set for an AI/ML model, this question is not applicable.

Summary of Device Performance (from the document):

The document concludes with: "These tests show that the p.d software performed equivalently to the predicate device when appropriate and that the software is deemed safe and effective for clinical use."

This is a general statement of performance, but it lacks the specific, quantifiable acceptance criteria and corresponding reported performance metrics that your request specifies. The 510(k) process primarily aims to demonstrate substantial equivalence, and the provided document reflects that focus.

Ask a specific question about this device