(212 days)
Oncospace is used to configure and review radiotherapy treatment with malignant or benign disease in the prostate, thoracic, pancreas, or head & neck regions. It allows for set up of radiotherapy treatment protocols, association of a potential treatment plan with the protocol(s), submission of a dose prescription and achievable dosimetric goals to a treatment planning system, and review of the treatment plan. It is intended for use by qualified, trained radiation therapy professionals (such as medical physicists, oncologists, and dosimetrists). This device is for prescription use by order of a physician.
The Oncospace software supports radiation oncologists and medical dosimetrists during radiotherapy treatment planning for prostate, thoracic, pancreas, and head & neck cases. The software includes machine learning algorithms that are locked during use. During treatment planning, the Oncospace software works in conjunction with, and does not replace, a treatment planning system (TPS). The Oncospace software is intended to augment the treatment planning process by: allowing the radiation oncologist to select and customize a treatment planning protocol that includes dose prescription (number of fractions, dose normalization), a delivery method (beam type and geometry), and protocol-based dosimetric goals/objectives for treatment targets, and organs at risk (OAR); predicting dosimetric goals/objectives for OARs based on patient-specific anatomical geometry; automating the initiation of plan optimization on a TPS by supplying the dose prescription, delivery method, protocol-based target objectives, and predicted OAR objectives; providing a user interface for plan evaluation against protocol-based and predicted goals.
Here's an analysis of the provided text to extract the requested information regarding the acceptance criteria and the study proving the device meets them:
Disclaimer: The provided text is a 510(k) summary, not a detailed scientific paper. Therefore, some information, especially regarding statistical significance, specific ground truth methods for training data, and detailed MRMC study results (beyond a qualitative statement), is either not present or not fully detailed.
Acceptance Criteria and Device Performance
The acceptance criterion for the Oncospace device appears to be a reduction in the number of iterations required to achieve a clinically viable and deliverable radiation treatment plan, without increasing iterations significantly in individual cases.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Reduce the number of iterations necessary to achieve a clinically viable and deliverable radiation treatment plan. | The average number of iterations was reduced by almost two-thirds using Oncospace. |
| Avoid significantly increasing iterations for individual cases. | Out of all plans tested, only one plan took more iterations (one more) using Oncospace versus traditional planning. |
Study Details
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: "Out of all the plans tested," and "A retrospective set of traditionally planned radiation treatment plans for prostate, thoracic, pancreas, and head and neck cancers were used." The exact number of plans in this "retrospective set" is not specified in the provided document.
- Data Provenance: Retrospective clinical data. The country of origin is not specified.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of those Experts
- Number of Experts: The document states that the testing demonstrated "acceptability to qualified clinical users" and "qualified clinical and non-clinical users." It also mentions "radiation oncologists and medical dosimetrists" in the device description. However, the exact number of experts involved in establishing the ground truth for the test set is not specified.
- Qualifications of Experts: "Qualified, trained radiation therapy professionals (such as medical physicists, oncologists, and dosimetrists)." Specific years of experienced are not specified.
4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set
The document describes a comparison of iteration numbers with and without Oncospace. It does not explicitly mention a multi-reader adjudication method for establishing ground truth or evaluating the test set results. The ground truth for the number of iterations in the traditional workflow was "the number of iterations when the plan was originally approved." For the Oncospace workflow, it was the number of iterations "to get to a clinically viable and deliverable plan when using Oncospace." The method of determining "clinically viable and deliverable" and any conflict resolution (adjudication) for this determination is not specified.
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?
This was not a traditional MRMC comparative effectiveness study in the sense of evaluating readers' diagnostic accuracy with and without AI. Instead, it was a study comparing a workflow metric (number of iterations) when using the device versus not using the device. The study involved a retrospective comparison of "traditionally planned radiation treatment plans" against plans generated using Oncospace.
The "effect size" (or improvement) reported is: "the average number of iterations was reduced by almost two thirds using Oncospace."
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
This was not a standalone performance study of the algorithm in isolation. The device, Oncospace, is designed to be used "in conjunction with, and does not replace, a treatment planning system (TPS)" and augments the process for "qualified, trained radiation therapy professionals." The study evaluated the device's impact within a human-in-the-loop workflow.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
The ground truth for the "number of iterations" in the traditional workflow was derived from the "number of iterations when the plan was originally approved." For the Oncospace workflow, it was the number of iterations "to get to a clinically viable and deliverable plan." This seems to be a process-based ground truth related to the number of workflow steps, verified as "clinically viable and deliverable" by qualified users. It does not appear to be based on pathology, long-term patient outcomes, or a detailed expert consensus review beyond the original planning approval.
8. The Sample Size for the Training Set
The document mentions that "Oncospace uses a database of approved treatment plans to derive individualized OAR dose goals." It also states "In the current software release, static machine learning models are used for prostate plan predictions, and statistical/database lookup methods are used for thoracic, pancreas, and head & neck plan predictions."
The sample size for the training set (the "database of approved treatment plans") is not specified in the document.
9. How the Ground Truth for the Training Set Was Established
The training set consists of a "database of approved treatment plans." The ground truth for these plans would inherently be the approved dosimetric goals and final plans themselves, as they represent clinically accepted treatment designs. The document implicitly suggests these are "approved" plans from clinical practice, implying they have undergone clinical review and acceptance. The specific process for this approval (e.g., expert consensus, adherence to a specific protocol) beyond being "approved treatment plans" is not explicitly detailed.
§ 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.