The Prelude software supports intra-operative radiation therapy workflows with intra-operative radiation devices like IntraOp® Mobetron®. It assists to find product specific machine parameters for treatment and can send those proposals to the intra-operative radiation device. The machine parameters are not intended to be used for direct control for the radiation device. Dose distribution visualizations are based on measured beam data and tissue inhomogeneities are not taken into account, the resulting dose distribution for anatomic locations in close proximity to bone and lung (or other tissue of high or low density) may differ from the presented visualization. Machine Output Quality can be visualized and recorded over time for quality assurance. The use of Prelude is restricted to medical professionals of radiation therapy.
Device Story
Prelude software supports intra-operative radiation therapy (IORT) workflows using IntraOp Mobetron. Input: dosimetric measurement data from radiation device; user-defined machine parameters (beam energy, applicator diameter, prescribed dose). Transformation: software calculates required treatment parameters and monitor units using IAEA or AAPM protocols; visualizes dose distribution based on water-equivalent medium (no tissue inhomogeneity correction). Output: treatment plan parameters; QA reports; trend analysis of machine output. Used in clinical radiation therapy settings by medical professionals. Healthcare providers use output to plan technical parameters for IORT; output assists in optimizing treatment delivery and streamlining QA. Benefits: efficient data integration; improved workflow; optimized IORT procedure through fast dose visualization.
Clinical Evidence
Bench testing only. Verification and validation performed using dosimetric measurement data from Mobetron device. Simulated clinical patient data confirmed expected treatment parameters. Usability testing demonstrated successful creation, approval, and database storage of treatment plans by medical professionals. No clinical prospective or retrospective studies were conducted; clinical evaluation relied on literature search and expert feedback.
Technological Characteristics
Software-based radiotherapy planning and QA system. Architecture: module-based, client/server with SQLite database. Connectivity: networked (hospital database, printer, touchscreen). Standards: ISO 14971 (risk management), IEC 62304 (software lifecycle), IEC 62083 (radiotherapy planning safety). Calculation principle: water-equivalent dose distribution based on measured beam data; IAEA/AAPM protocols for monitor units. Platform: Windows-based.
Indications for Use
Indicated for planning electron beam IORT treatment for any malignant or benign tumor. No patient population limitations. Intended for patients prescribed treatment with the Mobetron® device. Prescription use only.
Regulatory Classification
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.
{0}------------------------------------------------
March 27, 2018
Image /page/0/Picture/1 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services USA logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
MedCom GmbH % Mr. Johannes Messow Quality Manager Dolivostrasse 11 Darmstadt, Hessen 64293 GERMANY
Re: K180308
Trade/Device Name: Prelude Regulation Number: 21 CFR 892.5050 Regulation Name: Medical charged-particle radiation therapy system Regulatory Class: II Product Code: MUJ, LHO Dated: January 29, 2018 Received: February 2, 2018
Dear Mr. Messow:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
{1}------------------------------------------------
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm for the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Michael D. O'Hara For
Robert Ochs, Ph.D Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
# Indications for Use
510(k) Number (if known) K180308
Device Name Prelude
Indications for Use (Describe)
The Prelude Planning Software for the electron beam IORT treatment can be used for any malignant and benign tumor. For Prelude no limitation is given to the patient population. Local/Regional recommendations or guidelines may indicate patient who will benefit from IORT more than from other treatment modalities.
In general, since Prelude is tailored for the planning with the Mobetron®, it can be used for IORT treatment planning, if a patient is prescribed to be treated with the Mobetron®.
| Type of Use (Select one or both, as applicable) | |
|------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------|
| <div> <span> <span style="text-decoration: overline;">X</span> Prescription Use (Part 21 CFR 801 Subpart D) </span> </div> | <div> <span> Over-The-Counter Use (21 CFR 801 Subpart C) </span> </div> |
#### CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
#### *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
# III. 510(k) Summary of Safety and Effectiveness
## A. Submitter
| Name: | MedCom GmbH |
|---------------------|-------------------------------------------------|
| Address: | Dolivostr. 11<br>Darmstadt, HE 64293<br>Germany |
| Establishment Reg.: | 3006579682 |
| Telephone: | +49 (6151) 95147-285 |
| Fax: | +49 (6151) 95147-20 |
| Contact: | Mr. Johannes Messow<br>jmessow@medcom-online.de |
| Date: | Jan 29, 2018 |
## B. Device
| Trade Name: | Prelude | |
|-----------------|----------------------|-----------------------------------------------------|
| Common name: | IntraOp Prelude | |
| Classification: | Regulatory Class: | II |
| | Product Code: | MUJ |
| | Classification Name: | System, Planning,<br>Radiation Therapy<br>Treatment |
| | CFR Section: | 892.5050 |
| | Panel: | Radiology |
{4}------------------------------------------------
## C. Predicate Devices
| Device trade name: | Radiance |
|------------------------|---------------|
| 510(k) number: | K171885 |
| Company name: | GMV |
| Classification Number: | 892.5050 |
| Classification: | Class 2 |
| Product code: | MUJ |
| Device trade name: | Track-it |
| 510(k) number: | 510(K) Exempt |
| Company name: | PTW-FREIBURG |
| Classification Number: | 892.1940 |
| Classification: | Class I |
| Product code: | LHO |
{5}------------------------------------------------
### D. Reason for Submission
New device application
#### E. Standards
1. ISO 14971:2007, Medical devices - Application of risk management to medical devices. (General I (QS/RM))
2. IEC 62304:2006/AMD1:2015, Medical Device Software - Software Life Cycle Processes. (Software/Informatics)
3. IEC 62083:2009 - Medical electrical equipment - Requirements for the safety of radiotherapy treatment planning systems
#### F. Description
software supports the IORT treatment workflow. Prelude Dosimetric measurement data of the radiation device can be displayed by selecting the machine parameters. Upon that information the user can easily plan the treatment and the software calculate the required parameters for the IORT devices.
For quality assurance the machines parameters can be recorded and visualized.
For the calculation of the output factors or the monitor units either the IAEA or AAPM protocol is followed.
The software is intended to be used by medical professionals in the area of radiation therapy.
The main purpose is to plan the technical parameters required to perform an electron beam IORT to treat both malignant and benign tumors
Examples of compatible devices are:
| Device | Type | 510(k) / registration number |
|---------------------------------|----------------|------------------------------|
| Planning System,<br>QA software | GMV Radiance | K171885 |
| | PTW – Track It | 510(k) Exempt |
{6}------------------------------------------------
Image /page/6/Figure/2 description: The image shows a system overview diagram for Medcom Prelude. The diagram includes components such as the Medcom Prelude Installer, Windows Registry, Operating System, Medcom Prelude, and Medcom Database. It also shows actors like an Administrator and Medical Staff interacting with the system, as well as hardware components like a printer, touchscreen, and hospital database.
The Prelude software is developed in Microsoft Visual Studio in programming language C. As main architectonical style is a module concept. Each module consists of a standard and predefined set of function for data initialization, parameter-file handling, UI creation and handling.
The Prelude Database Server is written in C/C++ using Microsoft Foundation Classes (MFC) and an SQLite database.
For details of the Software Architecture refer to: 003_MC.5078.TDC.0001.System_Architecture
{7}------------------------------------------------
Image /page/7/Figure/2 description: The image shows a diagram of the Medcom Prelude architecture. The diagram includes components such as Kernel, Planning, Treatment, Invivo, QA, Settings, Database (Client), FileIO, Sub, UITools, Medcom Prelude Database, Hospital Database, Database Files, IntraOp Mobetron, Harddrive, Printer, and Touchscreen. The diagram also shows the connections between these components, as well as the interfaces between them.
Figure 1: Architecture Overview
Figure 1 shows an overview of the program and it´s modules. The blue line marks the MedCom Products (Prelude and its Database Server) and their interaction with internal/external devices.
{8}------------------------------------------------
## G. Intended Use
The Prelude software supports intra-operative radiation therapy workflows with intra-operative radiation devices like IntraOp® Mobetron®
It assists to find product specific machine parameters for treatment and can send those proposals to the intra-operative radiation device.
The machine parameters are not intended to be used for direct control for the radiation device.
Dose distribution visualizations are based on measured beam data and tissue inhomogeneities are not taken into account, the resulting dose distribution for anatomic locations in close proximity to bone and lung (or other tissue of high or low density) may differ from the presented visualization.
Machine Output Quality can be visualized and recorded over time for quality assurance.
The use of Prelude is restricted to medical professionals of radiation therapy.
## H. Indications for Use
The Prelude Planning Software for the electron beam IORT treatment can be used for any malignant and benign tumor.
For Prelude no limitation is given to the patient population. Local/Regional recommendations or guidelines may indicate patient who will benefit from IORT more than from other treatment modalities.
In general, since Prelude is tailored for the planning with the Mobetron®, it can be used for IORT treatment planning, if a patient is prescribed to be treated with the Mobetron®.
Prelude is a prescription device.
{9}------------------------------------------------
#### 1. Technological Comparison to Predicate Devices
#### The device Prelude is substantially equivalent to the following predicate devices:
| K171885 | GMV Radiance |
|---------------|--------------|
| 510(k) Exempt | PTW Track It |
The predicate device Radiance (GMV) has similar main functionalities and characteristics as Prelude for the planning part of an IORT treatment.
Both devices provide a visualization of the dose distributions in the treatment field. Both systems are based on measured dosimetric characteristic of the beam. Monitor Units calculation in both systems is based on Percentage Depth Dose curve along central axes of the beam.
Those are the core functions of both systems and they are similar.
Prelude, unlike Radiance, does not use 3D patient data (e.g. CT scans) so performed calculations are based on homogenous medium (i.e. water) and material heterogeneities are not taken into account. Since. IORT intends to treat mainly soft tissue (which, from the radiation perspective, is equivalent to water) water-based calculation of dose distribution and MUs provides very good approximation of clinical situation and the planning can be done faster.
Anyhow in an IORT treatment room, there is often no possibility to acquire CT scans during the treatment. Thus, planning on pre-operative images, like it is done with Radiance, is also an approximation of the treatment region during the surgery. This dissimilarity in the functionality of both systems should be considered insignificant.
The predicate device Track-It® (PTW) and Prelude are adequately similar concerning management of Quality Assurance of Electron Beam devices and analyzing QA results recorded over time. Both devices enable detailed tracking of QA measurements in order to analyze trends occurring in the machine functionality. The devices can be adapted to common QA protocols for medical accelerators (e.g. AAPM guidelines or IAEA protocols). QA sessions can be recorded offline and synchronized once a server connection is reestablished. It is possible to track data of multiple devices separately. Prelude and Track-It® have a client/server architecture with a server-side database that can be queried with custom filter conditions.
Prelude does not support multiple types of medical accelerator and currently only supports data tracking for electron beams, which are generated by the Mobetron® Prelude is not customizable to the same extent as the general-purpose QA data tracking tool Track-It®. These dissimilarities between Prelude and Track-It® are insignificant since Prelude is tailored and intended only for the use in combination with the Mobetron® accelerator. Hence, limitations in beam energies and accelerator types pose no limitations of safety, performance and effectiveness but are intended design decisions.
{10}------------------------------------------------
### J. Non-clinical Performance Data
Non-clinical verification and validation software tests were conducted to confirm that the Prelude System meets its intended use and is safe and effective.
Tests have been performed with dosimetric measurement data from a Mobetron® device. Clinical patient data was simulated and achieved results led to expected parameters for a treatment of the simulated input data.
Usability testing showed, that the user could successfully create a treatment plan. defining all necessary treatment parameters (beam energy, applicator diameter, prescribed dose, etc.). It was absolutely understandable and clear for the user, where to enter each parameter and how these parameters impact the dose distribution visualized by the software. The workflow offered by the software requires all crucial parameters to be entered before the Monitor Units can be calculated and the treatment plan can be approved.
The complete treatment plan was successfully approved by the user (with sufficient rights) and saved into the database. User was able review and confirm all treatment parameters by verifying the report created by the software and by accessing the plan from the database.
Based on extensive testing, briefly summarized above, one can conclude that all the usability goals were met. Tested software does not create any new risk to the intraoperative radiotherapy procedure performed with the Mobetron®. It is safe and usable in the clinical environment.
The tested software is safe and useful in the process of Intraoperative Radiotherapy. Based on performed tests and feedback provided by Mobetron users and other experts in that field, the IORT treatment delivery could be optimized due to fast dose distribution visualization with energy mixing.
Integration of all patient and treatment data into one software platform and one central database makes the data analysis and reporting very convenient and efficient. What is more. Quality Assurance management features allow streamlining workflow and tracking equipment performance.
It might be concluded that the software improves efficiency of IORT procedure by integrating various treatment planning and QA tools into a single, intuitive platform.
{11}------------------------------------------------
#### K. Conclusion
Based on the information provided in this Premarket Notification MedCom concludes that Prelude system is as safe and effective and substantially equivalent to the predicate devices described herein.
The risk analysis shows that the product is safe and the risk/benefit ratio is acceptable.
Risks identified with similar MedCom devices and similar marketed devices of other manufacturers were considered and included in the risk assessment of Prelude. For an effective identification, estimation and evaluation of risks, the risk assessment team included application specialists and a medical expert besides the development team and quality managers with risk management experience.
All identified risks were reduced by appropriate risk control measures to an acceptable level, also including risks which were evaluated as acceptable before any measures. The overall residual risk is acceptable. According to the intended use of Prelude, the users are medical professionals and familiar with IORT treatments and have sufficient knowledge in that respective area. The overall probability of serious injury was therefore evaluated as "improbable".
The Clinical Evaluation shows that the system is effective and comparable to existing procedures.
No issues have been detected that would prevent Prelude to be used in the clinical environment. Data has been collected through literature search which indicates that Prelude is state of the art like other tools currently on the market and thus a focused clinical evaluation appears sufficient.
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.