ACAM® 5 is intended as an aid in diagnosing hearing loss and fitting of hearing aids. The device consists of an audiometer that can be used individually or with the other ACAM modules for performing Real Ear Measurements (REM), Hearing Instrument Test (HIT) and loudness scaling. ACAM 5 should be used by persons trained in audiology on patients of any age who are able to understand the basic principles of the test method when explained by the operator.
Device Story
ACAM 5 is a modular audiometer system for clinical diagnosis of hearing loss and hearing aid fitting. Inputs include pure tones, speech signals, and ambient sounds; system utilizes headphones, bone conduction transducers, loudspeakers, and in-situ ear probes. Device performs signal analysis including RMS, FFT, and percentile analysis to support REM, HIT, and loudness scaling. Operated by trained professionals (audiologists, ENT specialists) in clinics. Output is displayed via software, providing diagnostic data and fitting reports to assist clinicians in optimizing hearing aid parameters. Benefits include improved accuracy in hearing aid fitting and diagnostic assessment through standardized protocols (NAL, DSL-IO) and real-life simulation via video sequences.
Clinical Evidence
Bench testing only. Compliance with international consensus standards (EN 60601-1, EN 60601-1-1, EN 60601-1-2) for electrical safety and electromagnetic compatibility, and performance standards (ANSI S3.6, ANSI S3.46, ANSI S3.22) for audiometry and real-ear performance characteristics.
Technological Characteristics
Modular audiometer system; 19" rack form factor. Components: control unit, test boxes, in-situ probes, headphones, loudspeakers. Connectivity: TCP/IP network protocol. Standards: IEC 60645, ISO 8253, ISO 16832, ANSI S3.6, ANSI S3.22, EN 60118-0, EN 60118-7, DIN IEC 60118-15, ISO 12124, ANSI S3.43. Electrical safety: EN 60601-1 Class 1, Type B.
Indications for Use
Indicated for patients of any age with demonstrated hearing loss capable of understanding test principles. Used by audiologists, hearing aid dispensers, nurses, and ENT specialists for diagnostic hearing evaluations, hearing aid fitting, and loudness scaling.
Regulatory Classification
Identification
An audiometer or automated audiometer is an electroacoustic device that produces controlled levels of test tones and signals intended for use in conducting diagnostic hearing evaluations and assisting in the diagnosis of possible otologic disorders.
{0}------------------------------------------------
APR - 8 2011
l
# : 510(k) Summary, ACAM 5
This summary of 510(k) is being submitted in accordance with 21 CFR 807.92.
| Submitted By: | Acousticon GmbH<br>Hirschbachstrasse 48<br>D-64354 Reinheim<br>Germany<br>Telephone: +49 6162 93240<br>Fax: +49 6162 932449<br>Email: harald.bonsel@acousticon.de |
|------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Contact Person: | Maureen N. Garner<br>New World Regulatory Solutions, Inc.<br>Telephone: (732) 779 7422<br>Fax: (732) 270 4829<br>Email: NWRSinc@gmail.com |
| Date Prepared: | March 3, 2011 |
| Proprietary Name: | ACAM® 5 Audiometer System |
| Common Name: | Audiometer |
| Classification Status: | Class II exempt, 21 CFR 874.1050, Audiometer |
| Subsequent, Classifications: | Class II, 21 CFR 874.3310, Hearing Aid Calibrator and<br>Analysis System<br>Class II, 21 CFR 874.1120, Electronic noise generator for<br>audiometric testing |
| Regulation Name: | Audiometer |
| Product Code: | EWO |
| Subsequent Product Codes: | ETW, ETS |
# Predicate Device Information:
.
- Siemens Unity 2 (K# unknown) and Siemens Unity 2 HIA and Probe, K071462 .
.
DC
4//////
{1}------------------------------------------------
### 510(k) SUMMARY, continued
### Device Description
ACAM® 5 is an audiometer with optional components for performing Real Ear Measurements (REM) Hearing Instrument Testing (HIT) and loudness scaling. It is intended to aid trained audiologists and hearing aid professionals in the diagnosis of hearing loss and the fitting of hearing aids. As a part of the REM and HIT modules ACAM performs several kinds of signal analysis including root mean squared (RMS), fast Fourier transformation (FFT) and percentile analysis (PA). ACAM® 5 gives an audiologist the ability to use one or any combination of the diagnostic tools recommended by the National Acoustics Laboratory (NAL) and Dr. Richard Seewald (DSL-IO).
Available ACAM® 5 hardware consists of an audiometer with a modular control unit for peripheral components, which include a large or small hearing instrument test box and an in sity ear probe for real ear measurement. Headphones for audiometry, bone conduction and loudness scaling. loudspeakers, a microphone and an interrupter switch are available for use with the audiometer.
ACAM®'s operational software meets the international software standards established by the Hearing Instruments Software Manufacturers Association (HIMSA) and the speech recognition standards (ISTS, International Speech Test Signals) established by the-European Hearing Instrument Manufacturers Association (EHIMA).
The ACAM® 5 system meets or exceeds the following international standards: IEC 60645, ISO 8253, ISO 16832, ANSI S3.6, ANSI S3.22, EN 60118-0, EN 60118-7, DIN IEC 60118-15, ISO 12124, ANSI S3.43
ACAM® 5 should be operated by individuals with education and training in the field of audiology such as audiologists, hearing aid dispensers, health care and school nurses and ear nose and throat specialists. ·
### Intended Use/Indications for Use
ACAM® 5 is intended as an aid in diagnosing hearing loss and fitting of hearing aids. The device consists of an audiometer that can be used individually or with the other ACAM modules for performing Real Ear Measurements (REM). Hearing Instrument Test (HIT) and loudness scaling. ACAM 5° should be used by persons trained in audiology on patients of any age who are able to understand the basic principles of the test method when explained by the operator.
{2}------------------------------------------------
### 510(k) Summary, continued
#### Technological Characteristics
The ACAM® 5 System has substantially the same technological characteristics as the predicate, Siemens Unity 2 audiometer (K# unknown), with the HIA and Probe for use with Unity 2, cleared on June 5, 2007 under K071462.
#### Similarities
Both the Acousticon ACAM® 5 and the Siemens Unity 2 are modular systems intended for the diagnosis of hearing loss and optimization of the acoustical parameters of hearing aid fitting. Both the ACAM® 5 (applicant) and Siemens (predicate) systems provide modular components that can be used individually or in tandem to support processes from hearing aid fitting. Both the predicate and the applicant systems are computer controlled and include software specific for their applications, including links to the NOAH™ software applications provided by the Hearing Instrument Manufacturers' Software Association (HIMSA™). Both the applicant and the predicate systems utilize Real Ear Measurement (REM) fitting protocols that include percentile measurement to analyze the dynamic feature of amplified speech signals. Both the applicant and the predicate systems allow for the use of fitting protocols provided by the National Acoustic Laboratory (NAL-NL1) and by Dr Richard Seewald (DSL-IO). Both the predicate and applicant systems utilize optional visual stimuli that accompany ambient background sounds. Both the predicate and applicant systems offer ambient sound modules to optimize hearing aid performance in real life situations. Both Systems have an audiometer module to measure hearing losses with pure tone and speech following the requirements of ANSI S3.6.
#### Differences
The predicate system uses single tone frequency scaling over a range of 125 - 8,000 Hz (normal mode) and 125 - 16.000 Hz (high frequency mode), using mean background noise levels and a fixed signal to noise ratio (SNR), while the applicant system uses single tone frequency scaling over a range of 125 - 8.000 Hz and does not have a high frequency mode. The predicate system offers ambient sounds accompanied by still pictograms (SPL O gram) of environmental surroundings and two speakers, while the applicant system employs video sequences (real life fitting, or RLF sequence) with up to 12 speakers. The applicant system provides a broader menu of ambient sound selections than the predicate system. The predicate integrated system includes hearing aid programming with a Siemens hearing aid. The applicant does not include hearing aid programming.
#### Comparison to Predicate Device
The ACAM 5 Audiometer is equivalent to the predicate device in intended use its technological characteristics, design and function, as demonstrated in the comparison table below:
{3}------------------------------------------------
| Device<br>Specifications | Siemens Unity 2, with HIA and Probe | | ACAM 5 | |
|--------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------|
| K Number | K# unknown, K071462 (HIA and Probe) | | K103298 | |
| Intended use | See indications for use | | See indications for use | |
| Indications for use | The Unity 2 is indicated for use in<br>conducting diagnostic hearing<br>evaluations and assisting in the diagnosis<br>of possible otologic disorders. The Unity<br>2 HIA and Probe are intended to be used<br>as a system to: (1) perform Real Ear<br>Measurement; (2) get an objective<br>indication of the characteristics of a<br>hearing aid; and (3) assist in the<br>adjustment of hearing aids while in use<br>by the patient. It is used by ENT<br>professionals and in clinics for hearing<br>aid fitting. This device can either be sold<br>individually or together with other Unity 2<br>modules. | | ACAM 5 is intended as an aid in<br>diagnosing hearing loss and fitting of<br>hearing aids. The device consists of an<br>audiometer that can be used individually<br>or with the other ACAM modules for<br>performing Real Ear Measurements<br>(REM), Hearing Instrument Test (HIT)<br>and loudness scaling. ACAM 5 should<br>be used by persons trained in audiology<br>on patients of any age who are able to<br>understand the basic principles of the<br>test method when explained by the<br>operator. | |
| Target population | Individuals of any age who have<br>demonstrated hearing loss, and who are<br>able to understand and respond to the<br>basic principles of the test method when<br>explained by the operator. | | Individuals of any age who have<br>demonstrated hearing loss, and who are<br>able to understand and respond to the<br>basic principles of the test method when<br>explained by the operator | |
| Anatomical sites | Ear | | Ear | |
| Where used | Clinics and on-site applications | | Clinics and on-site applications | |
| Energy used<br>and/or delivered | Hz | dB HL | Hz | dB HL |
| Air line<br>Headphones | 125 | 100 / 90 | 125 | 90 |
| | 250 | 110 / 110 | 250 | 110 |
| | 500 | 115 / 120 | 500 | 120 |
| | 750 | 120 / 120 | 750 | 120 |
| | 1000 | 120 / 120 | 1000 | 120 |
| | 1500 | 115 / 120 | 1500 | 120 |
| | 2000 | 115 / 120 | 2000 | 120 |
| | 3000 | 115 / 120 | 3000 | 120 |
| | 4000 | 115 / 120 | 4000 | 120 |
| | 6000 | 105 / 120 | 6000 | 120 |
| | 8000 | 110 / 105 | 8000 | 110 |
| | 10000 | / 100 | | |
| | 12500 | / 90 | | |
| | 16000 | / 60 | | |
| Bone line<br>Headphones | 125 | 40 | 125 | 45 |
| | 250 | 50 | 250 | 60 |
| | 500 | 70 | 500 | 70 |
| | 750 | 70 | 750 | 70 |
| | 1000 | 70 | 1000 | 70 |
| | 1500 | 70 | 1500 | 70 |
| | 2000 | 70 | 2000 | 75 |
| | 3000 | 70 | 3000 | 80 |
| | 4000 | 60 | 4000 | 80 |
| | 6000 | 60 | 6000 | 60 |
| Table of Similarities and Differences, continued | | | | |
| Device<br>Specifications | Siemens Unity 2 with HIA and Probe | | ACAM 5 | |
| Energy used<br>and/or delivered | Hz | dB HL | Hz | dB HL |
| Air Line Speakers | 125<br>250<br>500<br>750<br>1000<br>1500<br>2000<br>3000<br>4000<br>6000<br>8000 | 80<br>90<br>90<br>90<br>90<br>90<br>90<br>90<br>90<br>80<br>65 | 125<br>250<br>500<br>750<br>1000<br>1500<br>2000<br>3000<br>4000<br>6000<br>8000 | 68<br>85<br>95<br>95<br>95<br>95<br>95<br>100<br>100<br>95<br>75 |
| Human factors | Subjective loudness response | | Subjective loudness response | |
| Design | Modular components consisting of:<br>Audiometer and headphones, external<br>speakers, hearing instrument test box<br>and microphone, software | | Modular components consisting of:<br>Audiometer and headphones, external<br>speakers, hearing instrument test box<br>and microphone, software | |
| Testing Features | • Real Ear measurement<br>• Pure tone and speech audiometry<br>• Loudness scaling and noise impulse<br>audiometry<br>• ISTS. International Speech Test<br>Signal<br>• Pediatric audiometry, if requested<br>• Automated fitting report<br>• Percentile analysis | | • Real Ear measurement<br>• Pure tone and speech audiometry<br>• Loudness scaling and noise impulse<br>audiometry<br>• ISTS. International Speech Test<br>Signal<br>• Pediatric audiometry, if requested<br>• Automated fitting report<br>• Percentile Analysis | |
| Available Tests | Audiometer:<br>• Air conduction<br>• Bone conduction<br>• Free field (10 W integrated 2-channel<br>amplifier) | | Audiometer:<br>• Air conduction<br>• Bone conduction<br>• Free field 4 Channel Standard<br>(optional up to 12 Channel) with 20W<br>Power | |
| Tests conducted<br>above hearing<br>threshold | • SISI test<br>• ABLB test (Fowler)<br>• DLI test (Luescher)<br>• Stenger test<br>• Tone decay test (Carhart) | | • ABLB test (Fowler)<br>• Stenger test<br>• Tone decay test (Carhart)<br>• Speech Audiometry in quiet and in<br>Noise<br>• ANL(acceptable Noise Level) | |
| Tests conducted<br>above hearing<br>threshold | • SISI test<br>• ABLB test (Fowler)<br>• DLI test (Luescher)<br>• Stenger test<br>• Tone decay test (Carhart) | | • ABLB test (Fowler)<br>• Stenger test<br>• Tone decay test (Carhart)<br>• Speech Audiometry in quiet and in<br>Noise<br>• ANL (acceptable Noise Level) | |
# Table of Similarities and Differences
{4}------------------------------------------------
# Table of Similarities and Differences, continued
: .
{5}------------------------------------------------
| Device<br>Specifications | Siemens Unity 2 with HIA and Probe | ACAM 5 |
|------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Additional Tests<br>Offered | • REUR (Real Ear Unaided Response),<br>• OEG (Open Ear Gain)<br>• REOR (Real Ear Occluded Response)<br>• REAR (Real Ear Aided Response,<br>SPL level at the eardrum) | • REUR (Real Ear Unaided Response),<br>• OEG (Open Ear Gain)<br>• REAR (Real Ear Aided Response,<br>SPL level at the eardrum) |
| | • REIG (Real Ear Insertion Gain)<br>• RECD (Real Ear-to-Coupler<br>Difference)<br>• LI/LO (Input-/Output curve)<br>• Sound Mapping<br>• On top mode<br>• Percentile analysis | • REIG (Real Ear Insertion Gain)<br>• RECD (Real Ear-to-Coupler<br>Difference)<br>• LI/LO (Input-/Output curve)<br>• Percentile analysis |
| Technical<br>specifications | Common Data for all Applications:<br>• Frequency Accuracy: ± 1 %<br>• FFT: Resolution 1024 points,<br>Averaging: 10-100<br>• Intensity Accuracy: ± 1.5 dB<br>• Sweep Speed: 1.5 - 12 sec./decade at<br>25 Hz warble frequency (depending<br>on frequency resolution)<br>• Frequency Resolution: 1/3, 1/6, 1/12<br>and 1/24 octave<br>• Stimulus Distortion: Less than 1 %<br>THD | Common Data for all Applications:<br>• Frequency Accuracy: < 1 %<br>• FFT: Resolution 2048 points,<br>Averaging: 10-100<br>• Intensity Accuracy: ± 1.5 dB<br>• Sweep Speed: 1.5 - 12 sec./decade at<br>25 Hz warble frequency (depending<br>on frequency resolution)<br>• Frequency Resolution: up to 2048<br>points between 100Hz and 10kHz<br>• Stimulus Distortion: Less than 1 %<br>THD |
| Frequency Range | • 125 Hz - 8 kHz (AC & free field)<br>• 125 Hz - 16 kHz (AC, HF mode)<br>• 250 Hz - 6 kHz (BC) | • 125 Hz - 8 kHz (AC & free field)<br>• No HF mode<br>• 125 Hz - 8 kHz (BC) |
| Stimulus-Signal | • Pure tone, warble,<br>• Noise signals: White, narrow band,<br>speech<br>• ILTASS | • Pure tone, warble,<br>• Noise signals: White, narrow band,<br>speech |
| Measurement<br>Intensity Range | • AC: -10 - 130 dB HL<br>• BC: -10 - 80 dB HL | • AC: -10 - 120 dB HL<br>• BC: -10 - 70 dB HL |
| Frequency Range | • 125 Hz - 8 kHz (AC & free field)<br>• 125 Hz - 16 kHz (AC, HF mode)<br>• 250 Hz - 6 kHz (BC) | Audiometry<br>• 125 Hz - 8 kHz (AC, BC & free field)<br>HIT & REM<br>• 100 Hz - 10 kHz |
| Target gain<br>formulas | NAL-NL1 and DSL i/o; NAL-RP, Berger,<br>Pogo II, 1/3 Gain, 1/2 Gain, Fig6 (K-AMp) | NAL-NL1, DSL i/o, DSL mio; NAL-RP,<br>Berger, Pogo II, 1/3 Gain, 1/2 Gain, Fig6<br>(K-AMP), IDM, own Rules |
| Stimulus-Signal: | • Pure tone, warble,<br>• Noise signals: Narrow band, White,<br>Pink, Speech, ILTASS, ICRA, Chirp,<br>patient voice | • Pure tone, warble, CHIRP, Burst<br>• Noise signals: Narrow band, White,<br>Pink, Speech, ICRA,<br>• Real Signals: Speech, ISTS (about<br>200 live Signals) |
| Test Intensity<br>Range | Adjustable increments of 1 dB<br>• Speaker: 40 - 100 dB SPL | Adjustable increments of 1.dB<br>• Speaker: 0 - 100 dB SPL<br>• Open headphones: 0 - 100 dB SPL<br>• Insertion Earphones: 40 - 140 SPL |
| Device | Siemens Unity 2 with HIA and Probe | ACAM 5 |
| Specifications<br>Measurement | • Microphone: 40 - 145 dB SPL | • Microphone: <30 to >140 dB SPL |
| Intensity Range | | |
| Loudspeaker | • Max. 6 W into 8 ohms | • Max. 20 W into 4 ohms |
| Output | • Max. 10 W into 4 ohms | |
| Hearing Instrument | • Single measurement (configurable): | • Single measurement (configurable): |
| Analyzer | • OSPL90 | • OSPL90 |
| | • Full On Gain | • Full On Gain |
| | • Input/Output | • Input/Output |
| | • Attack/Release Time…
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.