TRANSONIC HEMODIALYSIS MONITOR, CARDIAC OUTPUT, MODEL HD01-CO
K980906 · Transonic Systems, Inc. · MQS · Oct 6, 1998 · Gastroenterology, Urology
Device Facts
Record ID
K980906
Device Name
TRANSONIC HEMODIALYSIS MONITOR, CARDIAC OUTPUT, MODEL HD01-CO
Applicant
Transonic Systems, Inc.
Product Code
MQS · Gastroenterology, Urology
Decision Date
Oct 6, 1998
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 876.5820
Device Class
Class 2
Indications for Use
The HD01-CO monitor is intended for use by trained medical personnel, for assessment of a patient's hemodynamic condition through estimation of cardiac output while undergoing hemodialysis treatment in a non-critical care setting. For use only by or on the order of a physician licensed by law to use or order the use of this device.
Device Story
Device measures cardiac output during hemodialysis using transit-time ultrasound dilution. System includes bench-top HD01 meter, two clip-on ultrasonic sensors (arterial/venous), and PC-based software. Operation: 10ml saline bolus injected into venous bubble trap for sensor calibration; 30ml saline bolus injected into venous line near patient for measurement. Bolus circulates through cardiopulmonary system; arterial sensor detects indicator dilution. Software integrates dilution curve using Stewart-Hamilton equations to calculate cardiac output. Used in clinical settings by trained medical personnel. Output displayed on PC; assists clinicians in hemodynamic assessment. Benefits include non-invasive monitoring without indwelling catheters through heart/lungs, reducing risks associated with traditional thermodilution methods.
Clinical Evidence
Bench testing and literature review provided. Bench accuracy ±5%, repeatability ±4%, cardiac output range 1-20 L/min. Clinical validation cited via 8 published studies (e.g., ASAIO Journal) comparing ultrasound dilution method to thermal methods. No new clinical trials conducted; reliance on established literature and bench performance data.
Technological Characteristics
Materials: plastic-encased ultrasonic sensors. Sensing: transit-time ultrasound. Energy: line-powered electronics. Connectivity: RS232 serial link to PC. Software: Windows-based application for signal processing and calculation. Standards: UL-544, IEC 601-1, 89/336/EEC. Ultrasound intensity levels 25-40 dB below CDRH limits.
Indications for Use
Indicated for patients undergoing hemodialysis treatment to assess hemodynamic condition via cardiac output estimation. For use by trained medical personnel under physician order in non-critical care settings.
Regulatory Classification
Identification
A hemodialysis system and accessories is a device that is used as an artificial kidney system for the treatment of patients with renal failure or toxemic conditions and that consists of an extracorporeal blood system, a conventional dialyzer, a dialysate delivery system, and accessories. Blood from a patient flows through the tubing of the extracorporeal blood system and accessories to the blood compartment of the dialyzer, then returns through further tubing of the extracorporeal blood system to the patient. The dialyzer has two compartments that are separated by a semipermeable membrane. While the blood is in the blood compartment, undesirable substances in the blood pass through the semipermeable membrane into the dialysate in the dialysate compartment. The dialysate delivery system controls and monitors the dialysate circulating through the dialysate compartment of the dialyzer.(1) The extracorporeal blood system and accessories consists of tubing, pumps, pressure monitors, air foam or bubble detectors, and alarms to keep blood moving safely from the blood access device and accessories for hemodialysis (§ 876.5540) to the blood compartment of the dialyzer and back to the patient. (2) The conventional dialyzer allows a transfer of water and solutes between the blood and the dialysate through the semipermeable membrane. The semipermeable membrane of the conventional dialyzer has a sufficiently low permeability to water that an ultrafiltration controller is not required to prevent excessive loss of water from the patient's blood. This conventional dialyzer does not include hemodialyzers with the disposable inserts (Kiil type) (§ 876.5830) or dialyzers of high permeability (§ 876.5860). (3) The dialysate delivery system consists of mechanisms that monitor and control the temperature, conductivity, flow rate, and pressure of the dialysate and circulates dialysate through the dialysate compartment of the dialyzer. The dialysate delivery system includes the dialysate concentrate for hemodialysis (liquid or powder) and alarms to indicate abnormal dialysate conditions. This dialysate delivery system does not include the sorbent regenerated dialysate delivery system for hemodialysis (§ 876.5600), the dialysate delivery system of the peritoneal dialysis system and accessories (§ 876.5630), or the controlled dialysate delivery system of the high permeability hemodialysis system § 876.5860). (4) Remote accessories to the hemodialysis system include the unpowered dialysis chair without a scale, the powered dialysis chair without a scale, the dialyzer holder set, dialysis tie gun and ties, and hemodialysis start/stop tray.
Predicate Devices
American Edwards Lab's COC-1 Thermodilution Cardiac Output Computer (K980906)
Submission Summary (Full Text)
{0}------------------------------------------------
OCT 6 1998 Transonic Systems
### 1 OF 8 K980906
Section 2 - Summary Device Safety and Effectiveness
## 2. 510(k) SUMMARY
This summary of 510(k) safety and effectiveness information is being submitted in accordance with the requirements of SMDA 1990 and 21 CFR 807.92, by:
| Contact Person: | Cornelis J. Drost, President<br>Transonic Systems, Inc.<br>34 Dutch Mill Road<br>Ithaca, NY 14850-9787, USA<br>Phone: 607-257-5300<br>FAX: 607-257-7256<br>Internet: www.transonic.com<br>E-Mail: cor@transonic.com |
|-----------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|-----------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
On:
March 10, 1998
# 2.1 Device Identification & Substantial Equivalency Claims
Table 2-1 summarizes the Device Identification and Substantial Equivalency Claims for the Transonic HD01-CO Cardiac Output Monitor.
| Trade name → | TRANSONIC HD01-CO<br>HEMODIALYSIS CARDIAC OUTPUT<br>MONITOR |
|-----------------------------------------------------|-------------------------------------------------------------------------|
| Common name → | Hemodialysis cardiac output monitor |
| Devices in this model family claimed → | Cardiac output monitor |
| Model Name → | HD01-CO |
| Legally marketed device<br>to which SE is claimed → | American Edwards Lab's COC-1<br>Thermodilution Cardiac Output Computer. |
# Table 2-1: Device Identification and Substantial Equivalency Claims
{1}------------------------------------------------
Section 2 - Summary Device Safety and Effectiveness
#### 2.2 Device Description.
The HD01 family of devices use transit-time ultrasound principles to measure blood flow and to register sound velocity indicator dilution curves. Standard Stewart-Hamilton equations are employed for the various calculations. Portions of these technologies are covered under Transonic Systems' USA and worldwide patents and pending patents.
Image /page/1/Figure/5 description: This image shows a diagram of a hemodialysis machine. The diagram includes a patient connected to the machine via two tubes labeled A and V. The machine also includes a Transonic Hemodialysis Monitor, a laptop, flow and dilution clip-on sensors, and a dialyzer. The diagram shows the flow of blood from the patient through the machine and back to the patient.
Figure 2-1: System block diagram of the HD01 flow/dilution meter.
All Transonic HD01-series hemodialysis monitor devices consist of the following components (see Figure 2-1):
- HD01 Flow/Dilution meter ( or HD01 meter) - This is a bench-top, line-powered electronic measurement unit with a serial RS232 data output link, and connections for ultrasonic flow/dilution sensors. (See Figure 1-3, and Figure 1-3, and Figure 1-4 on pages 1-1 through 1-3.
- . Dual flow/dilution sensor - these are two plastic-encased ultrasonic sensors connected to the HD01 unit (see Figure 1-1 on page 1-1). One sensor is individually referred to as the "arterial sensor" and is clipped to the patient's arterial hemodialysis line, while the other (the "venous sensor") is clipped to the venous hemodialysis line.
- . Monitor software (also referred to as software) - This is computer software installed on an IBM-PC compatible computer running Windows or Windows 95. The software receives signal data produced by the HD01 meter and performs the various device function calculations (QA, QB, R%, and CO - see Table 1-1 on page 1-1).
The various HD01 devices differ in their indications for use through the supplied software routines. The following section discusses the software routines for Cardiac Output measurement.
2-2
{2}------------------------------------------------
Transonic Systems
Section 2 - Summary Device Safety and Effectiveness
#### 2.3 Cardiac Output (CO) Measurement Technique
The Cardiac Output (CO) measurement technique requires the following HD01 sensor configuration and injectable indicator solution:
- ultrasonic dilution sensors clipped to the venous and arterial dialysis lines .
- . venous and arterial blood lines are connected as normal (not reversed) to the dialysis needles
- Body temperature (37°C) 0.9% saline solution .
The CO measurement starts by calibrating the venous indicator dilution sensor. This is done by injecting a 10 ml saline bolus into the venous bubble trap. Since all of the bolus volume passes through the venous sensor, the following equation determines that sensor's sensitivity to indicator dilution:
$$\mathcal{K} = \frac{\mathcal{V}_{\text{cat}}}{\mathcal{Q}_b \, ^\ast \mathcal{S}}$$
where:
| Vcal | = volume of calibration bolus injected (ml) |
|------|--------------------------------------------------|
| Qb | = mean dialysis blood flow (ml/min) |
| K | = concentration scaling factor (ppm/millivolt) |
| S | = area of ultrasonic dilution curve (volt - sec) |
Like the calibration, the actual CO measurement requires a saline injection into the venous dialysis line. The difference is that the measurement bolus is larger (30 ml), and it is injected at a location close to the patient. This bolus circulates through the cardiopulmonary system, a fraction of it returns to the arterial sensor, and the arterial sensor records the indicator dilution.
Finally, the HD01-CO software integrates the indicator dilution curve and calculates Cardiac Output from the following formula:
$$\mathcal{Q}_{co} = \frac{V_{meas}}{K S}$$
where:
$Q_{co}$ = cardiac output ( ml/min) = volume of injected bolus (ml saline) $V_{meas}$ = concentration scaling-factor (ppm/mv) K = area of dilution curve = 1 volt sec S
{3}------------------------------------------------
#### Section 2 - Summary Device Safety and Effectiveness
## 2.4 Intended Uses of the HD01 Cardiac Output Monitor
The HD01-series monitors are intended for use by trained medical personnel, for assessment of a patient's hemodynamic condition through cardiac output determination while undergoing hemodialysis treatment
For use only by or on the order of a physician licensed by law to use or order the use of this device.
### Contraindications:
- The H4D dual flow/dilution sensor is for clip-on use only onto the dialysis tubing . specific to the flow sensor, and never on arteries or veins.
- Safe and effective use of these devices depend on correct application technique, . adequate precaution and readiness for emergencies.
- Caution: Federal law restricts this device to use by or on the order of a physician. .
{4}------------------------------------------------
## 2.5 Summary of Technological Comparison with Predicate Device.
The Transonic HD01-CO Cardiac Output Monitoring device uses ultrasonic velocity measurements to measure indicator dilution.
American Edwards Lab's COC-1 Thermodilution Cardiac Output Computer uses the same Stewart-Hamilton indicator dilution equations, but measures indicator dilution through blood temperature changes.
### 2.6 Safety
The HD01-series devices meet all requirements of:
- UL-544 & IEC 601-1 ●
- . The European Economic Council Directive 89/336/EEC (electromagnetic compatibility)
- . Ultrasound intensity levels applied by the H4D clip-on flow/dilution sensors are 25 to 40 dB below FDA CDRH maximum pre-amendment levels for "Fetal Doppler and Other" applications, and have passed FDA review under 510(k) #K960817
All procedures required to execute these measurements (saline injection, change in blood line connections) are standard clinical procedures in which hemodialysis nurses are well trained.
The HD01 procedures introduce no extra components into the hemodialysis circuit, and at no time is patient sterility compromised.
Image /page/4/Picture/13 description: The image shows a black and white abstract pattern. The pattern consists of small, irregular black shapes scattered across a white background. The shapes are concentrated in the upper portion of the image, with fewer shapes appearing towards the bottom.
{5}------------------------------------------------
Transonic Systems
Section 2 - Summary Device Safety and Effectiveness
## 2.7 Effectiveness.
Table 2-2 lists printed publications that document the effectiveness of the HD01-CO cardiac output measurements, while Table 2-3 compares HD01-CO effectiveness with that of the predicate device. Appendix D contains copies of all these papers.
- 1. Krivitski, N.M., "Novel Method to Measure Access Flow During Hemodialysis by Ultrasound Dilution Technique," ASAIO Journal, Vol. 41, p. M741-M745, 1995.
- 2. Krivitski, N.M., "Cardiac Output Measurement in Extracorporeal Systems by Ultrasound Dilution," ASAIO Journal Abstracts, p. 82, 1994.
- 3. Nikiforov, U.V., Kisloukhine, V.V., Chaus, N.I., "Validation of a New Method to Measure Cardiac Output During Extracorporeal Detoxification," ASAIO Journal Vol. 42, No. 5, p. M903-M905, 1996.
- 4. Kisloukhine, V.V, Dean, D.A., "Validation of a Novel Ultrasound Dilution Method to Measure Cardiac Output During Hemodialysis," ASAIO Journal, Vol. 42, No. 5, p. M906-M907, 1996.
- J.J.. Glidden, D., Miranda, C.. "Access 5. Sands. Flow Measured during Hemodialysis," ASAIO Journal, Vol. 42, No. 5, p. M530-M532, 1996.
- 6. Depner, T.A., Eder, L.A., "Changes in Access Blood Flow and Appearance of Recirculation during Hemodialysis," XIIIth International Congress of Nephrology Abstracts, p. 570, 1995.
- 7. Chaus, N.I, Kislukhin, V.V., Dzemeshkevich, S.L., Zhidkov, I.L., "Comparison of Sound Velocity, Impedance, and Optical with Thermal Methods for Cardiac Output," FASEB Journal, Vol. 11, No. 3, Abstract #2872, 1997.
- 8. Depner, T.A. & Krivitski, N.M., "Influence of Access Blood Flow (AF) on Systemic Blood Flow in Hemodialysis Patients," JASN. Vol.8, p. 155A, 1997.
# Table 2-2: Cardiac Output Theory, Validation & Application Reports (Appendix D contains copies of all these papers)
20
{6}------------------------------------------------
2
# Section 2 - Summary Device Safety and Effectiveness
| | American Edwards COC-1 Thermodilution<br>Cardiac Output Computer with Swan Ganz<br>catheter | Transonic HD01-CO<br>with H4D sensor |
|----------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Indications | For assessment of a patient's hemodynamic<br>condition through cardiac output<br>determination | For assessment of a patient's hemodynamic<br>condition through cardiac output determination<br>while undergoing hemodialysis |
| Contra-<br>indications | Not for use on patients with recurring sepsis,<br>patients with a hypercoagulable state, or (for<br>some catheters) patients sensitive to heparin | Clip-on sensors for use only on patient-<br>connected hemodialysis bloodlines, never on<br>arteries or veins. |
| Safety | | |
| Measurement<br>Method | The medical<br>community<br>raises<br>serious<br>concerns on a possible higher co-morbidity<br>when Swan-Ganz catheters are used. | Saline injection into HD venous line.<br>No separate indwelling devices: measurement<br>uses sensor clamped-on to hemodialysis line |
| Procedural<br>Dangers to<br>Patient | Inject saline directly into vena cava.<br>Sterile indwelling catheter must be entered<br>into a vein, passed through the heart (through<br>two heart valves) and into the pulmonary<br>artery | Measurement consists of procedures which are<br>standard in hemodialysis administration |
| Electrical | Input leakage current < 50 $\mu$ A<br>Patient leakage current < 10 $\mu$ A<br>Patient isolation > 2500V<br>10 $\mu$ A safety-trip electronics to protect<br>against thermal sensor insulation failure | Input leakage current < 50 $\mu$ A<br>Patient leakage current < 10 $\mu$ A<br>Patient isolation > 2500V<br>Double insulated sensor electronics, plus wall<br>of sterile tubing. |
| Ultrasonic | Not applicable | Ultrasonic irradiation level is 320 times lower<br>than CDRH permitted level for peripheral<br>vessel use. (Already FDA-cleared under 510(K)<br>#K960817) |
| Effectiveness | | |
| Bench Accuracy | In vitro: $\pm$ 3% (0-4 ℃), or $\pm$ 4% (19-25 ℃)<br>+ thermistor-related sensing errors | From all sources: $\pm$ 5 % |
| Bench | Computational variations: $\pm$ 3% | Computational variations: Negligible |
| Repeatability | Variations from all sources: Not Specified | Variations from all sources: $\pm$ 4% |
| <i>In Vivo</i> Accuracy | $\pm$ 20% (inferred from literature) | $\pm$ 20% |
| Cardiac Output<br>Measurement<br>Range | 0.1 to 20 L/min | 1 to 20 L/min |
Table 2-3: Comparisons between the HD01 devices and the predicate device
2-7
{7}------------------------------------------------
K980906 - PAGE 8 OF 8
Transonic Systems
Section 2 - Summary Device Safety and Effectiveness
#### 2.7 Summary of Safety and Effectiveness.
The bench and clinical tests cited above demonstrate that, like the predicate devices, the HD01-CO device is safe and effective for its intended use.
Cornelia J. Frost
Cornelis J. Drost, President Transonic Systems Inc. 34 Dutch Mill Road Ithaca, NY 14850
March 10, 1998 Preparation date
22
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image shows the logo for the Department of Health & Human Services - USA. The logo is circular, with the text "DEPARTMENT OF HEALTH & HUMAN SERVICES - USA" arranged around the perimeter of the circle. In the center of the circle is an abstract symbol that resembles an eagle or a stylized human figure.
Food and Drug Administration 9200 Corporate Boulevard Rockville MD 20850
OCT 6 1998
Mr. Cornelius J. Drost President Transonic Systems Inc. 34 Dutch Mill Road Ithaca, New York 14850-9787
" Re: K980906 Model HD01-CO Hemodialysis Monitor for Cardiac Output Dated: July 7, 1998 Received: July 8, 1998 Regulatory Class: II 21 CFR 876.5820/Procode: 78 MQS
Dear Mr. Drost:
We have reviewed your section 510(k) notification of intent to market the device referenced above and we have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to 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. You may, therefore, market the device, subject to the general controls provisions Act (Act). The general controls provisions of the Act include requirements for registration, listing of devices, good manufacturing practices, labeling, and prohibitions against misbranding and adulteration.
This determination of substantial equivalence applies to the following transducers intended for use with the Transonics Systems Inc. HD01-Series Hemodialysis Monitors, as described in your premarket notification:
| Device Model | Transducer Model Number |
|--------------|--------------------------|
| HD01-CO | H4D FLOW/DILUTION SENSOR |
If your device is classified (see above) into either class II (Special Controls) or class III (Premarket Approval) it may be subject to such additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 895. A substantially equivalent determination assumes compliance with the Good Manufacturing Practice for Medical Devices: General (GMP) regulation (21 CFR Part 820) and that, through periodic GMP inspections, the FDA will verify such assumptions. Failure to comply with the GMP regulation may result in regulatory action. In addition, the Food and Drug Administration (FDA) may publish further announcements concerning your device in the Federal Register. Please note: this response to your premarket notification does not affect any obligation you may have under sections 531 and 542 of the Act for devices under the Electronic Product Radiation Control provisions, or other Federal laws or regulations.
This determination of substantial equivalence is granted on the condition that prior to shipping the first device, you submit a postclearance special report. This report should contain complete information, including acoustic output measurements based on production line devices, requested in Appendix G. (enclosed) of the Center's April 1995, "Format and Content of Diagnostic Ultrasound Special 510(k)." If the special report is incomplete or contains unacceptable values (e.g., acoustic output greater than approved levels), then the 510(k) clearance may not apply to the production units which as a result may be considered adulterated or misbranded.
{9}------------------------------------------------
Page 2 - Mr. Cornelis J. Drost
The special report should reference the manufacturer's 510(k) number. It should be clearly and prominently marked "ADD-TO-FILE" and should be submitted in duplicate to:
> Food and Drug Administration Center for Devices and Radiological Health Document Mail Center (HFZ-401) 9200 Corporate Boulevard Rockville, Maryland 20850
This letter will allow you to begin marketing your device as described in your premarket notification. The FDA finding of substantial equivalence of your device to a legally marketed predicate device results in a classification for your device and thus permits your device to proceed to market.
If you desire specific advice for your device on our labeling regulation (21 CFR Part 801 and additionally 809.10 for in vitro diagnostic devices), please contact the Office of Compliance at (301) 594-4591. Additionally, for questions on the promotion and advertising of your device, please contact the Office of Compliance at (301) 594-4639. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). Other general information on your responsibilities under the Act may be obtained from the Division of Small Manufacturers Assistance at its toll-free number (800) 638-2041 or at (301) 443-6597 or at its Internet address "dsmo@fdadr.cdrh.fda.gov".
If you have any questions regarding the content of this letter, please contact Mr. Richard J. Williams at (301) 594-1220.
Sincerely yours,
Jarind le. Seymon
Lillian Yin, Ph.D.
Director, Division of Reproductive, Abdominal, Ear, Nose and Throat, and Radiological Devices Office of Device Evaluation Center for Devices and Radiological Health
Enclosures
{10}------------------------------------------------
Page 1 of 1
## 510 (k) NUMBER (IF KNOWN) : K980906
DEVICE NAME: Transonic Hemodialysis Monitor, Cardiac Output, Model HD01-CO
## INDICATIONS FOR USE:
The HD01-CO monitor is intended for use by trained medical personnel, for assessment of a patient's hemodynamic condition through estimation of cardiac output while undergoing hemodialysis treatment in a non-critical care setting.
For use only by or on the order of a physician licensed by law to use or order the use of this device.
# (PLEASE DO NOT WRITE BELOW THIS LINE-CONTINUE ON ANOTHER PAGE IF NEEDED.)
Concurrence of CDRH, Office of Device Evaluation (ODE)
Prescription Use V (Per 21 CFR 801.109) OR
Over-The-Counter-Use (Optional Format 1-2-96)
Clifford C. Degnan
vision Sign-Off) Division of Reproductive, Abdominal, ENT, and Radiological I 510(k) Number
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.