The ABL90 FLEX PLUS System is an in vitro diagnostic, portable, automated analyzer that quantitatively measures: - blood gas (pCO2) in heparinized arterial, venous and capillary whole blood, and - pH and oximetry (ctHb) in heparinized capillary whole blood. The ABL90 FLEX PLUS System is intended for use by trained technologists, nurses, physicians and therapists. It is intended for use in a laboratory environment, near patient, or point-of-care setting. These tests are only performed under a physician's order. pH and pCO2: pH and pCO2 measurements are used in the diagnosis and treatment of life-threatening acid-base disturbances. ctHb (Total Hemoglobin): Total hemoglobin measurements are used to measure the hemoglobin content of whole blood for the detection of anemia in venous and arterial whole blood. Capillary whole blood is used to estimate the presence of ctHb. safeCLINITUBES are intended for the collection, mixing, and dispensing of capillary whole blood samples on the ABL90 FLEX PLUS System.
Device Story
The ABL90 FLEX PLUS System is a portable, automated in vitro diagnostic analyzer for blood gas and oximetry analysis. It accepts heparinized arterial, venous, or capillary whole blood samples. Capillary samples are collected using safeCLINITUBES. The device utilizes potentiometry (pH, pCO2) and spectrophotometry (ctHb) to analyze samples. The system features an automated sample inlet mechanism with specific modes for different sample types (S65 syringe, SP65 short probe, C65 capillary). Operated by trained technologists, nurses, physicians, or therapists in clinical or point-of-care settings, the device provides quantitative results to clinicians. These results are used to diagnose and treat life-threatening acid-base disturbances and detect anemia. The system aids clinical decision-making by providing rapid, accurate blood chemistry data at the point of care, potentially improving patient management in acute care environments.
Clinical Evidence
Bench testing only. Analytical performance was validated through precision studies (multi-day, multi-site, POC operators), linearity (CLSI EP06-A2), interference testing (CLSI EP07-ED3/EP37-ED1), and method comparison (CLSI EP09c-ED3). Precision for pCO2 in capillary mode showed SDs ranging from 1.207 to 2.770 mmHg. Method comparison against a comparator method for capillary samples yielded R² values of 0.93 (pH, pCO2) and 0.95 (ctHb). No clinical trials were required.
Technological Characteristics
The system uses potentiometric sensors for pH and pCO2 (Nernst equation) and spectrophotometry for ctHb. Consumables include a sensor cassette (SC) and solution pack (SP). Capillary samples are processed via safeCLINITUBES (70/100μL). The system is a portable, automated analyzer. Connectivity and software details are consistent with previously cleared versions (K240998). Sterilization and material specifications are maintained from the predicate.
Indications for Use
Indicated for use in patients requiring quantitative measurement of pH, pCO2, and ctHb in heparinized whole blood (arterial, venous, or capillary) to assist in the diagnosis and treatment of acid-base disturbances and anemia. Intended for use by trained healthcare professionals in laboratory or point-of-care settings.
Regulatory Classification
Identification
A blood gases (PCO2 , PO2 ) and blood pH test system is a device intended to measure certain gases in blood, serum, plasma or pH of blood, serum, and plasma. Measurements of blood gases (PCO2 , PO2 ) and blood pH are used in the diagnosis and treatment of life-threatening acid-base disturbances.
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K252207
B Applicant
Radiometer Medicals ApS
C Proprietary and Established Names
ABL90 FLEX PLUS System, safeCLINITUBES
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CHL | Class II | 21 CFR 862.1120 - Blood Gases (PCO2, PO2) And Blood Ph Test System | CH - Clinical Chemistry |
| GKR | Class II | 21 CFR 864.5620 - Automated hemoglobin system | HE - Hematology |
| JKA | Class II | 21 CFR 862.1675 - Blood specimen collection device | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
Modification to a previously cleared device.
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
B Measurand:
1. pH (acidity)
2. pCO2 (partial pressure of carbon dioxide)
3. ctHB (total hemoglobin concentration)
C Type of Test:
Quantitative - Sensors using Potentiometry for pH and pCO2 measurement; Spectrophotometry for the measurement of ctHb.
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The ABL90 FLEX PLUS System is an in vitro diagnostic, portable, automated analyzer that quantitatively measures:
- blood gas (pCO2) in heparinized arterial, venous and capillary whole blood, and
- pH and oximetry (ctHb) in heparinized capillary whole blood.
The ABL90 FLEX PLUS System is intended for use by trained technologists, nurses, physicians and therapists. It is intended for use in a laboratory environment, near patient, or point-of-care setting.
These tests are only performed under a physician's order.
pH and pCO2: pH and pCO2 measurements are used in the diagnosis and treatment of life-threatening acid-base disturbances.
ctHb (Total Hemoglobin): Total hemoglobin measurements are used to measure the hemoglobin content of whole blood for the detection of anemia in venous and arterial whole blood. Capillary whole blood is used to estimate the presence of ctHb.
safeCLINITUBES are intended for the collection, mixing, and dispensing of capillary whole blood samples on the ABL90 FLEX PLUS System.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
D Special Instrument Requirements:
ABL90 FLEX PLUS System
K252207 - Page 2 of 10
{2}
K252207 - Page 3 of 10
# IV Device/System Characteristics:
## A Device Description:
The ABL90 FLEX PLUS System consists of the ABL90 FLEX PLUS analyzer, sensor cassette (SC) and solution pack (SP) consumables, and related accessories for the analyzer as described in K240998. This submission is for the addition of capillary heparinized whole blood samples for pH and ctHB, and for capillary, arterial and venous heparinized whole blood samples for pCO2. The ABL90 FLEX PLUS System has an automated sample inlet mechanism, which can collect arterial and venous whole blood through two different measuring modes: the S65 syringe mode and the SP65 short probe mode, and capillary whole blood through the C65 capillary mode.
safeCLINITUBES are 70 and 100μL plastic capillary tubes with balanced heparin, mixing wires and end caps.
The ABL90 FLEX PLUS System was cleared in K241037 for the quantitative measurement of cK+, cNa+, cCa2+, glucose and lactate using arterial and venous heparinized whole blood samples. The system was cleared for the quantitative measurement of pH, blood gas (pO2), Oximetry (sO2, ctHb, FO2Hb, FCOHb, FMetHb, and FHHb) using arterial and venous heparinized whole blood samples in K240998.
## B Principle of Operation:
There are two different measuring principles employed by the ABL90 FLEX PLUS System: Potentiometry and spectrophotometry.
- Potentiometry: The potential of an electrode chain is measured by a voltmeter and related to the concentration of the sample (the Nernst equation). The potentiometric measuring principle is applied in the pH and pCO2 sensors.
- Spectrophotometry: Light passes through a cuvette that contains a hemolyzed blood sample. The absorption spectrum is used to calculate oximetry parameters. This measuring principle is used for ctHb.
# V Substantial Equivalence Information:
## A Predicate Device Name(s):
ABL90 FLEX PLUS
## B Predicate 510(k) Number(s):
K160153
## C Comparison with Predicate(s):
| Device & Predicate Device(s): | K252207 | K160153 |
| --- | --- | --- |
| Device Trade Name | ABL90 FLEX PLUS System | ABL90 FLEX PLUS |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | In vitro diagnostic that quantitatively measures | Same |
{3}
| Device & Predicate Device(s): | K252207 | K160153 |
| --- | --- | --- |
| | pH, blood gases, and oximetry. | |
| Intended Use and Environment | Intended for use by trained technologists, nurses, physicians, and therapists in a laboratory environment, near patient, or point-of-care setting. | Same |
| Prescription/OTC Use | Prescription Use | Same |
| General Device Characteristic Differences | | |
| Sample type | Balanced heparinized capillary whole blood for pH, ctHb and PCO2 using the safeCLINITUBES | No capillary whole blood claim for pH, ctHb and PCO2 |
VI Standards/Guidance Documents Referenced:
Clinical and Laboratory Standards Institute (CLSI) EP05-A3 – Evaluation of Precision of Quantitative Measurement Procedures
CLSI EP17-A2 2nd Edition – Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline
CLSI EP06-2nd Edition – Evaluation of Linearity of Quantitative Measurement Procedures
CLSI EP07-3rd Edition – Interference Testing in Clinical Chemistry
CLSI EP09c 3rd Edition – Measurement Procedure Comparison and Bias Estimation Using Patient Samples
CLSI EP37 1st Edition – Supplemental Tables for Interference Testing in Clinical Chemistry
CLSI EP39 1st Edition – A Hierarchical Approach to Selecting Surrogate Samples for the Evaluation of In Vitro Medical Laboratory Tests
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
Point of care precision (aqueous control material):
A multi-day precision study was performed at three point of care (POC) sites using four concentrations of aqueous control solutions. At each site, each level was tested as two replicates per run, two runs per day, for twenty days. At least three POC operators were
K252207 - Page 4 of 10
{4}
included at each site. Repeatability, within-laboratory precision, and reproducibility results are reported below:
| Parameter | QC Level | N | Mean | Repeatability | | Within Lab-Precision | | Reproducibility | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | | SD | CV% | SD | CV% | SD | CV% |
| pCO2 (mmHg) | L 1 | 243* | 70.5 | 0.53 | 0.7 | 1.13 | 1.6 | 1.16 | 1.6 |
| | L 2 | 244 | 42.7 | 0.23 | 0.5 | 0.5 | 1.2 | 0.50 | 1.2 |
| | L 3 | 244 | 23.1 | 0.12 | 0.5 | 0.27 | 1.2 | 0.29 | 1.2 |
| | L 4 | 244 | 97.3 | 1.17 | 1.2 | 1.81 | 1.9 | 2.08 | 2.1 |
*One L1 sample replicate was excluded due to insufficient sample being loaded onto the instrument.
Point of Care precision (Whole Blood) pCO2 in S65 and SP65 Mode:
A multi-day precision study was performed at three sites by at least three POC operators at each site, using balanced heparinized whole blood targeted to levels within the reportable range of pCO2. The whole blood precision was assessed using duplicate test results collected across multiple point of care sites using both the S65 and SP65 sampling modes. Samples were grouped into subintervals based on their mean values. The results are summarized below.
| Parameter (unit) | N | Test interval | Mean | Repeatability | |
| --- | --- | --- | --- | --- | --- |
| | | | | SD | CV% |
| S65 Mode | | | | | |
| pCO2 (mmHg) | 4 | 25 - <32 | 27.775 | 0.320 | 1.15 |
| | 166 | 32 - <48 | 40.417 | 0.271 | 0.67 |
| | 50 | 48 - <60 | 52.030 | 0.266 | 0.51 |
| | 26 | 60 - <80 | 67.908 | 0.495 | 0.73 |
| SP65 Mode | | | | | |
| pCO2 (mmHg) | 4 | 25 - <32 | 29.375 | 1.005 | 3.42 |
| | 160 | 32 - <48 | 40.448 | 0.168 | 0.42 |
| | 50 | 48 - <60 | 51.742 | 0.231 | 0.45 |
| | 27 | 60 - <80 | 68.989 | 0.334 | 0.48 |
# Within Sample Precision - Capillary Mode Fingerstick
A multi-day precision study to assess heparinized capillary whole blood sample within run precision in capillary mode was performed at two sites by at least two POC operators at each site. Capillary whole blood from 39 donors via finger stick puncture from two (2) fingers into 2 safeCLINITUBE capillary tubes was collected. Blood from each capillary pair was analyzed in singlet in capillary mode on one ABL90 FLEX PLUS analyzer. Samples were grouped into subintervals based on their mean values. The results are summarized below.
K252207 - Page 5 of 10
{5}
| Parameter (unit) | N | Test interval | Mean | Repeatability | |
| --- | --- | --- | --- | --- | --- |
| | | | | SD | CV% |
| pH | 20 | 7.2 - <7.35 | 7.325 | 0.012 | 0.17 |
| | 40 | 7.35 - <7.40 | 7.374 | 0.011 | 0.15 |
| | 18 | 7.40 - <7.55 | 7.430 | 0.016 | 0.21 |
| pCO2 (mmHg) | 6 | 25 - <35 | 32.233 | 1.626 | 5.04 |
| | 58 | 35 - <48 | 41.002 | 1.207 | 2.94 |
| | 14 | 48 - <60 | 51.636 | 2.770 | 5.36 |
| ctHb (g/dL) | 30 | 8 - <13.5 | 11.487 | 0.285 | 2.48 |
| | 46 | 13.5 - <17.5 | 14.930 | 0.248 | 1.66 |
## 2. Linearity:
Linearity testing was conducted in general accordance with CLSI EP06-A2. The linearity of the ABL90 FLEX PLUS System test for pCO2 was evaluated by preparing balanced heparinized venous whole blood samples. To achieve target concentrations, samples for pCO2 were prepared via tonometry. At least 10 replicates were run for each level. The results are summarized below. Linearity for pH, and ctHb was previously established in K240998.
| Parameter (units) | Reportable Range | Tested Range | Slope | Intercept | R2 |
| --- | --- | --- | --- | --- | --- |
| pC02 (mmHg) | 15.4-98.3 | 9.4 – 99.89 | 1.009 | 0 | 0.9995 |
## 3. Analytical Specificity/Interference:
Interference testing was performed according to CLSI EP07-ED3 and CLSI EP37-ED1 and consisted of two parts: paired-difference testing and dose-response experiments.
a. The paired-difference testing was conducted on all potential interferents. Matched samples were tested, one with no interferent and the other with the interferent. If no interference was found, no further testing was performed.
b. The dose-response experiment was only conducted on interferents found to have an effect via the paired-difference testing. This was carried out to determine the concentration at which clinically significant interference occurred.
Freshly drawn heparinized adult venous whole blood was used as starting material for the interference studies. Interference testing was conducted at two levels (i.e., low and high) for
K252207 - Page 6 of 10
{6}
pCO2. The following tables list the concentrations of each substance at which no significant interference was found.
Highest concentration tested at which no significant interference is observed
| Potential interferent for parameter pCO2 | Concentration |
| --- | --- |
| Bilirubin, conjugated | 40 mg/dL |
| Bilirubin, unconjugated | 40 mg/dL |
| Biotin | 3510 ng/mL |
| Hemolysis | 20% |
| Intralipid | 2000 mg/dL |
| Propofol | 4.8 mg/dL |
Interference for pH, and ctHb was previously established in K240998.
## 4. Assay Reportable Range:
The reportable ranges are
| Parameter | Unit | Reportable Range |
| --- | --- | --- |
| pH | pH Scale | 6.818 - 7.797 |
| pCO2 | mmHg | 15.4 - 98.3 |
| ctHb | g/dL | 0.1 - 24.0 |
## 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
pCO2: Traceable to the International System of Units (SI) via commercially available certified specialty medical gas standards.
Refer to K240998 for traceability information for pH and ctHB
## 6. Detection Limit:
Detection capability testing was conducted in general accordance with CLSI EP17-A2. To achieve target concentrations, heparinized venous whole blood samples for pCO2 were prepared via tonometry. Testing was performed on the ABL90 FLEX PLUS System using 3 reagent lots, 9 instruments, over the course of 9 days, using 4 independent samples, with at least 5 replicates/sample, and 60 replicates/reagent lot.
| Parameter (units) | Reportable Range | LoQ results |
| --- | --- | --- |
| pCO2 (mmHg) | 15.4-98.3 mmHg | 8.9 |
Detection limits for pH and ctHB were previously established in K240998
K252207 - Page 7 of 10
{7}
7. Assay Cut-Off:
Not applicable.
B Comparison Studies:
1. Method Comparison with Predicate Device:
Method comparison for pCO2 using heparinized arterial and venous whole blood specimens in S65 and SP65 mode and for pH, pCO2, and ctHb in heparinized capillary whole blood samples in C65 mode on the ABL90 FLEX PLUS System was done in general accordance with CLSI EP09c-ED3. Heparinized arterial and venous whole blood specimens (maximum of 10% contrived) that spanned the measuring range were collected across 3 POC sites to evaluate pCO2 measurements. Capillary blood samples (maximum of 10% contrived) collected across 2 POC sites in 2 safeCLINITUBE capillary tubes, with at least two POC users per site was compared to arterial whole blood specimens tested on a comparator method. Specifically, each capillary whole blood sample was measured once on the candidate device in C65 mode and once on the comparator device. A comparison between the two measurements was performed using linear regression analysis. The regression analysis are summarized below.
Method Comparison - pCO2 in Arterial and Venous Whole Blood
| Parameter | n | Range Min | Range Max | Intercept | Slope | R2 | Medical decision level (MDL) | Bias at MDL |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| S65 | | | | | | | | |
| pCO2 (mmHg) | 446 | 16.1 | 95 | 0.55 | 0.99 | 1.0 | 32 | 0.20 |
| | | | | | | | 48 | 0.03 |
| SP65 | | | | | | | | |
| pCO2 (mmHg) | 429 | 16.3 | 97.1 | 0.60 | 0.99 | 1.0 | 32 | 0.21 |
| | | | | | | | 48 | 0.02 |
K252207 - Page 8 of 10
{8}
Method comparison – capillary whole blood
| Parameter | N | Intercept | Slope | R² | MDL | Bias at MDL |
| --- | --- | --- | --- | --- | --- | --- |
| pH (pH scale) | 115 | -0.118 | 1.01 | 0.93 | 7.35 | -0.01 |
| | | | | | 7.45 | -0.01 |
| pCO2 (mmHg) | 119 | 3.094 | 0.95 | 0.93 | 32 | 1.6 |
| | | | | | 48 | 0.85 |
| ctHb (g/dL) | 110 | 0.713 | 0.99 | 0.95 | 7 | 0.66 |
| | | | | | 10 | 0.63 |
| | | | | | 17.5 | 0.57 |
| Parameter | N | Range Min | Range Max | MDL | Bias at MDL |
| --- | --- | --- | --- | --- | --- |
| pH | 115 | 6.87 | 7.78 | 7.35 | -0.01 |
| | | | | 7.45 | -0.01 |
| pCO2 (mmHg) | 119 | 17 | 92.9 | 32 | 1.6 |
| | | | | 48 | 0.85 |
| ctHb (g/dL) | 110 | 0.36 | 22 | 7 | 0.66 |
| | | | | 10 | 0.63 |
| | | | | 17.5 | 0.57 |
2. Matrix Comparison:
Not applicable.
C Clinical Studies:
1. Clinical Sensitivity:
Not applicable.
2. Clinical Specificity:
Not applicable.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable.
D Clinical Cut-Off:
Not applicable.
K252207 - Page 9 of 10
{9}
K252207 - Page 10 of 10
# E Expected Values/Reference Range:
Below are general reference ranges, cited from literature, for a normal, healthy population.
| Parameter | Unit | Reference range |
| --- | --- | --- |
| pCO2 | mmHg; Torr | 35-481 (male)
32-451 (female) |
| | kPa | 4.67-6.401 (male)
4.27-6.001 (female) |
| ctHb | (g/dL) | 13.5 – 17.53 (male) / 12.0 – 16.03 (female)^{2} |
| pH | | 7.35 – 7.45^{1} |
1 Tietz NW, Logan NM. Reference ranges, In: Fundamentals of clinical chemistry. 3rd ed. Philadelphia: WB Saunders Company 1987: 944-75.
2 Burtis CA, Ashwood ER, Bruns DE. Tietz textbook of clinical chemistry and molecular diagnostics. 5th ed. St. Louis: Saunders Elsevier, 2012.
# VIII Proposed Labeling:
The labeling supports the finding of substantial equivalence for this device.
# IX Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.