K214002 · Precision Biologic, Inc. · GGP · Dec 23, 2022 · Hematology
Device Facts
Record ID
K214002
Device Name
CRYOcheck Chromogenic Factor IX
Applicant
Precision Biologic, Inc.
Product Code
GGP · Hematology
Decision Date
Dec 23, 2022
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.7290
Device Class
Class 2
Attributes
Pediatric
Indications for Use
CRYOcheck Chromogenic Factor IX is for clinical laboratory use in the quantitative determination of factor IX activity in 3.2% citrated human plasma. It is intended to be used in identifying factor IX deficiency and as an aid in the management of hemophilia B in individuals aged 2 years and older. For in vitro diagnostic use.
Device Story
CRYOcheck Chromogenic Factor IX is an in vitro diagnostic reagent kit used for the quantitative determination of Factor IX (FIX) activity in human plasma. The device is used in clinical laboratories on automated coagulation analyzers (ACL TOP family). The assay utilizes a chromogenic method: human FIX in the sample is activated by human FXIa; the resulting FIXa activates human FX in the presence of human FVIII, calcium ions, and phospholipids. The amount of FXa generated is proportional to the FIX activity in the sample and is determined by the hydrolysis of a chromogenic FXa substrate, measured spectrophotometrically at 405 nm. The output is expressed as percent activity relative to a calibration curve. This information aids clinicians in diagnosing FIX deficiency and managing hemophilia B. The device is provided frozen to preserve component integrity.
Clinical Evidence
Bench testing only. Performance evaluated on ACL TOP series analyzers. Precision (within-lab %CV 3.7-14.5%) and reproducibility (across-site %CV 5.6-15.7%) established. Linearity range 0-200% FIX activity. LoB/LoD/LoQ determined to be 0.4%, 0.5%, and 0.5% respectively. Method comparison (n=368) against a validated laboratory-developed chromogenic assay showed strong correlation (Pearson r=0.992) and equivalent performance. Interference studies identified Rivaroxaban and warfarin as interfering substances.
Technological Characteristics
Chromogenic assay; reagents include human FVIII, FX, FXIa, FII, bovine FV, fibrin polymerization inhibitor, phospholipids, and chromogenic FXa substrate. Form factor: Frozen liquid reagents. Connectivity: Integrated with IL ACL TOP/ACL TOP Family 50 Series analyzers. Measurement: Spectrophotometric at 405 nm. Standards: CLSI EP05-A3, EP06, EP07, EP17-A2, EP25-A, EP28-A3c.
Indications for Use
Indicated for quantitative determination of factor IX activity in 3.2% citrated human plasma to identify factor IX deficiency and aid in management of hemophilia B in individuals aged 2 years and older.
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K214002
B Applicant
Precision BioLogic Inc.
C Proprietary and Established Names
CRYOcheck Chromogenic Factor IX
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| GGP | Class II | 21 CFR 864.7290 - Factor Deficiency Test | HE - Hematology |
## II Submission/Device Overview:
A Purpose for Submission:
Clearance of a new device
B Measurand:
Factor IX activity (%)
C Type of Test:
Quantitative chromogenic assay
## III Intended Use/Indications for Use:
A Intended Use(s):
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
See Indications for Use below.
## B Indication(s) for Use:
CRYOcheck Chromogenic Factor IX is for clinical laboratory use in the quantitative determination of factor IX activity in 3.2% citrated human plasma. It is intended to be used in identifying factor IX deficiency and as an aid in the management of hemophilia B in individuals aged 2 years and older. For in vitro diagnostic use.
## C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
## D Special Instrument Requirements:
Instrument Laboratory (IL) ACL TOP (K160276) and ACL TOP Family 50 Series (K150877)
## IV Device/System Characteristics:
### A Device Description:
CRYOcheck Chromogenic Factor IX is used for determination of FIX activity and contains the following four components, packaged in vials, and provided frozen to preserve the integrity of the components:
| Reagent Name | Format (per vial set; each box contains 4 vial sets | Description |
| --- | --- | --- |
| Reagent 1 | 1 x 0.75 mL Frozen | Human FVIII, human FX, bovine FV and a fibrin polymerization inhibitor |
| Reagent 2 | 1 x 2.3 mL Frozen | Human FXIa, human FII, calcium chloride and phospholipids |
| Reagent 3 | 1 x 1.0 mL Frozen | FXa Substrate containing EDTA and thrombin inhibitor |
| Diluent Buffer | 1x 10.0 mL Frozen | Tris buffer solution containing 1% BSA and a heparin antagonist |
### B Principle of Operation:
CRYOcheck Chromogenic Factor IX is a chromogenic factor IX assay. In this assay, FIX activity is determined in a chromogenic method, in which human FIX is activated by human FXIa and where formed FIXa activates human FX in the presence of human FVIII, calcium ions and phospholipid. Similar to in vivo conditions, FVIII is activated by thrombin which is generated during the incubation. The amount of FXa formed is related to the FIX activity and is determined from the hydrolysis of a chromogenic FXa substrate. The color produced by the release of p-Nitroanilide (pNA) is measured spectrophotometrically at 405 nm and is proportional to the factor IX in the sample. FIX results are reported in percent activity where 100% FIX activity is equivalent to 1.0 IU/mL.
### V Substantial Equivalence Information:
K214002 - Page 2 of 10
{2}
A Predicate Device Name(s):
HemosIL Factor IX Deficient Plasma
B Predicate 510(k) Number(s):
K031829
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K214002 | K031829 |
| --- | --- | --- |
| Device Trade Name | CRYOcheck
Chromogenic Factor IX | HemosIL Factor IX
Deficient Plasma |
| General Device Characteristic Similarities | | |
| Intended Use/Indications for Use | CRYOcheck
Chromogenic Factor IX
is for clinical laboratory use in the quantitative determination of factor IX activity in 3.2% citrated human plasma. It is intended to be used in identifying factor IX deficiency and as an aid in the management of hemophilia B in individuals aged 2 years and older. For in vitro diagnostic use | Human plasma immunodepleted of factor IX for the quantitative determination of factor IX activity in citrated plasma, based on activated partial thromboplastin time (APTT) assay, on IL Coagulation Systems. |
| Classification | Class II | Same |
| Regulation Section | 21 CFR 864.7290
Factor Deficiency Test | Same |
| Type of Test | Quantitative | Same |
| Measurand | Human Factor IX activity | Same |
| Expression of Results | Quantitative; Results are expressed as percent activity interpreted relative to a calibration curve. | Same |
| Instrument | ACL TOP/ACL TOP Family 50 Series | ACL instruments/ACL TOP Family |
| General Device Characteristic Differences | | |
| Device Description | CRYOcheck
Chromogenic Factor IX
is used for | The Factor IX deficient plasma kit consists of: Factor IX deficient |
K214002 - Page 3 of 10
{3}
K214002 - Page 4 of 10
| | determination of FIX activity and contains the following four components, packaged in vials and provided frozen to preserve the integrity of the components: **Reagent 1:** Human FVIII, human FX, bovine FV and a fibrin polymerization inhibitor. **Reagent 2:** Human FXIa, human FII, calcium chloride and phospholipids. **Reagent 3:** FXa Substrate containing EDTA and a thrombin inhibitor. **Diluent Buffer:** Tris buffer solution containing 1% BSA and a heparin antagonist | plasma (Cat. No. 0020011910): 10 x 1 mL vials of lyophilized human plasma that has been artificially depleted of factor IX containing buffer and stabilizers. The residual factor IX activity is less than or equal to 1% whereas all other coagulation factors have normal levels |
| --- | --- | --- |
| Methodology | FIX activity is determined in a chromogenic method, in which human FIX is activated by human FXIa and where formed FIXa activates human FX in the presence of human FVIII, calcium ions and phospholipid. Similar to in vivo conditions, FVIII is activated by thrombin which is generated during the incubation. The amount of FXa formed is related to the FIX activity and is determined from the hydrolysis of a chromogenic FXa substrate. The color produced by the release of pNA is measured spectrophotometrically | Factor IX activity in a patient’s plasma is determined by performing a modified activated partial thromboplastin time test (APTT). Patient plasma is diluted and added to a plasma deficient in factor IX. Correction of the clotting time is proportional to the concentration (% activity) of that factor in the patient plasma, interpolated from a calibration curve. |
{4}
| | at 405 nm and is proportional to the factor IX in the sample. | |
| --- | --- | --- |
| Calibrator and Control Plasma | CRYOcheck Reference Control Normal, CRYOcheck Abnormal 1 and CRYOcheck Abnormal 2 Reference Control | IL Coagulation Normal and Abnormal control |
| Storage | 18 months at ≤-70 °C | 3 weeks at -20°C |
| Assay Reportable Range | 0.5–200% FIX activity | 0.5–150% |
| Limit of Detection | LoB – 0.4% FIX activity
LoD – 0.5% FIX activity
LoQ – 0.5% FIX activity | NA |
VI Standards/Guidance Documents Referenced:
CLSI EP05-A3, Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline – Third Edition
CLSI EP06, Evaluation of Linearity of Quantitative Measurement Procedures, 2nd Edition
CLSI EP07, Interference Testing in Clinical Chemistry, 3rd Edition
CLSI EP17-A2, Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline – Second Edition
CLSI EP25-A, Evaluation of Stability of In Vitro Diagnostic Reagents; Approved Guideline
CLSI EP28-A3c, Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory; Approved Guideline – Third Edition
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility
a. Single Site Precision
This study was conducted at the internal site over 20 days with two runs per day and two replicates per run, for a total of 80 determinations per sample per reagent lot. Three lots of CRYOcheck Chromogenic Factor IX were tested with six panel members on a single IL ACL TOP 700 CTS by two operators alternating testing days. Test samples included one normal and two abnormal reference controls, as well as three patient plasma samples representing very low, low, and high levels of FIX activity. Precision estimates were calculated for each
K214002 - Page 5 of 10
{5}
of the following variance components: within-run, between-run, between-day, between-lot and within-laboratory precision. The results for within-run and total imprecision for all lots combined are provided in the summary table below.
| Sample | N | Mean (%) | Within-Run | | Between-Run | | Between-Day | | Between-lot | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal reference control | 240 | 114.9 | 3.9 | 3.4 | 0.2 | 0.2 | 1.6 | 1.4 | 1.1 | 0.9 | 4.2 | 3.7 |
| Abnormal 1 reference control | 240 | 39.3 | 1.3 | 3.4 | 0.5 | 1.2 | 0.4 | 1.1 | 1.1 | 2.8 | 1.8 | 4.5 |
| Abnormal 2 reference control | 240 | 10.4 | 0.7 | 6.3 | 0.2 | 1.6 | 0.2 | 2.0 | 0.3 | 3.3 | 0.8 | 7.3 |
| Plasma sample 1 | 240 | 1.2 | 0.1 | 9.8 | 0.0 | 0.9 | 0.0 | 2.4 | 0.1 | 10.3 | 0.2 | 14.5 |
| Plasma sample 2 | 240 | 6.1 | 0.5 | 7.9 | 0.0 | 0.0 | 0.2 | 2.8 | 0.4 | 6.3 | 0.6 | 10.1 |
| Plasma sample 3 | 240 | 174.0 | 5.4 | 3.1 | 3.3 | 1.9 | 0.8 | 0.5 | 0.4 | 0.2 | 6.4 | 3.7 |
# b. Multi-Site Reproducibility
This study was conducted at three testing sites over five days with two runs per day and three replicates per run for a total of 90 determinations. The study design included three different representative instrument models (one instrument per site). There were two operators at each site alternating test days. The study quantified three reagent lots testing one normal and two abnormal reference controls as well as three patient plasma samples representing very low, low, and high levels of FIX activity. Precision estimates were calculated for each of the following variance components: within-run, between-run, between-day, between-site and reproducibility. The results for overall reproducibility for all the lots combined are provided in the summary table below.
| Sample | N | Mean (%) | Within-Run | | Between-Run | | Between-Day | | Between-Site | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal reference control | 270 | 113.1 | 5.0 | 4.5 | 0.9 | 0.8 | 1.1 | 1.0 | 1.9 | 1.7 | 6.3 | 5.6 |
| Abnormal 1 reference control | 270 | 38.4 | 1.8 | 4.8 | 0.2 | 0.6 | 0.1 | 0.3 | 1.3 | 3.4 | 2.5 | 6.6 |
| Abnormal 2 reference control | 270 | 10.8 | 0.8 | 7.5 | 0.2 | 1.7 | 0.0 | 0.0 | 0.2 | 2.0 | 0.9 | 8.6 |
| Plasma sample 1 | 270 | 1.2 | 0.1 | 6.9 | 0.0 | 1.7 | 0.0 | 0.0 | 0.0 | 0.0 | 0.2 | 15.7 |
| Plasma sample 2 | 270 | 6.3 | 0.5 | 7.9 | 0.1 | 1.2 | 0.1 | 2.1 | 0.2 | 2.4 | 0.8 | 13.0 |
| Plasma sample 3 | 270 | 168.5 | 7.6 | 4.5 | 0.0 | 0.0 | 1.3 | 0.8 | 4.4 | 2.6 | 10.0 | 6.0 |
# 2. Linearity:
The linearity studies were performed following the CLSI EP06 $2^{\mathrm{nd}}$ Ed guideline using three reagent lots at one site on a single IL ACL TOP 700 CTS instrument. Fourteen sample dilutions were prepared using a high FIX plasma ( $\sim 230\%$ ) with congenital FIX deficient plasma ( $\sim 0\%$ ) to create sample dilutions ranging from $0 - 230\%$ FIX activity. Each dilution was tested in four replicates. The linear range for CRYOcheck Chromogenic Factor FIX assay was determined to be $0 - 200\%$ .
# 3. Analytical Specificity/Interference:
Interference study was conducted in accordance with the CLSI EP07-A3 guideline. A single lot of CRYOcheck Chromogenic Factor IX was used on an IL ACL TOP 700 CTS instrument.
K214002 - Page 6 of 10
{6}
Potentially interfering endogenous and exogenous substances were spiked into the control samples (one normal and one abnormal reference control plasma). Ten replicates were evaluated for each spiked plasma or matrix-blank plasma. The maximum concentration of each interferent was determined per CLSI EP37 guideline. None of the substances in the following table (endogenous or exogenous) were found to lead to clinically significant interference (up to the concentrations indicated in the table below).
| Interferent | Concentration |
| --- | --- |
| Unconjugated Bilirubin | 40 mg/dL |
| Conjugated Bilirubin | 23 mg/dL |
| Hemoglobin | 1000 mg/dL |
| Intralipid | 2000 mg/dL |
| Dabigatran | 0.04 mg/L |
| Fondaparinux | 0.26 mg/L |
| Low Molecular Weight Heparin (LMWH) | 1.5 IU/mL |
| Unfractionated Heparin | 1.2 IU/mL |
| Lupus Anticoagulant | dRVVT ratio = 1.8 |
4. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
Traceability
Three levels of CRYOcheck Reference controls are prepared from human citrated plasma with three different concentrations of hemostatic parameters. CRYOcheck Reference Control Normal (K013708) was normal human citrated plasma while CRYOcheck Abnormal 1 Reference Control (K952624) and CRYOcheck Abnormal 2 Reference Control (K952624) were the citrated human plasma with hemostatic parameter values in the borderline pathological range 30% to 44% and 9% to 17%, respectively. Calibrator value assignments are traceable to the WHO International Standard for Factor IX (4th IS Factors II, VII, IX, X, Plasma, 09/172).
Sample Stability
Sample stability studies were performed to support the recommended storage and handling instructions found in the device labeling. Citrated plasma samples were tested after storage in the following temperature ranges, room temperature (18–22°C) and below -70°C. The study was performed using two reagent lots of CRYOcheck Chromogenic Factor IX on IL ACL TOP 300 and IL ACL TOP 700 analyzers with five replicate measurements at each time point for each sample. The study data demonstrate that citrated plasma samples are stable for four hours when stored at room temperature (18–22°C), three months when stored at <-70°C, including up to two freeze thaw cycles.
Shelf-life Stability
The shelf-life stability study was performed to determine the shelf-life stability of CRYOcheck Chromogenic Factor IX when stored at ≤-70 °C. The study was conducted with five plasma samples (one normal, two abnormal reference controls and two patient plasmas)
K214002 - Page 7 of 10
{7}
using three lots of CRYOcheck Chromogenic Factor IX on an IL ACL TOP 700 CTS analyzer. Samples were thawed from ≤-70 °C storage and tested in five replicates for FIX activity at the following timepoints: 0, 6, 7, 12, 13, 18, 19, 24, 25, 36 and 37 months. The study is ongoing and current data supports the shelf-life stability claim of 18 months when the product is stored at ≤-70 °C.
## In Use Stability
The in-use stability studies were performed to characterize in-use stability of CRYOcheck Chromogenic Factor IX assay when maintained at three different in-use conditions: on-board ACL TOP analyzer (12–18°C), in a refrigerator (2–8°C) and refrozen at ≤-70°C after maintaining on board for 3 hours. Five plasma samples (one normal, two abnormal reference controls and two patient plasmas) were tested by one operator on one IL ACL TOP 700 CTS analyzer. Samples were tested in five replicates by using three lots of CRYOcheck Chromogenic Factor IX at each storage condition at each timepoint. The study data supports the in-use stability claim of 24-hours when the product is stored on-board (12–18°C), 48 hours at 2–8°C and 1 month stored at ≤-70°C if the product is stored on board and refrozen within 4 hours of the initial thaw. The refrozen product must be used within 8 hours of next thawing while kept on-board.
## 5. Detection Limit:
The limit of blank (LoB), limit of detection (LoD), and limit of quantification (LoQ) for test system were determined following the CLSI EP17-A2 guideline. Each study design included three reagent lots and one representative instrument model (IL ACL TOP 700 CTS).
The LoB was determined using four blank plasma samples obtained from individuals with severe congenital hemophilia B. Each sample was tested in triplicate using three lots of CRYOcheck Chromogenic Factor IX over five days on an IL ACL TOP instrument for N=15 determinations per reagent lot. The LoB was determined to be 0.4% FIX activity.
The LoD was determined using four plasma samples with low FIX activity obtained from individuals with congenital hemophilia B donors. Each sample was tested in triplicate using three lots of CRYOcheck Chromogenic Factor IX over five days on an IL ACL TOP instrument for N=15 determinations per reagent lot. The LoD was determined to be 0.5% FIX activity.
The LoQ was determined using four plasma samples with low FIX activity obtained from congenital hemophilia B donors. Samples were measured in triplicate using three lots of CRYOcheck Chromogenic Factor IX over five days on an IL ACL TOP 700 instrument. The samples were also measured in triplicate using a validated laboratory-developed chromogenic factor IX assay (ROX Factor IX) over five days to determine the assigned values. The LoQ was determined to be 0.5% FIX activity.
## 6. Assay Cut-Off:
Not Applicable
## 7. Recovery of FIX Replacement Therapies
K214002 - Page 8 of 10
{8}
The recovery of replacement therapy study was conducted to evaluate the recovery of FIX activity of seven FIX replacement therapies with one lot of CRYOcheck Chromogenic Factor IX. A congenital FIX deficiency plasma was used to prepare seven concentration levels for each FIX replacement therapy (1.0, 0.8, 0.6, 0.4, 0.2, 0.1, 0.05 IU/mL). Ten replicates of each level of each product were tested on an IL ACL TOP 700 CTS analyzer. The FIX percent recovery was determined from the measured versus expected FIX activity (%) of each product at each level. CRYOcheck Chromogenic Factor IX recovered FIX activity levels in plasma containing AlphaNine, Alprolix, BeneFIX, Ixinity, Rebinyn and Rixubiz at concentrations ranging from 0.05 to 1.0 IU/mL. There was an over estimation of Idelvion across all concentration relative to labeled potency.
| Product | Mean Percent Recovery (%) |
| --- | --- |
| AlphaNine SD | 96 |
| Alprolix | 116 |
| BeneFIX | 93 |
| Ixinity | 82 |
| Rebinyn | 117 |
| Rixubis | 102 |
| Idelvion | 153 |
## B Comparison Studies:
### 1. Method Comparison with Predicate Device:
The method comparison study was conducted using the CRYOcheck Chromogenic FIX on the Instrumentation Laboratory (IL) ACL TOP 700 and IL ACL TOP 750 CTS by testing n=386 clinical samples (citrated plasma) collected from the intended use population. Results from the CRYOcheck Chromogenic FIX were compared to results from the ROX Factor IX validated laboratory developed test. The following table summarizes the line equation from the Passing-Bablok regression analysis performed for the combined dataset.
| N | FIX Activity Range (%) | Slope (95% CI) | Intercept (95% CI) | Pearson Correlation Coefficient |
| --- | --- | --- | --- | --- |
| 368 | 0.7–190.7 | 1.10 (1.08, 1.12) | 0.64 (0.20, 1.34) | 0.992 |
### 2. Matrix Comparison:
Not Applicable
## C Clinical Studies:
### 1. Clinical Sensitivity:
Not Applicable
K214002 - Page 9 of 10
{9}
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
E Expected Values/Reference Range:
The reference interval study was conducted at one laboratory site. The FIX activity of plasma samples collected from 128 normal, ostensibly healthy individuals (≥ 18 years) was tested by two operators using three lots of CRYOcheck Chromogenic FIX on two Instrumentation Laboratory ACL TOP instruments. The reference interval was established by calculating the non-parametric 95% confidence interval (2.5th to 97.5th percentiles). The calculated normal reference range for CRYOcheck Chromogenic FIX is 78.8–154.9%.
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.
K214002 - Page 10 of 10
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.