K231031 · Instrumentation Laboratory Company · GKP · Jun 21, 2023 · Hematology
Device Facts
Record ID
K231031
Device Name
ACL TOP Family 70 Series
Applicant
Instrumentation Laboratory Company
Product Code
GKP · Hematology
Decision Date
Jun 21, 2023
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.5400
Device Class
Class 2
Indications for Use
The ACL TOP Family 70 Series (ACL TOP 370, ACL TOP 570 and ACL TOP 770 / 770s / 770 LAS) are bench top, fully automated, random access analyzers designed specifically for in vitro diagnostic clinical use by health care professionals in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The systems provide results for both direct hemostasis measurements and calculated parameters.
Device Story
Bench-top, fully automated, random access coagulation analyzers; used in hemostasis laboratories by healthcare professionals. Inputs: clinical samples (plasma). Principle: optical measurement (turbidimetric, chromogenic, immunological) at 405, 535, and 671 nm. Outputs: quantitative results for coagulation/fibrinolysis assays and calculated parameters. Features: pre-analytical HIL (Hemoglobin, Icteric, Lipemia) interference detection, underfilled tube detection, and clog detection. Updated features include 22-inch touchscreen, aesthetic GUI updates, 'Study Mode' for internal performance studies, and permission-based remote-control for desktop sharing/software updates. Clinical utility: aids in thrombosis and hemostasis assessment; provides standardized, automated testing to support clinical decision-making.
Clinical Evidence
Bench testing only. Precision studies (n=80 per model) evaluated D-Dimer, Factor VIII, PT, Fibrinogen, and Heparin assays, meeting all acceptance criteria for repeatability and within-laboratory precision. Method comparison studies (n=104-260 samples) against the predicate (ACL TOP 750 CTS) demonstrated high correlation (r > 0.99) across all assays, confirming equivalent performance.
Technological Characteristics
Benchtop, fully automated, random-access coagulation analyzer. Optical detection (405, 535, 671 nm). Barcode-based sample/reagent identification. Cap-piercing sample handling. Onboard refrigerated reagent storage with stirring. 22-inch color touchscreen interface. Connectivity includes remote-control functionality for desktop sharing and software updates. Compliant with IEC 61010-1, 61010-2-101, 61010-2-010, 61326-1, 61326-2-6, and 60601-1-2 standards.
Indications for Use
Indicated for use by healthcare professionals in hemostasis laboratories for coagulation and/or fibrinolysis testing to assess thrombosis and/or hemostasis. Prescription use only.
Regulatory Classification
Identification
A coagulation instrument is an automated or semiautomated device used to determine the onset of clot formation for in vitro coagulation studies.
Special Controls
*Classification.* Class II (special controls). A fibrometer or coagulation timer intended for use with a coagulation instrument is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.
Predicate Devices
ACL Top Family 50 Series: ACL Top 350 CTS; ACL Top 550 CTS; ACL Top 750; ACL Top 750 CTS; ACL Top 750 LAS (K150877)
Submission Summary (Full Text)
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
INSTRUMENT ONLY
## I Background Information:
A 510(k) Number
K231031
B Applicant
Instrumentation Laboratory Company
C Proprietary and Established Names
ACL TOP Family 70 Series
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| GKP | Class II | 21 CFR 864.5400 - Coagulation Instrument | HE - Hematology |
## II Submission/Device Overview:
A Purpose for Submission:
To release the updated ACL TOP Family 50 Series models under the trade name ACL TOP Family 70 Series.
B Type of Test:
Clotting, chromogenic, and immunological coagulation assays
## III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
The ACL TOP Family 70 Series (ACL TOP 370, ACL TOP 570 and ACL TOP 770 / 770s / 770 LAS) are bench top, fully automated, random access analyzers designed specifically for in vitro diagnostic clinical use by health care professionals in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The systems provide results for both direct hemostasis measurements and calculated parameters.
## C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
## IV Device/System Characteristics:
### A Device Description:
The ACL TOP Family 70 Series are fully automated coagulation analyzers that utilize the same intuitive software, the same consumables, reagents, calibrators and controls, and provide the same analytical methodology for routine and specialty assay result reporting as the predicate ACL TOP Family 50 Series.
The ACL TOP Family 70 Series instrument performs the following types of tests, using the same optical measuring wavelengths and test parameters as the predicate ACL TOP Family 50 Series:
- Coagulometric (Turbidimetric) Measurements
- Chromogenic (Absorbance) Measurements
- Immunological Measurements
The ACL TOP Family 70 Series also offers the same pre-analytical features available on the ACL TOP Family 50 Series. These features alert the instrument operator to a potential HIL (Hemoglobin, Icteric and Lipemia) interference situation specific to the assays requested for a sample, underfilled sample tubes or a detected clog.
### B Instrument Description Information:
1. **Instrument Name:**
ACL TOP Family 70 Series (ACL TOP 370, ACL TOP 570, ACL TOP 770, ACL TOP 770s, ACL TOP 770 LAS)
2. **Specimen Identification:**
Samples, reagents, and diluents are identified by a barcode reader.
3. **Specimen Sampling and Handling:**
Draw blood into a light blue top tube containing 3.2% sodium citrate. Using other anticoagulants may cause invalid results. Fill to the proper level, indicated by a fill line on the tube. Gently invert six times to mix. Process immediately.
4. **Calibration:**
The ACL TOP instrument makes dilutions, adds reagents, and takes readings, then generates a calibration curve. The instrument can store the ten most recent calibrations. However, only one calibration can be validated at any time.
K231031 - Page 2 of 14
{2}
K231031 - Page 3 of 14
5. Quality Control:
The ACL TOP instrument provides a Quality Control (QC) program that allows user to monitor performance characteristics of an analytical system for precision and accuracy as well as alert user to sources of unacceptable analytical performance.
V Substantial Equivalence Information:
A Predicate Device Name(s):
ACL Top Family 50 Series: ACL Top 350 CTS; ACL Top 550 CTS; ACL Top 750; ACL Top 750 CTS; ACL Top 750 LAS
B Predicate 510(k) Number(s):
K150877
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K231031 | K150877 |
| --- | --- | --- |
| Device Trade Name | ACL TOP Family 70 Series | ACL TOP Family 50 Series |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | The ACL TOP Family 70 Series (ACL TOP 370, ACL TOP 570 and ACL TOP 770 / 770s / 770 LAS) are bench top, fully automated, random access analyzers designed specifically for in vitro diagnostic clinical use by health care professionals in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The systems provide results for both direct hemostasis measurements and calculated parameters. | The ACL TOP Family 50 Series (ACL TOP 350 CTS, ACL TOP 550 CTS, ACL TOP 750, ACL TOP 750 CTS, ACL TOP 750 LAS) are bench top, fully automated, random access analyzers designed specifically for in vitro diagnostic clinical use in the hemostasis laboratory for coagulation and/or fibrinolysis testing in the assessment of thrombosis and/or hemostasis. The systems provides results for both direct hemostasis measurements and calculated parameters. |
| Test Methodology | • Coagulometric measurement
• Chromogenic measurement
• Immunological measurement | Same |
| Wavelengths | • 405 nm
• 535 nm | Same |
{3}
K231031 - Page 4 of 14
| | • 671 nm | |
| --- | --- | --- |
| Test Menu | • Clotting Assays
• Chromogenic Assays
• Immunological Assays | Same |
| Sample Matrix | 3.2% citrated plasma | Same |
| Sample Handling | Cap piercing, onboard storage | Same |
| Fluidic Handling | Aspiration, dispense, mixing, rinse, clean, temperature control, bulk fluids | Same |
| Reaction and Detection | Optics, temperature control | Same |
| Quality Control | Automated QC | Same |
| Reagents, Controls and Calibrators | Packaging, formulation, performance claims in labeling | Same |
| Onboard Reagent Storage | Stirring, temperature control | Same |
| System Software | Hardware control, user interface except as noted in Differences below | Same |
| Pre-Analytical HIL Check | Standard for all models: Third measurement wavelength at 535 nm and an additional emitter control channel | Same |
| Tube Fill Height Check | Standard for all models | Same |
| Clog Detection | Standard for all models | Same |
| General Device Characteristic Differences | | |
| External Skins and Chassis | On-market instrument appearance | Updated instrument appearance |
| Control Module | 22-inch Color Touchscreen Monitor | 17-inch Color Touchscreen Monitor |
| Software | Software v1.3
• Designed for the ACL TOP Family 70 Series using predicate ACL TOP Family 50 Series SW v6.5 as a foundation
• Updated Graphical User Interface (GUI) for aesthetics (e.g., higher resolution icons)
• Added the Study Mode internal function to support laboratories in more efficiently meeting their | Software v6.5 |
{4}
K231031 - Page 5 of 14
| | Quality System requirements. The Study Mode provides the interface for laboratories to organize and execute their internal performance studies, including collection of data for lot comparison, instrument comparison, or reference intervals.
• Added permission-based remote-control function for desktop sharing and remote software delivery and upgrades, utilizing security and privacy controls by design and installed by default. | |
| --- | --- | --- |
## VI Standards/Guidance Documents Referenced:
CLSI EP05-A3: Evaluation of Precision of Quantitative Measurement Procedures (3rd Edition);
IEC 61326-1:2020: Electrical equipment for measurement, control and laboratory use – EMC requirements – Part 1: General requirements;
IEC 61326-2-6:2020: Electrical equipment for measurement, control and laboratory use – EMC requirements – Part 2-6: IVD medical equipment;
IEC 61010-1:2017: Safety requirements for electrical equipment for measurement, control, and laboratory use - Part 1: General requirements;
IEC 61010-2-101:2018 Safety requirements for electrical equipment for measurement, control, and laboratory use - Part 2-101: IVD medical equipment;
IEC 61010-2-010:2019 Safety requirements for electrical equipment for measurement, control, and laboratory use - Part 2-010: Heating;
IEC 60601-1-2:2020: Edition Medical electrical equipment - Part 1-2: General requirements for basic safety and essential performance.
## VII Performance Characteristics (if/when applicable):
### A Analytical Performance:
1. **Precision/Reproducibility:**
Precision testing was performed on selected representative assays to evaluate the following test methodologies:
- Latex agglutination
- Clotting (Calibrated)
{5}
- Clotting (Non-calibrated)
- Chromogenic (Calibrated)
These selected assays include HemosIL D-Dimer HS 500 (K172903), HemosIL Factor VIII deficient plasma (K034007), HemosIL RecombiPlasTin 2G (K070005), and HemosIL Liquid Anti-Xa (K213464) represent the highest volume used in the market for each test methodology.
## D-Dimer Precision Study
Precision testing was performed for D-dimer with one reagent lot of HemosIL D-Dimer HS 500 using representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770). For each material, testing was executed for 20 days at two runs per day, 2 replicates per run (n=80) per instrument model. Low and high controls, as well as two sample pools, were tested. All acceptance criteria for repeatability and within-laboratory precision were met.
### ACL TOP 370 D-Dimer Precision Summary
| Material | N | Mean (ng/mL FEU) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Low Control | 80 | 710.7 | 38.8 | 5.5 | 0.0 | 0.0 | 18.8 | 2.6 | 43.1 | 6.1 |
| High Control | 80 | 2353.4 | 48.0 | 2.0 | 8.8 | 0.4 | 23.2 | 1.0 | 54.0 | 2.3 |
| Cut-off Pool | 80 | 619.8 | 24.5 | 4.0 | 0.0 | 0.0 | 13.1 | 2.1 | 27.8 | 4.5 |
| High Pool | 80 | 2373.8 | 33.1 | 1.4 | 14.4 | 0.6 | 13.8 | 0.6 | 38.6 | 1.6 |
### ACL TOP 570 D-Dimer Precision Summary
| Material | N | Mean (ng/mL FEU) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Low Control | 80 | 674.3 | 34.4 | 5.1 | 4.8 | 0.7 | 8.5 | 1.3 | 35.8 | 5.3 |
| High Control | 80 | 2472.4 | 31.6 | 1.3 | 22.0 | 0.9 | 6.1 | 0.2 | 39.0 | 1.6 |
| Cut-off Pool | 80 | 590.2 | 36.7 | 6.2 | 11.8 | 2.0 | 0.0 | 0.0 | 38.5 | 6.5 |
| High Pool | 80 | 2529.5 | 21.7 | 0.9 | 19.0 | 0.8 | 0.0 | 0.0 | 28.8 | 1.1 |
### ACL TOP 770 D-Dimer Precision Summary
| Material | N | Mean (ng/mL FEU) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Low Control | 80 | 676.9 | 30.5 | 4.5 | 0.0 | 0.0 | 10.2 | 1.5 | 32.2 | 4.8 |
| High Control | 80 | 2488.9 | 41.3 | 1.7 | 0.0 | 0.0 | 32.2 | 1.3 | 52.4 | 2.1 |
| Cut-off Pool | 80 | 569.9 | 36.5 | 6.4 | 0.0 | 0.0 | 6.4 | 1.1 | 37.1 | 6.5 |
| High Pool | 80 | 2486.6 | 50.2 | 2.0 | 0.0 | 0.0 | 0.0 | 0.0 | 50.2 | 2.0 |
K231031 - Page 6 of 14
{6}
D-Dimer Instrument-to-Instrument Variability
| Material | N | Mean (ng/mL FEU) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Between-Instrument | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Low Control | 240 | 687.3 | 34.7 | 5.1 | 0.0 | 0.0 | 13.3 | 1.9 | 19.8 | 2.9 | 42.1 | 6.1 |
| High Control | 240 | 2438.2 | 40.9 | 1.7 | 11.0 | 0.5 | 23.2 | 1.0 | 73.6 | 3.0 | 88.0 | 3.6 |
| Cut-off Pool | 240 | 593.3 | 33.1 | 5.6 | 4.8 | 0.8 | 7.6 | 1.3 | 24.8 | 4.2 | 42.3 | 7.1 |
| High Pool | 240 | 2463.3 | 36.9 | 1.5 | 9.5 | 0.4 | 0.0 | 0.0 | 80.3 | 3.3 | 88.9 | 3.6 |
Factor VIII Precision Study
Precision testing was performed for factor VIII with one reagent lot of HemosIL Factor VIII deficient plasma using representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770). For each material, testing was executed for 20 days at two runs per day, 2 replicates per run (n=80) per material per instrument model. Normal and abnormal controls, as well as two sample pools, were tested. All acceptance criteria for repeatability and within-laboratory precision were met.
ACL TOP 370 Factor VIII Precision Summary
| Material | N | Mean (%) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 92.06 | 2.58 | 2.8 | 1.63 | 1.8 | 1.29 | 1.4 | 3.31 | 3.6 |
| Abnormal Control | 80 | 28.44 | 0.78 | 2.8 | 0.95 | 3.3 | 0.57 | 2.0 | 1.35 | 4.8 |
| Plasma Pool 1 | 80 | 31.59 | 0.82 | 2.6 | 0.80 | 2.5 | 0.79 | 2.5 | 1.39 | 4.4 |
| Plasma Pool 2 | 80 | 8.43 | 0.27 | 3.2 | 0.00 | 0.0 | 0.15 | 1.7 | 0.30 | 3.6 |
ACL TOP 570 Factor VIII Precision Summary
| Material | N | Mean (%) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 92.66 | 2.67 | 2.9 | 2.26 | 2.4 | 0.00 | 0.0 | 3.50 | 3.8 |
| Abnormal Control | 80 | 28.78 | 0.64 | 2.2 | 0.87 | 3.0 | 0.00 | 0.0 | 1.08 | 3.7 |
| Plasma Pool 1 | 80 | 32.45 | 2.54 | 7.8 | 0.00 | 0.0 | 0.66 | 2.0 | 2.62 | 8.1 |
| Plasma Pool 2 | 80 | 9.01 | 0.22 | 2.4 | 0.13 | 1.5 | 0.20 | 2.2 | 0.32 | 3.6 |
ACL TOP 770 Factor VIII Precision Summary
| Material | N | Mean (%) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 94.22 | 2.43 | 2.6 | 1.20 | 1.3 | 1.69 | 1.8 | 3.19 | 3.4 |
| Abnormal Control | 80 | 29.58 | 0.59 | 2.0 | 0.95 | 3.2 | 0.86 | 2.9 | 1.41 | 4.8 |
| Plasma Pool 1 | 80 | 33.30 | 0.90 | 2.7 | 0.64 | 1.9 | 0.65 | 1.9 | 1.28 | 3.8 |
| Plasma Pool 2 | 80 | 9.01 | 0.22 | 2.4 | 0.00 | 0.0 | 0.11 | 1.2 | 0.24 | 2.7 |
K231031 - Page 7 of 14
{7}
Factor VIII Instrument-to-Instrument Variability
| Material | N | Mean (%) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Between-Instrument | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 240 | 92.98 | 2.56 | 2.8 | 1.75 | 1.9 | 1.21 | 1.3 | 1.01 | 1.1 | 3.48 | 3.7 |
| Abnormal Control | 240 | 28.93 | 0.68 | 2.3 | 0.92 | 3.2 | 0.56 | 2.0 | 0.55 | 1.9 | 1.39 | 4.8 |
| Plasma Pool 1 | 240 | 32.45 | 1.63 | 5.0 | 0.47 | 1.4 | 0.70 | 2.2 | 0.81 | 2.5 | 2.00 | 6.2 |
| Plasma Pool 2 | 240 | 8.82 | 0.23 | 2.7 | 0.03 | 0.3 | 0.15 | 1.8 | 0.33 | 3.8 | 0.44 | 4.9 |
Prothrombin Time (PT) Precision Study
Precision testing was performed for prothrombin time (PT) with one reagent lot of HemosIL RecombiPlasTin 2G using representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770). For each material, testing was executed for 20 days at two runs per day, 2 replicates per run (n=80) per material per instrument model. Three control levels, as well as one sample pool, were tested. All acceptance criteria for repeatability and within-laboratory precision were met.
ACL TOP 370 Prothrombin Time Precision Summary
| Material | N | Mean (sec) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 11.97 | 0.09 | 0.8 | 0.09 | 0.8 | 0.16 | 1.4 | 0.21 | 1.7 |
| Low Abn Control | 80 | 23.23 | 0.19 | 0.8 | 0.44 | 1.9 | 0.66 | 2.8 | 0.81 | 3.5 |
| High Abn Control | 80 | 36.62 | 0.39 | 1.1 | 0.95 | 2.6 | 1.28 | 3.5 | 1.64 | 4.5 |
| Plasma Pool | 80 | 38.00 | 0.47 | 1.2 | 0.61 | 1.6 | 1.29 | 3.4 | 1.50 | 4.0 |
ACL TOP 570 Prothrombin Time Precision Summary
| Material | N | Mean (sec) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 11.84 | 0.10 | 0.9 | 0.17 | 1.4 | 0.11 | 1.0 | 0.23 | 1.9 |
| Low Abn Control | 80 | 23.07 | 0.21 | 0.9 | 0.39 | 1.7 | 0.73 | 3.2 | 0.85 | 3.7 |
| High Abn Control | 80 | 36.72 | 0.30 | 0.8 | 1.01 | 2.8 | 1.42 | 3.9 | 1.77 | 4.8 |
| Plasma Pool | 80 | 37.82 | 0.40 | 1.1 | 0.88 | 2.3 | 1.14 | 3.0 | 1.50 | 4.0 |
ACL TOP 770 Prothrombin Time Precision Summary
| Material | N | Mean (sec) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 11.94 | 0.07 | 0.6 | 0.10 | 0.9 | 0.17 | 1.4 | 0.21 | 1.8 |
| Normal Control | 80 | 23.24 | 0.15 | 0.7 | 0.37 | 1.6 | 0.75 | 3.2 | 0.85 | 3.7 |
| Low Abn Control | 80 | 36.93 | 0.29 | 0.8 | 0.89 | 2.4 | 1.57 | 4.3 | 1.83 | 5.0 |
| High Abn Control | 80 | 38.10 | 0.34 | 0.9 | 0.71 | 1.9 | 1.32 | 3.5 | 1.54 | 4.0 |
K231031 - Page 8 of 14
{8}
Prothrombin Time Instrument-to-Instrument Variability
| Material | N | Mean (sec) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Between-Instrument | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 240 | 11.92 | 0.09 | 0.8 | 0.13 | 1.0 | 0.15 | 1.3 | 0.06 | 0.5 | 0.22 | 1.9 |
| Normal Control | 240 | 23.18 | 0.19 | 0.8 | 0.40 | 1.7 | 0.72 | 3.1 | 0.00 | 0.0 | 0.84 | 3.6 |
| Low Abn Control | 240 | 36.76 | 0.33 | 0.9 | 0.95 | 2.6 | 1.43 | 3.9 | 0.00 | 0.0 | 1.75 | 4.8 |
| High Abn Control | 240 | 37.97 | 0.41 | 1.1 | 0.74 | 2.0 | 1.25 | 3.3 | 0.00 | 0.0 | 1.51 | 4.0 |
Fibrinogen Precision Study
Precision testing was performed for fibrinogen with one reagent lot of HemosIL RecombiPlasTin 2G using representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770). For each material, testing was executed for 20 days at two runs per day, 2 replicates per run (n=80) per material per instrument model. Two control levels, as well as two sample pools, were tested. All acceptance criteria for repeatability and within-laboratory precision were met.
ACL TOP 370 Fibrinogen Precision Summary
| Material | N | Mean (mg/dL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 347.9 | 3.7 | 1.1 | 3.2 | 0.9 | 11.4 | 3.3 | 12.4 | 3.6 |
| Low Fib Control | 80 | 144.4 | 5.3 | 3.6 | 4.0 | 2.8 | 2.7 | 1.8 | 7.1 | 4.9 |
| Normal Pool | 80 | 291.2 | 4.3 | 1.5 | 7.8 | 2.7 | 8.5 | 2.9 | 12.3 | 4.2 |
| Abnormal Pool | 80 | 139.0 | 3.2 | 2.3 | 3.5 | 2.5 | 4.8 | 3.5 | 6.8 | 4.9 |
ACL TOP 570 Fibrinogen Precision Summary
| Material | N | Mean (mg/dL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 341.5 | 2.9 | 0.8 | 2.9 | 0.8 | 13.8 | 4.0 | 14.4 | 4.2 |
| Low Fib Control | 80 | 145.7 | 8.9 | 6.1 | 4.2 | 2.9 | 0.0 | 0.0 | 9.8 | 6.8 |
| Normal Pool | 80 | 287.5 | 3.3 | 1.1 | 5.9 | 2.1 | 8.2 | 2.9 | 10.7 | 3.7 |
| Abnormal Pool | 80 | 140.6 | 3.8 | 2.7 | 3.3 | 2.3 | 4.2 | 3.0 | 6.5 | 4.6 |
ACL TOP 770 Fibrinogen Precision Summary
| Material | N | Mean (mg/dL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 80 | 339.1 | 3.1 | 0.9 | 2.6 | 0.8 | 12.6 | 3.7 | 13.2 | 3.9 |
| Low Fib Control | 80 | 140.7 | 9.0 | 6.4 | 5.7 | 4.0 | 4.1 | 2.9 | 11.4 | 8.1 |
| Normal Pool | 80 | 284.5 | 6.0 | 2.1 | 4.0 | 1.4 | 8.1 | 2.8 | 10.9 | 3.8 |
| Abnormal Pool | 80 | 136.9 | 5.9 | 4.3 | 0.0 | 0.0 | 3.5 | 2.6 | 6.8 | 5.0 |
K231031 - Page 9 of 14
{9}
Fibrinogen Instrument-to-Instrument Variability
| Material | N | Mean (mg/dL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Between-Instrument | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| Normal Control | 240 | 342.9 | 3.2 | 0.9 | 2.9 | 0.8 | 12.6 | 3.7 | 3.5 | 1.0 | 13.8 | 4.0 |
| Low Fib Control | 240 | 143.6 | 7.9 | 5.5 | 4.7 | 3.3 | 2.5 | 1.7 | 2.2 | 1.6 | 9.8 | 6.8 |
| Normal Pool | 240 | 287.7 | 4.7 | 1.6 | 6.1 | 2.1 | 8.3 | 2.9 | 2.6 | 0.9 | 11.6 | 4.0 |
| Abnormal Pool | 240 | 138.8 | 4.4 | 3.2 | 2.8 | 2.0 | 4.2 | 3.0 | 1.4 | 1.0 | 6.9 | 4.9 |
# Heparin Precision Study
Precision testing was performed for heparin with one reagent lot of HemosIL Liquid Anti-Xa using representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770). For each material, testing was executed for 20 days at two runs per day, 2 replicates per run $(n = 80)$ per material per instrument model. Four control levels (2 for UF heparin; 2 for LMW heparin), as well as two sample pools (1 for UF heparin; 1 for LMW heparin), were tested. All acceptance criteria for repeatability and within-laboratory precision were met.
ACL TOP 370 Heparin Precision Summary
| Material | N | Mean (IU/mL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| UF Low Control | 80 | 0.37 | 0.007 | 1.8 | 0.006 | 1.7 | 0.000 | 0.0 | 0.009 | 2.5 |
| UF High Control | 80 | 0.67 | 0.009 | 1.3 | 0.007 | 1.0 | 0.007 | 1.0 | 0.013 | 2.0 |
| UF Pool | 80 | 0.56 | 0.010 | 1.8 | 0.009 | 1.7 | 0.010 | 1.8 | 0.017 | 3.1 |
| LMW High Control | 80 | 1.53 | 0.022 | 1.4 | 0.019 | 1.3 | 0.005 | 0.3 | 0.030 | 1.9 |
| LMW Low Control | 80 | 0.61 | 0.016 | 2.7 | 0.012 | 2.0 | 0.000 | 0.0 | 0.020 | 3.3 |
| LMW Pool | 80 | 0.68 | 0.015 | 2.2 | 0.008 | 1.2 | 0.008 | 1.2 | 0.019 | 2.7 |
ACL TOP 570 Heparin Precision Summary
| Material | N | Mean (IU/mL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| UF Low Control | 80 | 0.37 | 0.010 | 2.7 | 0.007 | 1.8 | 0.000 | 0.0 | 0.012 | 3.3 |
| UF High Control | 80 | 0.67 | 0.015 | 2.3 | 0.011 | 1.6 | 0.004 | 0.7 | 0.019 | 2.9 |
| UF Pool | 80 | 0.58 | 0.013 | 2.3 | 0.014 | 2.5 | 0.000 | 0.0 | 0.019 | 3.3 |
| LMW High Control | 80 | 1.54 | 0.027 | 1.7 | 0.056 | 3.6 | 0.000 | 0.0 | 0.062 | 4.0 |
| LMW Low Control | 80 | 0.61 | 0.018 | 2.9 | 0.021 | 3.4 | 0.005 | 0.9 | 0.028 | 4.6 |
| LMW Pool | 80 | 0.70 | 0.022 | 3.2 | 0.028 | 4.1 | 0.000 | 0.0 | 0.036 | 5.1 |
K231031 - Page 10 of 14
{10}
ACL TOP 770 Heparin Precision Summary
| Material | N | Mean (IU/mL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Within-Laboratory | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| UF Low Control | 80 | 0.36 | 0.005 | 1.4 | 0.004 | 1.1 | 0.000 | 0.0 | 0.006 | 1.8 |
| UF High Control | 80 | 0.66 | 0.010 | 1.5 | 0.006 | 0.9 | 0.002 | 0.3 | 0.012 | 1.8 |
| UF Pool | 80 | 0.56 | 0.007 | 1.2 | 0.010 | 1.7 | 0.003 | 0.6 | 0.012 | 2.2 |
| LMW High Control | 80 | 1.50 | 0.029 | 1.9 | 0.008 | 0.5 | 0.015 | 1.0 | 0.033 | 2.2 |
| LMW Low Control | 80 | 0.58 | 0.013 | 2.2 | 0.007 | 1.3 | 0.003 | 0.5 | 0.015 | 2.6 |
| LMW Pool | 80 | 0.66 | 0.013 | 2.0 | 0.008 | 1.3 | 0.000 | 0.0 | 0.016 | 2.4 |
Heparin Instrument-to-Instrument Variability
| Material | N | Mean (IU/mL) | Repeatability (Within-Run) | | Between-Run | | Between-Day | | Between-Instrument | | Total | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | | | SD | %CV | SD | %CV | SD | %CV | SD | %CV | SD | %CV |
| UF Low Control | 240 | 0.37 | 0.008 | 2.1 | 0.006 | 1.6 | 0.000 | 0.0 | 0.005 | 1.2 | 0.011 | 2.9 |
| UF High Control | 240 | 0.67 | 0.012 | 1.8 | 0.008 | 1.2 | 0.005 | 0.7 | 0.005 | 0.8 | 0.016 | 2.4 |
| UF Pool | 240 | 0.57 | 0.010 | 1.8 | 0.011 | 2.0 | 0.006 | 1.0 | 0.009 | 1.6 | 0.019 | 3.3 |
| LMW High Control | 240 | 1.53 | 0.026 | 1.7 | 0.034 | 2.2 | 0.000 | 0.0 | 0.023 | 1.5 | 0.049 | 3.2 |
| LMW Low Control | 240 | 0.60 | 0.016 | 2.6 | 0.015 | 2.4 | 0.000 | 0.0 | 0.014 | 2.3 | 0.026 | 4.3 |
| LMW Pool | 240 | 0.68 | 0.017 | 2.5 | 0.018 | 2.6 | 0.000 | 0.0 | 0.016 | 2.4 | 0.030 | 4.3 |
2. Linearity:
Refer to K150877
3. Analytical Specificity/Interference:
Refer to K150877
4. Accuracy (Instrument):
Method Comparison Studies
D-Dimer Method Comparison
A method comparison study for D-Dimer was performed with one lot of HemosIL D-Dimer HS 500 to compare the performance on representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770) to a representative ACL TOP Family 50 Series model (ACL TOP 750 CTS). The study included 138 native clinical patient samples, spanning the assay's analytical measuring range (AMR) to demonstrate equivalent performance between the subject device and predicate device. The first replicate result on the candidate device (ACL TOP Family 70 Series models) was compared to the duplicate mean on the predicate device (ACL TOP Family 50 Series).
K231031 - Page 11 of 14
{11}
D-Dimer method comparison results are summarized in the table below. All acceptance criteria were met, supporting the comparable performance of the ACL TOP Family 70 Series (subject device) to the ACL TOP Family 50 Series (predicate device) with the representative latex agglutination assay.
D-Dimer Method Comparison Results Summary
| Comparison | N | Range (ng/mL FEU) | r | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- |
| ACL TOP 370 vs. ACL TOP 750 CTS | 119 | 233 to 106,815 | 0.998 | 1.006 (0.9936, 1.013) | 5.701 (-16.66, 24.19) |
| ACL TOP 570 vs. ACL TOP 750 CTS | 120 | 239 to 104,313 | 0.998 | 1.003 (0.9930, 1.014) | 51.78 (27.91, 75.06) |
| ACL TOP 770 vs. ACL TOP 750 CTS | 116 | 230 to 109,752 | 0.998 | 1.022 (1.005, 1.034) | 0.557 (-37.66, 19.11) |
# Factor VIII Method Comparison Study
A method comparison study for factor VIII was performed with one lot of HemosIL Factor VIII deficient plasma (run with HemosIL SynthASil) to compare the performance on representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770) to a representative ACL TOP Family 50 Series model (ACL TOP 750 CTS). The first replicate result on the candidate device (ACL TOP Family 70 Series models) was compared to the duplicate mean on the predicate device (ACL TOP Family 50 Series). The study included 148 samples spanning the assay's AMR to demonstrate the equivalent performance between the subject and predicate devices.
Factor VIII method comparison results are summarized in the table below. All acceptance criteria were met, supporting the comparable performance of the ACL TOP Family 70 Series (subject device) to the ACL TOP Family 50 Series (predicate device) with the representative clotting (calibrated) assay.
Factor VIII Method Comparison Results Summary
| Comparison | N | Range (% Activity) | r | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- |
| ACL TOP 370 vs. ACL TOP 750 CTS | 104 | 0.5 to 156.6 | 0.998 | 1.001 (0.9849, 1.012) | -0.5437 (-1.766, -0.1074) |
| ACL TOP 570 vs. ACL TOP 750 CTS | 104 | 0.5 to 148.4 | 0.996 | 1.024 (1.004, 1.043) | -0.5256 (-2.2118, -0.1011) |
| ACL TOP 770 vs. ACL TOP 750 CTS | 104 | 0.7 to 153 | 0.998 | 1.006 (0.9954, 1.018) | -0.0587 (-0.3945, 0.0789) |
# Prothrombin Time (PT) Method Comparison Study
A method comparison study for prothrombin time (PT) was performed with one lot of HemosIL RecombiPlasTin 2G to compare the performance on representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570 and ACL TOP 770 LAS) to a representative ACL TOP Family 50 Series model (ACL TOP 750 CTS). The first replicate result on the candidate device (ACL TOP Family 70 Series models) was compared to the duplicate mean on the predicate device (ACL TOP Family 50 Series). The study included
K231031 - Page 12 of 14
{12}
121 native patient samples, spanning the normal and abnormal range to demonstrate the equivalent performance between the subject and predicate devices.
Prothrombin Time method comparison results are summarized in the table below. All acceptance criteria were met, supporting the comparable performance of the ACL TOP Family 70 Series (subject device) to the ACL TOP Family 50 Series (predicate device) with the representative clotting (non-calibrated) assay.
Prothrombin Time Method Comparison Results Summary
| Comparison | N | Range (Seconds) | r | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- |
| ACL TOP 370 vs. ACL TOP 750 CTS | 115 | 10.5 to 56.1 | 0.999 | 1.000 (1.000, 1.009) | 0.0500 (-0.1051, 0.050) |
| ACL TOP 570 vs. ACL TOP 750 CTS | 116 | 10.45 to 55.7 | 1.000 | 1.000 (1.000, 1.011) | 0.000 (-0.1550, 0.000) |
| ACL TOP 770 LAS vs. ACL TOP 750 CTS | 116 | 10.5 to 56.6 | 1.000 | 1.012 (1.007, 1.018) | -0.0939 (-0.1690, -0.0196) |
# Fibrinogen Method Comparison Study
A method comparison study for fibrinogen was performed with one lot of HemosIL RecombiPlasTin 2G to compare the performance on representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570 and ACL TOP 770 LAS) to a representative ACL TOP Family 50 Series model (ACL TOP 750 CTS). The first replicate result on the candidate device (ACL TOP Family 70 Series models) was compared to the duplicate mean on the predicate device (ACL TOP Family 50 Series). The study included 121 native patient samples, spanning the assay's AMR to demonstrate the equivalent performance between the subject and predicate devices.
Fibrinogen method comparison results are summarized in the table below. All acceptance criteria were met, supporting the comparable performance of the ACL TOP Family 70 Series (subject device) to the ACL TOP Family 50 Series (predicate device) with the representative clotting (calibrated) assay.
Fibrinogen Method Comparison Summary of Passing-Bablok Regression Results
| Comparison | N | Range (mg/dL) | r | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- |
| ACL TOP 370 vs. ACL TOP 750 CTS | 113 | 68.0 to 653.0 | 0.999 | 1.003 (0.9961, 1.009) | 4.963 (3.446, 6.907) |
| ACL TOP 570 vs. ACL TOP 750 CTS | 114 | 68.0 to 660.0 | 0.997 | 1.007 (1.000, 1.014) | 4.976 (2.604 to 7.000) |
| ACL TOP 770 LAS vs. ACL TOP 750 CTS | 114 | 62.0 to 640.0 | 0.999 | 0.9756 (0.9693, 0.9831) | -1.122 (-3.644, 0.5549) |
# Heparin Method Comparison Study
Method comparison testing for heparin was performed with one lot of HemosIL Liquid Anti-Xa to compare the performance on representative ACL TOP Family 70 Series models (ACL TOP 370, ACL TOP 570, and ACL TOP 770) to a representative ACL TOP Family 50 Series
K231031 - Page 13 of 14
{13}
model (ACL TOP 750 CTS). The first replicate result on the candidate device (ACL TOP Family 70 Series models) was compared to the duplicate mean on the predicate device (ACL TOP Family 50 Series). The study included 260 samples spanning the assay's AMR to demonstrate the equivalent performance between the subject and predicate devices.
Heparin method comparison results are summarized in the table below. All acceptance criteria were met, supporting the comparable performance of the ACL TOP Family 70 Series (subject device) to the ACL TOP Family 50 Series (predicate device) with the representative chromogenic (calibrated) assay.
Heparin Method Comparison Summary of Passing-Bablok Regression Results
| Comparison | N | Range (IU/mL) | r | Slope (95% CI) | Intercept (95% CI) |
| --- | --- | --- | --- | --- | --- |
| ACL TOP 370 vs. ACL TOP 750 CTS | 209 | 0.03 to 1.98 | 0.997 | 0.9950 (0.9870, 1.000) | -0.0129 (-0.0200, -0.0058) |
| ACL TOP 570 vs. ACL TOP 750 CTS | 204 | 0.03 to 2.06 | 0.997 | 1.005 (0.996, 1.020) | -0.0204 (-0.0306, -0.0100) |
| ACL TOP 770 vs. ACL TOP 750 CTS | 207 | 0.03 to 1.98 | 0.999 | 0.9804 (0.9716, 0.9888) | -0.0145 (-0.0203, -0.0091) |
5. Carry-Over:
Refer to K150877
B Other Supportive Instrument Performance Characteristics Data:
Refer to K150877
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.
K231031 - Page 14 of 14
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.