K071967 · Sysmex America, Inc. · GKZ · Nov 20, 2007 · Hematology
Device Facts
Record ID
K071967
Device Name
SYSMEX XE-5000
Applicant
Sysmex America, Inc.
Product Code
GKZ · Hematology
Decision Date
Nov 20, 2007
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 864.5220
Device Class
Class 2
Indications for Use
The Sysmex XE-5000 is an automated hematology analyzer for in-vitro diagnostic use in screening patient populations found in clinical laboratories. The XE-5000 classifies and enumerates the same parameters as the XE-2100 using whole blood as described below, cord blood for HPC and has a body fluid mode for body fluids. The Body Fluid mode analyzes WBC-BF, RBC-BF, MN%/#, PMN%/# and TC-BF in body fluids (cerebrospinal fluids (CSF), serous fluids, and synovial fluids with EDTA as needed). WBC, RBC, HGB, HCT, MCV, MCH, MCHC, PLT, NEUT%/#, LYMP %/#, MONO %/#, EO%/#, BASO %/#, NRBC, RDW-SD, RDW-CV, MPV, RET %/#, IRF, IG%/#, HPC#, RET-He, IPF, WBC-BF, RBC-BF, MN%/#, PMN%/#, TC-BF#
Device Story
Multi-parameter hematology analyzer; processes anticoagulated whole blood and body fluids. System components: Main Unit (aspiration, dilution, mixing, analysis), Auto Sampler (up to 100 tubes), and Information Processing Unit (IPU) for data management/operator interface. Methods: RF/DC detection, sheath flow DC detection, and semiconductor laser flow cytometry. Particle identification via forward scatter, fluorescence, and adaptive cluster analysis. Operator loads samples via manual, capillary, or automated sampler modes. IPU displays results, graphics, and flags; supports host computer transmission. Enables automated cell classification and enumeration, reducing manual microscopy requirements. Benefits: rapid, standardized quantitative analysis of blood and body fluid cellular components.
Clinical Evidence
Bench testing only. Data collected for carryover, linearity, accuracy, and reproducibility to demonstrate performance against manufacturer specifications for the body fluid mode. Comparison of XE-5000 body fluid mode to XE-2100 demonstrated excellent correlation.
Technological Characteristics
Automated hematology analyzer. Methods: RF/DC detection, sheath flow DC detection, semiconductor laser flow cytometry. Analyzes whole blood and body fluids. Connectivity: IPU with Windows 2000 OS, barcode reader, printer/host output. Calibration: XE Calibrator (X Cal). QC: e-Check (XE) 3-level control. Software: IPU PIM (Patient Information Manager) for data processing and user-definable flagging.
Indications for Use
Indicated for in-vitro diagnostic screening of patient populations in clinical laboratories using whole blood, cord blood, or body fluids (CSF, serous, synovial) to classify and enumerate hematological parameters.
Regulatory Classification
Identification
An automated differential cell counter is a device used to identify one or more of the formed elements of the blood. The device may also have the capability to flag, count, or classify immature or abnormal hematopoietic cells of the blood, bone marrow, or other body fluids. These devices may combine an electronic particle counting method, optical method, or a flow cytometric method utilizing monoclonal CD (cluster designation) markers. The device includes accessory CD markers.
Special Controls
*Classification.* Class II (special controls). The special control for this device is the FDA document entitled “Class II Special Controls Guidance Document: Premarket Notifications for Automated Differential Cell Counters for Immature or Abnormal Blood Cells; Final Guidance for Industry and FDA.”
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY INSTRUMENT ONLY TEMPLATE
A. 510(k) Number:
K071967
B. Purpose for Submission:
New Device
C. Manufacturer and Instrument Name:
Sysmex America, Inc., Sysmex® XE-5000 Analyzer
D. Type of Test or Tests Performed:
Quantitative, WBC, RBC, HGB, HCT, MCV, MCH, MCHC, PLT, NEUT%/#, LYMP %/#, MONO %/#, EO%/#, BASO %/#, NRBC, RDW-SD, RDW-CV, MPV, RET %/#, IRF, IG%/#, HPC#, RET-He, IPF, WBC-BF, RBC-BF, MN%/#, PMN%/#, TC-BF#
E. System Descriptions:
1. Device Description:
The Sysmex XE-5000 is part of The XE-Series instrument line. It is a multi-parameter hematology analyzer intended to perform tests in anticoagulated blood and body fluids. The instrument consists of three principal units: (1) Main Unit which aspirates dilutes, mixes and analyzed blood and body fluid simples; (2) Auto Sampler Units supplies samples to the Main Unit automatically; (3) IPU (Information Processing Unit) which processes data from the Main Unit and provides the operator interface with the system. The XE-5000 is equipped with a Sampler that provides continuous automated sampling for up to 100 tubes.
2. Principles of Operation:
The Sysmex XE-5000 performs analyses using the following methods: RF/DC Detection Method, Sheath Flow DC Detection Method, and Flow Cytometry Methods using a Semiconductor Laser. Particle characterization and identification is based on detection of forward scatter, fluorescence and adaptive cluster analysis. Using the same reagents as the XE-2100, the XE-5000 automatically classifies cells from blood and body fluids and carries out all processes automatically from aspiration of the sample to outputting the results.
{1}
The body fluid mode analysis mode of the XE-5000 uses the 4DIFF scattergram and the RBC distribution obtained from a specialized analysis sequence to calculate and display the WBC (WBC-BF) counts, mononuclear cell (MN)/polymorphonuclear cell (PMN) counts and percentages, TC-BF (Total Count) and RBC (RBC-BF) counts found in the body fluid.
Analysis results and graphics are displayed on the IPU screen. They can be printed on any of the available printers or transmitted to a Host computer.
3. Modes of Operation:
Manual, Capillary, Sampler (Automatic), Manual Closed
4. Specimen Identification:
Specimen information is managed by four menu lists and specimen identification input is manual (by operator) or by barcode reader.
5. Specimen Sampling and Handling:
There are three modes of specimen sampling: Manual, Capillary, Sampler (Automatic) and Manual Closed:
Venous blood is mixed with anticoagulant (EDTA 2K, EDTA-3K or EDTA-Na). Analyze samples within four hours of collection. If it is not possible to analyzed within four hours samples are refrigerated at 2-8oC until they can be analyzed.
Capillary blood samples are placed directly into diluent to dilute them. No anticoagulant is used. Alternatively, samples are collected in a microcollection system, anticoagulant added and then diluted.
6. Calibration:
The manufacturer's instructions are to be followed for materials and frequency of calibration. Following installation calibration, it is requested to verify instrument calibration every six months or on an "as needed" basis, and maintain good QC practices, to ensure the accuracy of the system.
7. Quality Control:
The XE-5000 uses a specific control material the e-Check (XE) control.
8. Software:
The role of the software on the XE-2100DC Analyzer is to operate the instrument in order to analyze whole blood samples, and to way to store and review data.
2
{2}
One of the software programs allows the user to set user-definable flags according to their laboratory protocol. The XE IPU PIM (Patient Information Manager) software analyzes the data and works in conjunction with the Windows 2000 operating system, which serves as an administrative function.
FDA has reviewed applicant’s Hazard Analysis and Software Development processes for this line of product types:
Yes ☐ X or No ☐
## F. Regulatory Information:
1. Regulation section:
21 CFR 864.5220, Automated Differential Cell Counter
2. Classification:
Class II
3. Product code:
GKZ, Counter, Differential Cell
4. Panel:
Hematology (81)
## G. Intended Use:
1. Indication(s) for Use:
The Sysmex XE-5000 is an automated hematology analyzer for in-vitro diagnostic use in screening patient populations found in clinical laboratories. The XE-5000 classifies and enumerates the same parameters as the XE-2100 using whole blood as described below, cord blood for HPC and has a body fluid mode for body fluids. The Body Fluid mode analyzes WBC-BF, RBC-BF, MN%/#, PMN%/# and TC-BF in body fluids (cerebrospinal fluids (CSF), serous fluids, and synovial fluids with EDTA as needed).
WBC, RBC, HGB, HCT, MCV, MCH, MCHC, PLT, NEUT%/#, LYMP %/#, MONO %/#, EO%/#, BASO %/#, NRBC, RDW-SD, RDW-CV, MPV, RET %/#, IRF, IG%/#, HPC#, RET-He, IPF, WBC-BF, RBC-BF, MN%/#, PMN%/#, TC-BF#
3
{3}
2. Special Conditions for Use Statement(s):
Not applicable.
## H. Substantial Equivalence Information:
1. Predicate Device Name(s) and 510(k) numbers:
Sysmex® XE-2100, K040073
2. Comparison with Predicate Device:
| Similarities | | |
| --- | --- | --- |
| Item | Sysmex® XE-5000 | Sysmex® XE-2100 |
| Intended Use | Used as a quantitative, automated hematology analyzer and leukocyte differential counter for in vitro diagnostic use in clinical laboratories. The body fluid application adds a quantitative, automated procedure of analyzing cerebrospinal fluid, serous fluid and synovial fluid. | Same |
| Methodology | Performs analyses using the following methods: RF/DC Detection Method, Sheath Flow DC Detection Method, and Flow Cytometry Methods using a Semiconductor Laser. | Same |
| Calibrator | XE Calibrator (X Cal) | Same |
| Specimen Type | Random whole blood and body fluid samples | Same |
| Differences | | |
| --- | --- | --- |
| Item | Sysmex® XE-5000 | Sysmex® XE-2100 |
| Parameters | Body Fluid Parameters : WBC, RBC MN%/#, PMN%/#, TC-BF# | Body Fluid Parameters: WBC, RBC |
| | Capillary Mode Parameter (whole blood): WBC, RBC, HGB, HCT, MCV, MCH, MCHC, PLT, NEUT%/#, LYMP %/#, MONO %/#, EO%/#, BASO %/#, NRBC%/#, RET %/#, IG%/# | Capillary Mode Parameter (whole blood): WBC, RBC, HGB, HCT, MCV, MCH, MCHC, PLT, RET %/# |
| Quality Control | e-Check(XE) – 3 Levels | e-Check– 3 Levels |
{4}
I. Special Control/Guidance Document Referenced (if applicable):
EP5A Evaluation of Precision Performance of Clinical Chemistry Device Approved Guideline, NCCLS
Guidelines for the valuation of blood cell analyzers including those used or differential leucocyte and reticulocyte counting and cell marker application, ICSH, Clin Lab Haematology, 1994, 16(2): 157-174.
Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices - Guidance for Industry and FDA Staff, May 11, 2005.
J. Performance Characteristics:
1. Analytical Performance:
a. Accuracy:
The accuracy study was performed on 284 body fluid samples (CSF, Serous and Synovial,) at three sites. The performance of the XE-5000 Body Fluid mode was compared to the XE 2100 Body Fluid Application and manual method for cellular enumeration of WBC and RBC. The WBC differential (MN%/# and PMN %/#) of the body fluid mode was compared to the manual method of cell identification using the laboratories' manual differential method. Results are as follows using Deming regression:
Accuracy of the XE-5000 White Cell Counts
| | n= | Mean | r | Slope | Intercept | Range x10³/μL |
| --- | --- | --- | --- | --- | --- | --- |
| XE-5000 WBC-BF vs. XE-2100 WBC | 269 | XE5 :1.121
XE21:1.2266 | 0.9965 | 0.929 | -0.0183 | 0-10.786 |
| XE-5000 TC-BF vs. XE-2100 WBC | 168 | XE5: 0.9967
XE21: 1.0617 | 0.9954 | 0.954 | -0.0165 | 0-10.786 |
| XE-5000 WBC-BF vs. Manual WBC | 254 | XE5 :1.0428
Man :1.1793 | 0.9616 | 0.876 | 0.0095 | 0-13.1 |
| XE-5000 TC-BF vs. Manual WBC | 161 | XE5 :0.9011
Man :1.0548 | 0.9501 | 0.867 | -0.0139 | 0-10.14 |
| XE-5000 WBC-BF vs. XE-5000 TC-BF | 185 | WBC: 0.9149
TC: 0.9499 | .9989 | 0.978 | -0.0140 | 0-10.14 |
Accuracy of the XE-5000 Red Blood Cell Counts
| | n= | Mean | r | Slope | Intercept | Range X10⁶/μL |
| --- | --- | --- | --- | --- | --- | --- |
| XE-5000 RBC-BF vs. XE-2100 RBC | 252 | XE5 :0.698
XE21 :0.0719 | 0.9974 | 0.989 | -0.0013
- | 0-4.880 |
| XE-5000 RBC-BF vs. Manual RBC | 167 | XE5: 0.05802
Man: 0.06278 | 0.9994 | 0.902 | 0.00142 | 0-5.370 |
{5}
Accuracy of XE-5000 Body Fluid Differential vs. Manual Differential
| | n= | Mean | r | Slope | Intercept | Range |
| --- | --- | --- | --- | --- | --- | --- |
| XE-5000 MN# vs. Manual MN# | 251 | XE5: 0.5211Man: 0.5465 | 0.9789 | 0.976 | -0.0121 | 0-9.929x103/μL |
| XE-5000 MN% vs. Manual MN% | 251 | XE5: 60.56Man: 68.86 | 0.7525 | 1.209 | -22.69 | 0-100% |
| XE-5000 PMN# vs. Manual PMN# | 251 | XE5: 0.6580Man: 0.5853 | 0.9239 | 1.120 | 0.0028 | 0-8.929x103/μL |
| XE-5000 PMN% vs. Manual PMN% | 251 | XE5: 39.10Man: 28.91 | 0.7589 | 1.195 | 4.54 | 0-100% |
| CSF: XE-5000 MN# vs. Manual MN# | 52 | XE5: 0.0400Man: 0.0398 | 0.9949 | 1.016 | -0.0004 | 0-0.330x103/μL |
| CSF: XE-5000 MN% vs. Manual MN% | 52 | XE5:67.37Man:84.33 | 0.5715 | 2.091 | -108.92 | 0-100% |
| CSF: XE-5000 PMN# vs. Manual PMN# | 52 | XE5:0.0266Man:0.0276 | 0.9963 | 0.941 | 0.0006 | 0-0.577x103/μL |
| CSF: XE-5000 PMN% vs. Manual PMN% | 52 | XE5:32.63Man:14.96 | 0.5614 | 2.150 | 0.46 | 0-100% |
| Serous: XE-5000 MN# vs. Manual MN# | 141 | XE5:0.6850Man:0.7170 | 0.9838 | 0.975 | -0.0138 | 0-9.929x103/μL |
| Serous: XE-5000 PMN% vs. Manual MN% | 141 | XE5:60.58Man:65.85 | 0.7947 | 1.097 | -11.62 | 0.9-100% |
| Serous: XE-5000 PMN# vs. Manual PMN# | 141 | XE5:0.6707Man:0.5459 | 0.8448 | 1.397 | -0.0919 | 0-8.062x103/μL |
| Serous: XE-5000PMN% vs. Manual PMN% | 141 | XE5:38.81Man:30.92 | 0.8168 | 1.074 | 5.59 | 0-98% |
| Synovial: XE-5000 MN# vs. Manual MN# | 58 | XE5:0.5541Man:0.5864 | 0.8984 | 1.015 | -0.0408 | 0-2.567x103/μL |
| Synovial: XE5000 MN% vs. Manual MN% | 58 | XE5:54.40Man:62.33 | 0.8350 | 1.040 | -10.41 | 4.3-99% |
| Synovial: XE-5000 PMN# vs. Manual PMN# | 58 | XE5:1.1930Man:1.1809 | 0.9885 | 0.947 | 0.0746 | 0-8.929x103/μL |
| Synovial: XE-5000 PMN% vs. Manual PMN% | 58 | XE5:45.60Man:36.53 | 0.8188 | 1.009 | 8.75 | 0-96% |
{6}
Capillary Mode on Whole Blood
A study was performed to compare the Capillary Mode to the Auto and Manual modes on the XE-5000. 115 samples were run in the auto (sampler) mode and the capillary mode. 66 samples were run in the manual and capillary mode. The results are as follow using Deming regression:
Accuracy of XE-5000 Capillary to Sampler (Auto) and Manual modes
| Parameter | n= | Mean | r | Slope | Intercept | Range |
| --- | --- | --- | --- | --- | --- | --- |
| WBC XE-5000Sampler vs. Capillary | 115 | Auto:13.298Cap: 13.610 | 0.9989 | 0.984 | -0.088 | 1.66-279.98x103/μL |
| RBC XE-5000Sampler vs. Capillary | 115 | Auto: 4.220Cap: 4.195 | 0.9571 | 1.009 | -0.013 | 2.56-7.11x106/μL |
| HGB XE-5000Sampler vs. Capillary | 115 | Auto:12.249Cap: 12.181 | 0.9562 | 1.069 | -0.770 | 8.10-16.20g/dL |
| HCT XE-5000Sampler vs. Capillary | 115 | Auto:38.397Cap: 37.194 | 0.9195 | 1.027 | 0.207 | 23.90-52.00% |
| MCV XE-5000Sampler vs. Capillary | 115 | Auto:91.805Cap: 89.411 | 0.9851 | 1.061 | -3.093 | 59.9-115.0fL |
| MCH XE-5000Sampler vs. Capillary | 115 | Auto:29.179Cap: 29.222 | 0.9856 | 1.003 | -0.132 | 18.70-37.60pg |
| MCHC XE-5000Sampler vs. Capillary | 115 | Auto:31.790Cap: 32.682 | 0.9271 | 0.940 | 1.075 | 27.50-36.10g/dL |
| PLT XE-5000Sampler vs. Capillary | 115 | Auto:251.157Cap:227.852 | 0.9898 | 1.060 | 9.53212.150 | 13-1685x103/μL |
| WBC XE-5000Manual vs. Capillary | 66 | Man:18.350Cap: 18.812 | 0.9993 | 1.007 | -0.591 | 1.66-284.26x103/μL |
| RBC XE-5000Manual vs. Capillary | 66 | Man: 4.093Cap: 4.140 | 0.9495 | 1.020 | -0.130 | 2.88-7.07x106/μL |
| HGB XE-5000Manual vs. Capillary | 66 | Man: 11.57Cap: 11.60 | 0.9417 | 1.082 | -0.98 | 8.4-15.9g/dL |
| HCT XE-5000Manual vs. Capillary | 66 | Man: 36.63Cap: 36.62 | 0.9143 | 1.010 | -0.34 | 26-52% |
| MCV XE-5000Manual vs. Capillary | 66 | Man: 90.59Cap: 89.41 | 0.9968 | 1.044 | -2.77 | 59.9-114.2fL |
| MCH XE-5000Manual vs. Capillary | 66 | Man: 28.50Cap: 28.27 | 0.9904 | 0.994 | 0.39 | 18.7-33.1pg |
| MCHC XE-5000Manual vs. Capillary | 66 | Man: 31.49Cap: 31.62 | 0.9501 | 1.109 | -3.57 | 28.0-35.4g/dL |
| PLT XE-5000Manual vs. Capillary | 66 | Man: 263.7Cap: 241.7 | 0.9899 | 1.069 | 5.5 | 11-1687x103/μL |
{7}
WBC-D on Whole Blood Mode
Seventy-one samples were analyzed to compare the WBC-D on the XE-5000 to the XE-2100. The expected result (±5.0%) is based on samples with WBC counts >4.0×10³/uL. The results are as follows:
Accuracy of WBC-D on XE-5000 vs. XE-2100 Auto Mode
| WBC-D
XE-2100
Mean | WBC-D
XE-5000
Mean | Percent
Deviation | Expected result | Range | n= |
| --- | --- | --- | --- | --- | --- |
| 18.87 | 18.95 | 0.42% | ±5.0% | 1.82-
284.26×10³/μL | 66 |
b. Precision/Reproducibility:
Within run precision was performed on using CSF, Synovial and Serous fluid types assayed 10 consecutive times and covered the whole measuring range for the WBC and RBC parameters. In addition, a precision study was performed (10 consecutive replicates on several samples) to show that the differential parameters of the Capillary Mode of the XE-5000 met the performance specifications at specific mean values for each of the differential parameters. Results for all studies were within manufacturer specifications.
A precision was also performed to show that the WBC-D parameter (Whole Blood Mode) met the performance specifications at specific normal mean value (WBC ≥ 4.0 × 10³/μL). Within run precision data was collected and ten consecutive replicates on three normal samples were analyzed on the XE-5000. Performance was within performance specifications.
c. Linearity:
Linearity was performed on the WBC-BF, RBC-BF and TC-BF parameters by diluting samples with instrument diluent. Linearity was tested on the following:
| Parameter | XE-5000 Body Fluid Ranges |
| --- | --- |
| WBC-BF | 0.000 – 0.050 ×10³/μL (within ±0.010 × 10³/ μL)
0.050 – 10.000 ×10³/μL (≤20%) |
| RBC-BF | 0.000 – 5.000 ×10⁶/μL (≤2.0% or within ±0.020 × 10⁶/ μL) |
| TC-BF | 0.000 – 0.050 ×10³/μL (within ±0.010 × 10³/ μL)
0.050 – 10.000 ×10³/μL (≤20%) |
{8}
9
Results: Linearity Results for Body Fluid Mode
| Parameter | Range Tested | Units | r² | r | Slope | Intercept |
| --- | --- | --- | --- | --- | --- | --- |
| WBC-BF | 0.001-0.052 | x10³/μL | 0.00 | 0.99 | 0.9974 | 1.0093 |
| | 0.001-5.901 | x10³/μL | 1.00 | 1.00 | 1.0005 | 0.0557 |
| | 0.268-10.547 | x10³/μL | 1.00 | 1.00 | 0.9949 | 0.0946 |
| | 0.009-56.281 | x10³/μL | 1.00 | 1.00 | 0.9902 | 138.1555 |
| RBC-BF | 0.001-0.032 | x10⁶/μL | 1.00 | 1.00 | 0.9995 | 0.0002 |
| | 0.000-0.048 | x10⁶/μL | 1.00 | 1.00 | 1.0027 | 0.0004 |
| | 0.001-1.445 | x10⁶/μL | 1.00 | 1.00 | 1.0033 | 115.3005 |
| | 0.140-5.307 | x10⁶/μL | 1.00 | 1.00 | 1.0119 | 0.0677 |
| | 0.002-5.359 | x10⁶/μL | 1.00 | 1.00 | 1.0081 | 0.0286 |
| TC-BF | 0.001 - 0.049 | x10³/μL | 0.99 | 0.99 | 1.0125 | -0.0003 |
| | 0.264 - 10.549 | x10³/μL | 1.00 | 1.00 | 0.9943 | 0.1010 |
| | 0.014 - 56.22 | x10³/μL | 1.00 | 1.00 | 1.0022 | 0.0824 |
d. Carryover:
Carry-over effect was evaluated by assaying a sample with a high cell count three consecutive times followed immediately by testing a low count sample consecutively 3 times for WBC-BF, RBC-BF, TC-BF and WBC-DF (Whole Blood Mode). Types of fluid samples used were CSF, Serous, and Synovial. Performance met manufacturer's specifications for all parameters.
e. Interfering Substances:
Results may be compromised with clotted samples and synovial samples that contain uric acid crystals or have a high viscosity.
Samples results with Errors related to WBC-BF and RBC-BF parameters should not be used.
2. Other Supportive Instrument Performance Data Not Covered Above:
Stability on Whole Blood
Specimens used to determine sample stability were split into 2 aliquots--one room temperature (RT) (20-28°C) and the other at low temperature (LT) (4°C). The separate aliquots were stored at room temperature and low temperature respectively at baseline (immediately after blood collection), 24, 48, 72 and 96 hours.
Normal samples are stable up to 48 hours at room temperature (20-28°C) and at low temperature (4°C) for the following parameters: WBC, RBC, HGB, HCT, MCV, MCH, MCHC, PLT, Neut %, Lymph%, Mono%, Eosin% and Baso%.
{9}
K. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
L. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
10
{10}
11
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.