K210346 · Sysmex America, Inc. · GKZ · Nov 8, 2022 · Hematology
Device Facts
Record ID
K210346
Device Name
Sysmex XW-100 Automated Hematology Analyzer
Applicant
Sysmex America, Inc.
Product Code
GKZ · Hematology
Decision Date
Nov 8, 2022
Decision
SESE
Submission Type
Dual Track
Regulation
21 CFR 864.5220
Device Class
Class 2
Attributes
Pediatric
Indications for Use
The XW-100 Automated Hematology Analyzer (XW-100) is a quantitative automated hematology analyzer intended for in vitro diagnostic use to classify and enumerate the following parameters for venous whole blood anticoagulated with K2/K3 EDTA: WBC, RBC, HGB, HCT, MCV, PLT, LYM%, Other WBC%, NEUT%, LYM#, Other WBC#, and NEUT#. It is not for use in diagnosing or monitoring patients with primary or secondary chronic hematologic diseases/disorders, oncology patients, critically ill patients, or children under the age of 2.
Device Story
XW-100 is an automated hematology analyzer for CLIA-waived settings; processes venous whole blood samples (K2/K3 EDTA). Uses impedance technology (direct current) with hydrodynamic focusing for cell counting/sizing; photometric method for hemoglobin. Operator manually mixes and loads samples. Device generates histograms from pulse heights to identify cell populations and calculate 12 hematology parameters (CBC, 3-part WBC differential, MCV). Software version 1.14 includes modified print suppression rules to simplify flagging for non-specialist operators. Results assist clinicians in basic hematologic assessment; suppression rules prevent reporting of potentially unreliable data in complex clinical cases. Benefits include rapid, automated blood analysis in point-of-care environments by non-laboratory personnel.
Clinical Evidence
No clinical trials; bench testing only. Internal study (N=139) and prospective sample challenge study (N=173) compared software v1.14 against v1.03 and v1.13. Samples included normal and abnormal blood with various interferences (e.g., cold agglutinins, lipemia, nucleated RBCs). Deming regression showed high correlation (r > 0.90) for all parameters. Confirmatory methods included blood smear analysis (CLSI H20-A2) and Sysmex XN-10 analyzer. Results confirmed that v1.14 maintains appropriate suppression of unreliable parameters.
Technological Characteristics
Impedance-based (DC) cell counter with hydrodynamic focusing; photometric hemoglobin measurement. Dimensions: 7"x14"x18". Standalone system. Factory calibrated. Uses XW Pack L (lyse) and XW Pack D (diluent). Software-based result suppression logic. Complies with IEC 61010-1, IEC 61326-1, and IEC 61326-2-6.
Indications for Use
Indicated for quantitative hematology analysis of venous whole blood (K2/K3 EDTA) in patients aged 2 years and older. Not for use in oncology, critically ill, or patients with chronic hematologic disorders.
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.”
Predicate Devices
XW-100 Automated Hematology Analyzer for CLIA Waived Use (K172604)
{0}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
INSTRUMENT ONLY
## I Background Information:
A 510(k) Number
K210346
B Applicant
Sysmex America, INC.
C Proprietary and Established Names
Sysmex XW-100 Automated Hematology Analyzer
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| GKZ | Class II | 21 CFR 864.5220 - Automated Differential Cell Counter | HE - Hematology |
## II Submission/Device Overview:
A Purpose for Submission:
This submission is a Dual 510(k) and CLIA Waiver by Application (Dual Submission) tracked as K210346 and CW170012. K210346 was submitted for clearance of a device modification.
B Type of Test:
Complete blood count (WBC, RBC, HGB, HCT, MCV, PLT) and leukocyte 3-part differential (LYM%, Other WBC%, NEUT%, LYM#, Other WBC#, NEUT#).
## III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
B Indication(s) for Use:
The XW-100 Automated Hematology Analyzer (XW-100) is a quantitative automated hematology analyzer intended for in vitro diagnostic use to classify and enumerate the following parameters for venous whole blood anticoagulated with K2/K3 EDTA: WBC, RBC, HGB, HCT, MCV, PLT, LYM%, Other WBC%, NEUT%, LYM#, Other WBC#, and NEUT#. It is not for use in diagnosing or monitoring patients with primary or secondary chronic hematologic diseases/disorders, oncology patients, critically ill patients, or children under the age of 2.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
The XW-100 is intended to be used by operators with a minimum of an earned high school diploma or equivalent.
IV Device/System Characteristics:
A Device Description:
The XW-100 Automated Hematology Analyzer (XW-100) for CLIA Waived Use is an electrical resistance blood cell counter. This technology may also be referred to as Direct Current (DC) or impedance. The XW-100 analyzes human whole blood specimens anticoagulated with K2EDTA or K3EDTA and reports results for 12 hematology parameters, including the basic complete blood count (CBC), 3-part white blood cell (WBC) differential, and MCV.
Principles of Operation
The XW-100 uses direct current with hydrodynamic focusing for all parameters except hemoglobin, which is measured photometrically. The patient sample is aspirated, measured, diluted with diluent (and lysed for WBC measurement), then directed into a transducer chamber by a hydrodynamic focusing nozzle. The transducer chamber has a minute hole, or aperture. Electrodes are mounted on both sides of the aperture chamber, through which the direct current flows. Blood cells suspended in the diluted sample are injected through the aperture by the hydrodynamic focusing nozzle. The hydrodynamic focusing nozzle is positioned in front of the aperture and in line with the aperture's center. All blood cells are separated from each other and pass through the aperture in one direction, one cell at a time. When a cell passes through the aperture, it causes a change in the direct current resistance, which is proportional to the cell's size. These resistance changes are captured as electric pulses. The various blood cell counts are calculated by counting the pulses that occur in each cell size category. The analyzer then determines blood cell volume and identifies cells by creating and analyzing histograms of the various cell populations using their respective pulse heights. Hemoglobin is measured photometrically using a non-cyanide method.
B Instrument Description Information:
1. Instrument Name:
XW-100 Automated Hematology Analyzer for CLIA Waived Use
K210346 - Page 2 of 11
{2}
K210346 - Page 3 of 11
2. Specimen Identification:
Specimen identification input is manual (by operator).
3. Specimen Sampling and Handling:
The XW-100 processes anticoagulated venous whole blood collected in K2EDTA or K3EDTA collection tubes. Samples are manually mixed by inversion and loaded into an onboard sample adapter one at a time.
4. Calibration:
The XW-100 is factory calibrated.
5. Quality Control:
The XW-100 system performance is evaluated using XW QC CHECK, a stabilized whole blood matrix quality control material designed for statistical process control of the analyzer. Assayed parameters include: WBC, RBC, HGB, HCT, MCV, MCH, MCHC, PLT, LYM%, OTHER WBC%, NEUT%, LYM#, OTHER WBC#, NEUT#, RDW-SD, RDW-CV and MPV.
V Substantial Equivalence Information:
A Predicate Device Name(s):
XW-100 Automated Hematology Analyzer for CLIA Waived Use
B Predicate 510(k) Number(s):
K172604
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K210346 | K172604 |
| --- | --- | --- |
| Device Trade Name | XW-100 Automated Hematology Analyzer for CLIA Waived Use | XW-100 Automated Hematology Analyzer for CLIA Waived Use |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | The XW-100 Automated Hematology Analyzer (XW-100) is a quantitative automated hematology analyzer intended for in vitro diagnostic CLIA waived use to classify and enumerate the following | Same |
{3}
| | parameters for venous whole blood
anticoagulated with K2/K3 EDTA: WBC, RBC, HGB, HCT, MCV, PLT, LYM%,
Other WBC%, NEUT%, LYM#, Other WBC#, and NEUT#. It is not for use in diagnosing or monitoring patients with primary or secondary chronic hematologic diseases/disorders, oncology patients, critically ill patients, or children under the age of 2. | |
| --- | --- | --- |
| Test Principle | Impedance technology (direct current detection) with hydrodynamic focusing for all parameters except hemoglobin, which is measured photometrically. | Same |
| Measuring Channel | Single hydrodynamic focused impedance chamber | Same |
| Sample Type | Anticoagulated (K2EDTA or K3EDTA) venous whole blood | Same |
| Sample Aspiration Volume | 15 μL | Same |
| Analysis Reagents | XW Pack L (Lyse)
XW Pack D (Diluent) | Same |
| System Throughput | 20 cycles per hour | Same |
| Test System Dimensions | Width: 7 inches
Height: 14 inches
Depth: 18 inches | Same |
| Mode of Operation | Whole blood mode | Same |
| Calibration and Quality Control | XW QC CHECK (K143577)
SCSTM-1000 Calibrator | Same |
K210346 - Page 4 of 11
{4}
| | (K943268) | |
| --- | --- | --- |
| General Device Characteristic Differences | | |
| CLIA Waiver Software Version | Version 1.14 with modification to print suppression rule | Version 1.03 |
VI Standards/Guidance Documents Referenced:
CLSI H20-A2 – Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods; Approved Standard – Second Edition
IEC 61010-1, Safety requirements for electrical equipment for measurement, control and laboratory use. Part 1: General requirements
IEC 61326-1, Electrical equipment for measurement, control and laboratory use - EMC requirements - Part 1: General requirements
IEC 61326-2-6, Electrical equipment for measurement, control and laboratory use - EMC requirements - Part 2-6: Particular requirements - In vitro diagnostic (IVD) medical equipment
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
Refer to K172604
2. Linearity:
Refer to K172604
3. Analytical Specificity/Interference:
Refer to K172604
4. Accuracy (Instrument):
Refer to K172604 and CW170012
5. Carry-Over:
Refer to K172604
K210346 - Page 5 of 11
{5}
B Other Supportive Instrument Performance Characteristics Data:
1. Internal study to evaluate new version of software v1.14 with modification to print suppression rule
An internal study was performed to evaluate:
- The effectiveness of the new software version with suppression rule modification to appropriately suppress parameters according to the XW-100 algorithm suppression rules (used to simplify flagging for CLIA waived use).
- The results unsuppressed by the new software and to assess the accuracy of unsuppressed results for all reported parameters.
A total of 139 residual whole blood samples (mix of normal and abnormal) collected in K2EDTA anticoagulant were run on two XW-100 CLIA waived analyzers using the on-market software version (v1.13) and within a target of one hour all samples were run on two additional XW-100 CLIA waived analyzers using the proposed modified software version (v1.14).
The results using both versions of software were compared to assess the frequency of suppression for all parameters, as well as evaluate the comparability of the reported parameters. Deming linear regression analysis was performed on all unsuppressed results for all reported parameters. The results of this regression analysis are shown in the table below.
K210346 - Page 6 of 11
{6}
| Internal Study Deming Regression Analysis | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Measurand | N | Result Range (N=139) | Correlation Coefficient | Slope | 95% (CI) | Intercept | 95% (CI) |
| WBC (x 10³/μL) | 70 | 3.0–22.8 | 0.9981 | 0.9985 | 0.9792, 1.0178 | 0.0279 | -0.1043, 0.1601 |
| RBC (x 10⁶/μL) | 129 | 2.28–5.86 | 0.9967 | 1.0086 | 0.9937, 1.0236 | -0.0111 | -0.0695, 0.0473 |
| HGB (g/dL) | 57 | 10.2–15.6 | 0.9874 | 0.9977 | 0.9580, 1.0373 | 0.0145 | -0.4867, 0.5157 |
| HCT (%) | 58 | 28.0–47.1 | 0.9927 | 1.0030 | 0.9759, 1.0300 | 0.1220 | -0.9107, 1.1548 |
| PLT (x 10³/μL) | 121 | 107–570 | 0.9945 | 0.9885 | 0.9657, 1.0113 | 3.4479 | -2.5141, 9.4099 |
| MCV (fL) | 58 | 80.6–108.2 | 0.9971 | 1.0024 | 0.9854, 1.0195 | -0.3465 | -1.9205, 1.2275 |
| NEUT# (x 10³/μL) | 70 | 1.1–16.8 | 0.9978 | 1.0022 | 0.9816, 1.0228 | -0.0062 | -0.1141, 0.1017 |
| NEUT% | 70 | 21.8–91.9 | 0.9821 | 1.0126 | 0.9701, 1.0552 | -0.9453 | -4.1267, 2.2362 |
| LYMPH# (x 10³/μL) | 70 | 0.2–8.2 | 0.9956 | 0.9740 | 0.9392, 1.0087 | 0.04297 | -0.0077, 0.0936 |
| LYMPH% | 70 | 1.2–47.5 | 0.9951 | 0.9958 | 0.9717, 1.0200 | 0.02710 | -0.4449, 0.4991 |
| OTHER WBC# (x 10³/μL) | 61 | 0.1–2.5 | 0.9098 | 0.9164 | 0.6813, 1.1515 | 0.0648 | -0.0962, 0.2258 |
| OTHER WBC % | 62 | 1.2–30.7 | 0.9129 | 1.0580 | 0.9417 to 1.1743 | -0.4484 | -1.5124 to 0.6156 |
Conclusion: The results from this study demonstrated that the new version of software is comparable to the prior version of software. Appropriate suppression of results is maintained with the new version of software.
# 2. Sample challenge study
A prospective study was performed to confirm the appropriate suppression of results with v1.14 software for samples associated with interferences, artifacts, or associated conditions for which results from certain parameters should be suppressed in a CLIA Waived environment. In this study, 173 pre-selected, de-identified leftover K2EDTA venous whole
K210346 - Page 7 of 11
{7}
blood (normal and abnormal) samples were tested on XW-100 CLIA Waived analyzers using software versions v1.03 (K172604 clearance), v1.13 (on-market), or v1.14 (candidate device) by trained operators. The samples were also run on the Sysmex XN-10 analyzer (K112605). Blood smear analysis and WBC differential counts were performed on all samples as a confirmatory method by qualified examiners in accordance with CLSI H20-A2 – Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods; Approved Standard – Second Edition.
Samples with interfering substances, rare cells, pathologies, or morphologies with emphasis on samples with known conditions to affect RBC indices were specifically targeted for challenge samples. Samples with parameter flags (Alert High and Alert Low) were also evaluated in the study. A list of abnormalities targeted for challenge samples is provided below.
| Challenge Samples |
| --- |
| Cold Agglutinins |
| Fragmented RBC’s |
| High Lipids |
| High WBC Count |
| Hyperglycemia |
| Hypernatremia |
| Hypochromic Anemia |
| Hyponatremia |
| Immunoglobulin |
| Immunosuppressive Drugs |
| In Vivo Hemolysis |
| Large and Giant Platelets |
| Microcytes |
| Microorganisms
(bacterial aggregates, parasites, fungi) |
| Nucleated RBCs |
| Platelet Agglutination |
| Platelet Aggregates |
| Warm Agglutinins |
| Other (primarily High MCV,
Immature Granulocytes, Atypical
Lymphocytes) |
Deming linear regression analysis was performed on all unsuppressed results for all reported parameters. The results of this regression analysis are shown in the table below.
K210346 - Page 8 of 11
{8}
| Sample Challenge Study Software version v1.03 (K172604) compared to v1.14 (candidate) | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Measurand | N | Result Range (N=173) | Correlation Coefficient | Slope | 95% (CI) | Intercept | 95% (CI) |
| WBC (x 10³/μL) | 87 | 3.0–45.9 | 0.9995 | 1.0070 | 0.9922, 1.0218 | -0.02695 | -0.1549, 0.1010 |
| RBC (x 10⁶/μL) | 133 | 2.37–5.71 | 0.9985 | 1.0116 | 1.0013, 1.0218 | -0.0118 | -0.0497, 0.0261 |
| HGB (g/dL) | 91 | 10.2–18.3 | 0.9971 | 1.0053 | 0.9900, 1.0207 | -0.1249 | -0.3184, 0.0686 |
| HCT (%) | 112 | 25.0–51.1 | 0.9982 | 1.0115 | 1.0001, 1.0229 | 0.0794 | -0.3247, 0.4834 |
| PLT (x 10³/μL) | 102 | 104–804 | 0.9977 | 1.0045 | 0.9913, 1.0178 | -0.7271 | -4.4504, 2.9962 |
| MCV (fL) | 112 | 71.3–111.0 | 0.9990 | 1.0188 | 1.0098, 1.0278 | -1.3206 | -2.1296, -0.5116 |
| NEUT# (x 10³/μL) | 87 | 1.7–40.5 | 0.9993 | 1.0156 | 1.0015, 1.0296 | -0.0528 | -0.1457, 0.0400 |
| NEUT% | 87 | 29.6–97.1 | 0.9926 | 0.9761 | 0.9524, 0.9999 | 2.0669 | 0.2159, 3.9179 |
| LYMPH# (x 10³/μL) | 87 | 0.2–9.4 | 0.9974 | 1.0167 | 0.9876, 1.0459 | -0.0029 | -0.0472, 0.0412 |
| LYMPH% | 87 | 2.0–66.7 | 0.9968 | 0.9938 | 0.9764, 1.0111 | 0.2754 | -0.0460, 0.5968 |
| OTHER WBC# (x 10³/μL) | 79 | 0.0–2.2 | 0.9188 | 0.9753 | 0.8721, 1.0785 | -0.0272 | -0.0975, 0.0430 |
| OTHER WBC % | 78 | 0.7–29.3 | 0.9523 | 0.9545 | 0.8906, 1.0184 | -0.1008 | -0.6642, 0.4626 |
K210346 - Page 9 of 11
{9}
| Sample Challenge Study Software version v1.13 (on-market) compared to v1.14 (candidate) | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Measurand | N | Result Range (N=173) | Correlation Coefficient | Slope | 95% (CI) | Intercept | 95% (CI) |
| WBC (x 10³/μL) | 82 | 3.2–54.4 | 0.9997 | 1.0074 | 0.9979, 1.0169 | -0.0206 | -0.1118, 0.0705 |
| RBC (x 10⁶/μL) | 131 | 2.33–5.73 | 0.9988 | 1.0320 | 1.0228, 1.0412 | -0.0655 | -0.1006, -0.0303 |
| HGB (g/dL) | 83 | 10.0–17.9 | 0.9980 | 1.0228 | 1.0104, 1.0351 | -0.0069 | -0.1708, 0.1570 |
| HCT (%) | 100 | 25.3–50.7 | 0.9982 | 1.0353 | 1.0210, 1.0496 | -0.4120 | -0.9451, 0.1211 |
| PLT (x 10³/μL) | 102 | 116–821 | 0.9968 | 1.0111 | 0.9896, 1.0326 | 0.7837 | -4.7345, 6.3020 |
| MCV (fL) | 100 | 72.2–110.1 | 0.9983 | 1.0485 | 1.0373, 1.0598 | -3.6551 | -4.6946, -2.6155 |
| NEUT# (x 10³/μL) | 82 | 1.6–48.5 | 0.9995 | 0.9986 | 0.9836, 1.0135 | 0.0603 | -0.0437, 0.1643 |
| NEUT% | 82 | 29.3–96.9 | 0.9911 | 0.9636 | 0.9372, 0.9899 | 3.0143 | 0.9764, 5.0522 |
| LYMPH# (x 10³/μL) | 82 | 0.2–9.4 | 0.9961 | 1.0062 | 0.9509, 1.0615 | -0.0089 | -0.0904, 0.0726 |
| LYMPH% | 82 | 2.1–66.9 | 0.9963 | 0.9945 | 0.9697, 1.0192 | -0.0445 | -0.4965, 0.4074 |
| OTHER WBC# (x 10³/μL) | 73 | 0.0–2.1 | 0.9186 | 1.0611 | 0.9086, 1.2136 | -0.0526 | -0.1476, 0.0424 |
| OTHER WBC % | 75 | 0.4–28.9 | 0.9462 | 0.9654 | 0.8319, 1.0990 | 0.0311 | -0.9067, 0.9690 |
The results of this study demonstrated that appropriate and expected suppression of results occurred for the XW-100 CLIA Waived analyzer with v1.14 software for challenge samples, as confirmed by blood smear analysis with WBC differential counts and results from the XN-10 analyzer. Regression analysis indicated that the v1.14 software performed similar to the previously cleared software (v1.03, K172604 and CW170012) and software currently on the market (v1.13).
K210346 - Page 10 of 11
{10}
Conclusion: The software change does not impact the appropriate suppression of results for challenging samples and unaffected parameters maintain similar performance to the previously cleared XW-100 CLIA Waived analyzer.
## 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.
K210346 - Page 11 of 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.