The X100 with Full Field Peripheral Blood Smear Application is intended to locate and display images of white cells, red cells, and platelets acquired from fixed and stained peripheral blood smears and assists a qualified technologist in conducting a WBC differential, RBC morphology evaluation, and platelet estimate using those images. For in vitro diagnostic use only. For professional use only.
Device Story
Device consists of X100 Microscope (optic scanning unit) and X100 Scopiobox (analysis computer). System captures multiple images of blood smear slides under varying illumination conditions without immersion oil; uses physical model to reconstruct high-resolution images. Automatically locates and presents images of WBCs, RBCs, and platelets. User reviews suggested WBC classification (18 categories), RBC morphology, and platelet estimation; may manually adjust classifications or detections. Used in clinical laboratory settings by trained technologists. Output assists in hematological assessment; improves efficiency of manual review processes.
Clinical Evidence
Method comparison study of 645 specimens (335 normal, 310 diseased) across three sites compared subject device to manual light microscopy. WBC differential showed high correlation (r=0.94-0.98). Overall WBC differential efficiency 96.29%, sensitivity 87.86%, specificity 97.62%. RBC morphology evaluation showed 99.77% overall agreement. Platelet estimation correlation r=0.94, efficiency 94.89%. Precision studies (repeatability/reproducibility) per CLSI EP05-A3 met acceptance criteria.
Technological Characteristics
System comprises X100 Microscope and Scopiobox computer. Imaging uses high-resolution camera, multi-illumination capture, and physical model reconstruction (no immersion oil). Connectivity: Standalone/networked. Software: Deterministic artificial neural networks (ANNs) for cell classification. Calibration: Mechanical/optical via standard blood smear. QC: Daily standard slide verification. Complies with IEC 62471 (photobiological safety).
Indications for Use
Indicated for use by qualified technologists to assist in WBC differential, RBC morphology evaluation, and platelet estimation from fixed and stained peripheral blood smears. Intended for professional in vitro diagnostic use.
Regulatory Classification
Identification
An automated cell-locating device is a device used to locate blood cells on a peripheral blood smear, allowing the operator to identify and classify each cell according to type. (Peripheral blood is blood circulating in one of the body's extremities, such as the arm.)
Predicate Devices
EasyCell Cell Locator (k092116)
Romanowsky stain manual light microscope process for cell classification (21CFR 864.3600)
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
K201301
B Applicant
Scopio Labs LTD.
C Proprietary and Established Names
X100 with Full Field Peripheral Blood Smear (PBS) Application
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| JOY | Class II | 21 CFR 864.5260 - Automated Cell-Locating Device | HE - Hematology |
## II Submission/Device Overview:
A Purpose for Submission:
Clearance of a new device
B Type of Test:
White blood cell (WBC) differential, red blood cell (RBC) morphology evaluation and platelet estimation
## III Intended Use/Indications for Use:
A Intended Use(s):
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
See Indications for Use below.
## B Indication(s) for Use:
The X100 with Full Field Peripheral Blood Smear Application is intended to locate and display images of white cells, red cells, and platelets acquired from fixed and stained peripheral blood smears and assists a qualified technologist in conducting a WBC differential, RBC morphology evaluation, and platelet estimate using those images. For in vitro diagnostic use only. For professional use only.
## C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
## IV Device/System Characteristics:
### A Device Description:
X100 with Full Field Peripheral Blood Smear (PBS) Application automatically locates and presents images of blood cells on peripheral smears. The user browses through the imaged smear to gain high-level general impression. The user reviews the suggested classification of each white cell according to type and may manually change the suggested classification of any cell. The user can also characterize red cell morphology on observed images. In addition, the system suggests the location of platelets. The user reviews each detected platelet and the suggested platelet estimation and may manually change the detections or the estimation. The Full Field PBS is intended to be used by skilled users, trained in the use of the device and in the identification of blood cells.
The Full Field PBS consists of two major components: 1) The X100 Microscope, an optic scanning unit where sample slides are inserted to the digital microscope for imaging, and 2) The X100 Scopiobox, an operating and analyzing computer which controls the X100 microscope and serves the Full Field PBS application.
To acquire a high-resolution image, the sample slide is moved by the X100 microscope positioning stage under its main optic tube, which has a microscope objective with a tube lens and high-resolution camera. The X100 microscope captures multiple images of the sample under a plurality of illumination conditions (different durations, different illumination angles, different illumination patterns, different wavelengths), without the need for immersion oil. Using a physical model and the captured images, the X100 Scopiobox reconstructs high-resolution images of the sample.
### B Instrument Description Information:
1. Instrument Name:
X100 with Full Field Peripheral Blood Smear Application
2. Specimen Identification:
K201301 - Page 2 of 11
{2}
The slide's barcode is captured automatically and assigned to each case. The device also supports typing the barcode manually.
3. Specimen Sampling and Handling:
A peripheral blood sample collected in K₂EDTA or K₃EDTA tubes is mixed manually or automatically. A thin blood film is wedged on a clean dry glass slide (a blood smear) and stained with Romanowsky stain. After the staining process is completed, the slide is covered using any standard cover slipping method.
4. Calibration:
The Full Field PBS system requires initial calibration for its mechanical and optical performances. An initial calibration process is performed on a standard blood smear slide as part of the manufacturing process of the device. The calibration is verified after installation by a technician or a qualified operator. Calibration can also be performed if a problem arises in the daily QC testing.
5. Quality Control:
Quality Control (QC) testing is performed on a daily basis ("daily QC"). The daily QC involves testing a standard blood smear slide prepared on the same day. During the daily QC the user reviews the images received from the Full Field PBS and verifies that at least 95% of the WBCs in the scanned image were identified and located correctly by the system. The Full Field PBS application maintains a digital QC log, enabling the user to review and to track the history of QC testing performed by the Full Field PBS.
V Substantial Equivalence Information:
A Predicate Device Name(s):
Easy Cell Locator
Light, Microscope
B Predicate 510(k) Number(s):
K092116
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K201301 | K092116 |
| --- | --- | --- |
| Device Trade Name | X100 with Full Field Peripheral Blood Smear Application | EasyCell Cell Locator |
K201301 - Page 3 of 11
{3}
K201301 - Page 4 of 11
| General Device Characteristic Similarities | | |
| --- | --- | --- |
| Intended Use / Indications for Use | The X100 with Full Field Peripheral Blood Smear Application is intended to locate and display images of white cells, red cells, and platelets acquired from fixed and stained peripheral blood smears and assists a qualified technologist in conducting a WBC differential, RBC morphology evaluation, and platelet estimate using those images. For in vitro diagnostic use only. For professional use only. | The EasyCell is intended to locate and display images of white cells, red cells, and platelets acquired from fixed and stained peripheral blood smears and assists a qualified technologist in conducting a WBC differential, RBC morphology evaluation, and platelet estimate using those images. For in vitro diagnostic use only. For professional use only. |
| Sample Type | Stained blood film glass slides of peripheral whole blood | Same |
| Sample Preparation | Romanowsky stain | Same |
| Analysis Technique: White Blood Cells | WBC are located/counted by moving according to the battlement pattern (ensuring that each cell is counted only once). Cell images are analyzed using standard mathematical methods, including deterministic artificial neural networks (ANN's) trained to distinguish between classes of white blood cells. The cell images are pre-classified, and the user reviews the suggested classification, and accepts or reclassifies the images. | Same |
| Analysis Technique: Red Blood Cells | Red blood cells: The device presents an overview image. The examiners characterize red blood cell morphology from the image. | Same |
{4}
| Daily QC | The QC procedure controls for slide preparation (both smearing and staining) and device performance. If the QC procedure does not pass, the operator must resolve the problem and rerun the QC before processing samples. | Same |
| --- | --- | --- |
| General Device Characteristic Differences | | |
| Analysis Technique: Platelets | Platelets are automatically located/counted by moving according to the battlement pattern (ensuring that each cell is counted only once). The user reviews the suggested estimate of the platelet concentration, and accepts or modifies the result. | The device presents a series of images. The reviewers manually count and estimate the platelet concentration from the images according to a procedure in the User's Manual. |
| Pre-classified WBC | Cell images are grouped into eighteen (18) categories: Band Neutrophils; Segmented Neutrophils; Lymphocytes; Atypical Lymphocytes; Large Granular Lymphocytes; Aberrant Lymphocytes; Monocytes; Eosinophils; Basophils; Promyelocyte; Metamyelocytes; Myelocytes; Blasts; Plasma Cells; Nucleated Red Blood Cells; Unclassified; Smudge cells; Dirt | Cell images are grouped into eight (8) categories: Neutrophils (Band or Segmented; Lymphocytes; Monocytes; Eosinophils; Basophils; Nucleated Red Blood Cells; Smudge cells; Other (which is intended to hold morphologically abnormal cells.) |
| High-Resolution Image Acquisition | Fully automated scan and image acquisition. Captures multiple images under plurality of illumination conditions and reconstructs a 100X magnification image of the viewed area, without the need for immersion oil. | Fully automated scan and image acquisition. Captures images at 10X resolution to locate certain cells and then capture images of those cells using a 100X magnification lens and immersion oil. |
K201301 - Page 5 of 11
{5}
VI Standards/Guidance Documents Referenced:
CLSI EP05-A3: Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline - Third Edition
CLSI EP12-A2: User Protocol for Evaluation of Qualitative Test Performance; Approved Guideline - Second Edition
CLSI EP17-A2: Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline - Second Edition
CLSI H20-A2: Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods; Approved Standard - Second Edition
IEC 62471 First edition 2006-07: Photobiological safety of lamps and lamp systems
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
**Repeatability**
The repeatability study was performed according to the CLSI EP05-A3 Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline—Third Edition.
A 20x2x2 repeatability study for the analyses of white blood cells differential and platelet estimation was conducted using a single instrument at a single site with 15 selected test samples. Over the course of 20 testing days, 2 daily runs were performed using 2 replicas. The selected samples represented different clinical conditions, to include all automatically located and pre-classified cell types. In total, 1,200 scans were analyzed.
As a high-level summary, the following tables capture, for each variance component, the maximum measurement received for the upper bound of the 95% CI of the standard deviation. All repeatability study results met acceptance criteria.
| Maximum SD upper bound values of 95% CI | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Cell Type | Variance Components | | | | | | | |
| | Repeatability | | Between-Run | | Between-Day | | Within-Laboratory Precision | |
| | Mean | SD upper bound of 95% CI | Mean | SD upper bound of 95% CI | Mean | SD upper bound of 95% CI | Mean | SD upper bound of 95% CI |
| Segmented & Band Neutrophil | 53.3 % | 1.8 % | 83.4% | 1.3 % | 66.4 % | 1.9 % | 75.2 % | 2.2 % |
| Lymphocyte | 48.6 % | 1.6 % | 48.6% | 0.8 % | 18.2 % | 1.9 % | 18.2 % | 2.1 % |
| Variant Forms Lymphocyte | 6 % | 1.3 % | 6 % | 0.4 % | 2.8 % | 0.7 % | 6 % | 1.3 % |
| Monocyte | 9.7 % | 1.6 % | 3.7 % | 0.5 % | 5.9 % | 0.8 % | 9.7 % | 1.6 % |
| Eosinophil | 6.3 % | 0.6 % | 2.6 % | 0.3 % | 3.3 % | 0.8 % | 3.3 % | 0.8 % |
| Basophil | 0.5 % | 0.4 % | 0.5 % | 0.3 % | 0.5 % | 0.6 % | 0.5 % | 0.7 % |
| Plasma cell | 0.6 % | 0.4 % | 0.6 % | 0.2 % | 0.5 % | 0.1 % | 0.5 % | 0.4 % |
K201301 - Page 6 of 11
{6}
Maximum SD upper bound values of 95% CI
| Cell Type | Variance Components | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Repeatability | | Between-Run | | Between-Day | | Within-Laboratory Precision | |
| | Mean | SD upper bound of 95% CI | Mean | SD upper bound of 95% CI | Mean | SD upper bound of 95% CI | Mean | SD upper bound of 95% CI |
| Immature Granulocyte | 0.8 % | 0.5 % | 0.7 % | 0.3 % | 0.7 % | 0.7 % | 0.7 % | 0.7 % |
| Blast | 3 % | 1.2 % | 3 % | 0.4 % | 0 % | 0 % | 3 % | 1.1% |
| NRBC | 5.8 % | 0.6 % | 3.5 % | 0.2 % | 3.5 % | 0.4 % | 5.8 % | 0.6 % |
Maximum SD upper bound values of 95% CI
| Cell Type | Variance Components | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Repeatability | | Between-Run | | Between-Day | | Within-Laboratory Precision | |
| | Mean | SD upper bound values of 95% CI | Mean | SD upper bound values of 95% CI | Mean | SD upper bound values of 95% CI | Mean | SD upper bound values of 95% CI |
| Platelet Estimation | 305.5 | 31.7 | 155.3 | 18.1 | 153.1 | 23.8 | 213.9 | 34.4 |
# Reproducibility
The reproducibility study was performed according to the CLSI EP05-A3 Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline—Third Edition.
A 3x5x5 reproducibility study for the analyses of white blood cells differential and platelet estimation was performed across 3 different sites. The study was conducted at each site, with 10 test samples, for 5 testing days, using 5 replicas scanned with the local device. The selected samples represented different clinical conditions, to include all automatically located and pre-classified cell types. In total, 750 scans were analyzed.
As a high-level summary, the following tables capture, for each variance component, the maximum measurement received for the standard deviation. Reproducibility study results passed pre-defined acceptance criteria.
Maximum SD Values
| Cell Type | Variance Components | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| | Repeatability | | Between-Day | | Within-Laboratory Precision | | Between-Site | | Reproducibility | |
| | Mean | SD | Mean | SD | Mean | SD | Mean | SD | Mean | SD |
| Segmented & Band Neutrophil | 52.9 % | 1.7 % | 50.6 % | 1.1 % | 52.9 % | 1.7 % | 50.6 % | 3.9 % | 50.6 % | 4.2 % |
| Lymphocyte | 23.4 % | 1.4 % | 26.5 % | 2 % | 26.5 % | 2.2 % | 17.2 % | 2.8 % | 26.5 % | 3.1 % |
| Variant Forms Lymphocyte | 9.9 % | 1.1 % | 5.2 % | 1.3 % | 5.2 % | 1.5 % | 5.2 % | 1.1 % | 5.2 % | 1.9 % |
| Monocyte | 6.5 % | 1.2 % | 6.5 % | 0.6 % | 6.5 % | 1.3 % | 8.2 % | 1.2 % | 8.2 % | 1.5 % |
| Eosinophil | 2.7 % | 0.4 % | 2.7 % | 0.3 % | 2.7 % | 0.5 % | 2.7 % | 0.4 % | 2.7 % | 0.7 % |
| Basophil | 0.5 % | 0.3 % | 0.8 % | 0.1 % | 0.5 % | 0.3 % | 0.6 % | 0.3 % | 0.8 % | 0.4 % |
| Plasma cell | 0.6 % | 0.2 % | 0.6 % | 0.1 % | 0.6 % | 0.3 % | 0.6 % | 0.4 % | 0.6 % | 0.5 % |
| Immature Granulocyte | 1.8 % | 0.5 % | 1.8 % | 0.4 % | 1.8 % | 0.6 % | 1.8 % | 1 % | 1.8 % | 1.2 % |
| Blast | 4.3 % | 0.8 % | 4.3 % | 0.1 % | 4.3 % | 0.8 % | 4.3 % | 1.1 % | 4.3 % | 1.4 % |
| NRBC | 6.7 % | 0.5 % | 6.7 % | 0.1 % | 6.7 % | 0.6 % | 6.7 % | 0.9 % | 6.7 % | 1.1 % |
K201301 - Page 7 of 11
{7}
| Maximum SD Values | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Cell Type | Variance Components | | | | | | | | | |
| | Repeatability | | Between-Day | | Within-Laboratory Precision | | Between-Site | | Reproducibility | |
| | Mean | SD | Mean | SD | Mean | SD | Mean | SD | Mean | SD |
| Platelet Estimation | 217.2 | 22.0 | 217.2 | 17.8 | 217.2 | 28.3 | 217.2 | 29.7 | 217.2 | 41.0 |
2. Linearity:
Not applicable.
3. Analytical Specificity/Interference:
Not applicable.
4. Accuracy (Instrument):
## Method Comparison
A Method Comparison study was conducted to compare the results achieved by trained examiners using the X100 with Full Field Peripheral Blood Smear Application (the Test Method) to the results achieved by using a manual light microscope. The study was performed according to the CLSI H20-A2: Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods; Approved Standard—Second Edition.
A total of 645 specimens were collected and analyzed at three sites. 335 specimens were from normal (healthy) subjects and 310 were from subjects with specific disease conditions. Slides were prepared from each specimen. The slides were randomly selected, blinded and evaluated by two examiners at each site.
## White Blood Cells
Following analysis at each site, a pooled analysis of the multi-center results was conducted. The following table summarizes the results of the Deming regression comparison method for the multi-center study. All 95% CI of slope and intercept and Pearson correlation coefficient met the acceptance criteria for accuracy measured by Deming regression for WBC differential.
WBC correlation between reference method and test method (Multi-center Deming Regression for 200 WBC Differential)
| Cell Type | Intercept (95% CI) | Slope (95% CI) | Pearson correlation coefficient (r) |
| --- | --- | --- | --- |
| Neutrophil (%) | 0.39 | 1.00 | 98% |
| | (-0.44 to 1.21) | (0.99 to 1.01) | |
K201301 - Page 8 of 11
{8}
| Cell Type | Intercept (95% CI) | Slope (95% CI) | Pearson correlation coefficient (r) |
| --- | --- | --- | --- |
| Lymphocyte (%) | -0.51 | 0.99 | 96% |
| | (-1.02 to 0.00) | (0.96 to 1.02) | |
| Monocyte (%) | -0.15 | 0.94 | 95% |
| | (-0.60 to 0.31) | (0.86 to 1.02) | |
| Eosinophil (%) | 0.00 | 0.89 | 98% |
| | (-0.17 to 0.16) | (0.82 to 0.96) | |
Overall WBC differential efficiency (agreement), sensitivity and specificity were measured, as well as for distributional WBC (Band and Segmented Neutrophil, Monocyte, Lymphocyte and Eosinophil) and morphological WBC (Immature Granulocyte, Variant Forms Lymphocyte, Blast, NRBC and Plasma cell) between subject device and manual microscope.
## WBC Differential Efficiency, Sensitivity and Specificity
| | Morphological Abnormality | Distributional Abnormality | Overall |
| --- | --- | --- | --- |
| Efficiency | 96.82%
(96.12% to 97.43%) | 95.75%
(94.95% to 96.46%) | 96.29%
(95.77% to 96.76%) |
| Sensitivity | 85.46%
(80.19% to 89.78%) | 88.83%
(85.94% to 91.31%) | 87.86%
(85.38% to 90.06%) |
| Specificity | 97.79%
(97.16% to 98.31%) | 97.43%
(96.70% to 98.03%) | 97.62%
(97.16% to 98.02%) |
Predicted bias analysis (Bland-Altman) of WBC differential is summarized below. The mean differences and 95% limits of agreements per cell type were measured.
## Red Blood Cells
Results of overall agreement for RBC morphology evaluation are shown below. Results passed pre-defined acceptance criteria.
### Red blood cells overall agreement
| RBC | Overall Agreement with 95% CI |
| --- | --- |
| Overall | 99.77%
(99.71% to 99.83%) |
| RBC Morphology Group | Overall Agreement with 95% CI |
| --- | --- |
| Color | 99.49%
(99.14% to 99.73%) |
| Shape | 99.77%
(99.68% to 99.84%) |
| Size | 99.61%
(99.36% to 99.78%) |
| Inclusions | 100.00%
(99.93% to 100.00%) |
K201301 - Page 9 of 11
{9}
| RBC Morphology Group | Overall Agreement with 95% CI |
| --- | --- |
| Arrangement | 96.65%
(95.52% to 97.57%) |
## Platelet Estimation
Platelet estimation efficiency, sensitivity and specificity measurements between subject device and manual microscope are as follows. Results passed pre-defined acceptance criteria.
### Platelet Estimation Efficiency, Sensitivity and Specificity
| Platelet Estimation | |
| --- | --- |
| Efficiency | 94.89%
(92.78% to 96.53%) |
| Sensitivity | 90.00%
(83.51% to 94.57%) |
| Specificity | 96.28%
(94.11% to 97.82%) |
## Method Comparison Study of 100 to 200 WBC Differential and 5 to 10 FOV Platelet Estimation
All slides from the Method Comparison study were also analyzed by Full Field PBS device using 100 WBC differential and 5 FOV platelet estimation. The results were compared to the 200 WBC differential and 10 FOV platelet estimation of the manual light microscope. Accuracy (Deming Regression), efficiency, sensitivity and specificity were measured.
## White Blood Cells
### 100 WBC correlation between reference method and 200 WBC test method
| Cell Type | Intercept
(95% CI) | Slope
(95% CI) | Pearson correlation coefficient (r) |
| --- | --- | --- | --- |
| Neutrophil (%) | 0.87
(0.00 to 1.75) | 0.99
(0.98 to 1.01) | 98% |
| Lymphocyte (%) | -0.50
(-1.01 to 0.00) | 0.99
(0.96 to 1.01) | 96% |
| Monocyte (%) | -0.13
(-0.57 to 0.31) | 0.93
(0.86 to 1.01) | 94% |
| Eosinophil (%) | 0.01
(-0.20 to 0.22) | 0.88
(0.80 to 0.97) | 97% |
### 100 WBC Efficiency, Sensitivity and Specificity
| | Morphological Abnormality | Distributional Abnormality | Overall |
| --- | --- | --- | --- |
| Efficiency | 96.48%
(95.74% to 97.12%) | 95.06%
(94.21% to 95.82%) | 95.77%
(95.22% to 96.27%) |
K201301 - Page 10 of 11
{10}
| Sensitivity | 81.06%
(75.34% to 85.94%) | 86.35%
(83.23% to 89.07%) | 84.83%
(82.14% to 87.26%) |
| --- | --- | --- | --- |
| Specificity | 97.79%
(97.16% to 98.31%) | 97.17%
(96.41% to 97.80%) | 97.50%
(97.03% to 97.91%) |
Platelets
5 FOV Platelet Estimation Efficiency, Sensitivity and Specificity
| Platelet Estimation | |
| --- | --- |
| Efficiency | 94.55%
(92.39% to 96.24%) |
| Sensitivity | 90.00%
(83.51% to 94.57%) |
| Specificity | 95.84%
(93.58% to 97.48%) |
5. Carry-Over:
Not applicable.
B Other Supportive Instrument Performance Characteristics Data:
Not Applicable.
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.
K201301 - Page 11 of 11
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.