The Sight OLO is a quantitative multi-parameter automated hematology analyzer intended for in vitro diagnostic use in screening capillary or venous whole blood samples collected in K2EDTA blood collection tubes, or fingertip samples collected using the Sight OLO test kit micro-capillary tubes. When used with the Sight OLO cartridge, the Sight OLO utilizes computer imaging and computer vision algorithms to enumerate the following CBC parameters in whole blood: WBC, RBC, HGB, HCT, MCV, MCH, MCHC, RDW, PLT, NEUT%/#, LYMPH %/#, MONO %/#, EO%/#, and BASO%/#. The Sight OLO is indicated for use by clinical laboratories to identify and classify one or more of the formed elements of blood in children 3 months and above, adolescents and adults.
Device Story
Sight OLO is a compact, computer vision-based hematology analyzer for clinical laboratories. It processes 17 µL whole blood samples (capillary or venous K2EDTA) using a disposable cartridge containing an imaging chamber and hemoglobin measurement cavity. The device performs automated staining and monolayer formation; it then uses a fluorescence microscope to capture bright-field and fluorescence images. Computer vision algorithms analyze these images based on cell intensity, size, shape, and morphology to quantify CBC parameters and 5-part leukocyte differentials. Hemoglobin is measured via absorbance at four wavelengths. The device is operated via a touchscreen; results are used by clinicians for hematological screening and decision-making. It provides automated, rapid blood analysis, reducing the need for manual microscopy.
Clinical Evidence
Method comparison study (CLSI H20-A2, H26-A2, EP09-A3) conducted at 3 US sites using 700 residual clinical K2EDTA whole blood samples (pediatric and adult). Compared Sight OLO to Sysmex XN-Series. Results showed high correlation (r=0.646 to 0.997) across all measurands. Flagging study compared Sight OLO to manual light microscopy (n > 200 samples); demonstrated 91.0% sensitivity (PPA) and 92.6% specificity (NPA) for detecting distributional and morphological abnormalities.
Technological Characteristics
Compact computer vision-based hematology analyzer. Uses disposable cartridges with imaging chambers and hemoglobin measurement cavities. Employs fluorescence microscopy and multi-wavelength absorbance (four wavelengths) for HGB. Factory calibrated; traceable to CLSI H26-A2. Software-based analysis using computer vision algorithms. Connectivity via internet for QC data. Sterilization/biocompatibility managed via disposable test kit components.
Indications for Use
Indicated for clinical laboratories to identify and classify formed blood elements in children 3 months and older, adolescents, and adults using capillary or venous K2EDTA whole blood or fingertip samples.
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}
FDA
U.S. FOOD & DRUG
ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
## I Background Information:
A 510(k) Number
K211840
B Applicant
Sight Diagnostics Ltd.
C Proprietary and Established Names
Sight OLO
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:
Modification of a cleared device
B Measurand:
WBC, RBC, HGB, HCT, MCV, MCH, MCHC, RDW, PLT, NEUT%/#, LYMPH%/#, MONO%/#, EOS%/# and BASO%/#
C Type of Test:
Quantitative complete blood count (CBC) with 5-part leukocyte differential: WBC, RBC, HGB, HCT, MCV, MCH, MCHC, RDW, PLT, NEUT%/#, LYMPH%/#, MONO%/#, EOS%/# and BASO%/#.
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
III Intended Use/Indications for Use:
A Intended Use(s):
See Indications for Use below.
B Indication(s) for Use:
The Sight OLO is a quantitative multi-parameter automated hematology analyzer intended for in vitro diagnostic use in screening capillary or venous whole blood samples collected in K2EDTA blood collection tubes, or fingertip samples collected using the Sight OLO test kit micro-capillary tubes.
When used with the Sight OLO cartridge, the Sight OLO utilizes computer imaging and computer vision algorithms to enumerate the following CBC parameters in whole blood: WBC, RBC, HGB, HCT, MCV, MCH, MCHC, RDW, PLT, NEUT%/#, LYMPH %/#, MONO %/#, EO%/#, and BASO%/#.
The Sight OLO is indicated for use by clinical laboratories to identify and classify one or more of the formed elements of blood in children 3 months and above, adolescents and adults.
C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
D Special Instrument Requirements:
Sight OLO
IV Device/System Characteristics:
A Device Description:
The Sight OLO device was cleared under K190898. Since its original clearance, the designs and components of the Sight OLO have remained the same, whereas the analysis software algorithms of the Sight OLO have been updated. However, the Sight OLO remains a quantitative, multiparameter, automated in vitro diagnostic hematology analyzer that screens whole blood samples collected from venous and/or capillary blood and provides results for complete blood count (CBC) parameters and a 5-part leukocyte differential.
The Sight OLO device is a compact computer vision-based platform for blood analysis. The Sight OLO device consists of a scanning and analyzing unit and a CBC test kit, which includes a disposable cartridge (1). The disposable cartridge contains an imaging chamber and a hemoglobin (Hgb) measurement cavity. In addition to the disposable cartridge, the CBC test kit also includes a mixing bottle (2) containing 1333 µL diluent and sealed with pierceable foil, a dropper cap (3) integrated with 10 µL end-to-end micro-capillary and containing dried fluorescent staining reagents, and a 17 µL micro-capillary (4, off the shelf). Pre-dilution and staining of blood sample occurs in the mixing bottle and blood sample is added to the disposable
{2}
cartridge, which is then inserted into the device through the loading slot. Using dedicated staining, the proposed platform provides CBC analysis. The device is operated through the touch screen interface.

(1)

(2)

(3)
## B Principle of Operation:
The Sight OLO device is a computer vision based platform for blood analysis. The platform combines computer-vision algorithms for image processing to identify and quantify blood components (e.g., red blood cells) and their characteristics (e.g., cell volume) in an automated fashion.
The disposable cartridge loaded with whole blood sample is inserted into the device for automatic staining and monolayer formation. The device uses computer-vision algorithms to visually scan a stained blood sample under a fluorescence microscope. The device utilizes three wavelengths bright-field images, and fluorescence mages to derive the complete blood count of the sample. The captured images are analyzed, and the software identifies the visual differences between the different blood components or abnormalities while relying on characteristics such as intensity, size, shape, fluorescence intensity, and morphology. Hemoglobin is measured by a unique channel in the device that measures the absorbance of undiluted whole blood in four wavelengths. The technique is based on an absorbance optical measurement through a small volume cavity with a short light path.
The Sight OLO device provides complete blood count information with 5-part differentials for white blood cell types. Specifically, the CBC parameters measured by the Sight OLO device are listed below and include: White Blood Cell Count (WBC), Red Blood Cell Count (RBC), Hemoglobin (HGB), Hematocrit (HCT), Mean Cell Volume (MCV), Mean Cell Hemoglobin (MCH), Mean Cell Hemoglobin Concentration (MCHC), RBC Distribution Width (RDW), Platelet Count (PLT), Neutrophil Percent and Count (NEUT%/#), Lymphocyte Percent and Count (LYMPH %/#), Monocyte Percent and Count (MONO %/#), Eosinophil Percent and Count (EOS%/#), and Basophil Percent and Count (BASO%/#).
## C Instrument Description Information:
1. Instrument Name:
Sight OLO
K211840 - Page 3 of 17
{3}
K211840 - Page 4 of 17
2. Specimen Identification:
Specimen identification is performed by use of a barcode reader or manually typing the sample ID on the Sight OLO screen.
3. Specimen Sampling and Handling:
The Sight OLO device can be used with either non-anticoagulated fingertip samples or capillary and venous anticoagulated whole blood samples collected in K₂EDTA tubes. Capillary blood sampling is performed by routine finger prick puncture following each user facility’s standard guidelines. Per the Operator’s Manual, fingertip samples are collected directly from the fingertip into the Sight OLO test kit microcapillaries. Venous and capillary whole blood samples are collected into K₂EDTA tubes or microtubes (respectively) using each user facility’s standard procedure. Venous and capillary whole blood should be sufficiently mixed and stored at room temperature for less than eight hours before use.
4. Calibration:
The Sight OLO device is factory calibrated prior to shipping to the end user, and no further calibration is needed. The calibration of Sight OLO is traceable to the reference methods described in CLSI H26-A2.
5. Quality Control:
Whole blood quality control material OLO Control (three levels: high, medium, low) provided by R&D Systems (Minneapolis, MN) is available for the Sight OLO to monitor the performance of the analyzer. It is a stabilized whole blood matrix designed for statistical process control of the Sight OLO.
Quality control range limits are downloaded automatically by an internet connection (or configured locally by scan of QR codes printed on Quality Control product insert). Lot expiration and results validity checks are done using the instrument software via the user interface.
V Substantial Equivalence Information:
A Predicate Device Name(s):
Sight OLO
B Predicate 510(k) Number(s):
K190898
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K211840 | K190898 |
| --- | --- | --- |
| Device Trade Name | Sight OLO | Sight OLO |
| General Device Characteristic | | |
{4}
K211840 - Page 5 of 17
| Device & Predicate Device(s): | K211840 | K190898 |
| --- | --- | --- |
| Similarities | | |
| Intended Use/Indications for Use | Sight OLO is a quantitative multi-parameter automated hematology analyzer intended for in vitro diagnostic use in screening capillary or venous whole blood samples collected in K2EDTA blood collection tubes, or fingertip samples collected using the Sight OLO test kit microcapillary tubes.
When used with the Sight OLO cartridge, the Sight OLO utilizes computer imaging and computer vision algorithms to enumerate the following CBC parameters in whole blood: WBC, RBC, HGB, HCT, MCV, MCH, MCHC, RDW, PLT, NEUT%/#, LYMPH %/#, MONO%/#, EO%/#, and BASO%/#.
The Sight OLO is indicated for use by clinical laboratories to identify and classify one or more of the formed elements of blood in children 3 months and above, adolescents and adults. | Sight OLO is a quantitative multi-parameter automated hematology analyzer intended for in vitro diagnostic use in screening capillary or venous whole blood samples collected in K2EDTA blood collection tubes, or fingertip samples collected using the Sight OLO test kit microcapillary tubes.
When used with the Sight OLO cartridge, the Sight OLO enumerates the following CBC parameters in whole blood: WBC, RBC, HGB, HCT, MCV, MCH, MCHC, RDW, PLT, NEUT%/#, LYMPH %/#, MONO%/#, EO%/#, and BASO%/#.
The Sight OLO is indicated for use in clinical laboratories to identify and classify one or more of the formed elements of blood in children 3 months and above, adolescents and adults. |
| Components | • Scanning and analyzing device (include microscope)
• Test kit (including a disposable cartridge, a Microsafe microcapillary tube, a dropper cap containing dried reagents and attached to another microcapillary tube and a mixing bottle containing liquid diluent) | Same |
| Test Parameters | WBC, RBC, HGB, HCT, MCV, MCH, MCHC, RDW, PLT, NEUT%/#, LYMPH %/#, MONO %/#, EO%/#, and BASO%/# | Same |
{5}
| Device & Predicate Device(s): | K211840 | K190898 |
| --- | --- | --- |
| Analysis modes | Whole blood (capillary and venous) | Same |
| Specimen collection | Either capillary and venous anticoagulated whole blood samples collected into K2EDTA microtubes / tubes, or capillary samples collected directly from the fingertip into the OLO test kit micro-capillary tubes | Same |
| Sample volume | 17 μL | Same |
| Calibration / Quality Control | Factory calibrated
Optional control kit OLO Control (3 levels) will be provided to user (used if needed) | Factory calibrated
Optional control kit CBC-OPT (3 levels) will be provided to user (used if needed) |
| General Device Characteristic Differences | | |
| Software version | 2.57b | 2.29.4 |
VI Standards/Guidance Documents Referenced:
ASTM D7386-16, Standard Practice for Performance Testing of Packages for Single Delivery Systems [5-113]
CLSI EP09-A3: Measurement Procedure Comparison and Bias Estimation Using Patient Samples; Approved Guideline – Third Edition [7-296]
CLSI H20-A2, Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods; Approved Standard – Second Edition [7-165]
CLSI H26-A2, Validation, Verification, and Quality Assurance of Automated Hematology Analyzers; Approved Standard – Second Edition [7-210]
CLSI EP25-A, Evaluation of Stability of In Vitro Diagnostic Reagents; Approved Guideline [7-235]
IEC 62304-2006, Medical device software - Software life-cycle processes [13-79]
IEC 62366, Medical devices – Application of usability engineering to medical devices [5-129]
ISO 14971-2019, Medical devices - Application of risk management to medical devices [5-125]
ISO 15223-1-2016, Medical devices – Symbols to be used with medical device labels, labelling and information to be supplied – Part 1 general requirements [5-117]
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
K211840 - Page 6 of 17
{6}
Refer to K190898
2. Linearity:
Refer to K190898
3. Analytical Specificity/Interference:
Refer to K190898
Deoxyhemoglobin
Since the previous clearance of the Sight OLO, an additional interferent, deoxyhemoglobin, has been evaluated. The purpose of this study was to characterize the susceptibility of the Sight OLO device to low blood oxygen saturation (i.e. lack of oxygen as an interferent) as a potential endogenous interfering substance. The study was conducted using the same protocol used previously in K190898. A total of 14 normal fresh venous whole blood samples were used. Each sample was scanned three times (2 replicates each time) on each of three Sight OLO devices. Each sample was scanned one time after undergoing mixing procedure designed to ensure complete oxygen saturation of the sample (O2Hb > 90%), one time under target reduced oxygen saturation (O2Hb 20-30%), and one time after resaturation (O2Hb > 90%). The first replicate scan under target reduced oxygen saturation and the first replicate scan after resaturation of each sample were used in the analysis. For each sample, the bias was calculated for the following measurands: RBC, WBC, HGB, HCT and PLT, which was determined by the differences between the samples with the interference introduced (reduced oxygen saturation; O2Hb within 20-30%) versus the paired control samples without the interference (full oxygen saturation; O2Hb >90%). Overall, the result showed that there was no interference caused by reduction of oxyhemoglobin to 25% for the following Sight OLO measurands: RBC, WBC, HGB, HCT, and PLT.
4. Assay Reportable Range:
Refer to K190898
5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
Sample Stability and Transportation studies – Refer to K190898
Test Kit Shelf-Life Stability
An ongoing stability study of the Test Kit following the same protocol described in K190898 has now reached the 18-month time point. The purpose of the real-time stability study is to establish the shelf-life stability of the Sight OLO TK1 test kit when it is stored at its recommended storage conditions (18–26°C). Three lots of test kits were assessed for functional and analytical tests on no more than five Sight OLO instruments. Each test kit lot was stored at recommended temperature and tested at defined time points (4, 8, 12, 13, 18, 24, 26, 30, 36, 38 months), for a total of 11 time points per lot, including baseline (manufacturing lot release served as time zero baseline). Current results support a shelf-life
K211840 - Page 7 of 17
{7}
stability claim of 18 months from time of production when stored at the recommended temperature (18–26°C).
## Device Calibration Stability
An ongoing calibration stability study of the Sight OLO following the same protocol described in K190898 submission has reached a 15-month time point. The purpose of the study was to establish the calibration stability of the Sight OLO over time. A total of 1,177 samples collected for the method comparison study were analyzed on 3 Sight OLO and 3 Sysmex XN-Series instruments at 3 clinical sites. Sample results within the 5 to 95 percentile range per measurand (RBC, HGB, HCT, MCH, PLT, WBC, and MCV) were included in the analysis and the relative errors of the Sight OLO to the Sysmex XN-Series were computed per sample per measurand. Linear regression of the relative error versus the days since the first samples was analyzed along with the 95% confidence bands were plotted and the results compared to pre-defined acceptance criteria. Current results support a calibration stability claim of 15 months.
6. Detection Limit:
Refer to K190898
7. Assay Cut-Off:
Not applicable
8. Accuracy (Instrument):
Not applicable
9. Carry-Over:
Not applicable
## B Comparison Studies:
1. Method Comparison with Predicate Device:
A method comparison study using 700 pediatric and adult samples covering the analytical measurement range from three US sites was conducted. Both normal and pathological samples were included in the assessment. The pathological samples included the following conditions: acute inflammation, bacterial and viral infections, aplastic anemia, acute and chronic leukemias (lymphocytic or myelocytic), multiple myeloma (plasma cell leukemia), microcytic anemia, normocytic anemia, macrocytic anemia, hemoglobinopathies, thalassemia, iron and folate deficiencies and giant platelets. The collected samples covered an age range of 3 months to 94 years old, 32% of which were pediatric samples (3M-21Y). The study population included 365 males (52%) and 335 females (48%).
Passing-Bablok regression analysis was performed for each measurand with results from the Sight OLO device against the results from the Sysmex XN-Series Hematology Analyzer. For
K211840 - Page 8 of 17
{8}
each regression analysis, the slope, intercept and the 95% two-sided confidence interval (CI) around the slope and intercept were calculated, as well as the correlation coefficient. The overall bias was calculated as the median of differences, where differences were taken either as absolute or relative according to the nature of data. In addition, the predicted bias and its 95% CI at the medical decision points were calculated for WBC, HGB and PLT.
The analysis for the method comparison study was conducted on the data from each of the three sites and all sites combined, and only the results of the latter were compared to the acceptance criteria. The results showed that all measurands met the prespecified acceptance criteria for correlation, bias, slope, intercept (and the 95% two-sided confidence interval (CI) around the slope and intercept). Overall, the method comparison results demonstrate that, like the original cleared Sight OLO, the Sight OLO with updated algorithms generates comparable results to the predicate Sysmex XN-Series device.
| Results Summary: Sight OLO vs. Sysmex XN-Series – All Sites Combined | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Measurand | N | Results Range | Correlation Coefficient (r) | Slope (95% CI) | Intercept (95% CI) | Median Bias | Median Relative Bias (%) |
| WBC x10^{3}/μL | 662 | 0.31 to 98.77 | 0.997 | 1.016 (1.008, 1.024) | 0.014 (-0.025, 0.067) | 0.11 | 1.92% |
| RBC x10^{6}/μL | 674 | 1.86 to 7.29 | 0.991 | 1.019 (1.008, 1.029) | 0.09 (0.045, 0.13) | 0.16 | 4.07% |
| PLT x10^{3}/μL | 642 | 21.0 to 1026.0 | 0.984 | 1 (0.989, 1.016) | 9.00 (5.981, 11.236) | 9 | 4.52% |
| HGB g/dL | 694 | 4.9 to 21.2 | 0.99 | 1.03 (1.019, 1.041) | -0.02 (-0.144, 0.11) | 0.3 | 2.86% |
| HCT % | 675 | 15.2 to 63.7 | 0.983 | 1.029 (1.013, 1.044) | -0.569 (-1.147, 0.007) | 0.5 | 1.33% |
| MCV fL | 675 | 57.3 to 121.2 | 0.941 | 0.888 (0.862, 0.915) | 7.55 (5.192, 9.855) | -2.3 | -2.61% |
| RDW % | 643 | 10.6 to 29.4 | 0.941 | 1 (0.98, 1.034) | -0.1 (-0.593, 0.176) | -0.1 | -0.77% |
| MCH pg | 670 | 14.9 to 42.0 | 0.976 | 1 (0.987, 1.01) | -0.4 (-0.677, -0.002) | -0.4 | -1.34% |
| MCHC g/dL | 670 | 26.0 to 36.6 | 0.687 | 0.69 (0.636, 0.75) | 10.77 (8.775, 12.545) | 0.5 | 1.47% |
| NEUT% | 558 | 1.1 to 96.7 | 0.988 | 0.995 (0.983, 1.008) | 0.93 (0.15, 1.704) | 0.6 | 0.99% |
| NEUT# x10^{3}/μL | 547 | 0.02 to 52.65 | 0.996 | 1.023 (1.013, 1.033) | 0.025 (-0.002, 0.061) | 0.12 | 3.22% |
| LYMPH% | 581 | 0.9 to 98.9 | 0.991 | 1 (0.992, 1.013) | 0.9 (0.534, 1.063) | 0.9 | 3.92% |
| LYMPH# x10^{3}/μL | 569 | 0.02 to 50.06 | 0.995 | 1.031 (1.016, 1.047) | 0.049 (0.023, 0.074) | 0.1 | 6.28% |
| MONO% | 582 | 0.0 to 35.6 | 0.926 | 0.909 (0.872, 0.947) | -0.127 (-0.434, 0.199) | -0.9 | -10.81% |
K211840 - Page 9 of 17
{9}
K211840 - Page 10 of 17
| Results Summary: Sight OLO vs. Sysmex XN-Series – All Sites Combined | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Measurand | N | Results Range | Correlation Coefficient (r) | Slope (95% CI) | Intercept (95% CI) | Median Bias | Median Relative Bias (%) |
| MONO# x10³/μL | 570 | 0.0 to 7.89 | 0.947 | 1.0 (0.97, 1.024) | -0.05 (-0.065, -0.035) | -0.05 | -9.51% |
| EOS% | 535 | 0.0 to 33.3 | 0.978 | 1.0 (1.0, 1.043) | 0.2 (0.106, 0.2) | 0.2 | 11.76% |
| EOS# x10³/μL | 522 | 0.0 to 4.24 | 0.98 | 1.034 (1.0, 1.083) | 0.0 (0.008, 0.01) | 0.01 | 14.28% |
| BASO% | 538 | 0.0 to 3.1 | 0.658 | 1.333 (1.214, 1.5) | -0.2 (-0.25, -0.129) | 0 | -0.01% |
| BASO# x10³/μL | 525 | 0.0 to 0.47 | 0.646 | 1.333 (1.2, 1.5) | -0.013 (-0.015, -0.008) | 0 | -0.05% |
The predicted bias and its 95% CI at the medical decision points were within the pre-defined acceptance criteria for individual sites as well as all sites combined.
| Medical Decision Point | Site | Bias | 95% CI |
| --- | --- | --- | --- |
| WBC, 2x10³/μL | Site 1 | 0.03 | (-0.04, 0.12) |
| | Site 2 | -0.08 | (-0.15, 0.08) |
| | Site 3 | 0.03 | (-0.07, 0.13) |
| | All sites | 0.03 | (-0.15, 0.07) |
| HGB, 6 g/dL | Site 1 | 0.5 | (0.34, 0.66) |
| | Site 2 | 0.1 | (0.00, 0.20) |
| | Site 3 | 0.25 | (0.2, 0.46) |
| | All sites | 0.3 | (0.2, 0.55) |
| HGB, 10 g/dL | Site 1 | 0.2 | (0.00, 0.3) |
| | Site 2 | 0.1 | (0.00, 0.27) |
| | Site 3 | 0.00 | (-0.17, 0.37) |
| | All sites | 0.0 | (0.0, 0.2) |
| PLT, 50x10³/μL | Site 1 | 4.0 | (0.34, 15.32) |
| | Site 2 | 4.5 | (0.65, 7.7) |
| | Site 3 | 8.0 | (5.34, 13.66) |
| | All sites | 5.5 | (2.34,10.99) |
## Concordance Analysis at Medical Relevant Points
The results of the method comparison studies demonstrated there were constant bias and proportional bias for some measurands. Therefore, for each medical relevant point, a truth table with Bayesian analysis was performed to calculate the positive percent agreement (PPA), negative percent agreement (NPA) and overall percent agreement (OPA) between the Sight OLO and the Sysmex XN-Series Analyzer (all tables shown below). Based on the expert clinician review, none of the observed discordances would affect clinical decision making for the specific patients.
{10}
| PLT at 50 x 10³/μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 30 | 0 | 30 |
| | Negative (Normal) | 2 | 609 | 611 |
| | Total | 32 | 609 | 641 |
| | | PPA 93.75% | NPA 100.0% | OPA 99.7% |
| Thrombocytosis (PLT > 450 x 10³/μL) | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 42 | 8 | 50 |
| | Negative (Normal) | 1 | 590 | 591 |
| | Total | 43 | 598 | 641 |
| | | PPA 97.7% | NPA 98.7% | OPA 98.6% |
| Thrombocytopenia (PLT < 150 x 10³/μL) | Sysmex XN | | | |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 101 | 4 | 105 |
| | Negative (Normal) | 8 | 524 | 532 |
| | Total | 110 | 531 | 637 |
| | | PPA 92.7% | NPA 99.2% | OPA 98.1% |
| Neutrophilia, adults (22+ years): > 7,500 neutrophils /μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 62 | 7 | 69 |
| | Negative (Normal) | 1 | 309 | 310 |
| | Total | 63 | 316 | 379 |
| | | PPA 98.4% | NPA 97.8% | OPA 97.9% |
| Neutrophilia, children (<22 years): > 8,500 neutrophils /μL | Sysmex XN | | | |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 15 | 0 | 15 |
| | Negative (Normal) | 0 | 153 | 153 |
| | Total | 15 | 153 | 168 |
| | | PPA 100% | NPA 100% | OPA 100% |
| Lymphocytosis, adults and adolescents (12+ years): > 4,500 lymphocytes /μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 10 | 0 | 10 |
| | Negative (Normal) | 0 | 478 | 478 |
| | Total | 10 | 479 | 488 |
K211840 - Page 11 of 17
{11}
| | PPA
100% | NPA
100% | OPA
100% | |
| --- | --- | --- | --- | --- |
| | | | | |
| Lymphocytosis, young children (<12 years): > 10,000 lymphocytes /μL | Sysmex XN | | | |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 0 | 0 | 0 |
| | Negative (Normal) | 0 | 77 | 77 |
| | Total | 0 | 77 | 77 |
| | PPA
N/A | NPA
100% | OPA
100% | |
| | | | | |
| Monocytosis, adults and adolescents (12+ years): > 800 - 1300 monocytes /μL | Sysmex XN | | | | |
| --- | --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Ambiguous (within range) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 31 | 3 | 1 | 35 |
| | Ambiguous (within range) | 9 | 56 | 9 | 74 |
| | Negative (Normal) | 0 | 31 | 353 | 384 |
| | Total | 40 | 90 | 363 | 493 |
| | | PPA
100% | | NPA
99.7% | OPA
99.7% |
| Monocytosis, young children (<12 years): > 1000 - 1500 monocytes /μL | Sysmex XN | | | | |
| | | Positive (Abnormal) | Ambiguous (within range) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 7 | 0 | 0 | 7 |
| | Ambiguous (within range) | 1 | 3 | 2 | 6 |
| | Negative (Normal) | 0 | 2 | 62 | 64 |
| | Total | 8 | 5 | 64 | 77 |
| | | PPA
100% | | NPA
100% | OPA
100% |
| Eosinophilia, adults (22+ years): > 400 eosinophils /μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 18 | 6 | 24 |
| | Negative (Normal) | 2 | 323 | 325 |
| | Total | 20 | 329 | 349 |
| | | PPA
90.0% | NPA
98.2% | OPA
97.7% |
| Eosinophilia, pediatrics (<22 years): > 700 eosinophils /μL | Sysmex XN | | | |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 5 | 0 | 5 |
| | Negative (Normal) | 0 | 166 | 166 |
| | Total | 5 | 166 | 171 |
K211840 - Page 12 of 17
{12}
| PPA
100% | | NPA
100% | | OPA
100% | |
| --- | --- | --- | --- | --- | --- |
| Basophilia: >1%-2% basophils | Sysmex XN | | | | |
| --- | --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Ambiguous (within range) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 5 | 11 | 1 | 17 |
| | Ambiguous (within range) | 1 | 30 | 48 | 79 |
| | Negative (Normal) | 0 | 26 | 416 | 442 |
| | Total | 6 | 67 | 465 | 538 |
| | | PPA
100% | | NPA
99.8% | OPA
99.8% |
| Severe Leukopenia: < 2,000 WBC/μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 41 | 4 | 45 |
| | Negative (Normal) | 0 | 614 | 614 |
| | Total | 41 | 618 | 659 |
| | | PPA
100% | NPA
99.4% | OPA
99.4% |
| Neutropenia: < 1,000 neutrophils /μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 19 | 4 | 23 |
| | Negative (Normal) | 2 | 522 | 524 |
| | Total | 21 | 526 | 547 |
| | | PPA
90.5% | NPA
99.2% | OPA
98.9% |
| Severe Neutropenia: < 500 neutrophils /μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 3 | 0 | 3 |
| | Negative (Normal) | 3 | 541 | 543 |
| | Total | 6 | 541 | 547 |
| | | PPA
50% | NPA
100% | OPA
99.5% |
| Lymphocytopenia: < 1,000 lymphocytes /μL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 96 | 4 | 100 |
| | Negative (Normal) | 20 | 446 | 466 |
| | Total | 116 | 450 | 566 |
| | | PPA
82.8% | NPA
99.1% | OPA
95.8% |
K211840 - Page 13 of 17
{13}
| Monocytopenia: < 100 – 200 monocytes /μL | Sysmex XN | | | | |
| --- | --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Ambiguous (within range) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 6 | 4 | 0 | 10 |
| | Ambiguous (within range) | 2 | 8 | 13 | 23 |
| | Negative (Normal) | 0 | 2 | 535 | 537 |
| | Total | 8 | 14 | 548 | 570 |
| | | PPA 100% | | NPA 100% | OPA 100% |
| Moderate anemia, 5+ years: HGB < 11 g/dL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 219 | 1 | 220 |
| | Negative (Normal) | 9 | 407 | 416 |
| | Total | 228 | 408 | 636 |
| | | PPA 96.1% | NPA 99.8% | OPA 98.4% |
| Moderate anemia, <5 years: HGB < 10 g/dL | Sysmex XN | | | |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 19 | 1 | 20 |
| | Negative (Normal) | 0 | 30 | 30 |
| | Total | 19 | 31 | 50 |
| | | PPA 100% | NPA 96.8% | OPA 98.0% |
| Severe anemia, 22+ years: HGB < 8 g/dL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 45 | 0 | 45 |
| | Negative (Normal) | 10 | 411 | 421 |
| | Total | 55 | 411 | 466 |
| | | PPA 81.8% | NPA 100% | OPA 97.9% |
| Severe anemia, pediatrics: HGB < 6 g/dL | Sysmex XN | | | |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 1 | 0 | 1 |
| | Negative (Normal) | 0 | 219 | 219 |
| | Total | 1 | 219 | 220 |
| | | PPA 100% | NPA 100% | OPA 100% |
| Polycythemia, females: HGB > 16.5 g/dL | Sysmex XN | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 4 | 3 | 7 |
| | Negative (Normal) | 0 | 327 | 327 |
| | Total | 4 | 330 | 334 |
K211840 - Page 14 of 17
{14}
K211840 - Page 15 of 17
| | | PPA
100% | NPA
99.1% | OPA
99.1% |
| --- | --- | --- | --- | --- |
| Polycythemia, males: HGB
> 18.5 g/dL | | Sysmex XN | | |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 3 | 4 | 7 |
| | Negative (Normal) | 0 | 352 | 352 |
| | Total | 3 | 356 | 359 |
| | | PPA
100% | NPA
98.9% | OPA
98.9% |
2. Matrix Comparison:
A capillary vs. venous matrix comparison study consisting of 67 normal and pathological paired capillary K2EDTA whole blood and venous K2EDTA whole blood specimens were used. Paired specimens collected from the same individuals were assayed in duplicate on the OLO device to compare performance between capillary whole blood samples and venous whole blood samples, and the results were analyzed for all applicable measurands. Analysis included Passing-Bablok regression analysis per measurand (Bland Altman plots, slope, intercept, with 95% confidence intervals, correlation coefficient, and % bias), between the average of two venous whole blood sample repeats and the average of two capillary whole blood sample repeats from the same individual on the Sight OLO. Overall, the study results from the Sight OLO device show comparable performance characteristics for K2EDTA capillary and K2EDTA venous whole blood samples.
C Clinical Studies:
1. Clinical Sensitivity:
A flagging study was conducted, comparing the Sight OLO to manual light microscopy for normal (no flags) and abnormal (flags present) for 108 normal samples and 100 abnormal samples at three clinical study sites. Three blood films were prepared for each sample. Two qualified morphology examiners evaluated one of the three blood films. In each blood film a 200-cell count was performed for a total of 400 cells for the two examiners together. Two types of abnormalities were evaluated: (1) distributional abnormal samples, which are samples where the quantity of at least one of the WBC diffs% parameters reside outside of the normal concentrations, and (2) morphological abnormal samples, which are samples that contain atypical forms of the normal cell types in ordinary blood samples. Three Sight OLO instruments were used for the study (one at each site) and one lot of Sight OLO test kits was used. Overall, the flagging capability of the Sight OLO device met the pre-defined acceptance criteria for both overall sensitivity and specificity.
| Distributional Flagging | Reference Method – Manual Microscopy | | | |
| --- | --- | --- | --- | --- |
| | | Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 83 | 6 | 89 |
| | Negative (Normal) | 11 | 108 | 119 |
| | Total | 94 | 114 | 208 |
{15}
| | | % | 95% CI | |
| --- | --- | --- | --- | --- |
| Sensitivity (PPA) | | 88.3% | 80.0% | 94.0% |
| Specificity (NPA) | | 94.7% | 88.9% | 98.0% |
| Overall Agreement | | 91.8% | 87.2% | 95.2% |
| Distributional Flagging (with flagged WBC-diff removed) | Reference Method – Manual Microscopy |
| --- | --- |
| Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 55 | 3 | 58 |
| Negative (Normal) | 9 | 100 | 109 |
| Total | 64 | 103 | 157 |
| |
| | % | 95% CI |
| Sensitivity (PPA) | 85.9% | 75.0% | 93.4% |
| Specificity (NPA) | 97.1% | 91.7% | 99.4% |
| Overall Agreement | 92.8% | 87.8% | 96.2% |
| Morphological Flagging | Reference Method – Manual Microscopy |
| --- | --- |
| Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 21 | 20 | 41 |
| Negative (Normal) | 1 | 166 | 167 |
| Total | 22 | 186 | 208 |
| |
| | % | 95% CI |
| Sensitivity (PPA) | 95.5% | 77.2% | 99.9% |
| Specificity (NPA) | 89.3% | 83.4% | 93.3% |
| Overall Agreement | 89.9% | 85.0% | 93.6% |
| Overall Flagging Performance | Reference Method – Manual Microscopy |
| --- | --- |
| Positive (Abnormal) | Negative (Normal) | Total |
| Sight OLO | Positive (Abnormal) | 6 | 0 | 10 |
| Negative (Normal) | 0 | 535 | 537 |
| Total | 8 | 548 | 570 |
| |
| | % | 95% CI |
| Sensitivity (PPA) | 91.0% | 83.6% | 95.8% |
| Specificity (NPA) | 92.6% | 85.9% | 96.8% |
| Overall Agreement | 91.8% | 87.2% | 95.2% |
2. Clinical Specificity:
See Clinical Sensitivity above.
3. Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):
Not applicable
K211840 - Page 16 of 17
{16}
D Clinical Cut-Off:
Not applicable
E Expected Values/Reference Range:
Refer to K190898
F Other Supportive Instrument Performance Characteristics Data:
Refer to K190898
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.
K211840 - Page 17 of 17
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.