(502 days)
Not Found
Yes
The device description explicitly states that the SSD contains "AI100 with Shonit™ software" and the intended use mentions "AI100 with Shonit™ is a cell locating device". While the "Mentions AI, DNN, or ML" section is marked "Not Found", the product name and software description strongly suggest the use of AI/ML for cell location and analysis.
No
This device is for in-vitro diagnostic use, specifically for locating and characterizing blood cells for review, not for treating any medical condition.
Yes
The "Intended Use / Indications for Use" section explicitly states that "AI100 with Shonit™ is a cell locating device intended for in-vitro diagnostic use in clinical laboratories." It also describes its use for differential count of White Blood Cells, characterization of Red Blood Cells morphology, and Platelet morphology, all of which are diagnostic tasks performed in clinical laboratories.
No
The device description explicitly states that the device consists of hardware components such as a microscope, camera, motorized stage, and compute parts, in addition to the software.
Yes, this device is an IVD (In Vitro Diagnostic).
Here's why:
- Explicit Statement: The "Intended Use / Indications for Use" section explicitly states: "AI100 with Shonit™ is a cell locating device intended for in-vitro diagnostic use in clinical laboratories."
- Intended Use: The device is intended for "differential count of White Blood Cells (WBC), characterization of Red Blood Cells (RBC) morphology and Platelet morphology." These are diagnostic tests performed on biological samples (peripheral blood smears) outside of the body.
- Clinical Laboratory Setting: The intended use specifies "in clinical laboratories," which is a typical setting for IVD devices.
- Analysis of Biological Samples: The device analyzes "peripheral blood smears," which are biological samples.
- Diagnostic Information: The output of the device (cell location and presentation of images for review and identification) provides information used in the diagnosis of various conditions related to blood cell abnormalities.
The combination of these factors clearly indicates that the AI100 with Shonit™ device is an In Vitro Diagnostic device.
No
The provided text does not contain any explicit statement that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
AI100 with Shonit™ is a cell locating device intended for in-vitro diagnostic use in clinical laboratories.
AI100 with Shonit™ is intended for differential count of White Blood Cells (WBC), characterization of Red Blood Cells (RBC) morphology and Platelet morphology. It automatically locates blood cells on peripheral blood smears and presents images of the blood cells for review.
A skilled operator, trained in the use of the device and in the review of blood cells, identifies each cell according to type.
Product codes
JOY
Device Description
The AI100 with Shonit™ is for prescription use only.
Physical Properties of the AI100 with Shonit™ 5.5.1
Weight: 40kg Width: 553mm Depth: 485mm Height: 485mm
Components of the AI100 with Shonit™ 5.5.2
The AI100 with Shonit™ device consists of a high-resolution microscope with LED illumination, and compute parts such as the motherboard, CPU, RAM, Wi-Fi dongle, SSD containing AI100 with Shonit™ software, motorized XYZ stage, a camera with firmware, PCB and its firmware for driving motor and LED, SMPS, power supply and a casing. It is capable of handling one Peripheral Blood Smear (PBS) slide at a time.
Software plays an intrinsic role in the A1100 with Shonit™ device, and the combination of hardware and software works together for the device to achieve its intended use. The main functions of the software can be summarized as follows:
- Allow the user to set up the device and perform imaging of a PBS slide.
- Control the hardware components (Camera, LEDs, Stages, etc) to take images of a . PBS slide.
- Store and manage images and other data corresponding to the PBS slide and present them to the user.
- Analyze images and allows user to identify components in the images and create a ● report for review.
- Allow the user to finalize, download and print a report.
Mentions image processing
On each FOV image, image processing is applied to extract and classify WBCs, RBCs, and Platelets.
Mentions AI, DNN, or ML
Yes, neural network of convolutional type is mentioned in device comparison table.
Input Imaging Modality
Microscopy/Optical Imaging (capturing FOV images)
Anatomical Site
Peripheral blood smears
Indicated Patient Age Range
The study included samples across all age groups newborn, infant, child, adolescent and adults.
Intended User / Care Setting
Clinical laboratories. A skilled operator, trained in the use of the device and in the review of blood cells, identifies and classifies each cell according to type.
Description of the training set, sample size, data source, and annotation protocol
Not Found.
Description of the test set, sample size, data source, and annotation protocol
Not Found.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Analytical Performance: Precision, Repeatability
- WBC Repeatability: 12 samples, 20 x 2 x 2 single-site repeatability study. All tests met acceptance criteria.
- RBC Repeatability: 12 samples, 20 x 2 x 2 single-site repeatability study. All tests met acceptance criteria.
- PLT Repeatability: 12 samples, 20 x 2 x 2 single-site repeatability. All tests met acceptance criteria.
Analytical Performance: Reproducibility
- WBC Reproducibility: 13 samples, 3x5x5 reproducibility study using three instruments for five days with five replicates. All tests met acceptance criteria.
- RBC Reproducibility: 13 samples, 3x5x5 reproducibility study. All tests met acceptance criteria.
- PLT Reproducibility: 13 samples, 3x5x5 reproducibility study. All tests met acceptance criteria.
Method Comparison Study
- Study Type: Method comparison study comparing AI100 with Shonit™ to manual microscopy. Performed according to CLSI H20-A2.
- Sample Size: 882 samples (298 normal, 584 abnormal), collected across four sites. Samples included all age groups (newborn, infant, child, adolescent, adults).
- Key Results (WBCs - Passing-Bablok regression):
- Neutrophils (%): Slope 1.024 (95% CI: 1.016, 1.032), Intercept -1.78 (95% CI: -2.249, -1.346), Pearson's correlation 0.962.
- Lymphocytes (%): Slope 1.025 (95% CI: 1.016, 1.034), Intercept -0.587 (95% CI: -0.881, -0.306), Pearson's correlation 0.960.
- Eosinophils (%): Slope 1.029 (95% CI: 1.012, 1.05), Intercept -0.039 (95% CI: -0.07, -0.01), Pearson's correlation 0.907.
- Monocytes (%): Slope 1.083 (95% CI: 1.051, 1.117), Intercept -0.462 (95% CI: -0.66, -0.304), Pearson's correlation 0.789.
- All 95% CI for slope and intercept met acceptance criteria.
Key results (WBC Abnormalities - Sensitivity, Specificity, Overall Agreement):
* Morphological Abnormality: Overall Agreement 91.7% (90.4%, 92.8%), Sensitivity 95.3% (92.8%, 96.7%), Specificity 90.9% (89.4%, 92.2%).
* Distributional Abnormality: Overall Agreement 96.4% (95.5%, 97.2%), Sensitivity 91.0% (86.8%, 93.9%), Specificity 97.2% (96.3%, 97.9%).
* Overall: Overall Agreement 95.0% (94.0%, 95.9%), Sensitivity 92.7% (89.2%, 95.0%), Specificity 95.4% (94.3%, 96.3%).
* All 95% CI values met acceptance criteria.
Key results (RBC Morphologies - Sensitivity, Specificity, Overall Agreement):
* Anisocytosis: Sensitivity 91.1% (88.1%, 93.4%), Specificity 95.9% (94.7%, 96.9%), Overall Agreement 94.7% (93.6%, 95.7%).
* Macrocytosis: Sensitivity 90.7% (87.0%, 93.5%), Specificity 96.6% (95.5%, 97.4%), Overall Agreement 95.5% (94.5%, 96.4%).
* Poikilocytosis: Sensitivity 96.3% (94.8%, 97.3%), Specificity 88.1% (85.8%, 90.0%), Overall Agreement 92.1% (90.7%, 93.2%).
* All 95% CI values met acceptance criteria.
Key results (Platelet Morphologies - Sensitivity, Specificity, Overall Agreement):
* Platelets: Sensitivity 100% (99.8%, 100%), Specificity 100% (34.2%, 100%), Overall Agreement 100% (99.8%, 100%).
* Giant Platelets: Sensitivity 99.1% (98.4%, 99.5%), Specificity 92.4% (90.3%, 94.1%), Overall Agreement 96.4% (95.4%, 97.1%).
* Platelet clumps: Sensitivity 91.6% (89.5%, 93.4%), Specificity 96.3% (94.9%, 97.3%), Overall Agreement 94.2% (93.0%, 95.2%).
* Overall Platelets: Sensitivity 97.9% (97.1%, 98.4%), Specificity 94.6% (92.8%, 95.9%), Overall Agreement 96.8% (96.0%, 97.4%).
* All 95% CI values met acceptance criteria.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Sensitivity, Specificity, and Overall Agreement were used as key metrics in the Method Comparison Study. Pearson's correlation coefficient was also reported for WBC regression analysis.
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 864.5260 Automated cell-locating device.
(a)
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.)(b)
Classification. Class II (performance standards).
0
Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.
September 19, 2023
SigTuple Technologies Pvt. Ltd. % Jinjie Hu President and Principal Consultant Axteria BioMed Consulting Inc. 8040 Cobble Creek Circle Potomac, Maryland 20854
Re: K221309
Trade/Device Name: AI100 with Shonit Regulation Number: 21 CFR 864.5260 Regulation Name: Automated Cell-Locating Device Regulatory Class: Class II Product Code: JOY Dated: February 22, 2023 Received: February 22, 2023
Dear Jinjie Hu:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal
1
statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801 and Part 809); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
Min Wu-S
Min Wu, Ph.D. Branch Chief Division of Immunology and Hematology Devices OHT7: Office of In Vitro Diagnostics Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
2
Indications for Use
510(k) Number (if known)
Device Name AI100 with Shonit
Indications for Use (Describe)
AI100 with Shonit™ is a cell locating device intended for in-vitro diagnostic use in clinical laboratories.
A1100 with Shonit™ is intended for differential count of White Blood Cells (WBC), characterization of Red Blood Cells (RBC) morphology and Platelet morphology. It automatically locates blood cells on peripheral blood smears and presents images of the blood cells for review.
A skilled operator, trained in the use of the device and in the review of blood cells, identifies each cell according to type.
| Type of Use (Select one or both, as applicable) | |
|---|---|
| ------------------------------------------------- | -- |
X Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
3
5 510(k) Summary
5.1 General Information
| Submitter: | SigTuple Technologies Pvt. Ltd.
First Floor, L-162, 14th Cross Road, Sector 6, HSR Layout,
Bangalore, Karnataka -56102
India |
|-----------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Contact Person: | Jinjie Hu, PhD
Axteria BioMed Consulting Inc.
8040 Cobble Creek Circle
Potomac, MD 20854, USA
Tel: +1 (301) 814 4985
Email: jinjie.hu@axteriabiomed.com |
| Contact Person: | Tathagato Rai Dastidar
SigTuple Technologies Pvt. Ltd.
First Floor, L-162, 14th Cross Road, Sector 6, HSR Layout,
Bangalore, Karnataka -56102, India
trd@sigtuple.com
+91-9341232063 |
| Date Prepared: | May 1, 2022 |
Purpose of Submission: To obtain a substantial equivalence for the AI100 with Shonit™
5.2 Measurand
White Blood Cells (WBC), Red Blood Cells (RBC) and Platelets (PLT).
5.3 Device Information
| Proprietary Name of the Device: | AI100 with Shonit™ |
|---|---|
| Common Name: | Automated cell locating device |
| Classification Name: | Automated cell-locating device |
| Regulation Number: | 21 CFR 864.5260 |
| Classification Name and Reference: | Class II |
| Device product Code: | JOY |
| Panel: | Hematology |
5.4 Intended use/Indication for use
AI100 with Shonit™ is a cell locating device intended for in-vitro diagnostic use in clinical laboratories.
AI100 with Shonit™ is intended for differential count of White Blood Cells (WBC), characterization of Red Blood Cells (RBC) morphology and Platelet morphology. It automatically locates blood cells on peripheral blood smears and presents images of the blood cells for review.
A skilled operator, trained in the use of the device and in the review of blood cells, identifies and classifies each cell according to its characterizations.
4
5.5 Device Description
The AI100 with Shonit™ is for prescription use only.
Physical Properties of the AI100 with Shonit™ 5.5.1
Weight: 40kg Width: 553mm Depth: 485mm Height: 485mm
Components of the AI100 with Shonit™ 5.5.2
The AI100 with Shonit™ device consists of a high-resolution microscope with LED illumination, and compute parts such as the motherboard, CPU, RAM, Wi-Fi dongle, SSD containing AI100 with Shonit™ software, motorized XYZ stage, a camera with firmware, PCB and its firmware for driving motor and LED, SMPS, power supply and a casing. It is capable of handling one Peripheral Blood Smear (PBS) slide at a time.
Software plays an intrinsic role in the A1100 with Shonit™ device, and the combination of hardware and software works together for the device to achieve its intended use. The main functions of the software can be summarized as follows:
- Allow the user to set up the device and perform imaging of a PBS slide. ●
- Control the hardware components (Camera, LEDs, Stages, etc) to take images of a . PBS slide.
- Store and manage images and other data corresponding to the PBS slide and present them to the user.
- Analyze images and allows user to identify components in the images and create a ● report for review.
- Allow the user to finalize, download and print a report.
5.5.3 Consumables required to produce blood smears to be used on AI100 with Shonit™
The following consumables are needed to produce blood smears:
- Romanowsky stain such as Leishman, Wright Giemsa (WG) or Wright (W) stains ●
- Slides
- EDTA sample tube (K2EDTA)
- . Automatic slide maker-stainer, or smear/stain slides manually
5.5.4 Specimen Identification
Peripheral blood samples typically flagged by a cell-counter indicating an abnormal morphology.
5.5.5 Anticoagulant
K2EDTA is the anticoagulant to be used. All samples used in the analytical and clinical studies were collected using K2EDTA as the anticoagulant.
5.5.6 Calibration
Device calibration is required to ensure that the system performs optimally. The device calibration is to be performed under the following circumstances -
-
- Once every six months.
-
- After the device is serviced by a SigTuple technician.
-
- If and when a new OQ slide is issued by SigTuple.
5
5.5.7 Mini-Calibration
Mini-calibration is required to ensure that the system performs optimally. The minicalibration is to be performed under the following circumstances -
-
- When the device is serviced (and recommended by the SigTuple support team).
5.5.8 Quality Control
The AI100 with Shonit™ device performs a series of self-tests during startup after powering up or a reset of the system. On startup, all software components and hardware components are checked and confirmed to be behaving normally before the system is allowed to start a PBS scan. Communication with the hardware is tested continuously during system operation and appropriate messages are displayed to the user if any errors occur during its operation.
5.5.8.1 Performance Qualification
The AI100 with Shonit™ device contains a set of tests to check and verify whether all its components are behaving as expected and performing within their normal operating ranges. It uses an Operational Qualification (OQ) slide that is provided to the user along with the device. The tests are mostly automated and only require the user to trigger the tests; the exceptions are the test that checks the LCD touchscreen as well as the loading and unloading of the OQ slide. This set of tests is recommended to be run daily by the user before using the system.
5.5.8.2 Operational Qualification
In addition to the Performance Qualification tests, another set of tests is also provided and these test more functionalities and components of the device in a more detailed manner. This set of tests is of longer duration and does not need to be performed daily; they are recommended to be run once every 3 months. These tests require the same OO slide and need no user intervention other than inserting the OQ slide and touching the LCD touchscreen when prompted.
5.5.9 Principle of Operation
The principle of operation of the AI100 with Shonit™ device broadly mirrors the reference method of manual microscopy.
The first step is to find whether the PBS slide is well prepared and is suitable for microscopy reading and report preparation. Once the user enters information about the slide on the UI and triggers the scan, the device moves the slide to the imaging area and performs pre-scan steps, which involve identifying the optimal area of the smear for scanning.
If the optimal area is not found, the slide is rejected and the user is notified with appropriate error messages. If an optimal area is identified, scanning (capturing FOV images) proceeds from the center of the optimal area in an outward spiral fashion. Focusing is done at each image location to capture the most optimal image. The image at each FOV is checked to ensure appropriate quality for image processing. The scan stops when the required number of FOVs are captured or the required number of WBCs are encountered, depending on the scan mode selected by the user.
On each FOV image, image processing is applied to extract and classify WBCs, RBCs, and Platelets. This is a multi-step process for each cell type and the type of processing varies between each of them. WBCs are classified into Neutrophils, Lymphocytes, Monocytes, Eosinophils, Basophils, Immature Granulocytes (IGs), Atypical Cells / Blasts and NRBCs. RBCs are classified according to size (Normocyte, Round Macrocyte, Ovalo Macrocyte) and
6
shape (Normal, Target, Teardrop, Echinocyte, Elliptocyte, Fragmented). Platelets are classified into Normal, Large, Giant Platelets and Platelet Clumps.
The device then allows the user to review the identified and classified cells, including cells that could not be classified and generate a microscopy report. The user may re-classify cells and add impressions as they deem fit and approve the report. The report is then available for printing and/or distribution according to the workflow of the laboratory/hospital.
Substantial Equivalence Information 5.6
5.6.1 Technological Characteristics Comparison with Predicate Device
Like the predicate device, AI100 with Shonit™ locates white blood cells, stores digital images of the cells and displays the images in an organized manner and suggests a cell class for each cell to aid operators in performing the differential count procedure. A competent operator is required to verify or modify the suggested classification of each cell. It is intended to be used by skilled operators, trained in the use of the device and in recognition of blood cells. Like the predicate device, AI100 with Shonit™ presents images from which it is possible to characterize red blood cells according to size and shape and identify platelet morphology.
5.7 Principle of Operation/Comparison with Predicate Device
The method requires a skilled operator to review the images of the cells as does the predicate device. See below for the substantial equivalence comparisons.
| Characteristic | CellaVision® DC-1 (K200595) | AI100 with Shonit™ (K221309) |
|---|---|---|
| Intended Use | CellaVision® DC-1 is an automated | |
| cell-locating device intended for in- | ||
| vitro diagnostic use in clinical | ||
| laboratories. |
CellaVision® DC-1 is intended to
be used by operators trained in the
use of the device. Peripheral Blood
Application:
The CellaVision Peripheral Blood
Application is intended for
differential count of white blood
cells (WBC), characterization of red
blood cell (RBC) morphology and
platelet estimation.
The CellaVision® DC-1 with the
Peripheral Blood Application
automatically locates blood cells on
peripheral blood (PB) smears.
The application presents images of
the blood cells for review. A skilled
operator trained in recognition of
blood cells, identifies and verifies | AI100 with Shonit™ is a cell
locating device intended for in-
vitro diagnostic use in clinical
laboratories.
AI100 with Shonit™ is intended
for differential count of White
Blood Cells (WBC),
characterization of Red Blood
Cells (RBC) morphology and
Platelet morphology. It
automatically locates blood cells
on peripheral blood smears and
presents images of the blood
cells for review.
A skilled operator, trained in the
use of the device and in the
review of blood cells, identifies
and classifies each cell according
to type. |
| | the suggested classification of each
cell according to type. | |
| Intended Use
Population | The intended use population is
patients whose blood samples have
been flagged as abnormal by an
automated cell counter. | Same |
| Analytes | Automated cell-locating device for
cell-location and identification of
RBC, WBC or platelets for in-vitro
use. Verification of results by
human operator. | Same |
| Major Parts of the
System (that are
similar) | • Computer module (integrated)
• Digital color camera
• Control unit (integrated in camera)
• Casing
• Data base | Same |
| Light Source | LED (Light Emitting Diode) | Same |
| Sample Source | Stained blood film on glass slides of
peripheral whole blood. | Same |
| Sample Preparation | Romanowsky stain | Same |
| Analysis Technique
WBCs | White blood cells are pre-classified
and presented to the operator. To
complete the differential, the
operator needs to verify that all
located WBCs are correctly
classified. All cells must be
classified and verified before the
order can be signed. | Same |
| Analysis Technique
RBCs | The device pre-characterizes the
RBC morphology based on the
overview image of the RBC
monolayer, followed by the
operator's verification or
modification of the suggested
results. | Same |
| Image Interpretation
Requirements | A skilled operator is required to
differentiate and finally modify
and/or confirm the pre-
classification/characterization of the
located blood cells. | Same |
| Result Format for
WBC, RBC | The differential proportional count
is normally based on 100 white
blood cells. The number of WBCs
can be modified if required. The
result can be presented as the | Same |
| | number of located cells or as % of
total number of WBCs.
The result of RBC characterization
is presented as a grading for each
morphology. | |
| User Interface | The User Interface is primarily
designed to allow the user to view
the images of the WBCs, RBCs and
Platelets and review the
classification. The user will be able
to make corrections to the results
and generate a report. | Same |
| Operators'
Competence | The operator is trained in the
recognition of blood cells and in the
use of the device. | Same |
| Decision Support | The device includes white blood cell
reference cells. | Same |
| Loading Capacity | 1 slide | Same |
| Immersion Oil
Application | Manual application | Same |
| Neural Network | Neural network of convolutional
type | Same |
Table 1: Comparison with Predicate Device: Similarities
7
8
Table 2: Comparison with Predicate Device: Differences
| Characteristic | CellaVision® DC-1 (K200595) | AI100 with Shonit™ (K221309) |
|---|---|---|
| Major Parts of | ||
| the System (that | ||
| are different) | • Motorized microscope | |
| • XY stage | • Non-motorized microscope | |
| • XYZ stage | ||
| • Cloud reporting platform | ||
| Analysis | ||
| Technique | ||
| WBC | White Blood Cells: | |
| Cells are located/counted by moving | ||
| according to the battlement track | ||
| pattern. | White Blood Cells: | |
| Cells are located and counted by | ||
| moving according to the outwardly | ||
| increasing spiral path. | ||
| Analysis | ||
| Technique | ||
| Platelet | Platelets: | |
| The operator manually counts and | ||
| estimates the platelet concentration | ||
| from the overview image according | ||
| to a standardized procedure. | ||
| From an overview image | ||
| corresponding to eight high power | ||
| fields, the platelet level is estimated. | ||
| The concentration of platelets is | ||
| estimated by the user. | Platelets: | |
| Platelets are pre-classified based on | ||
| morphology and images are displayed | ||
| to the user. | ||
| The operator verifies the suggested | ||
| classification and confirms the | ||
| qualitative output of 'Detected' vs 'Not | ||
| Detected' for each platelet type. | ||
| The system uses a qualitative output to | ||
| show results for platelets. |
9
| | | The user is presented with platelet
images, classified based on
morphology. The user can review the
classification and confirm the
qualitative output of 'Detected' vs 'Not
Detected' against each platelet
morphology category. |
|------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Image
Magnification | The device has two objective lenses,
one at 10X and one at 100X
magnification. | The device has one objective lens at
40X magnification. |
| Information
Transfer from
Instrument to
Printer or
Network | The system can interact with a
laboratory information system
(LIS).
The system will retrieve order data
from the LIS and send results back
to the LIS. | The current system does not interact
with a laboratory information system
(LIS). |
| Decision
Support | The operator can add his/her own
reference cells. | The operator cannot add his/her own
reference cells. |
| Calibration | Recommended calibration once a
year by a service engineer. | Recommended calibration once in 6
months by a service engineer or the
user. |
| Anticoagulant | Clinical study was done using K3
EDTA and scientific justification
(unrelated to the device) was given
to prove equivalence between K2
EDTA and K3 EDTA. | Clinical study was done using K2
EDTA. |
Brief Discussion of Clinical Tests Supporting a Determination of Substantial 5.8 Equivalence
Studies with blood samples collected in K2EDTA tubes have been performed to confirm equivalence with the standard method (microscopy review result of the blood smear) for differentiation of WBCs, characterization of RBCs and identify Platelet morphology with the subject device AI100 with Shonit™.
Electrical Safety and Electromagnetic Compatibility (EMC) 5.9
Electrical Safety and EMC testing was conducted on the AI100 with Shonit™. The tests show that the AI100 with Shonit™ is in conformity with the following standards:
- IEC 61010-1: 2010 (Amendment 1:2016)
- IEC 61010-2-101: 2015 ●
- IEC 60601-1-2:2014+A1:2020 ●
- IEC 61326-1: 2012 (EN 61326-1:2013)
- IEC 61326-2-6: 2012 (EN 61326-2-6:2013) ●
We have performed an analysis and Gap Assessment with the newer version of each standard and concluded that AI100 with Shonit™ is in compliance with the following updated versions of the standards:
- . IEC 61010-1: 2017
10
- IEC 61010-2-101: 2018 ●
- IEC 61326-1: 2020-10
- IEC 61326-2-6: 2020-10 ●
Software Verification and Validation Testing 5.10
Software verification and validation testing were conducted and documentation was provided as recommended by FDA's Guidance for Industry and Staff, "Guidance for the Content of premarket Submissions for Software Contained in Medical Devices." The software application was considered as a "moderate" level of concern, since a malfunction, failure, or latent design flaw in the software could lead to an erroneous diagnosis or a delay in delivery of appropriate medical care that could lead to a minor injury.
Analytical Performance: Precision, Repeatability 5.11
The repeatability study was conducted in a clinical setting using a single instrument at a single site. The study outline for the repeatability study known as 20 x 2 single-site repeatability study was based on CLSI EP05-A3 (Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline - Third Edition).
5.11.1 WBC Repeatability
12 samples were used for the study. All slides were processed on AI100 with Shonit™ according to the study outline of 20 x 2 x 2 single-site repeatability study. The evaluation was performed on the pre-classified results suggested by the device. The proportional cell count in percent for each cell class was used to estimate variance components for repeatability (repeatability standard deviation, between-run standard deviation, between-day standard deviation and within-laboratory standard deviation). All tests met acceptance criteria.
5.11.2 RBC Repeatability
12 samples were used for the study. All slides were processed on the AI100 with Shonit™ according to the study outline of 20 x 2 x 2 single-site repeatability study. The evaluation was performed on the pre-characterized results suggested by the device. Repeatability in terms of RBC shape and size for each morphological characteristic was evaluated. Overall agreement for the grades for RBC size (Normocytes, Oval macrocytes, Round macrocytes) and RBC Poikilocytes (Normal Cells, Echinocytes, Target cells, Elliptocytes, Teardrop cells, Fragmented cells, Ovalocytes) for each run were used for analysis. All tests met acceptance criteria.
5.11.3 PLT Repeatability
12 samples were used for the study. All slides were processed on the AI100 with Shonit™ according to the study outline of 20 x 2 x 2 single-site repeatability. The evaluation was performed on the pre-characterized results suggested by the device. Overall agreement for the qualitative grade – 'Detected/Not Detected' for each run was used for analysis. All tests met acceptance criteria.
Analytical Performance: Reproducibility 5.12
The reproducibility study was performed according to the CLSI's 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, RBC and platelet classification was performed across three different devices. The study was conducted using 13 test samples, for 5 testing days, using 5 replicates scanned on the three devices.
11
In total, 975 scans were analyzed. For each tested sample, Standard Deviations were estimated for the variance components: between day, within-device, between device, and reproducibility.
5.12.1 WBC Reproducibility
13 samples were included in the study. One slide was prepared from each sample and processed on three instruments for five days (a 3 x 5 x 5 study). The evaluation was performed on the pre-classified results suggested by the device. The proportional cell count in percent for each cell class was used to estimate variance components for reproducibility (reproducibility standard deviation, repeatability standard deviation, between-day standard deviation, within-laboratory standard deviation and between-site standard deviation). All tests met acceptance criteria.
5.12.2 RBC Reproducibility
13 samples were included in the study. One slide was prepared from each sample and processed on three instruments for five days (a 3 x 5 x 5 study). The evaluation was performed on the pre-characterized results suggested by the device. Reproducibility in terms of RBC shape and size for each morphological characteristic was evaluated. Overall agreement for the grades for RBC size (Normocytes, Oval macrocytes, Round macrocytes) and RBC Poikilocytes (Normal Cells, Echinocytes, Target cells, Elliptocytes, Teardrop cells, Fragmented cells, Ovalocytes) for each run were used for analysis. All tests met acceptance criteria.
5.12.3 PLT Reproducibility
13 samples were included in the study. One slide was prepared from each sample and processed on three instruments for five days (a 3 x 5 x 5 study). The evaluation was performed on the pre-characterized results suggested by the device. Overall agreement for qualitative grade - 'Detected' output for each run was used for analysis. All tests met acceptance criteria.
5.12.4 Linearity
Not applicable
5.12.5 Carryover Not applicable
5.12.6 Interfering Substance
Not applicable
5.13 Method Comparison Study
A method comparison study was conducted to compare the results achieved by trained qualified reviewers using the AI100 with Shonit™ system to the results achieved by performing manual microscopy. 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 guidelines.
A total of 882 samples were collected and analyzed across four sites. Out of these 882 samples, 298 samples were normal and 584 samples were abnormal. The sample distribution followed the CLSI H20-A2 standard. The study included samples across all age groups newborn, infant, child, adolescent and adults. Blood samples were collected in K2 EDTA vacutainers for the study and peripheral blood smears were prepared and stained using
12
Romanowsky stain. The stained slides were read by two medical reviewers at each site both on the AI100 with Shonit™ device and manual microscope (reference method).
White Blood Cells (WBCs)
The below table summarizes the results of Passing-Bablok regression comparison method for the multi-site study.
| WBC Cell type | Slope
95% CI | Intercept
95% CI | Pearson's correlation
coefficient (r) |
|-----------------|-------------------------|----------------------------|------------------------------------------|
| Neutrophils (%) | 1.024
(1.016, 1.032) | -1.78
(-2.249, -1.346) | 0.962 |
| Lymphocytes (%) | 1.025
(1.016, 1.034) | -0.587
(-0.881, -0.306) | 0.960 |
| Eosinophils (%) | 1.029
(1.012, 1.05) | -0.039
(-0.07, -0.01) | 0.907 |
| Monocytes (%) | 1.083
(1.051, 1.117) | -0.462
(-0.66, -0.304) | 0.789 |
Table 3: Regression Analysis for WBC - AI100 with Shonit™ vs Manual Microscopy
All the 95% CI values for slope and intercept met the acceptance criteria for the accuracy measured by Passing-Bablok regression for WBC differential counts.
Sensitivity, specificity, and overall agreement for distributional WBC abnormalities (Neutrophils, Lymphocytes, Monocytes, and Eosinophils), morphological WBC abnormalities (Immature Granulocytes, Atypical Cells/Blasts, and NRBCs) and overall WBC abnormalities were evaluated between the candidate device and manual microscopy. The results are summarized in the table below.
| Table 4: Distributional and Morphological Abnormalities for WBCs - AI100 with | |
|---|---|
| Shonit™ vs Manual Microscopy |
| WBC
Abnormality | Morphological
Abnormality
95% CI | Distributional
Abnormality
95% CI | Overall
95% CI |
|----------------------|----------------------------------------|-----------------------------------------|-------------------------|
| Overall
Agreement | 91.7%
(90.4%, 92.8%) | 96.4%
(95.5%, 97.2%) | 95.0%
(94.0%, 95.9%) |
| Sensitivity | 95.3%
(92.8%, 96.7%) | 91.0%
(86.8%, 93.9%) | 92.7%
(89.2%, 95.0%) |
| Specificity | 90.9%
(89.4%, 92.2%) | 97.2%
(96.3%, 97.9%) | 95.4%
(94.3%, 96.3%) |
All the 95% CI values for sensitivity, specificity, and overall agreement for distributional WBC abnormalities, morphological WBC abnormalities and overall WBC abnormalities met the acceptance criteria.
13
Red Blood Cells (RBCs)
Sensitivity, specificity, and overall agreement for RBC morphologies (size and shape) were evaluated between the candidate device and manual microscopy. The results are summarized in the table below.
| Table 5: Overall Agreement for RBC Size and Shape between AI100 with Shonit™ vs | |
|---|---|
| Manual Microscopy |
| RBC Abnormality | Sensitivity
95% CI | Specificity
95% CI | Overall Agreement
95% CI |
|-----------------|-------------------------|-------------------------|-----------------------------|
| Anisocytosis | 91.1%
(88.1%, 93.4%) | 95.9%
(94.7%, 96.9%) | 94.7%
(93.6%, 95.7%) |
| Macrocytosis | 90.7%
(87.0%, 93.5%) | 96.6%
(95.5%, 97.4%) | 95.5%
(94.5%, 96.4%) |
| Poikilocytosis | 96.3%
(94.8%, 97.3%) | 88.1%
(85.8%, 90.0%) | 92.1%
(90.7%, 93.2%) |
All the 95% CI values for sensitivity, specificity, and overall agreement for RBC morphologies (size and shape) met the acceptance criteria.
Platelets
Sensitivity, specificity, and overall agreement for platelet morphologies were evaluated between the candidate device and manual microscopy. The results are summarized in the table below.
| Table 6: Overall Agreement for Platelet – Comparison between AI100 with Shonit™ vs | |||
|---|---|---|---|
| Manual Microscopy | |||
| Platelet Type | Sensitivity | ||
| 95% CI | Specificity | ||
| 95% CI | Overall Agreement | ||
| 95%CI | |||
| Platelets | 100% | ||
| (99.8%, 100%) | 100% | ||
| (34.2%, 100%) | 100% | ||
| (99.8%, 100%) | |||
| Giant Platelets | 99.1% | ||
| (98.4%, 99.5%) | 92.4% | ||
| (90.3%,94.1%) | 96.4% | ||
| (95.4%, 97.1%) | |||
| Platelet clumps | 91.6% | ||
| (89.5%,93.4%) | 96.3% | ||
| (94.9%, 97.3%) | 94.2% | ||
| (93.0%, 95.2%) | |||
| Overall Platelets | 97.9% | ||
| (97.1%,98.4%) | 94.6% | ||
| (92.8%, 95.9%) | 96.8% | ||
| (96.0%, 97.4%) |
All the 95% CI values for sensitivity, specificity, and overall agreement for platelet morphologies met the acceptance criteria.
14
5.14 -Proposed Labeling
The labeling satisfies the requirement of 21 CFR Part 809.subpart B.
5.15 Conclusion
AI100 with Shonit™ has the same intended use as the predicate device, the CellaVision® DC-1 analyzer cleared in K200595. AI100 with Shonit™ and the predicate device are quantitative, automated cell locating devices for In Vitro Diagnostic Use in clinical laboratories with the same Intended Use.
Both these cell locators can be used with K2 EDTA whole blood. Both systems are to be used by trained medical professionals to identify WBCs, RBCs and Platelets. Both systems can handle only one peripheral blood smear slide at a time which is smeared and prepared using Romanowski stain. Both systems have LED light source, use microscopic lenses and a camera for imaging, and deploy neural networks of convolution type for image analysis.
The differences have been analyzed and found to be minor technological differences which do not affect the safety and effectiveness of the device.
The analytical and clinical performance studies of the AI100 with Shonit™ were conducted per the study protocols covering all cell types and morphologies that the system is intended to identify. For WBCs, samples covered both normal and abnormal levels for neutrophils, eosinophils, lymphocytes, and monocytes. Samples with abnormal concentrations of IGs, atypical cells or blasts and NRBCs were also included in the study. For RBCs, the samples studied covered all morphological characteristics. For Platelet morphology, samples with Platelet abnormalities such as Giant Platelets and Platelet Clumps, were covered.
The clinical and analytical performance comparison study results demonstrate that the A1100 with Shonit™ system is substantially equivalent to the predicate device (CellaVision® DC-1) system. The studies met their predefined acceptance criteria successfully. The device is safe to use with no adverse events reported during the study.