AI100 with Shonit

K221309

SigTuple Technologies Pvt. Ltd. · cleared 2023-09-19 · product code JOY · Hematology

Premarket evidence — what FDA accepted

Device typehardware with ml
source quote (p.5)
“The AI100 with ShonitTM 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 ShonitTM 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 AI100 with ShonitTM device, and the combination of hardware and software works together for the device to achieve its intended use.”
AlgorithmNeural network of convolutional type
source quote (p.9)
“Neural network of convolutional type”
Adaptive (vs locked)FDA source did not state this
PCCPFDA source did not state this
Cybersecurity addressedFDA source did not state this

Validation studies (7)

Retrospective clinical

n=882 patients · 4 site(s)

endpoints: differential count of White Blood Cells (WBC); characterization of Red Blood Cells (RBC) morphology; Platelet morphology; Sensitivity, specificity, and overall agreement for distributional WBC abnormalities; morphological WBC abnormalities; overall WBC abnormalities; Sensitivity, specificity, and overall agreement for RBC morphologies (size and shape); Sensitivity, specificity, and overall agreement for platelet morphologies

standards: CLSI H20-A2: Reference Leukocyte (WBC) Differential Count (Proportional) and Evaluation of Instrumental Methods; Approved Standard – Second edition guidelines.

Standalone

n=12 patients · 1 site(s)

endpoints: proportional cell count in percent for each cell class was used to estimate variance components for repeatability

standards: CLSI EP05-A3 (Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline – Third Edition).

Standalone

n=12 patients · 1 site(s)

endpoints: 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 Poikilocytcs (Normal Cells, Echinocytes, Target cells, Elliptocytes, Teardrop cells, Fragmented cells, Ovalocytes) for each run were used for analysis.

standards: CLSI EP05-A3 (Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline – Third Edition).

Standalone

n=12 patients · 1 site(s)

endpoints: Overall agreement for the qualitative grade – ‘Detected/Not Detected' for each run was used for analysis.

standards: CLSI EP05-A3 (Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline – Third Edition).

Standalone

n=13 patients

endpoints: proportional cell count in percent for each cell class was used to estimate variance components for reproducibility

standards: CLSI's EP05-A3 Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline—Third Edition.

Standalone

n=13 patients

endpoints: 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 Poikilocytcs (Normal Cells, Echinocytes, Target cells, Elliptocytes, Teardrop cells, Fragmented cells, Ovalocytes) for each run were used for analysis.

standards: CLSI's EP05-A3 Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline—Third Edition.

Standalone

n=13 patients

endpoints: Overall agreement for qualitative grade – ‘Detected’/’Not Detected' output for each run was used for analysis.

standards: CLSI's EP05-A3 Evaluation of Precision of Quantitative Measurement Procedures; Approved Guideline—Third Edition.

Reported performance (20 observations)

sensitivityas written: “WBC Abnormalities (Distributional) Sensitivity”0.91CI (86.8%, 93.9%)
source quote (p.13)
“91.0% (86.8%, 93.9%)”
specificityas written: “WBC Abnormalities (Distributional) Specificity”0.972CI (96.3%, 97.9%)
source quote (p.13)
“97.2% (96.3%, 97.9%)”
sensitivityas written: “WBC Abnormalities (Morphological) Sensitivity”0.953CI (92.8%, 96.7%)
source quote (p.13)
“95.3% (92.8%, 96.7%)”
specificityas written: “WBC Abnormalities (Morphological) Specificity”0.909CI (89.4%, 92.2%)
source quote (p.13)
“90.9% (89.4%, 92.2%)”
sensitivityas written: “WBC Abnormalities (Overall) Sensitivity”0.927CI (89.2%, 95.0%)
source quote (p.13)
“92.7% (89.2%, 95.0%)”
specificityas written: “WBC Abnormalities (Overall) Specificity”0.954CI (94.3%, 96.3%)
source quote (p.13)
“95.4% (94.3%, 96.3%)”
sensitivityas written: “RBC Anisocytosis Sensitivity”0.911CI (88.1%, 93.4%)
source quote (p.14)
“91.1% (88.1%, 93.4%)”
specificityas written: “RBC Anisocytosis Specificity”0.959CI (94.7%, 96.9%)
source quote (p.14)
“95.9% (94.7%, 96.9%)”
sensitivityas written: “RBC Macrocytosis Sensitivity”0.907CI (87.0%, 93.5%)
source quote (p.14)
“90.7% (87.0%, 93.5%)”
specificityas written: “RBC Macrocytosis Specificity”0.966CI (95.5%, 97.4%)
source quote (p.14)
“96.6% (95.5%, 97.4%)”
sensitivityas written: “RBC Poikilocytosis Sensitivity”0.963CI (94.8%, 97.3%)
source quote (p.14)
“96.3% (94.8%, 97.3%)”
specificityas written: “RBC Poikilocytosis Specificity”0.881CI (85.8%, 90.0%)
source quote (p.14)
“88.1% (85.8%, 90.0%)”
sensitivityas written: “Platelets Sensitivity”1CI (99.8%, 100%)
source quote (p.14)
“100% (99.8%, 100%)”
specificityas written: “Platelets Specificity”1CI (34.2%, 100%)
source quote (p.14)
“100% (34.2%, 100%)”
sensitivityas written: “Giant Platelets Sensitivity”0.991CI (98.4%, 99.5%)
source quote (p.14)
“99.1% (98.4%, 99.5%)”
specificityas written: “Giant Platelets Specificity”0.924CI (90.3%, 94.1%)
source quote (p.14)
“92.4% (90.3%, 94.1%)”
sensitivityas written: “Platelet clumps Sensitivity”0.916CI (89.5%, 93.4%)
source quote (p.14)
“91.6% (89.5%, 93.4%)”
specificityas written: “Platelet clumps Specificity”0.963CI (94.9%, 97.3%)
source quote (p.14)
“96.3% (94.9%, 97.3%)”
sensitivityas written: “Overall Platelets Sensitivity”0.979CI (97.1%, 98.4%)
source quote (p.14)
“97.9% (97.1%, 98.4%)”
specificityas written: “Overall Platelets Specificity”0.946CI (92.8%, 95.9%)
source quote (p.14)
“94.6% (92.8%, 95.9%)”

Each value carries its own analysis unit and task — never compare or pool across devices. Source: 510(k) summary PDF.

Predicate network

Postmarket — what happened after clearance

1
recalls in product code, 24mo
1
MAUDE reports in code, 12mo
-40%
vs code's own 3-yr baseline
1
drift signals on this device
  • recall_reason_pattern

    Software/algorithm-related recall in product code JOY (Cellavision AB Forskningsbyn Ideon Scheelevagen 19a Lund Sweden, initiated 2025-10-08): "Automated cell-locating device barcode reader may read the barcode of the previously processed slide resulting in a misattribution of diagnostic results." Recalling firm is another firm in the same product code.

    first seen 2026-07-08 · recall res_event_number:97835

Recall and MAUDE counts are product-code-level (reports aren't reliably attributable to one device); a recall is shown as device-attributed only when the recall record itself lists this clearance number. Signals are descriptive observables with sources — never a judgment that the device is unsafe or drifting. Snapshot 2026-07-08.

Reimbursement — how devices like this got paid

Not yet tracked — no payment pathway indexed for this clearance (the reimbursement corpus is a growing seed set).

Applicable FDA guidance — what the submission is measured against

FDA guidance documents and guiding principles applicable to 510(k) AI/ML devices in the Hematology panel. A curated reference index, not legal or regulatory advice — each item states its own status, and a draft is never binding.

Applicability is derived from the device's FDA advisory panel and pathway — cross-cutting guidances apply to every AI/ML device; panel-specific ones are flagged. Titles, dates, and links verified against fda.gov as of July 2026.

Constat Precedent · public FDA/CMS data · descriptive decision-support, not regulatory or reimbursement advice. Share this page: constat.dev/precedent/device/K221309