ST AIA-PACK 25-OH VITAMIN D, ST AIA-PACK 25-OH VITAMIN D CALIBRATOR SET, AIA-PACK 25-OH VITAMIN D CONTROL SET, AND ST AI
K123131 · Tosoh Bioscience, Inc. · MRG · Feb 8, 2013 · Clinical Chemistry
Device Facts
Record ID
K123131
Device Name
ST AIA-PACK 25-OH VITAMIN D, ST AIA-PACK 25-OH VITAMIN D CALIBRATOR SET, AIA-PACK 25-OH VITAMIN D CONTROL SET, AND ST AI
Applicant
Tosoh Bioscience, Inc.
Product Code
MRG · Clinical Chemistry
Decision Date
Feb 8, 2013
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1825
Device Class
Class 2
Indications for Use
ST AIA-PACK 25-OH Vitamin D is designed for in vitro diagnostic use only for the quantitative measurement of total 25-hydroxyvitamin D (25-OH vitamin D) in human serum, Na-heparinized or EDTA plasma on TOSOH AIA System Analyzers. The Tosoh ST AIA-PACK 25-OH Vitamin D is intended as an aid in the determination of Vitamin D sufficiency. The ST AIA-PACK 25-OH Vitamin D Calibrator Set is intended for in vitro diagnostic use only for the calibration of the ST AIA-PACK 25-OH Vitamin D assay. The AIA-PACK 25-OH Vitamin D Control Set is intended for in vitro diagnostic use only for performing quality control procedures with the ST AIA-PACK 25-OH Vitamin D assay.
Device Story
The ST AIA-PACK 25-OH Vitamin D is a one-step delayed competitive enzyme immunoassay performed in a test cup. Input: human serum, Na heparinized plasma, or EDTA plasma. Process: sample pretreatment with sodium hydroxide dissociates 25-OH vitamin D from binding proteins; 25-OH vitamin D binds to monoclonal antibody immobilized on magnetic beads; enzyme-labeled 25-OH vitamin D is added to compete for binding sites. After incubation and washing, a fluorogenic substrate (4-methylumbelliferyl phosphate) is added. Output: fluorescence signal inversely proportional to 25-OH vitamin D concentration. Used in clinical laboratories on TOSOH AIA System Analyzers. Results assist clinicians in assessing Vitamin D sufficiency and patient management.
Clinical Evidence
No clinical diagnostic studies performed. Evidence consists of analytical bench testing: precision (CLSI EP5-A2), linearity (CLSI EP6-A), interference (CLSI EP7-A2), and method comparison against the predicate (n=156 samples, Deming slope 0.934, r=0.944). Reference range established using 233 healthy individuals.
Technological Characteristics
Fluorescence immunoassay; uses magnetic beads coated with sheep monoclonal anti-25-OH Vitamin D antibody; enzyme-labeled conjugate (bovine alkaline phosphatase); fluorogenic substrate 4-methylumbelliferyl phosphate (4MUP). Dimensions/form factor: test cups for AIA-2000 analyzer. Connectivity: standalone analyzer. Sterilization: not applicable (reagents). Software: automated analyzer control.
Indications for Use
Indicated for quantitative measurement of total 25-hydroxyvitamin D in human serum, Na-heparinized, or EDTA plasma to aid in determining Vitamin D sufficiency. Contraindicated for use with hemolyzed samples.
Regulatory Classification
Identification
A vitamin D test system is a device intended for use in clinical laboratories for the quantitative determination of 25-hydroxyvitamin D (25-OH-D) and other hydroxylated metabolites of vitamin D in serum or plasma to be used in the assessment of vitamin D sufficiency.
Special Controls
*Classification.* Class II (special controls). Vitamin D test systems must comply with the following special controls:(1) Labeling in conformance with 21 CFR 809.10 and
(2) Compliance with existing standards of the National Committee on Clinical Laboratory Standards.
Predicate Devices
DiaSorin Inc. 25-Hydroxyvitamin D 125I RIA Kit (k983617)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k123131
B. Purpose for Submission:
New assay
C. Measurand:
25-hydroxy Vitamin D
D. Type of Test:
Quantitative immunoassay
E. Applicant:
Tosoh Biosciences, Inc.
F. Proprietary and Established Names:
ST AIA-PACK 25-OH Vitamin D
ST AIA-PACK 25-OH Vitamin D Calibrator Set
AIA-PACK 25-OH Vitamin D Control Set
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| MRG | II | 862.1825 Vitamin D Test System | Chemistry (75) |
| JIT | II | 862.1150 Calibrator | Chemistry (75) |
| JJX | I, reserved | 862.1660 Quality control material (assayed and unassayed) | Chemistry (75) |
{1}
H. Intended Use:
1. Intended use(s):
See indications for use.
2. Indication(s) for use:
ST AIA-PACK 25-OH Vitamin D is designed for in vitro diagnostic use only for the quantitative measurement of total 25-hydroxyvitamin D (25-OH vitamin D) in human serum, Na-heparinized or EDTA plasma on TOSOH AIA System Analyzers. The Tosoh ST AIA-PACK 25-OH Vitamin D is intended as an aid in the determination of Vitamin D sufficiency.
The ST AIA-PACK 25-OH Vitamin D Calibrator Set is intended for in vitro diagnostic use only for the calibration of the ST AIA-PACK 25-OH Vitamin D assay.
The AIA-PACK 25-OH Vitamin D Control Set is intended for in vitro diagnostic use only for performing quality control procedures with the ST AIA-PACK 25-OH Vitamin D assay.
3. Special conditions for use statement(s):
For prescription use only.
Do not use hemolyzed sample. Hemolyzed sample will give erroneous results.
4. Special instrument requirements:
TOSOH AIA-2000 System Analyzer
I. Device Description:
1. Tosoh’s ST AIA-PACK 25-OH Vitamin D kit is provided as:
- 5 trays of 20 plastic test cups containing twelve magnetic beads coated with lyophilized anti-25-OH vitamin D sheep monoclonal antibody with sodium azide as a preservative.
- 5 vials containing 5 mL 25-OH vitamin D conjugated to bovine alkaline phosphatase.
2. Tosoh’s ST AIA-PACK 25-OH Vitamin D Calibrator set is sold separately and contains:
Six assigned concentrations of 25-OH Vitamin D in human serum (described on each vial) with sodium azide as preservative in aliquots of 1.0 mL, comes in lyophilized form, with vitamin D at target values of 0 (base material), 10, 20, 40, 80, and 165 ng/mL.
{2}
3. Tosoh's AIA-PACK 25-OH Vitamin D Control Set is sold separately and contains:
Two level controls (approximately 20 and 80 ng/mL) in human serum supplied lyophilized in 1 mL vials.
4. Tosoh's AIA-PACK 25-OH Vitamin D Pretreatment Set is sold separately and contains:
Six empty vials for performing pretreatment of test samples, four 4 mL bottles of ST AIA-PACK 25-OH Vitamin D Pretreatment Set (a buffered solution containing no detectable concentration of 25-OH Vitamin D with sodium azide as a preservative), one 32 mL bottle of ST AIA-PACK 25-OH Vitamin D Pretreatment-1 (an aqueous solution containing sodium hydroxide), and six 5 mL bottles of ST AIA-PACK 25-OH Vitamin D Pretreatment-2 (a buffered solution containing surfactant)
The calibrator and control materials has been tested by FDA-approved methods and found negative for the presence of HBsAg, antibody to HIV-1/2 and HCV.
J. Substantial Equivalence Information:
1. Predicate device name(s):
DiaSorin 25-Hydroxyvitamin D ¹²⁵I RIA Kit
2. Predicate 510(k) number(s):
k983617
3. Comparison with predicate:
| Similarities and Differences | | |
| --- | --- | --- |
| Items | ST AIA-PACK 25-OH Vitamin D (Candidate Device) | DiaSorin 25-Hydroxyvitamin D ¹²⁵I RIA Kit (Predicate Device) |
| Intended Use/Indications for Use | Device is designed for in vitro diagnostic use only for the quantitative measurement of total 25-hydroxyvitamin D in serum or plasma. Vitamin D is intended as an aid in the determination of Vitamin D sufficiency. | Same |
| Matrix | EDTA plasma, Na-heparinized plasma, or serum | Plasma or serum |
| Assay Principle | Fluorescence Immunoassay | Radioimmunoassay |
| Reference Range | 10.83 to 54.75 ng/mL | 9 to 37.6 ng/mL |
| Assay Range | 4 – 120 ng/mL | 4.8 – 100 ng/mL |
{3}
| Similarities and Differences | | |
| --- | --- | --- |
| Item | ST AIA-PACK 25-OH Vitamin D Calibrator Set | 25-OH D3 Calibrators for Diasorin125I RIA Kit (Predicate Device k983617) |
| Intended use | For in vitro diagnostic use in calibration of Vitamin D assay | Same |
| Matrix | Lyophilized human serum | Liquid human serum |
| Number of calibrators | 6 | Same |
| Range | 0-165 ng/mL | 0-100 ng/mL |
| Storage temperature | 2-8°C | same |
| Similarities and Differences | | |
| --- | --- | --- |
| Item | AIA-PACK 25-OH Vitamin D Control Set | 25-OH-D Controls for Diasorin125I RIA Kit (Predicate Device k983617) |
| Intended Use | For in vitro diagnostic for performing quality control procedures of the Vitamin D assay | Same |
| Matrix | Lyophilized human serum | Liquid human serum |
| Number of vials | 2 | Same |
| Levels | 2 levels at approximately 20 and 80 ng/mL of 25-OH Vitamin D | Two levels at 9 and 37.6 ng/mL of 25-OH Vitamin D |
| Storage temperature | 2-8°C | same |
# K. Standard/Guidance Document Referenced (if applicable):
CLSI C28-A3, Defining, Establishing, and verifying Reference Intervals in the Clinical Laboratory; Approved Guideline
CLSI EP05-A2, Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline-Second Edition
CLSI EP6-A, Evaluation of the Linearity of Quantitative Measurement Procedures
CLSI EP07-A2, Interference Testing in Clinical Chemistry; Approved Guideline - Second Edition
CLSI EP17-A, Protocols for Determination of Limits of Detection and Limits of Quantitation
CLSI EP21-A, Estimation of Total Analytical Error for Clinical Laboratory Methods
{4}
# L. Test Principle:
The ST AIA-PACK 25-OH Vitamin assay consists of a pretreatment step to release 25-OH Vitamin D from its serum transporter. Pretreated samples are then added to a ST AIA-PACK 25-OH Vitamin D test cup that contain 25-OH vitamin D-specific monoclonal antibody immobilized on magnetic beads to which 25-OH Vitamin D binds. Next, 25-OH vitamin D conjugated to bovine alkaline phosphatase is added to the reaction mixture, which competes with 25-OH vitamin D for binding to the antibody on magnetic beads. Subsequently, the magnetic beads are washed to remove the unbound enzyme labeled 25-OH vitamin D and are then incubated with a fluorogenic substrate, 4-methylumbelliferyl phosphate (4MUP). The amount of enzyme-labeled 25-OH vitamin D that binds to the beads is inversely proportional to the 25-OH vitamin D concentration in the test sample.
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
# a. Precision/Reproducibility:
Precision of the ST AIA-PACK 25-OH Vitamin D assay was evaluated according to CLSI EP5-A2. Three reagent lots and three analyzers were utilized in the study. Two replicates of each of the three levels of pooled and spiked Na-heparinized plasma, EDTA plasma and serum specimens were tested on two separate occasions per day for 20 non-consecutive days, leading to the generation of 80 data points for each sample type. Mean, within-run CV and total precision CV are summarized in the table below.
| Sample | Mean (ng/mL) | Within-run | | Total | |
| --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV |
| Serum 1 | 16.0 | 1.2 | 7.3 | 1.2 | 7.4 |
| | 36.0 | 1.0 | 2.7 | 1.3 | 3.7 |
| | 94.1 | 1.5 | 1.6 | 2.2 | 2.3 |
| Serum 2 | 21.8 | 0.7 | 3.3 | 0.8 | 3.8 |
| | 44.4 | 1.6 | 3.6 | 1.5 | 3.3 |
| | 98.0 | 1.9 | 2.0 | 2.0 | 2.0 |
| Serum 3 | 21.8 | 0.9 | 4.3 | 1.3 | 5.8 |
| | 46.5 | 1.8 | 3.9 | 1.8 | 3.9 |
| | 103.7 | 2.1 | 2.0 | 2.4 | 2.3 |
| Na-Heparin Plasma 1 | 15.7 | 0.8 | 4.8 | 1.0 | 6.4 |
| | 32.9 | 0.8 | 2.4 | 1.4 | 4.1 |
{5}
| | 75.4 | 1.2 | 2.2 | 1.6 | 2.9 |
| --- | --- | --- | --- | --- | --- |
| Na-Heparin Plasma 2 | 21.5 | 1.0 | 4.5 | 1.0 | 4.4 |
| | 47.0 | 1.2 | 2.6 | 1.5 | 3.3 |
| | 102.8 | 1.9 | 2.7 | 1.9 | 2.7 |
| Na-Heparin Plasma 3 | 21.8 | 1.1 | 5.2 | 1.1 | 5.2 |
| | 50.0 | 1.6 | 3.1 | 2.0 | 4.0 |
| | 108.9 | 1.8 | 1.7 | 3.3 | 3.0 |
| EDTA Plasma 1 | 13.7 | 0.7 | 4.9 | 0.9 | 6.6 |
| | 34.7 | 0.9 | 2.7 | 1.3 | 3.9 |
| | 71.1 | 1.2 | 1.7 | 1.9 | 2.7 |
| EDTA Plasma 2 | 24.4 | 0.8 | 3.3 | 1.0 | 4.1 |
| | 47.4 | 0.9 | 2.0 | 1.4 | 2.9 |
| | 105.2 | 1.5 | 1.4 | 2.3 | 2.2 |
| EDTA Plasma 3 | 25.6 | 1.1 | 4.2 | 1.2 | 4.7 |
| | 50.3 | 1.0 | 1.9 | 1.6 | 3.2 |
| | 110.9 | 1.3 | 1.2 | 2.8 | 2.5 |
Precision of the ST AIA-PACK 25-OH Vitamin D Control Set was evaluated according to CLSI EP5-A2. The protocol consisted of testing 2 levels of controls in 2 replicates per run, 2 runs per day for 20 non-consecutive days on one analyzer generating a total of 80 data points for each control level. Mean, within-run CV and total precision CV are summarized in the table below.
| Sample | Mean (ng/mL) | Within-run | | Total | |
| --- | --- | --- | --- | --- | --- |
| | | SD | %CV | SD | %CV |
| Control Level 1 | 20.0 | 0.79 | 3.9 | 1.16 | 5.8 |
| Control Level 2 | 79.1 | 1.63 | 2.1 | 2.22 | 2.8 |
## b. Linearity/assay reportable range:
Linearity was evaluated according to CLSI guideline EP6-A. Samples were prepared by mixing a high spiked serum sample with a low serum sample to obtain 11 concentrations across the range $2.6\mathrm{ng / mL}$ to $158.7\mathrm{ng / mL}$, with each sample being assayed in 4 replicates. The data showed the following linear regression: $\mathrm{Y} = 1.0366\mathrm{X} + 0.1327$, $\mathrm{r} = 0.9975$
The sponsor claimed that the assay range is 4 to $120\mathrm{mg / dL}$
{6}
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
**Traceability**
The calibrators for use with the ST AIA-PACK 25-OH Vitamin D are prepared gravimetrically. The commercially available stock of 25-hydroxycholecalciferol is used to make the internal standards by gravimetrical dilution into vitamin-free serum. The initial value for the internal material is assigned using the candidate device compared to the predicate device.
**Value Assignment**
ST AIA-Pack 25-OH Vitamin D Calibrator Set contains 6 levels of different concentrations of 25-hydroxycholecalciferol in steroid free human serum devoid of detectable vitamin D at target values of 0 (base material), 10, 20, 40, 80, and 165 ng/mL.
AIA-PACK 25-OH Vitamin Control Set contains 2 levels of 25-hydroxycalciferol in steroid free human serum at target values of 20 and 80 ng/mL.
Production lots of kit calibrators and control materials are value assigned against internal standards using 3 reagent lots, 5 runs on two different instruments for a total of 30 replicates. The assigned value is the mean of the replicates. The controls are labeled with the assigned values as mean ±20%.
**Shelf-life Stability**
Real-time stability studies were performed for the control materials and the calibrators. The stability study protocol and the acceptance criteria have been reviewed and found to be acceptable. The real time stability study supports a stability of 6 months when materials are stored at 2-8°C.
**Open-Vial Stability**
The stability study protocol and the acceptance criteria to determine open-vial stability of the control materials and the calibrators have been reviewed and found to be acceptable. The reconstituted controls were stable for 1 day when stored at 18-25°C, for 14 days when stored at 2-8°C, 60 days when stored at -20°C. Reconstituted calibrators were stable for 1 day when stored at 2-8°C.
For the calibration frequency, the sponsor claimed that the calibration is stable for up to 90 days.
d. Detection limit:
The sponsor performed a detection limit study to support their low end measuring range according to the CLSI guideline EP17-A.
For LoB determination, three blank samples were measured in three independent runs with 60 replicates per run giving 180 determinations in total. The LoB is calculated as the mean of the 57th and 58th highest values for the blanks. The LoB was estimated to be 1.6 ng/mL.
{7}
For LoD determination, six low level samples were measured in 3 independent runs with 10 replicates per run generating 180 measurements. The LoD samples were made by diluting commercial serum samples to yield concentrations ranging from 1.23-6.38 ng/mL. The LoD was calculated to be 2.6 ng/mL.
For LoQ determination, the test results from the LoD determination were used to calculate the functional sensitivity of the assay. Sponsor defines the LoQ as the interassay precision ≤ 20% CV. The LoQ was determined to be 2.9 ng/mL.
The measuring range of the ST AIA-PACK 25-OH Vitamin D assay is 4.0 to 120 ng/mL.
e. Analytical specificity:
Cross reactivity
To estimate cross reactivity of various Vitamin D metabolites with 25-OH Vitamin D, aliquots of samples of moderate Vitamin D levels were spiked with 25-OH Vitamin D metabolites.
Cross reactivity from compounds listed below were evaluated. Results are tabulated:
| Cross-reactant | Spiked (ng/mL) | % Cross Reactivity |
| --- | --- | --- |
| 25-OH Vitamin D2 | 30 | 101 |
| 25-OH Vitamin D3 | 158.2 | 99.2 |
| 3-epi 25-OH Vitamin D2 | 30 | 131.3 |
| 3-epi 25-OH Vitamin D3 | 30 | 107 |
| 24,25-(OH)2 Vitamin D2 | 100 | 5.2 |
| 24,25-(OH)2 Vitamin D3 | 100 | 18 |
| Vitamin D3 | 1000 | <0.1 |
| Vitamin D2 | 1000 | 0.5 |
| 1,25-(OH)2 Vitamin D3 | 1000 pg/mL | <0.1 |
| 1,25-(OH)2 Vitamin D2 | 1000 pg/mL | <0.1 |
| Paricalcitol | 2 | <0.1 |
Interference
The sponsor performed studies to evaluate the effects of potential interferents on the performance of the ST AIA-25-OH Vitamin assay, following CLSI EP7-A2. Testing was done in the presence of 14 to 80 ng/mL 25-OH vitamin D and different concentrations of the listed compounds. All samples were run in triplicate. Percent recovery was calculated relative to control samples
{8}
containing vitamin D without spiked endogenous compounds. The highest concentrations at which non-significant interference (defined by the sponsor as $\leq 10\%$ bias relative to the control) are shown below:
| Compound | Concentration above which significant interference observed |
| --- | --- |
| Bilirubin (conjugated) | 18.4 mg/dL |
| Bilirubin (unconjugated) | 16.8 mg/dL |
| Triglycerides | 357 mg/dL |
| Hemoglobin | 11.4 mg/dL |
| Human serum albumin (protein) | 8.5 g/dL |
| Ascorbic acid | 20 mg/dL |
| EDTA-2K | 10 mg/mL |
| Heparin | 100 U/mL |
| Rheumatoid Factor | 500 IU/mL |
The sponsor has the following limitations in their labeling:
"Do not use hemolyzed sample. Hemolyzed sample will give erroneous results."
f. Assay cut-off:
Not applicable.
# 2. Comparison studies:
a. Method comparison with predicate device:
A method comparison study was performed with the predicate device (Diasorin 25-Hydroxyvitamin D $^{125}$ I RIA Kit). A total of 156 unaltered human serum samples were measured in singlicate. The samples ranged in concentration from $6.2\mathrm{ng / mL}$ to $103.2\mathrm{ng / mL}$ .
Results of the Deming regression analysis are presented in the table below:
| | Deming |
| --- | --- |
| Slope (95% CI) | 0.934 (0.884 to 0.979) |
| Intercept (95% CI) | 2.53 (0.86 to 4.34) |
| Correlation Coefficient | 0.944 |
| Bias | 0.61 |
b. Matrix comparison:
115 matched sets of serum, Na-heparin-plasma, and EDTA-plasma were assayed in singlicate with one reagent lot on one AIA-2000 analyzer. Samples tested ranged from 11.0 to $112.8\mathrm{ng / mL}$ .
Results of Regression Analysis:
{9}
| Matrix Y | Slope | | Intercept | | R |
| --- | --- | --- | --- | --- | --- |
| | Deming | Linear | Deming | Linear | |
| Na-Heparin plasma | 0.993 | 0.988 | -0.390 | -0.20 | 0.995 |
| EDTA plasma | 1.041 | 1.034 | 0.91 | 1.14 | 0.994 |
Based on the study data, the sponsor claims that EDTA and sodium heparin are acceptable anti-coagulants for the vitamin D assay.
3. Clinical studies:
a. Clinical Sensitivity:
Not applicable
b. Clinical specificity:
Not applicable
c. Other clinical supportive data (when a. and b. are not applicable):
Not applicable
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
To determine the reference range for the ST-AIA-PACK 25-OH Vitamin D assay, a total of 233 serum specimens form 50 females and 183 males (ages 19 to 80 years old) were measured. The specimens were obtained from the northern and southern regions of the United States from apparently healthy individuals who were not taking more than the normal Vitamin D supplements i.e. 2000 IU. Specimens with high parathyroid hormone, thyroid stimulating hormone, calcium, magnesium, and phosphorus were excluded from the data. Samples were collected in April and July 2012. The following results were obtained:
Lowest 25-OH Vitamin D concentration: 7.23 ng/mL
Highest 25-OH Vitamin D concentration: 56.70 ng/mL
Observed central 95% range: 10.83 to 54.75 ng/mL
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
{10}
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
11
Predicate graph will load when search results are available.
Embedding visualization will load when search results are available.
PDF viewer will load when search results are available.
Loading panels...
Select an item from Submissions
Click any panel, subpart, regulation, product code, or device to see details here.
Section Matches
Results will appear here.
Product Code Matches
Results will appear here.
Special Control Matches
Results will appear here.
Loading collections...
Loading
My Alerts
You will receive email notifications based on the filters and frequency you set for each alert.
Sort by:
Create Alert
Search Filters
Agent Token
Create a read-only bearer token for Claude, ChatGPT, or other agents that can call HTTP APIs.
Copy this now. It will not be shown again.
Connected apps
Apps you authorized through browser sign-in. Disconnecting revokes their access immediately.
Learn the FDA Browser
Two short videos show you everything — or skip straight to the written tutorial if you'd rather read. You can reopen this any time from the Tutorial button in the top bar.
Part 1 — Search, results, and everyday workflows 16 min
Part 2 — Embeddings: the galaxy map 3 min
1. Search: exact and fuzzy
Type a phrase like "coronary artery calcification" into the search box. You get two kinds of results. Exact results match the literal phrase — prefix searches work ("coronary artery calcificati") but suffix searches do not. Fuzzy results match on the meaning and intent of your phrase rather than the exact words, and are sorted by relevance score. Hover over the Exact or Fuzzy badge on any row to see exactly why it matched.
Use the checkboxes above the results to narrow: SaMD keeps only software-only devices, AI / ML keeps only devices with AI.
Exact vs. fuzzy search: what's the difference?
Exact matches on the literal phrase (prefix search works, suffix does not). Fuzzy matches on the meaning and intent of the phrase rather than the exact words. Hover over the badge on any row to see why it matched.
You search "coronary artery calcification" and want only software devices with AI. What two filters do you apply?
Narrow by SaMD (software-only devices), then narrow by AI/ML (devices with AI).
2. The results table
Scroll right in the results table. The intended use is extracted for you — no need to open the PDF. The device story gives a high-level snapshot of what the device does and how it's used. The AI Performance sub-table shows each output name, acceptance criteria, observed values, and development/test dataset descriptions — the same format Innolitics uses for regulatory strategy outputs, and the fastest high-level fingerprint of an AI device. It is AI-generated but has been very reliable in practice.
Where do you find a device's intended use without opening the PDF?
Scroll right in the search results table. The intended use column is extracted for you; no need to dig into the 510(k) summary PDF.
What does the AI Performance sub-table show, and why is it useful?
Output name, acceptance criteria, observed values, development dataset description, and test dataset description. It's the same format we use for regulatory strategy output and Fast 510(k) input, and the fastest high-level fingerprint of an AI device. AI-generated but reliable in practice.
3. Judging fuzzy relevance
Fuzzy results trail off in relevance as you scroll. Use three signals to decide how far down to go: the fuzzy badge explanations, the intended use column, and whether your target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, you're past the relevant zone. A top hit with a low score (~0.4) and a stretched explanation is a hint the closest predicates are far away — the project may be headed for De Novo. Note the fuzzy search is a pattern match: it doesn't handle negation ("not") well, and hardware devices can appear — filter by SaMD/AI ML to cut them.
How do you judge how far down fuzzy search results to go?
Use the relevancy signals: the fuzzy badge explanations, the intended use column, and whether the target output (e.g., Cobb angle) still appears in the AI Performance sub-table. Once it stops appearing, results are trailing off in relevancy.
4. Device detail page: chat and citations
Click a device name to open its detail page: device facts on the left, a chat window on the right. Ask something like "Describe the training data". The answer carries little citation bubbles — click one to jump to the highlighted passage in the source PDF, so you can verify every AI answer against the document. There's also a Download PDF button for sharing.
How do you verify an AI chat answer on the device detail page?
Click the citation bubbles to jump to the relevant highlight in the source document.
Reading rule for every project: how many summaries do you read in full?
At least the three most relevant 510(k) or De Novo summaries, in full. After that, use targeted chat questions to confirm your memory quickly. The tool supports this professional habit — it doesn't replace it.
5. Side-by-side comparison
Select multiple rows in the results table (aim for under ~10), then open the PDF Viewer tab. Ask one question — it goes to all selected devices in parallel, each with citations. This is the fastest way to compare and contrast devices: training data, PCCP scope, how they handled adding new scanners, and so on.
What does the side-by-side PDF viewer mode do?
Select multiple devices, open the PDF viewer tab, and ask one question (e.g., "Describe the training data"). It queries all selected devices simultaneously with citations, so you can compare and contrast quickly.
6. Collections
With rows selected, go to the Collections tab and create a labeled collection (e.g., "Cobb Angle Project"). Reload that selection any time — before a client call, pull up the collection and ask questions across all of its devices at once.
How do you save a set of selected devices for later use?
Select the rows, go to the Collections tab, and create a labeled collection (e.g., "Cobb Angle Project"). You can reload the selection anytime and carry it into the PDF viewer and other tabs that support selections.
7. Product codes and the regulations tree
Click a product code in the results to jump to it in the regulations tree — identification text, sibling product codes, and devices you can open in a PDF viewer on the right. Click a regulation number to see its identification, special controls, and related product codes. You can also search by product code or regulation number at the top of the tree. Always read the special controls if any exist for your device — it broadens your search and sharpens pre-kickoff research.
What can you do from the regulations tree view?
Browse product codes and regulation numbers, read the identification text and special controls, browse sibling product codes, open device PDFs on the right, and search by product code or regulation number at the top of the tree.
8. Chart view
Click Show Chart and segment by regulation number (or product code) to see which regulations dominate your result set. Clicking a regulation takes you into the regulations tree. Great for spotting that most matches are, say, hardware laparoscopic devices — a cue to go back and filter.
How do you see which regulations dominate a search result set?
Click "Show Chart" and segment by Regulation Number. Clicking a regulation takes you to the regulations tree.
9. The predicate graph
Open the Predicates tab for a family-tree view of predicate relationships. Click a node to trace its parents and children; selections from search carry over pre-selected. Commonly predicated devices are worth reading — a lot of people predicated them for a reason. The visual lineage is also handy on client calls, e.g. to show how a predicate family evolved and justify why your predicate still holds.
In the predicate graph, why are commonly predicated devices worth reading?
A lot of people predicated them for a reason. Clicking a node traces parents and children, and selections from search carry over pre-selected.
10. Embeddings: the galaxy map
The Embeddings tab plots every matching document in a 2-D "galaxy map" where semantically similar devices cluster together. Hover or click clusters to explore, and let AI label the clusters for you. Embeddings beat product codes for grouping: two devices can carry different product codes (LLZ vs. QIH) yet do the same thing — the embedding captures the meaning of the intended use and device story. This is also exactly how retrieval-augmented generation (RAG) works under the hood, and it makes a great visual on client calls.
Try it yourself
Head to the search page and work through a few of these AI/ML fuzzy searches to build intuition: perivascular fat on CT · aortic valve calcification opportunistic screening on noncontrast CT · breast cancer prediction on digital pathology slides · autism detection · gestational age prediction · a hearing aid that can also detect a pulse · foundation model based analysis of ECG · large language models · penetration test. Watch how the relevance scores, intended use, and AI Performance tables tell you when results stop being meaningful.