K242870 · Beckman Coulter, Inc. · MMI · Jun 16, 2025 · Clinical Chemistry
Device Facts
Record ID
K242870
Device Name
Access hsTnI
Applicant
Beckman Coulter, Inc.
Product Code
MMI · Clinical Chemistry
Decision Date
Jun 16, 2025
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1215
Device Class
Class 2
Indications for Use
Access hsTnl is a paramagnetic particle, chemiluminescent immunoassay for the quantitative determination of cardiac troponin I (cTnl) levels in human serum and plasma using the Access 2 Immunoassay Systems to aid in the diagnosis of myocardial infarction (MI).
Device Story
Access hsTnI is a two-site immunoenzymatic sandwich assay for quantitative measurement of cardiac troponin I (cTnI). Input: human serum or plasma samples. Process: sample mixed with surfactant-containing buffer and monoclonal anti-cTnI antibody conjugated to alkaline phosphatase; paramagnetic particles coated with monoclonal anti-cTnI antibody added; cTnI binds to solid phase; unbound materials washed away via magnetic field; chemiluminescent substrate added; light production measured by luminometer. Output: light signal directly proportional to analyte concentration, automatically calculated via stored calibration. Used in clinical laboratory settings by trained technicians on Access 2 or DxC 500i Immunoassay Systems. Results assist clinicians in diagnosing myocardial infarction. Benefits include high-sensitivity detection of cardiac injury markers.
Clinical Evidence
Bench testing only. Studies conducted per CLSI guidelines (EP05-A3, EP06, EP17-A2, EP09-ED3). Platform equivalency study (N=106 serum, N=122 plasma) showed slope 1.00±0.10 and r=0.999. Method comparison across three sites using >200 samples met acceptance criteria (slope 1.00±0.10, r≥0.90). Precision: within-lab SD ≤1.15 pg/mL for <11.5 pg/mL; CV ≤10% for ≥11.5 pg/mL. LoB/LoD <4.0 pg/mL; LoQ ≤5.0 pg/mL at 20% CV. Carryover observed at high concentrations (>150,000 pg/mL) and addressed via labeling limitations.
Technological Characteristics
Paramagnetic particle, chemiluminescent sandwich immunoassay. Reagents: mouse monoclonal anti-human cTnI antibody and sheep monoclonal anti-human cTnI-alkaline phosphatase conjugate. Automated immunoassay instrument platform (Access 2 or DxC 500i). Measuring range: 2.0–27,027 pg/mL. Open pack stability: 64 days at 2–10°C. Connectivity: integrated into clinical analyzer systems.
Indications for Use
Indicated for the quantitative determination of cardiac troponin I (cTnI) levels in human serum and plasma to aid in the diagnosis of myocardial infarction (MI).
Regulatory Classification
Identification
A creatine phosphokinase/creatine kinase or isoenzymes test system is a device intended to measure the activity of the enzyme creatine phosphokinase or its isoenzymes (a group of enzymes with similar biological activity) in plasma and serum. Measurements of creatine phosphokinase and its isoenzymes are used in the diagnosis and treatment of myocardial infarction and muscle diseases such as progressive, Duchenne-type muscular dystrophy.
{0}
FDA U.S. FOOD & DRUG ADMINISTRATION
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
ASSAY ONLY
## I Background Information:
A 510(k) Number
K242870
B Applicant
Beckman Coulter, Inc.
C Proprietary and Established Names
Access hsTnI
D Regulatory Information
| Product Code(s) | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| MMI | Class II | 21 CFR 862.1215 - Creatine Phosphokinase/Creatine Kinase Or Isoenzymes Test System | CH - Clinical Chemistry |
## II Submission/Device Overview:
A Purpose for Submission:
Addition of previously cleared assay to a new instrument
B Measurand:
Cardiac Troponin (cTnI)
C Type of Test:
Quantitative Immunoassay
Food and Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993-0002
www.fda.gov
{1}
K242870 - Page 2 of 9
## III Intended Use/Indications for Use:
### A Intended Use(s):
See Indications for Use below.
### B Indication(s) for Use:
Access hsTnI is a paramagnetic particle, chemiluminescent immunoassay for the quantitative determination of cardiac troponin I (cTnI) levels in human serum and plasma using the Access 2 Immunoassay Systems to aid in the diagnosis of myocardial infarction (MI).
### C Special Conditions for Use Statement(s):
Rx - For Prescription Use Only
### D Special Instrument Requirements:
DxC 500i Clinical Analyzer
## IV Device/System Characteristics:
### A Device Description:
The Access hsTnI reagent packs contain specific reagents for the in vitro diagnostic measurement of cTnI including:
- R1a: Dynabeads paramagnetic particles coated with mouse monoclonal anti-human cTnI antibody suspended in TRIS buffered saline, with surfactant, bovine serum albumin (BSA), < 0.1% sodium azide, and 0.1% ProClin 300.
- R1b: 0.1 N NaOH
- R1c: TRIS buffered saline, surfactant, protein (mouse), < 0.1% sodium azide, and 0.1% ProClin 300.
- R1d: Sheep monoclonal anti-human cTnI alkaline phosphatase conjugate diluted in ACES buffered saline, with surfactant, BSA matrix, protein (bovine, sheep, mouse), <0.1% sodium azide, and 0.25% ProClin 300.
### B Principle of Operation:
The Access hsTnI assay is a two-site immunoenzymatic (“sandwich”) assay. Monoclonal anti-cTnI antibody conjugated to alkaline phosphatase is added to a reaction vessel along with a surfactant-containing buffer and sample. After a short incubation, paramagnetic particles coated with monoclonal anti-cTnI antibody are added. The human cTnI binds to the anti-cTnI antibody on the solid phase, while the anti-cTnI antibody-alkaline phosphatase conjugate reacts with different antigenic sites on the cTnI molecules.
After incubation, materials bound to the solid phase are held in a magnetic field while unbound materials are washed away. Then, the chemiluminescent substrate is added to the vessel and light generated by the reaction is measured with a luminometer. The light production is directly proportional to the concentration of analyte in the sample. Analyte concentration is automatically
{2}
determined from a stored calibration.
V Substantial Equivalence Information:
A Predicate Device Name(s):
Access hsTnI
B Predicate 510(k) Number(s):
K230648
C Comparison with Predicate(s):
| Device & Predicate Device(s): | K242870 | K230648 |
| --- | --- | --- |
| Device Trade Name | Access hsTnI | Access hsTnI |
| General Device Characteristic Similarities | | |
| Intended Use/Indications For Use | Quantitative determination of cardiac troponin I (cTnI) levels in human serum and plasma to aid in the diagnosis of myocardial infarction (MI). | Same |
| Assay Principle | Chemiluminescent sandwich assay | Same |
| Sample Type | Serum and Lithium Heparin plasma | Same |
| Analytical Measuring Range | 2.0 pg/mL to 27,027 pg/mL | Same |
| Sample Volume | 55 μL | Same |
| Open pack stability | Stable at 2 to 10°C for 64 days after opening | Same |
| Extended Range | 1:5 dilution factor and limitation statement related to carryover | Same |
| General Device Characteristic Differences | | |
| Instrument Required | DxC 500i Clinical Analyzer | Access 2 Immunoassay System |
| Wash Buffer | A16793 (10L container) | A16792 (2L container) |
K242870 - Page 3 of 9
{3}
VI Standards/Guidance Documents Referenced:
1. CLSI EP06-Ed2: Evaluation of the Linearity of Quantitative Measurement Procedures: A Statistical Approach; Approved Guideline
2. CLSI EP17-A2: Evaluation of Detection Capability for Clinical Laboratory Measurement Procedures; Approved Guideline – Second Edition
3. CLSI EP05-A3: Evaluation of Precision of Qualitative Measurement Methods Procedures; Approved Guideline – Third Edition
4. CLSI EP09c: Measurement Procedure Comparison and Bias Estimation Using Patient Samples; Approved Guideline – Third Edition
VII Performance Characteristics (if/when applicable):
A Analytical Performance:
1. Precision/Reproducibility:
**Repeatability and Within-Laboratory Precision study**
The sponsor evaluated precision of the Access hsTnI assay on the DxC 500i Clinical Analyzer in several studies following the recommendations in CLSI EP05-A3. Six levels of lithium heparin plasma and serum pools, and serum-based commercial control materials with troponin concentrations spanning the measuring range were each tested on a single DxC 500i instrument using a single reagent pack lot and calibrator lot at a single site. Each sample was assayed in duplicate, in two runs per day, over 20 days for a total of 40 runs and a minimum of 80 measurement per sample. The within-laboratory (total) imprecision and within-run (repeatability) %CV and SD results for this study are shown below:
| DxC 500i Serum Results | | | | | |
| --- | --- | --- | --- | --- | --- |
| Sample | Mean (pg/mL) | Within-Run (Repeatability) | | Within-Laboratory (Total) | |
| | | SD | CV% | SD | CV% |
| Control L1 | 46.7 | 0.8 | 1.8 | 1.2 | 2.5 |
| Control L2 | 1500.0 | 27.6 | 1.8 | 34.8 | 2.3 |
| Control L3 | 17400.7 | 448.3 | 2.6 | 466.1 | 2.7 |
| Pool 1 | 3.2 | 0.2 | 5.5 | 0.3 | 9.3 |
| Pool 2 | 8.7 | 0.3 | 3.7 | 0.5 | 5.2 |
| Pool 3 | 15.9 | 0.4 | 2.3 | 0.9 | 5.8 |
| Pool 4 | 77.7 | 1.7 | 2.2 | 2.2 | 2.8 |
| Pool 5 | 4001.7 | 63.3 | 1.6 | 120.3 | 3.0 |
| Pool 6 | 17289.2 | 414.7 | 2.4 | 572.3 | 3.3 |
K242870 - Page 4 of 9
{4}
| DxC 500i Lithium Heparin | | | | | |
| --- | --- | --- | --- | --- | --- |
| Sample | Mean (pg/mL) | Within-Run (Repeatability) | | Within-Laboratory (Total) | |
| | | SD | CV% | SD | CV% |
| Control L1 | 47.7 | 1.8 | 3.8 | 2.3 | 4.8 |
| Control L2 | 1502.7 | 36.2 | 2.4 | 73.2 | 4.9 |
| Control L3 | 18246.1 | 654.5 | 3.6 | 838.9 | 4.6 |
| Pool 1 | 10.5 | 0.4 | 3.6 | 0.5 | 4.8 |
| Pool 2 | 16.4 | 0.7 | 4.0 | 0.9 | 5.4 |
| Pool 3 | 110.3 | 3.8 | 3.4 | 5.5 | 5.0 |
| Pool 4 | 4605.6 | 166.3 | 3.6 | 283.6 | 6.2 |
| Pool 5 | 19027.4 | 778.9 | 4.1 | 1334.0 | 7.0 |
| Pool 6 | 2.6 | 0.3 | 11.6 | 0.3 | 12.9 |
## Reproducibility Study
Reproducibility of the Access hsTnI assay was evaluated on the DxC 500i instrument platform following CLSI EP05-A3 guideline. Reproducibility panel testing consisted of six serum samples and six lithium heparin plasma samples with troponin concentrations across the measuring range tested in replicates of three, in two runs per day, separated by at least 2 hours between runs, for five (5) days, generating thirty measurements for each panel at each of three sites with a single instrument per site, for a total of 90 measurements per panel overall. The reproducibility %CV and SD results for this study are shown below:
| DxC 500i Reproducibility - Serum | | | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | Mean (pg/mL) | Reproducibility | | Repeatability | | Between-Site | | Between-Lot | | Between-Day | | Between-Run |
| | | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| Panel 1 | 10.32 | 0.40 | 3.9 | 0.37 | 3.6 | 0.13 | 1.2 | 0.003 | 0.0 | 0.108 | 1.0 | 0 |
| Panel 2 | 21.30 | 0.80 | 3.8 | 0.69 | 3.2 | 0.32 | 1.5 | 0.063 | 0.3 | 0.246 | 1.2 | 0 |
| Panel 3 | 97.27 | 4.38 | 4.5 | 3.06 | 3.1 | 2.19 | 2.3 | 0.750 | 0.8 | 2.114 | 2.2 | 0 |
| Panel 4 | 4813 | 148.46 | 3.1 | 143.1 | 3.0 | 25.4 | 0.5 | 0.414 | 0.0 | 0 | 0 | 30.49 |
| Panel 5 | 23125 | 753.33 | 3.3 | 706 | 3.1 | 262.9 | 1.1 | 5.697 | 0.0 | 0 | 0 | 0 |
| DxC 500i Reproducibility - Lithium Heparin Plasma | | | | | | | | | | | | |
| Sample | Mean (pg/mL) | Reproducibility | | Repeatability | | Between-Site | | Between-Lot | | Between-Day | | Between-Run |
| | | SD | CV | SD | CV% | SD | CV% | SD | CV% | SD | CV% | SD |
| Panel 0 | 2.509 | 0.269 | 10.7 | 0.183 | 7.3 | 0.17 | 6.7 | 0.010 | 0.4 | 0.047 | 1.9 | 0.088 |
| Panel 1 | 11.831 | 0.572 | 4.8 | 0.412 | 3.5 | 0 | 0 | 0 | 0 | 0.230 | 1.9 | 0.326 |
| Panel 2 | 19.035 | 0.688 | 3.6 | 0.576 | 3.0 | 0.30 | 1.6 | 0.010 | 0.1 | 0.216 | 1.1 | 0.067 |
| Panel 3 | 83.689 | 4.562 | 5.5 | 3.906 | 4.7 | 0.83 | 1.0 | 0.117 | 0.1 | 2.148 | 2.6 | 0.477 |
| Panel 4 | 5006.95 | 223.10 | 4.5 | 131.20 | 2.6 | 176.6 | 3.5 | 33.86 | 0.7 | 15.168 | 0.3 | 0 |
| Panel 5 | 23731.3 | 888.95 | 3.7 | 864.50 | 3.6 | 155.4 | 0.7 | 17.41 | 0.1 | 135.67 | 0.6 | 0 |
K242870 - Page 5 of 9
{5}
Multiple temperature (run and calibration) within laboratory study: The hsTnI assay imprecision was evaluated using lithium heparin plasma samples, under the following temperature conditions:
Calibrating at 18°C and running samples at 18°C, 23°C and 28°C
Calibrating at 23°C and running samples at 18°C, 23°C and 28°C
Calibrating at 28°C and running samples at 18°C, 23°C and 28°C
For each set of temperature conditions, six lithium heparin plasma samples with TnI concentrations of approximately 3, 10, 18, 80, 4000, and 18,000 pg/mL were used in the determination of imprecision. Each sample was assayed in duplicate, in two runs per day, over at least 20 days for a total of 40 runs and 80 replicates for each sample at each of the nine combinations of temperature conditions noted above. Testing was performed on one DxC 500i instrument using one reagent lot and one calibrator lot. The following results from one set of temperature conditions are representative of the results from this precision study:
| Thermal Imprecision Study Results: DxC 500i; Calibration at 18°C; Run at 18°C | | | | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Sample | N | Mean | Repeatability (within-run) | | Between-Run | | Between-Day | | Total (Within-Lab) | |
| | | | SD | CV% | SD | CV% | SD | CV% | SD | CV% |
| Sample 1 | 80 | 3 | 0.22 | 7.2 | 0.20 | 6.6 | 0.00 | 0.0 | 0.3 | 9.8 |
| Sample 2 | 80 | 12 | 0.30 | 2.6 | 0.20 | 1.8 | 0.20 | 1.4 | 0.4 | 3.5 |
| Sample 3 | 80 | 19 | 0.6 | 3.0 | 0.0 | 0.0 | 0.2 | 0.9 | 0.6 | 3.1 |
| Sample 4 | 80 | 93 | 2.0 | 2.2 | 1.2 | 1.3 | 0.4 | 0.4 | 2.4 | 2.6 |
| Sample 5 | 80 | 4413 | 116.4 | 2.6 | 0.1 | 0.0 | 68.5 | 1.6 | 135.1 | 3.1 |
| Sample 6 | 80 | 19786 | 700.6 | 3.5 | 11.2 | 0.1 | 232.8 | 1.2 | 738.3 | 3.7 |
2. Linearity:
The linearity of the Access hsTnI assay on the DxC 500i instrument was evaluated following the recommendations in CLSI EP06-A2 using lithium heparin plasma samples covering the full range of the assay. Testing consisted of 9 sample panels across the measuring range, performed on two instruments using 2 reagent lots and a single calibrator lot. A minimum of seven test replicates per linearity sample were measured using two test runs, four replicates per sample per run. The results are summarized below:
Results; Linear regression equation:
$$y = 0.964x + 0.066$$ (range tested 1.83 to 35152.97 pg/mL)
The largest deviations in recovery in the full AMR results was 5.67%.
3. Analytical Specificity/Interference:
The Analytical Specificity/Interference performance was evaluated in K172787 and the claims are unchanged.
K242870 - Page 6 of 9
{6}
# 4. Assay Reportable Range:
$2.0 - 27,027 \mathrm{pg} / \mathrm{mL}$ .
The sponsor performed studies to evaluate total carryover (intra-assay carryover and intermodule carryover (carryover from the clinical chemistry module to the immunoassay module)) and included a limitation in the labeling describing the carryover observed.
Studies indicate that if a sample with $cTnI > 150,000 \, pg/mL$ ( $ng/L$ ) is tested on an Access 2 system, intra-assay carryover may be observed if Access hsTnI is tested after the high $cTnI$ sample. The extent of carryover observed is directly proportional to the $cTnI$ concentration that is present in the high sample. In studies, the estimated carryover was $3-5 \, pg/mL$ ( $ng/L$ ) from a high sample at $270,000 \, pg/mL$ ( $ng/L$ ) and $5-8 \, pg/mL$ ( $ng/L$ ) from a high sample at $500,000 \, pg/mL$ ( $ng/L$ ).
Additionally, BEC included a second limitation statement to address the inter-assay carryover:
When a sample containing high cardiac troponin (cTnI) $>27,000~\mathrm{pg / mL}$ is tested on an Access Immunoassay other than Access hsTnI, carryover of cTnI may be observed if the next test(s) performed is Access hsTnI. This form of carryover has been observed in the sample immediately following, and up to the third subsequent sample processed after the high cTnI sample. The magnitude of carryover observed is directly proportional to the cTnI concentration present in the high sample. Representative data for the potential magnitude of carryover from samples with different concentrations of cTnI tested is provided below:
| High cTnI Concentration (pg/mL) | Observed Carryover Magnitude (pg/mL) |
| --- | --- |
| ~27,000 | 3.2 |
| ~50,000 | 4.5 |
| ~110,000 | 9.3 |
| ~150,000 | 19.6 |
| ~270,000 | 22.3 |
| ~500,000 | 44.9 |
| ~1,000,000 | 77.8 |
To reduce the risk of inter-assay carryover when testing Access hsTnI on the DxC 500i Clinical Analyzer, it is strongly recommended to test all Access hsTnI samples on a dedicated instrument, separate from other Access Immunoassays.
# 5. Traceability, Stability, Expected Values (Controls, Calibrators, or Methods):
Traceability and stability are the same as described in K222881.
# 6. Detection Limit:
Studies were performed to determine the Limit of Blank (LoB), Limit of Detection
K242870 - Page 7 of 9
{7}
(LoD) and Limit of Quantitation (LoQ) for the Access hsTnI assay on the DxC 500i instrument following the recommendations in CLSI EP17-A2.
The study protocol was carried out on three DxC 500i analyzers, which tested one reagent lot each. The LoB evaluation required a total of 60 replicates on each instrument by running four test samples, five replicates in a single test run, one run per day for three days. Four separate lots of zero-level (S0) Access hsTnI calibrator served as the four LoB test samples. For the LoD and LoQ experiment, a total of 45 replicates were generated per test sample on each instrument by testing nine replicates per sample per test run and completing one run per day for five days. For estimation of LoD and LoQ, 13 lithium heparin plasma samples containing low levels of hsTnI analyte were measured. These studies support the sponsor's claimed measuring range of 2.0 pg/mL to 27,027 pg/mL.
## Thermal Sensitivity Study
A second study was performed to evaluate the LoQ of the Access hsTnI assay across various calibration and run temperatures. 13 lithium heparin plasma samples containing low concentrations of Troponin I analyte were tested on one DxC 500i analyzer at each of three ambient run and calibration temperatures (18°C, 23°C, and 28°C). A total of 45 replicates were generated per test sample per temperature on each instrument by testing nine replicates per sample per test run and completing one run per day for five days.
These studies support the sponsor's claimed measuring range of 2.0 pg/mL to 27,027 pg/mL.
## 7. Assay Cut-Off:
Not applicable.
## B Comparison Studies:
### 1. Method Comparison with Predicate Device:
A Method Comparison study conducted at three (3) testing sites evaluated 208 unique intended use lithium heparin samples with two (2) lots of reagents used at each site. One (1) calibrator lot was used for all testing. Results of this method comparison study were analyzed using Weighted Deming regression model and representative results of a single site are summarized below:
| N | Intercept [95% CI] | Slope [95% CI] | Correlation Coefficient (r) |
| --- | --- | --- | --- |
| 208 | 0.49 [0.30 - 0.77] | 0.97 [0.95 - 0.98] | 0.999 |
A second method comparison study was conducted to determine the equivalency of serum. Testing occurred over multiple days using DxC 500i clinical analyzer-Access 2 instrument pairs, with a single lot of hsTnI and calibrator. Representative results of the study are summarized below:
K242870 - Page 8 of 9
{8}
| Range | N | Passing Bablok Regression | | | | |
| --- | --- | --- | --- | --- | --- | --- |
| | | Slope | | Intercept | | Correlation Coefficient |
| | | Estimate | 95% CI | Estimate | 95% CI | |
| 2.12 – 23,211 | 98 | 1.0 | (0.99, 1.02) | -0.245 | (-0.670, 0.068) | 1.0 |
**Thermal Method Comparison Study:**
The sponsor also performed thermal method comparison studies that show that the performance of the candidate device at different calibration and run temperature conditions is unchanged from K172787.
**Matrix Comparison:**
Not applicable.
**C Clinical Studies:**
1. **Clinical Sensitivity:**
The sponsor provided information to support that the modification to the candidate device did not impact the clinical performance claims described in K172787.
2. **Clinical Specificity:**
See clinical sensitivity above.
3. **Other Clinical Supportive Data (When 1. and 2. Are Not Applicable):**
Not applicable.
**D Clinical Cut-Off:**
The sponsor provided information to support that the modification to the candidate device did not impact the clinical cutoffs described in K172787.
**E Expected Values/Reference Range:**
The sponsor provided information to support that the modification to the candidate device did not impact the 99th percentile upper reference limits described in K172787.
**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.
K242870 - Page 9 of 9
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.