Remnant de-identified human serum samples; Remnant de-identified human urine samples
Remnant clinical samples were used to conduct method comparison studies to demonstrate substantial equivalence between the new device and the predicate device/IDMS reference method.
Human serum samples; Sample Size: 48; Number of Sites: 1 (Internal Siemens R&D)
IDMS Reference Method
Linear regression (Slope, Intercept, Correlation Coefficient)
Indications for Use
The CRE2 method is an in vitro diagnostic test for the quantitative measurement of creatinine in human serum, plasma, and urine on the Dimension® clinical chemistry system. Creatinine measurements are used in the diagnosis and treatment of certain renal diseases, in monitoring renal dialysis, and as a calculation basis for measuring other urine analytes.
Device Story
The Dimension® Creatinine (CRE2) Flex® reagent cartridge is an in vitro diagnostic reagent system used on the Dimension® clinical chemistry system. It utilizes a modified kinetic Jaffe technique where creatinine reacts with picrate in a strong base (sodium hydroxide) to form a red chromophore. Potassium ferricyanide is included to oxidize bilirubin and prevent interference. The system measures the rate of increasing absorbance at 510 nm and 600 nm (bichromatic rate technique), which is directly proportional to creatinine concentration. The device is operated by trained laboratory technicians in a clinical laboratory setting. Output is a quantitative creatinine concentration value used by clinicians to diagnose and treat renal disease, monitor dialysis, and calculate other urine analytes.
Clinical Evidence
Bench testing only. Precision studies (repeatability and intermediate precision) performed per CLSI EP5-A2 across serum and urine pools. Linearity validated with R²=0.9999 for both serum and urine. Analytical sensitivity (LoB, LoD, LoQ) determined per CLSI EP17-A2. Interference testing performed per CLSI EP7-A2. Method comparison against predicate (k925668) using 191 serum and 113 urine samples showed high correlation (r=0.999 and r=0.996 respectively). Reference ranges validated per CLSI C28-A3c.
Technological Characteristics
Quantitative, photometric/colorimetric assay using modified kinetic Jaffe methodology. Reagents: Lithium Picrate (125 mM) and Sodium Hydroxide (2000 mM) with potassium ferricyanide (2.7 mM). Detection: Bichromatic rate (510/600 nm). Form factor: Flex® reagent cartridge for Dimension® EXL 200 system. Calibration: 3-level Chem 1 Calibrator (DC18C), traceable to NIST SRM 914a. Connectivity: Integrated with Dimension® clinical chemistry system.
Indications for Use
Indicated for quantitative measurement of creatinine in human serum, plasma, and urine to aid in diagnosis and treatment of renal diseases, monitoring renal dialysis, and as a calculation basis for other urine analytes.
Regulatory Classification
Identification
A creatinine test system is a device intended to measure creatinine levels in plasma and urine. Creatinine measurements are used in the diagnosis and treatment of renal diseases, in monitoring renal dialysis, and as a calculation basis for measuring other urine analytes.
Predicate Devices
Dimension® clinical chemistry system Creatinine (CREA) Flex® reagent cartridge (k925668)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY ONLY TEMPLATE
A. 510(k) Number:
k132638
B. Purpose for Submission:
New device
C. Measurand:
Creatinine
D. Type of Test:
Quantitative, photometric/colorimetric method
E. Applicant:
Siemens Healthcare Diagnostics Inc.
F. Proprietary and Established Names:
Dimension® Creatinine (CRE2) Flex® reagent cartridge
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| CGX | Class II | Creatinine test system (21CFR 862.1225) | 75-Chemistry |
H. Intended Use:
1. Intended use(s):
See indications for use below.
{1}
2. Indication(s) for use:
The CRE2 method is an in vitro diagnostic test for the quantitative measurement of creatinine in human serum, plasma, and urine on the Dimension® clinical chemistry system. Creatinine measurements are used in the diagnosis and treatment of certain renal diseases, in monitoring renal dialysis, and as a calculation basis for measuring other urine analytes.
3. Special conditions for use statement(s):
Not applicable
4. Special instrument requirements:
Dimension® EXL 200 clinical chemistry system
I. Device Description:
Dimension® Creatinine (CRE2) Flex® reagent cartridge includes two major reagents. Reagent 1 consists of 125 mM Lithium Picrate and reagent 2 consists of 2000 mM Sodium Hydroxide with 2.7 mM potassium ferricyanide.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Dimension® clinical chemistry system Creatinine (CREA) Flex® reagent cartridge
2. Predicate 510(k) number(s):
k925668
3. Comparison with predicate:
Similarities
| | Dimension® Creatinine (CRE2) Flex® reagent cartridge (Candidate device) | Dimension® clinical chemistry system Creatinine (CREA) Flex® reagent cartridge (Predicate Device) k925668 |
| --- | --- | --- |
| Intended Use | The CRE2 method is an in vitro diagnostic test for the quantitative measurement of creatinine in human serum, plasma, and urine on the Dimension® clinical chemistry system. Creatinine measurements are used in the diagnosis and treatment of certain renal diseases, in monitoring renal dialysis, and as a calculation basis for measuring other urine analytes. | Same |
{2}
3
| Device Technology (detection) | Modified Jaffe Methodology (creatinine alkaline picrate) with photometric detection | Same |
| --- | --- | --- |
| Detection Conditions | Wavelength = 510 and 600 nm
Type of Measurement = Bichromatic rate | Same |
| Sample Volume | 20 μL | Same |
| Reagents | Reagent 1 = Lithium Picrate (125 mM)
Reagent 2 = Sodium Hydroxide (2000 mM) with potassium ferricyanide (2.7 | Same |
| Reagent Volumes | Volume of Reagent 1 used = 74 μL
Volume of Reagent 2 used = 18 μL
Volume of Diluent used = 258 μL | Same |
| Calibration Interval | 90 days - same reagent lot | Same |
| Limit of Blank/Analytical Sensitivity | Limit of Blank: 0.05 mg/dL | Analytical Sensitivity: 0.05 mg/dL |
| Calibration | Chem 1 Calibrator (DC18C)
3 levels (n=3) | Same |
## Differences
| | Dimension® Creatinine (CRE2) Flex® reagent cartridge (Candidate device) | Dimension® clinical chemistry system Creatinine (CREA) Flex® reagent cartridge (Predicate Device) k925668 |
| --- | --- | --- |
| Measuring Range (serum) | 0.15 - 20.00 mg/dL | 0 - 20.0 mg/dL |
| Measuring Range (urine) | 5.00 - 400.00 mg/dL | 0 - 200.0 mg/dL |
| Expected Values | Serum and Plasma
Males: 0.70 - 1.30 mg/dL
Females: 0.55 - 1.02 mg/dL
Urine
Males: 0.95 - 2.49 g/24 hr
Females: 0.60 - 1.80 g/24 hr | Serum
Males: 0.8 - 1.3 mg/dL
Females: 0.6 - 1.0 mg/
Urine
Males: 0.6 - 2.5 g/24 hr
Females: 0.6 - 1.5 g/24 hr |
| Interferences | No significant interference at a Creatinine concentration of 1.5 mg/dL from:
Hemoglobin at 500 mg/dL Bilirubin (conjugated) at 20 mg/dL, Bilirubin (unconjugated) at 10 mg/dL
Lipemia (Intralipid) at 1000 mg/dL. | No significant interference at a Creatinine concentration of 1.7 mg/dL from:
Hemoglobin at 1000 mg/dL, Bilirubin (unconjugated) at 5 mg/dL
Lipemia (Intralipid) at 200 mg/dL |
{3}
4
K. Standard/Guidance Document Referenced (if applicable):
- CEN 13640: Stability Testing of In Vitro Diagnostic Reagents
- CLSI EP07-A2: Interference Testing in Clinical Chemistry; Approved Guideline
- CLSI EP09-A2-IR Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline
- CLSI EP05-A2: Evaluation of Precision Performance of Quantitative Measurement Methods: Approved Guideline
- CLSI EP-06-A: Evaluation of the Linearity of Quantitative Measurement
- CLSI EP17-A2: Protocols for Determination of Limits of Detection and Limits of Quantitation
- CLSI C28-A3c: Defining, Establishing, and Verifying Reference Intervals in the Clinical Laboratory; Approved Guideline- Third Edition
L. Test Principle:
Dimension® Creatinine (CRE2) Flex® reagent cartridge is used to measure the creatinine concentration in human serum, plasma, and urine on the Dimension® clinical chemistry system using quantitative, photometric/colorimetric methods. The CRE2 method uses a modified kinetic Jaffe technique to measure the creatinine concentration. In the presence of a strong base such as sodium hydroxide, picrate reacts with creatinine to form a red chromophore. The system monitors rate of increasing absorbance at 510 nm due to the formation of this chromophore is directly proportional to the creatinine concentration in the sample and is measured using a bichromatic (510, 600nm) rate technique. Bilirubin is oxidized by potassium ferricyanide to prevent interference.
M. Performance Characteristics (if/when applicable):
The following data represent typical method performance. These data were collected on the Dimension EXL 200 integrated chemistry system.
1. Analytical performance:
a. Precision/Reproducibility:
Within-run (repeatability) and total imprecision (Intermediate precision) studies for the Dimension® Creatinine (CRE2) Flex® reagent cartridge were designed from CLSI Guideline EP5- A2, “Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline – Second Edition.”
The precision/repeatability study was performed using two (2) serum pools, three (3) levels of BioRad Multiqual serum material, two (levels) of BioRad Liquicheck urine material and two (2) urine pool.
The samples were tested on Dimension® clinical chemistry system using five different creatinine concentrations 0.71, 1.32, 1.79, 7.04 and 15.79 mg/dL, respectively. The urine was tested with four different creatinine concentrations 39.31,
{4}
62.28, 142.80 and 339.56 mg/dL, respectively. For intermediate precision, testing was performed over twenty (20) days, two (2) separate runs with two test samples for each test material. The results are summarized below:
| | | | Repeatability | | Within-Lab | |
| --- | --- | --- | --- | --- | --- | --- |
| Sample | | Mean (mg/dL | SD | %CV | SD | %CV |
| Serum | Serum Pool 1 | 1.32 | 0.04 | 3.0 | 0.04 | 3.2 |
| | Serum Pool 2 | 15.79 | 0.19 | 1.2 | 0.19 | 1.2 |
| | BioRad Multiqual Level 1 | 0.71 | 0.03 | 4.7 | 0.04 | 5.1 |
| | BioRad Multiqual Level 2 | 1.79 | 0.04 | 2.1 | 0.05 | 2.8 |
| | BioRad Multiqual Level 3 | 7.04 | 0.07 | 1.0 | 0.09 | 1.3 |
| | | | | | | |
| Urine | Urine Pool 1 | 39.31 | 1.52 | 3.9 | 1.53 | 3.9 |
| | Urine Pool 2 | 339.56 | 4.28 | 1.3 | 4.59 | 1.4 |
| | BioRad Liquicheck Level 1 | 62.28 | 0.61 | 1.0 | 1.41 | 2.3 |
| | BioRad Liquicheck Level 2 | 142.80 | 1.56 | 1.1 | 3.39 | 2.4 |
b. Linearity/assay reportable range:
1) Serum samples
Samples were prepared by using serum spiked with creatinine stock at mean concentrations of 0, 0.34, 0.69, 1.38, 2.75, 5.50, 8.25, 11.00, 13.75, 16.50, 19.25, 22 mg/dL in serum for Dimension® clinical chemistry system. At each creatinine level, 5 replicates were tested. Values from the 12 levels were compared with previously established target values. The results from regression analysis are summarized below:
$$
Y = 1.0063x + 0.1027, R^2 = 0.9999
$$
The results of the linearity study support the claimed measuring range of 0.15 - 20.00 mg/dL for creatinine in Dimension® Creatinine (CRE2) Flex® reagent cartridge
2) Urine samples
The samples were prepared by urine spiked with glucose stock at mean concentrations of and 2.61, 9.22, 15.82, 29.03, 55.45, 108.29, 161.13, 213.98, 266.82, 319.66, 372.50, 425.34 mg/dL in urine for Dimension® clinical chemistry system. At each creatinine level, 5 replicates were tested. Values from
{5}
the 12 levels were compared with previously established target values. The results from regression analysis are summarized below:
$$
\mathrm {Y} = 0. 9 9 8 3 \mathrm {x} + 0. 4 1 0 3, \mathrm {R} ^ {2} = 0. 9 9 9 9
$$
The results of the linearity study support the claimed measuring range of 5-400 mg/dL for creatinine in Dimension® Creatinine (CRE2) Flex® reagent cartridge
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability, stability and value assignment -
Traceability and value assignment: The values assigned to Dimension CHEM1 calibrator for creatinine are traceable to NIST SRM 914a. NIST SRM914a is an Isotope Dilution-Liquid Chromatography/ Mass Spectrometry (IDMS) traceable standard. The commutability of the creatinine working standards is verified using recovery of NIST SRM 967, an IDMS traceable, commutable, and frozen serum creatinine reference material. Dimension Instruments are calibrated with the working standards and used to assign the product calibrators via the standard value assignment process. The CHEM I calibrator described in the Dimension Creatinine (CRE2) labeling was previously cleared. The 510(k) number for this product is K860021.
A Flex® cartridge open well stability study was conducted to ensure the reagents perform consistently throughout the claimed open well stability which is 3 days. The protocol and acceptance criteria were found adequate.
d. Detection limit:
The Limit of Blank, Limit of Detection and Limit of Quantitation of Dimension® Creatinine (CRE2) Flex® reagent cartridge were determined according to CLSI EP17-A2 in the following manner:
LoB = Mean of Blank Measurement + 1.645 x Standard Deviation of Blank Measurements
LoD = Limit of Blank + CpSDs
- Cp is a correction factor for the 95% CI normal variate to account for bias in the SDS estimate.
- SDS is an estimate of method imprecision pooled from replicates of the low analyte samples
The Limit of Quantitation (LoQ) for the Dimension® Creatinine (CRE2) Flex® reagent cartridge for serum and plasma is 0.15 mg/dL and based on allowable total error of 0.15 mg/dL, determined consistent with CLSI Guideline EP17-A2.
6
{6}
Based upon the results, the results are as follows:
| Dimension® CRE2 Limit of Detection Results with Serum | | |
| --- | --- | --- |
| Limit | Protocol | Value |
| LoB | 4 samples with no analyte were tested (N=5) for 3 days, one run per day, 2 reagent lots, | 0.05 mg/dL |
| LoD | 4 low patient serum samples were tested (N=5) for 3 days, one run per day, 2 reagent lots | 0.1 mg/dL |
| LoQ | LoQ was determined by evaluating 4 low level samples with multiple replicates over 3 days multiple measurements per sample. Sponsor defined LoQ as concentration with 20% CV inter-precision at the 95% confidence limit. | 0.15 mg/dL |
| Dimension® CRE2 Limit of Detection Results with Urine | | |
| --- | --- | --- |
| Limit | Protocol | Value |
| LoB | 4 samples with no analyte were tested (N=5) for 3 days, one run per day, 2 reagent lots, | 1.00 mg/dL |
| LoD | 4 low patient urine samples were tested (N=5) for 3 days, one run per day, 2 reagent lots | 2.00 mg/dL |
| LoQ | LoQ was determined by evaluating 4 low level samples with multiple replicates over 3 days multiple measurements per sample. Sponsor defined LoQ as concentration with 20% CV inter-precision at the 95% confidence limit. | 5.00 mg/dL |
{7}
The claimed measuring range is 0.15 - 20.00 and 5 - 400 mg/dL for serum and urine creatinine in Dimension® Creatinine (CRE2) Flex® reagent cartridge respectively based on LoQ and linearity.
See linearity study in M.1.b of this 510(k) decision summary.
e. Analytical specificity:
Interference studies were performed for the creatinine measurement function by evaluating potential interfering substances spiked into serum and urine pools at two different creatinine levels, 1.5 and 5.0 mg/dL for serum/plasma, 40 to 175 mg/dL for urine. CLSI EP7A2 was followed for the interference testing. Substances were spiked into serum and urine pool to assess common or known substances which could interfere with the Dimension® Creatinine (CRE2) Flex® reagent cartridge. The sponsor defines interference as bias exceeding 10%. The following substances produced less than 10% deviation when tested on Dimension® Creatinine (CRE2) Flex® reagent cartridge at levels equal to the concentrations listed below.
Serum/Plasma
| Substance | Concentration of Substance (mg/dL) |
| --- | --- |
| Acetaminophen | 20 |
| Acetoacetate | 20 |
| Amikacin | 8 |
| Ampicillin | 5.3 |
| Ascorbic Acid | 6 |
| Caffeine | 6 |
| Carbamazepine | 3 |
| Cephalexin | 25 |
| Cephapirin | 25 |
| Cephradine | 25 |
| Chloramphenicol | 5 |
| Chlordiazepoxide | 1 |
| Chlorpromazine | 0.2 |
| Cholesterol Supertrate | 503 |
| Cimetidine | 2 |
| Dextran 40 | 6000 |
| Diazepam | 0.51 |
| Digoxin | 6.1ng/mL |
| EDTA | 200 |
| Erythromycin | 6 |
| Ethanol | 400 |
| Ethosuximide | 25 |
| Furosemide | 6 |
| Gentamicin | 1 |
{8}
9
| Ibuprofen | 50 |
| --- | --- |
| Immunoglobulin G (IgG) | 5000 |
| Isopropanol | 1.0 g/dL |
| Lidocaine | 1.2 |
| Lithium | 2.2 |
| Nicotine | 0.1 |
| Nortriptyline | 1000 ng/mL |
| Penicillin G (1654 | 25 U/mL |
| Pentobarbital | 8 |
| Phenobarbital | 10 |
| Phenytoin | 5 |
| Potassium oxalate | 500 mg/dL |
| Primidone | 4 |
| Propoxyphene | 0.16 |
| Protein, Albumin | 6000 |
| Protein, Total | 12g/dL |
| Salicylic acid | 60 |
| Sodium fluoride | 400 |
| Theophylline | 4 |
| Urea | 500 |
| Uric acid | 20 |
| Valproic acid | 50 |
| Vancomycin | 10 |
Urine
| Substance | Concentration of Substance (mg/dL) |
| --- | --- |
| 50% Acetic Acid | 25mL/24 hr collection |
| 6N Hydrochloric Acid | 0.6% |
| 6N Nitric Acid | 0.6% |
| Acetone | 100 mg/dL |
| Bilirubin (conjugated) | 2 mg/dL |
| Boric Acid | 1% w/v |
| Ethanol | 1 g/dL |
| Gamma Globulin | 0.5 g/dL |
| Glucose | 2 g/dL |
| Hemoglobin | 115 mg/dL |
| Human Serum Albumin | 0.5 g/dL |
| Oxalic Acid | 0.1 g/dL |
| Sodium Carbonate | 5g/24 hr collection |
| Sodium Fluoride | 1% w/v |
The following substances had no significant interference (less than 10% interference) when tested on Dimension® Creatinine (CRE2) Flex® reagent cartridge at the concentrations listed below.
{9}
Serum/plasma
| Substance | Concentration of Substance |
| --- | --- |
| Acetone | 9.375 mg/dL |
| Bilirubin (unconj) | 10 mg/dL |
| Bilirubin (conjugated) | 20 mg/dL |
| Cefoxitin | 3.75 mg/dL |
| Cephalothin | 10.0 mg/dL |
| Glucose | 400 mg/dL |
| Intralipid 20% | 1000 mg/dL |
| Pyruvate | 5.26 mg/dL |
| Triglycerides | 2500 mg/dL |
Urine
| Substance | Concentration of Substance |
| --- | --- |
| Ascorbic Acid | 0.10 g/dL |
f. Assay cut-off:
Not applicable.
2. Comparison studies:
a. Method comparison with predicate device:
A total of 191 serum, and 113 urine samples were tested with the Dimension CREA assay cleared under K925668 (Method X) and the candidate Dimension® Creatinine (CRE2) Flex® reagent cartridge (Method Y)
The results across the full assay range were analyzed by linear regression.
Serum and urine samples were analyzed in singlicate and samples tested ranged from 0.4-19.8 mg/dL and 13.5-372.7 mg/dL respectively.
| Comparative Method | Range (mg/dL) | Slope | Intercept (mg/dL) | Correlation Coefficient | n | Sample type |
| --- | --- | --- | --- | --- | --- | --- |
| Dimension CREA Assay | 0.4 – 19.8 | 1.00 | -0.08 | 0.999 | 191 | serum |
| Dimension CREA Assay | 13.5 – 372.7 | 1.04 | -3.58 | 0.996 | 113 | urine |
{10}
# b. Matrix comparison:
Fifty six (56) serum and lithium heparin plasma samples were tested on the Dimension® Creatinine (CRE2) Flex® reagent cartridge. One replicate of each sample was processed. All samples in the study were fresh and never frozen. The eight spiked sample sets were prepared by spiking equal amounts of purified creatinine into the matched serum and lithium heparin plasma samples. The samples ranged from 0.5-17.35 mg/dL
The following table summarizes the matrix comparison studies:
| Serum vs. | Slope | Intercept | Correlation Coefficient (r) | Range | n |
| --- | --- | --- | --- | --- | --- |
| Lithium Heparin Plasma | 1.05 | -0.02 | 0.998 | 0.50 – 17.35 | 56 |
The study demonstrated that serum and is equivalent to lithium heparin plasma for the Dimension CRE2 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:
Serum/Plasma
Transference defined in CLSI C28-A3c was used to validate established reference ranges for serum and plasma creatinine following CLSI C28-A3c. Serum samples from forty normal healthy adult female donors and forty-three normal healthy adult male donors were tested $N = 1$ using the Dimension CRE2 assay. The range was considered validated if $\leqslant 10\%$ of the samples fell outside of established range.
{11}
| | Males | Females |
| --- | --- | --- |
| Reference Range | 0.70-1.30 g/day | 0.55-1.02 g/day |
| N | 43 | 40 |
| Outside Range # | 2 | 1 |
| % Outside Range | 4.7% | 2.5% |
These data support the published ranges for Males (0.7 to 1.3 mg/dL (Tietz 1999) and Females (0.55 to 1.02 mg/dL (Clin Chem 54:3 (2008)).
Urine
Published reference ranges were validated for urine specimens using samples from twenty normal healthy adult female donors and twenty-two normal healthy adult male donors following CLSI C28-A3c. Samples were processed N=1 using the Dimension CRE2 assay. The range was considered validated if ≤10% of the samples fell outside of established range.
| | Males | Females |
| --- | --- | --- |
| Reference Range | 0.95-2.49 g/day | 0.6-1.80 g/day |
| N | 22 | 20 |
| Outside Range # | 2 | 1 |
| % Outside Range | 9.10% | 5.00% |
The above data support the published ranges for Males (0.95 to 2.49 g/day (Clin Chem Acta 344 (2004) 137-148) and Females (0.6 to 1.8 g/day (Tietz 1999)).
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.