K061830 · Nova Biomedical Corp. · CIG · Nov 1, 2006 · Clinical Chemistry
Device Facts
Record ID
K061830
Device Name
STAT PROFILE CRITICAL CARE XPRESS (CCX), MODEL 1+
Applicant
Nova Biomedical Corp.
Product Code
CIG · Clinical Chemistry
Decision Date
Nov 1, 2006
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1110
Device Class
Class 2
Indications for Use
The Stat Profile Critical Care Xpress Analyzer is intended for in vitro diagnostic use by health care professionals and for point-of-care usage in the quantitative determination of pH, PCO2, PO2, SO2%, Hematocrit (Hct), total Hemoglobin (tHb), Oxyhemoglobin (O2Hb), Carboxyhemoglobin (COhb), Methemoglobin (MetHb), Reduced Hemoglobin (HHb), Oxygen content (O2Ct), Oxygen capacity (O2Cap), and total Bilirubin (tBil) in heparinized whole blood; Na+, K+, Cl-, Ca++, Mg++, Glucose (Glu), Lactate (Lac), BUN (Urea), and Creatinine (Creat) in heparinized whole blood, serum, or plasma. Total Bilirubin (tBil) was not evaluated on neonatal samples. The intended use of the Nova Stat Profile Critical Care Xpress CO-Oximeter Calibration Cartridge with Bilirubin and Deproteinizing Solution is for the quantitative determination of total hemoglobin, oxyhemoglobin, carboxyhemoglobin, methemoglobin, deoxyhemoglobin and total bilirubin in human blood using the Nova Stat Profile Critical Care Xpress Analyzer. Nova Stat Profile Critical Care Xpress CO-Oximeter Controls and Auto cartridge QC are intended for in vitro diagnostic use by healthcare professionals for monitoring the performance of Nova Biomedical Stat Profile Critical Care Xpress Analyzers.
Device Story
Stat Profile Critical Care Xpress (CCX) Analyzer performs quantitative total bilirubin measurement in heparinized whole blood; utilizes existing spectrophotometer hardware; adds new software algorithm for direct bilirubin detection at specific wavelength. Device used in point-of-care or clinical settings by healthcare professionals. Input: heparinized whole blood sample. Output: quantitative total bilirubin concentration (mg/dL). Healthcare providers use output for clinical decision-making regarding patient bilirubin levels. Benefits: rapid, point-of-care assessment of bilirubin alongside existing blood gas/electrolyte panels.
Clinical Evidence
No clinical data provided; bench testing only.
Technological Characteristics
Quantitative absorbance assay; spectrophotometry; benchtop analyzer. Measures total bilirubin directly via specific wavelength. Calibrators/controls traceable to NIST SRM 916A. Connectivity: standalone. Software-based algorithm for analyte quantification.
Indications for Use
Indicated for quantitative determination of total bilirubin in heparinized whole blood for adult patients. Not for use on neonates. For prescription use by healthcare professionals in point-of-care or clinical settings.
Regulatory Classification
Identification
A bilirubin (total or direct) test system is a device intended to measure the levels of bilirubin (total or direct) in plasma or serum. Measurements of the levels of bilirubin, an organic compound formed during the normal and abnormal distruction of red blood cells, if used in the diagnosis and treatment of liver, hemolytic hematological, and metabolic disorders, including hepatitis and gall bladder block.
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k061830
B. Purpose for Submission:
Addition of the detection of total bilirubin to the Nova Stat Profile Clinical Care Xpress (CCX) System.
C. Measurand:
Bilirubin, Total
D. Type of Test:
Quantitative Absorbance Assay
E. Applicant:
Nova Biomedical Corporation
F. Proprietary and Established Names:
Nova Stat Profile Clinical Care Xpress (CCX 1+) System
G. Regulatory Information:
1. Regulation section:
21 CFR § 862.1110, Bilirubin (total or direct) test system
21 CFR § 862.1150, Calibrator, Secondary Control
21 CFR § 862.1660, Quality control material (assayed and unassayed)
2. Classification:
Class II (Assay)
Class II (Calibrator)
Class I, reserved (General Controls)
3. Product code:
CIG, diazo colorimetry, bilirubin
JIT, calibrator, secondary
JJY, multi-analyte controls, all kinds (assayed and unassayed)
4. Panel:
75 (Clinical Chemistry)
H. Intended Use:
1. Intended use(s):
See Indications for use.
2. Indication(s) for use:
The Stat Profile Critical Care Xpress Analyzer is intended for in vitro diagnostic use by health care professionals and for point-of-care usage in the quantitative determination of pH, PCO2, PO2, SO2%, Hematocrit (Hct), total Hemoglobin (tHb), Oxyhemoglobin (O2Hb), Carboxyhemoglobin (COhb), Methemoglobin (MetHb), Reduced Hemoglobin (HHb), Oxygen content (O2Ct), Oxygen capacity (O2Cap), and total Bilirubin (tBil) in heparinized whole blood; Na+, K+, Cl-, Ca++, Mg++, Glucose (Glu), Lactate (Lac), BUN (Urea), and Creatinine (Creat) in heparinized whole blood, serum, or plasma. Total Bilirubin (tBil) was not evaluated on neonatal samples.
{1}
The intended use of the Nova Stat Profile Critical Care Xpress CO-Oximeter Calibration Cartridge with Bilirubin and Deproteinizing Solution is for the quantitative determination of total hemoglobin, oxyhemoglobin, carboxyhemoglobin, methemoglobin, deoxyhemoglobin and total bilirubin in human blood using the Nova Stat Profile Critical Care Xpress Analyzer.
Nova Stat Profile Critical Care Xpress CO-Oximeter Controls and Auto cartridge QC are intended for in vitro diagnostic use by healthcare professionals for monitoring the performance of Nova Biomedical Stat Profile Critical Care Xpress Analyzers.
3. Special conditions for use statement(s):
For prescription use. Not for use on neonates.
4. Special instrument requirements:
Nova Stat Profile Clinical Care Xpress (CCX 1+) System
I. Device Description:
The Nova Stat Profile Clinical Care Xpress System was previously cleared under 510(k)s k020297 and k022746. The current submission (k061830) is for the addition of total bilirubin to the analytes measured by the instrument. Total Bilirubin is an in vitro diagnostic assay for the quantitative determination of total bilirubin in human heparinized whole blood. The calibrators or controls that are available are traceable to NIST Standard Reference Material 916A Bilirubin.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Dade Dimension RXL, Radiometer ABL 800 Flex
2. Predicate 510(k) number(s):
k840777 and k050869 respectively.
3. Comparison with predicate:
| Comparison | | | |
| --- | --- | --- | --- |
| Item | Device | Predicate (Dimension RXL) | Predicate (ABL 800 Flex) |
| Analyte | Total Bilirubin | Total Bilirubin | Total Bilirubin |
| Operating Principle | Spectrophotometry, Direct | Spectrophotometry, Indirect | Spectrophotometry, Direct |
| Measuring Range | 0.5-35.1 mg/dL | 0-25 mg/dL | 0-23.4 mg/dL test range 0-58.5 mg/dL measuring range |
| Sample Size | 110 μL | 65 μL | 85 μL |
| Cycle Time | 100 seconds | 12 minutes | 145 seconds |
| Calibration | Automatic for total hemoglobin/bilirubin | Manual for total bilirubin | Manual for total hemoglobin |
| Analyzer Type | Bench top | Floor model | Bench top |
| Calibrators | One level | Three levels | One level |
| Controls | Three levels | Three levels | Four levels |
{2}
3
K. Standard/Guidance Document Referenced (if applicable):
None identified.
L. Test Principle:
The sample collection, preparation, and application to the analyzer is the same as for the previously cleared CCX model. The existing spectrophotometer in the analyzer is used to measure total bilirubin directly at a specific wavelength accomplished through the addition of a new algorithm in the instrument software.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Within-run precision was determined by measuring twenty (20) replicates of a given sample on two different analyzers. The samples analyzed were NOVA CO-Oximeter Controls Levels 7 (3.4 - 4.6 mg/dL), 8 (8.8 - 11.2 mg/dL), 9 (17.6 - 22.4 mg/dL) and whole blood. Heparinized whole blood was analyzed twenty (20) consecutive times on the STP CCX1+ CO-Oximeter. The whole blood samples were modified to yield bilirubin concentrations of 1 mg/dL and 12 mg/dL. Results are summarized below.
Control Level 7 Within Run Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 20 | 4.2 | 0.04 | 0.87 |
| 2 | Total Bilirubin | 20 | 4.0 | 0.05 | 1.30 |
Control Level 8 Within Run Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 20 | 10.1 | 0.15 | 1.53 |
| 2 | Total Bilirubin | 20 | 9.8 | 0.14 | 1.42 |
Control Level 9 Within Run Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 20 | 19.5 | 0.19 | 0.97 |
| 2 | Total Bilirubin | 20 | 19.8 | 0.09 | 0.48 |
{3}
4
Whole Blood Within Run Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 20 | 1.2 | 0.07 | 6.69 |
| 2 | Total Bilirubin | 20 | 1.0 | 0.09 | 8.81 |
| 1 | Total Bilirubin | 20 | 12.7 | 0.36 | 2.84 |
| 2 | Total Bilirubin | 20 | 12.1 | 0.40 | 3.33 |
Day to Day precision was determined by triplicate measurements of a given sample on each of 20 test runs over 20 days. The samples analyzed were the NOVA CO-Oximeter Controls Levels 7, 8, and 9. Results are summarized below.
Control Level 7 Day to Day Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 60 | 4.2 | 0.08 | 1.82 |
| 2 | Total Bilirubin | 60 | 4.0 | 0.08 | 1.93 |
Control Level 8 Day to Day Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 60 | 10.1 | 0.16 | 1.60 |
| 2 | Total Bilirubin | 60 | 10.0 | 0.19 | 1.87 |
Control Level 9 Day to Day Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 60 | 20.1 | 0.30 | 1.52 |
| 2 | Total Bilirubin | 60 | 20.0 | 0.30 | 1.52 |
Precision of the STP CCX1 + COOX in the high end of the claimed total bilirubin reference range (0.2 to 1.0 mg/dL) was determined by measuring day to day precision of a bilirubin concentration of 1.0 mg/dL. The day to day precision was determined by analyzing triplicate measurements of these samples in 20 runs over 10 days on two instruments. Results are summarized below.
{4}
Normal Level Day to Day Precision
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | Total Bilirubin | 60 | 1.1 | 0.05 | 4.78 |
| 2 | Total Bilirubin | 60 | 1.0 | 0.07 | 6.53 |
# b. Linearity/assay reportable range:
The measuring range of the device (0.5 to $35.1\mathrm{mg / dL}$ ) was evaluated by comparing the two modes of the device, COOX only mode (using a $115~\mu \mathrm{L}$ sample volume) and COOX with ABG mode (using a $210~\mu \mathrm{L}$ sample volume). Of the 80 samples, seven samples ranging from 0.1 to $0.7\mathrm{mg / dL}$ were clinical samples and the remaining samples spanning from 2.3 to $35.0\mathrm{mg / dL}$ were spiked whole blood samples. The two studies are summarized below:
A single analysis of heparinized whole blood from healthy volunteers was processed on the STP CCX1+ CO-OXIMETER (COOX only mode) and compared to a single analysis on the Dade Dimension RxL. Total bilirubin level in heparinized blood was manipulated by spiking with bilirubin stock solution to obtain samples in the range of $0.5\mathrm{mg / dL} - 35.0\mathrm{mg / dL}$ . Eighty (80) samples were analyzed in a randomized fashion. A least squares regression analysis of the data was performed to assess system performance. Results are summarized below.
STP CCX1+ CO-OXIMETER ONLY ANALYSIS versus Dade Dimension RxL:
| Unit | Analyte | n | r2 | Slope | Y-Intercept |
| --- | --- | --- | --- | --- | --- |
| 1 | tBil | 80 | 0.989 | 1.022 | 0.146 |
| 2 | tBil | 80 | 0.989 | 1.014 | 0.057 |
A single analysis of heparinized whole blood from healthy volunteers was processed on the STP CCX CO-OXIMETER as a combined analysis (COOX with ABG mode) and compared to a single analysis on the STP CCX1+ CO-OXIMETER (COOX only mode). Total bilirubin level in heparinized blood was manipulated by spiking with bilirubin stock solution to obtain samples in the range of $0.5\mathrm{mg / dL} - 35.0\mathrm{mg / dL}$ . A least squares regression analysis of the data was performed to assess system performance. Results are summarized below.
STP CCX1+ CO-OXIMETER AGB with COOX versus the COMBINED ANALYSIS:
| Unit | Analyte | n | r2 | Slope | Y-Intercept |
| --- | --- | --- | --- | --- | --- |
| 1 | tBil | 80 | 0.989 | 1.007 | 0.067 |
| 2 | tBil | 80 | 0.988 | 1.004 | 0.220 |
{5}
c. Traceability, Stability, Expected values (controls, calibrators, or methods): The calibrators and controls are traceable to NIST Standard Reference Material 916A Bilirubin. Stability characteristics of the controls and calibrators were determined using real time studies. The data submitted supports an open vial stability of 35 days and an unopened vial stability of 2 years at room temperature for both the controls and calibrator.
d. Detection limit: The lower limit of detection for total bilirubin was determined by measuring day to day imprecision of a solution containing $\sim 0.4\mathrm{mg / dL}$ bilirubin which is below the low end of the analyzer's measurement range of $0.5 - 35.1\mathrm{mg / dL}$ . Results are summarized below.
| Unit | Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- | --- |
| 1 | tBil | 60 | 0.4 | 0.08 | 19.19 |
| 2 | tBil | 60 | 0.3 | 0.10 | 32.42 |
e. Analytical specificity: Investigation of interference effects to total bilirubin measurements on the Nova CCX1+ CO-Oximeter was performed using high levels of potential interfering substances including: Lipids, Evans Blue, Indocyanine Green, Methylene Blue and EDTA. Samples spiked with all potentially interfering substances were within $+/- 1.0$ mg/dL of the reference instrument for all substances except $3\%$ Lipid and $15\mathrm{mg / L}$ Methylene Blue which showed biases of $>1.0\mathrm{mg / dL}$ . These substances (3% Lipid and $15\mathrm{mg / L}$ Methylene Blue) are identified as interfering substances in the operator's manual. The results are summarized below as the averages of three replicates.
| Whole Blood ~7.0 mg/dl bilirubin spiked with various potential interfering substances | CCX1+ (mg/dL) | DADE (mg/dL) | Bias vs. Dade (mg/dL) |
| --- | --- | --- | --- |
| Blood (Control) | 7.0 | 6.5 | 0.5 |
| Lipid (3%) | 4.8 | 6.2 | -1.4 |
| Lipid (1%) | 5.6 | 6.5 | -0.9 |
| Lipid (0.5%) | 6.2 | 6.8 | -0.6 |
| Evans Blue (5 mg/L) | 6.0 | 6.2 | -0.2 |
| Methylene Blue (15 mg/L) | 4.9 | 6.2 | -1.3 |
| Patent Blue (10 mg/L) | 6.4 | 6.3 | 0.1 |
| Indocyanine Green (5 mg/L) | 6.6 | 5.9 | 0.7 |
| EDTA (15 %) | 7.0 | 6.4 | 0.6 |
Potential hemoglobin interference was also tested by modifying heparinized whole blood. For each of three levels of tHb, the total bilirubin concentration was manipulated by spiking with a bilirubin stock solution. A single analysis of each sample was processed on the STP CCX1 +
{6}
CO-Oximeter and compared to a single analysis on the Dade Dimension RxL. The sponsor defined interference non-interference as the total bilirubin value being within $+/- 1.0 \, \mathrm{mg/dL}$ or $10\%$ of the reference instrument.
| tHb | CCX tHb (g/dL) | CCX tBil (mg/dL) | Dade RxL tBil (mg/dL) | CCX Bias vs. Dade (mg/dL) | CCX % Diff. Vs. Dade |
| --- | --- | --- | --- | --- | --- |
| Low tHb | 5.2 | 3.5 | 3.1 | 0.4 | 11.76 |
| | 6.9 | 4.3 | 4.7 | -0.4 | -8.56 |
| | 7.1 | 17.1 | 17.4 | -0.3 | -1.44 |
| | 9.8 | 0.6 | 0.6 | 0.0 | 1.82 |
| | 7.7 | 6.7 | 6.9 | -0.2 | -2.70 |
| | | | | | |
| Normal tHb | 14.1 | 0.5 | 0.6 | -0.1 | -15.31 |
| | 14.1 | 4.1 | 9.7 | 0.4 | 10.62 |
| | 16.1 | 17.7 | 17.0 | 0.7 | 4.26 |
| | 17.0 | 10.7 | 11.2 | -0.5 | -4.65 |
| | 17.2 | 18.6 | 18.1 | 0.5 | 2.83 |
| | | | | | |
| High tHb | 22.6 | 31.8 | 33.5 | -1.7 | -4.98 |
| | 22.6 | 2.0 | 1.8 | 0.2 | 9.50 |
| | 22.9 | 4.2 | 4.2 | 0.0 | -0.48 |
| | 21.6 | 20.4 | 19.6 | 0.8 | 3.85 |
| | 22.6 | 10.6 | 9.8 | 0.8 | 8.53 |
f. Assay cut-off: Not Applicable.
# 2. Comparison studies:
a. Method comparison with predicate device: Un-spiked samples obtained from hospital patients were processed on the STP CCX1 + CO-Oximeter (COOX only mode) using two instruments and compared to a single analysis on the Dade Dimension RxL. A total of 68 samples were analyzed and a least squares regression analysis of the data was performed to assess system performance. Results are summarized below:
| Instrument | Analyte | n | r2 | Slope | y-intercept | Min | Max |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | tBil | 62 | 0.9849 | 1.017 | 0.116 | 0.5 | 32.5 |
| 2 | tBil | 62 | 0.9867 | 1.013 | 0.089 | 0.6 | 32.8 |
b. Matrix comparison: See above: Method comparison with predicate device
# 3. Clinical studies:
a. Clinical Sensitivity: Not Applicable.
{7}
b. Clinical specificity:
Not Applicable.
c. Other clinical supportive data (when a. and b. are not applicable):
A Point of Care study was performed at a single site using 110 individuals (55 hospital personnel, 50 Point of Care (POC) personnel, and 5 laboratory personnel). Performance of the device was evaluated by comparing results from 88 clinical samples spanning a total bilirubin range from 0.5 to 33.5 mg/dL performed by both hospital personnel and non-hospital personnel. Results of the comparison are summarized below:
| Analyte | n | r² | Slope | Y-Intercept |
| --- | --- | --- | --- | --- |
| Total Bilirubin | 88 | 0.998 | 1.007 | 0.044 |
Precision was also evaluated by POC personnel using the same control levels as in the Precision/Reproducibility section above. Results are summarized below.
Control Level 7 Run to Run Precision
| Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- |
| Total Bilirubin | 20 | 4.7 | 0.05 | 1.01 |
Control Level 8 Run to Run Precision
| Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- |
| Total Bilirubin | 20 | 9.98 | 0.04 | 0.41 |
Control Level 9 Run to Run Precision
| Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- |
| Total Bilirubin | 20 | 20.3 | 0.23 | 1.16 |
Control Level 7 Within Run Precision
| Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- |
| Total Bilirubin | 20 | 4.7 | 0.05 | 1.01 |
Control Level 8 Within Run Precision
| Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- |
| Total Bilirubin | 20 | 10.2 | 0.06 | 0.58 |
Control Level 9 Within Run Precision
| Analyte | n | Mean (mg/dL) | SD | CV (%) |
| --- | --- | --- | --- | --- |
| Total Bilirubin | 20 | 20.5 | 0.099 | 0.48 |
{8}
4. Clinical cut-off:
Not Applicable.
5. Expected values/Reference range:
The sponsor included the following reference values for normal total bilirubin levels in the operator’s manual:
Total Bilirubin (tBil) Adult: 0.2 – 1.0 mg/dL
From: The reference value for total bilirubin was obtained from Tietz, Norbert W., ed. 1983. Clinical Guide to Laboratory Tests. Philadelphia, PA: W.B. Saunders Co.
N. Instrument Name:
Nova Stat Profile Clinical Care Xpress (CCX 1+) System
O. System Descriptions:
1. Modes of Operation:
The instrument has several modes of operation for the various analytes and sample types (whole blood, serum, and plasma). For total bilirubin, the instrument can use only the whole blood sample type.
2. Software:
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☐ X ☐ or No ☐
3. Specimen Identification:
Sample identification is performed through an interface which instructs the device which sample type is to be detected.
4. Specimen Sampling and Handling:
The sponsor indicates in the operator’s manual that correct handling is critical to ensure that the blood gas values obtained accurately reflect the in vivo state. It is recommended that the samples be well mixed prior to introduction into the analyzer and that the samples be analyzed within 15 minutes for blood gases. The sponsor references CLSI document C32-P. Vol. 13, No. 17. Considerations in the Simultaneous Measurement of Blood Gases, Electrolytes, and Related Analytes in Whole Blood: Proposed Guideline.
5. Calibration:
The instrument has a two-point and single-point automatic calibration for total bilirubin. The same dye reagents (cleared in k022746) are used for the measurement of total bilirubin and there is no change to the formulation of the calibrators as a result of the added analyte measurement.
6. Quality Control:
The sponsor provides several levels of controls for use with the instrument and QC procedures are listed in the operator’s manual. An acceptable range for each control level is printed on the control solution label and the user is referred to the troubleshooting section of the operator’s manual if control results fall outside these ranges. The same reagents dyes (cleared in k022746) are used for the measurement of total bilirubin and there is no change to the formulation of the controls as a result of the added analyte
9
{9}
measurement.
P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:
Q. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
R. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
10
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.