The DataPro™/DataPro Plus™ Clinical Chemistry Analyzer is a fully automated clinical chemistry analyzer intended for routine diagnostic clinical laboratory use. The DataPro™ has replaceable parts, automated maintenance monitoring and backup of both patient and system data. With a throughput of up to 230 tests per hour, the DataPro™ is intended for small and medium-sized laboratories, or as a backup analyzer in large volume laboratories. The DataPro™/DataPro Plus™ Clinical Chemistry Analyzer is intended to be used in the diagnosis of disease or other conditions, including a determination of the state of health, in order to cure, mitigate, treat, or prevent disease or its sequelae related to the measurement of various clinical assays, such as Albumin, Alkaline Phosphatase, Alanine Aminotransferase (ALT), Aspartate Aminotransferase (AST), Urea Nitrogen (BJ N), Calcium, Cholesterol, Creatinine, Direct Bilirubin, Glucose, Phosphorus, Total Billirubin, Total Protein, Triglyceride, and Uric Acid. The DataPro™, and all of the reagents included in this test system are for in vitro diagnostic use only.
Device Story
DataPro™/DataPro Plus™ is a fully automated clinical chemistry analyzer for in vitro diagnostic use in clinical laboratories. Device processes patient samples to measure clinical assays (e.g., glucose, proteins, enzymes, lipids). System features automated maintenance monitoring, replaceable parts, and data backup capabilities. Throughput up to 230 tests/hour. Operated by laboratory personnel to assist in disease diagnosis and health status monitoring. Output provides quantitative assay results used by clinicians to inform treatment and diagnostic decisions.
Clinical Evidence
No clinical data. Performance established via bench testing per CLSI standards (EP5, EP6, EP9). Precision (CVs reported for 15 analytes), linearity (reportable ranges defined), and method comparison (N=40-60 samples per analyte, correlation coefficients R=0.9254-0.9952) were evaluated against predicate methods.
Technological Characteristics
Fully automated clinical chemistry analyzer; throughput up to 230 tests/hour; includes automated maintenance monitoring and data backup systems. Designed for in vitro diagnostic use.
Indications for Use
Indicated for use in clinical laboratories for the diagnosis of disease or health status assessment via measurement of clinical assays including Albumin, ALP, ALT, AST, BUN, Calcium, Cholesterol, Creatinine, Direct Bilirubin, Glucose, Phosphorus, Total Bilirubin, Total Protein, Triglyceride, and Uric Acid. Intended for small to medium-sized laboratories or as a backup in large-volume facilities.
Regulatory Classification
Identification
A glucose test system is a device intended to measure glucose quantitatively in blood and other body fluids. Glucose measurements are used in the diagnosis and treatment of carbohydrate metabolism disorders including diabetes mellitus, neonatal hypoglycemia, and idiopathic hypoglycemia, and of pancreatic islet cell carcinoma.
Special Controls
*Classification.* Class II (special controls). The device, when it is solely intended for use as a drink to test glucose tolerance, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 862.9.
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k042767
B. Purpose for Submission:
Thermo Electron Corporation proposes to manufacture and introduce into interstate commerce, for commercial distribution, the Thermo Electron DataPro™ / DataPro Plus™ Clinical Chemistry Analyzer. This is being submitted for use with previously FDA cleared reagents manufactured by Trace and/or DMA, now doing business as Thermo Electron Corporation.
C. Measurand:
Glucose, Alkaline phosphatase, Albumin, Aspartate amino transferase (AST/SGOT), Bilirubin total, Bilirubin direct, Calcium, Creatinine, Urea nitrogen, Total protein, Phosphorus, Cholesterol, Triglyceride, Uric acid, Alanine amino transferase (ALT/SGPT).
D. Type of Test:
Quantitative assays for the DataPro™ / DataPro Plus™ Clinical Chemistry Analyzer
E. Applicant:
Thermo Electron Corporation
F. Proprietary and Established Names:
DataPro™ / DataPro Plus™ Clinical Chemistry Analyzer
G. Regulatory Information:
1. Regulation section:
21 CFR § 862.1345 Glucose test system.
21 CFR § 862.1050 Alkaline phosphatase or isoenzymes test system.
21 CFR § 862.1035 Albumin test system.
21 CFR § 862.1100 Aspartate amino transferase (AST/SGOT) test system.
21 CFR § 862.1110 Bilirubin (total or direct) test system.
21 CFR § 862.1110 Bilirubin (total or direct) test system.
21 CFR § 862.1145 Calcium test system.
21 CFR § 862.1225 Creatinine test system.
21 CFR § 862.1770 Urea nitrogen test system.
21 CFR § 862.1635 Total protein test system.
21 CFR § 862.1580 Phosphorus (inorganic) test system.
21 CFR § 862.1175 Cholesterol (total) test system.
21 CFR § 862.1705 Triglyceride test system.
21 CFR § 862.1775 Uric acid test system.
21 CFR § 862.1030 Alanine amino transferase (ALT/SGPT) test system.
21 CFR § 862.2160 Discrete Photometric Chemistry Analyzer for Clinical Use
{1}
2. Classification:
Class II, Class I (reserved), Class I
3. Product code:
PC Common Name
CFR HEXOKINASE, GLUCOSE
NITROPHENYLPHOSPHATE, ALKALINE PHOSPHATASE OR
CJE ISOENZYMES
CIX BROMCRESOL GREEN DYE-BINDING, ALBUMIN
CIT NADH OXIDATION/NAD REDUCTION, AST/SGOT
CIG DIAZO COLORIMETRY, BILIRUBIN
CIC CRESOLPHTHALEIN COMPLEXONE, CALCIUM
CGX ALKALINE PICRATE, COLORIMETRY, CREATININE
CDQ UREASE AND GLUTAMIC DEHYDROGENASE, UREA NITROGEN
CEK BIURET (COLORIMETRIC), TOTAL PROTEIN
CEO PHOSPHOMOLYBDATE (COLORIMETRIC), INORGANIC PHOSPHORUS
CHH ENZYMATIC ESTERASE--OXIDASE, CHOLESTEROL
CDT LIPASE HYDROLYSIS/GLYCEROL KINASE ENZYME, TRIGLYCERIDES
CDO ACID, URIC, URICASE (U.V.)
CKA NADH OXIDATION/NAD REDUCTION, ALT/SGPT
4 ANALYZER, CHEMISTRY (PHOTOMETRIC, DISCRETE), FOR CLINICAL
JJE USE
Panel:
Chemistry (75)
H. Intended Use:
1. Intended use(s):
See Indications for use below.
2. Indication(s) for use:
The DataPro™ / DataPro Plus™ Clinical Chemistry Analyzer is a fully automated clinical chemistry analyzer intended for routine diagnostic clinical laboratory use. The DataPro™ has replaceable parts, automated maintenance monitoring and backup of both patient and system data. With a throughput of up to 230 tests per hour, the DataPro™ is intended for small and medium-sized laboratories, or as a backup analyzer in large volume laboratories.
The DataPro™ / DataPro Plus™ Clinical Chemistry Analyzer is intended to be used in the diagnosis of disease or other conditions, including a determination of the state of health, in order to cure, mitigate, treat, or prevent disease or its sequelae related to the measurement of various clinical assays, such as Albumin, Alkaline Phosphatase, Alanine Aminotransferase (ALT), Aspartate Aminotransferase (AST), Urea Nitrogen (BUN), Calcium, Cholesterol, Creatinine, Direct Bilirubin, Glucose, Phosphorus, Total Bilirubin, Total Protein, Triglyceride, and Uric Acid.
{2}
3. Special conditions for use statement(s):
The DataPro™, and all of the reagents included in this test system are for in vitro diagnostic use only.
4. Special instrument requirements:
DataPro™ / DataPro Plus™ Clinical Chemistry Analyzer
I. Device Description:
The DataPro™/DataPro Plus™ (with cuvette washer) is a random access discrete photometric analyzer, capable of performing 48 different tests to 48 samples in a walk-away manner. In Clinical analysis, its purpose is for In Vitro Diagnostics. It performs Laboratory Chemistry Analysis in automated and selective form, either in routine or Stat mode.
The analyzer incorporates robotics, computer and communication technology to render simple and reliable long-term operation. The DataPro™ consists of a system of modules (reagent tray, sampling system and reaction tray) performing specific functions, computer controlled and with bi-directional communication.
Cuvettes are disposable and not for reuse, except where a washer is installed and enabled. Washing occurs automatically after the completion of each run. When the washer is in use, at the beginning of the next run, the system will use the next set of cuvettes after the ones used in the previous run. This prevents over use of the same cuvettes. Precision data were generated using this option at one test site compared to two other sites.
Colors of the cuvettes in the Reaction Tray field are coded as follows:
- Dark Grey: New cuvettes.
- Light Grey: Used, then washed cuvettes (when washer installed).
- Black: The checked absorbance of the empty cuvette is higher than the limit specified in the parameters. It is therefore considered dirty and will not be used. It is washed (where applicable) in the next run. If washing doesn't help, change the cuvette.
For more detailed information see section O. System Descriptions below.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Trace America, Inc reagents as follows: Glucose (HK), Alkaline Phosphatase, Albumin Reagent - Bromcresol Green Method, AST Incorporating Dynamic Stabilization Technology (DST), Direct Bilirubin Reagent - Acid Diazo Method, Total/Direct Bilirubin Reagent, Calcium Arsenazo III Reagent, Creatinine Reagent - Picric Acid Method, Urea (Urea Nitrogen) - Incorporating DST, Total Protein Reagent - Biuret Method, Phosphorus Reagent-Direct UV Method,
{3}
Cholesterol- Incorporating DST, Enzymatic Triglycerides Reagent, Uric Acid Incorporating DST, and ALT Incorporating DST.
Ciba Corning Diagnostics Corp., Model 550 Express Clinical Chemistry Analyzer
2. Predicate 510(k) number(s):
k980026, k012518, k870372, k961114, k870365, k911866, k903896, k870366, k971477, k870371, k870368, k962890, k860730, k971485, k961123, k872302 respectively as listed above.
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Reagents | Same | Same |
| Analyzer | | |
| • Discrete Photometric Analyzer | Same | Same |
| • Software Driven | Same | Same |
| • For clinical laboratory professionals | Same | Same |
| • Automated dilutions | Same | Same |
| • Sample reruns | Same | Same |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Reagents | Automation on | Generic |
| Testing Process | DataPro™ Analyzer | reagent/replacement reagents |
| Analyzer | DataPro™ Analyzer | 550 Express Analyzer |
| | | |
K. Standard/Guidance Document Referenced (if applicable):
All data was collected and statistical analysis for all methods performed according to National Committee of Clinical Laboratory Standards (NCCLS now CLSI) by standards such as:
EP5 - Evaluation of Precision Performance of Clinical Chemistry Devices
EP6 - Evaluation of the Linearity of Quantitative Analytical Methods
EP9 - Method Comparison and Bias Estimation Using Patient Samples
L. Test Principle:
The package insert for each analyte states the test principle.
{4}
# M. Performance Characteristics (if/when applicable):
# 1. Analytical performance:
a. Precision/Reproducibility:
Precision was performed per - CLSI Precision Standard, EP5. The results are presented below.
| | | | Total | | With in run | |
| --- | --- | --- | --- | --- | --- | --- |
| Level | Assay | Mean | SD | CV(%) | SD | CV(%) |
| I | Glu | 93 | 8.4 | 9.4 | 3.5 | 3.9 |
| II | Glu | 300 | 16.5 | 5.9 | 11.4 | 4.1 |
| I | ALP | 95 | 3.3 | 3.3 | 1.9 | 1.9 |
| II | ALP | 483 | 15.0 | 3.3 | 7.2 | 1.6 |
| I | ALB | 3.0 | 0.12 | 3.9 | 0.09 | 3.0 |
| II | ALB | 2.2 | 0.08 | 2.1 | 0.05 | 2.1 |
| I | AST | 29 | 1.1 | 3.9 | 0.8 | 1.0 |
| II | AST | 176 | 5.6 | 3.2 | 1.8 | 1.0 |
| I | T. Bili | 1.1 | 0.06 | 5.6 | 0.04 | 3.8 |
| II | T. Bili | 7.1 | 0.17 | 2.4 | 0.07 | 1.0 |
| I | D. Bili | 0.7 | 0.10 | 15.2 | 0.03 | 4.6 |
| II | D. Bili | 3.3 | 0.26 | 8.1 | 0.06 | 1.8 |
| I | Ca | 8.6 | 0.22 | 2.5 | 0.16 | 1.9 |
| II | Ca | 13.5 | 0.24 | 1.9 | 0.16 | 1.2 |
| I | Creat | 3.0 | 0.10 | 3.0 | 0.08 | 2.5 |
| II | Creat | 6.7 | 0.20 | 2.8 | 0.15 | 2.1 |
| I | BUN | 14 | 1.0 | 8.5 | 0.8 | 6.6 |
| II | BUN | 54 | 3.4 | 7.6 | 2.2 | 4.9 |
| I | T. Prot | 6.9 | 0.29 | 4.1 | 0.19 | 2.6 |
| II | T. Prot | 5.2 | 0.22 | 0.22 | 0.11 | 2.0 |
| I | Phos | 3.6 | 0.09 | 2.7 | 0.07 | 1.9 |
| II | Phos | 6.8 | 0.32 | 4.6 | 0.11 | 1.6 |
| I | Chol | 144 | 5.1 | 3.5 | 3.8 | 2.6 |
| II | Chol | 250 | 11.4 | 4.5 | 6.9 | 2.7 |
| I | Trig | 80 | 4.6 | 5.8 | 3.5 | 4.4 |
| II | Trig | 142 | 7.8 | 5.6 | 5.9 | 4.2 |
| I | UA | 6.2 | 0.18 | 3.0 | 0.09 | 1.4 |
| II | UA | 12.0 | 0.26 | 2.3 | 0.08 | 0.7 |
| I | ALT | 25 | 1.0 | 3.9 | 0.8 | 3.1 |
| II | ALT | 88 | 3.9 | 3.9 | 2.5 | 2.4 |
{5}
| Cuvette Wash Option Precision Study | | | | | | | |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Site | Level | Assay | Mean | Total | | Between run | |
| | | | | SD | CV(%) | SD | CV(%) |
| 1 | I | T. Prot | 4.47 | 0.28 | 6.2 | 0.17 | 3.8 |
| 1 | II | T. Prot | 3.32 | 0.21 | 6.4 | 0.11 | 3.4 |
| 2 | I | T. Prot | 4.45 | 0.11 | 2.5 | 0.11 | 2.5 |
| 2 | II | T. Prot | 3.29 | 0.10 | 3.1 | 0.10 | 3.1 |
| C/Wash | I | T. Prot | 4.41 | 0.12 | 2.7 | 0.12 | 2.7 |
| C/Wash | II | T. Prot | 3.24 | 0.09 | 2.9 | 0.09 | 2.9 |
b. Linearity/assay reportable range:
Linearity was performed per - CLSI Linearity Standard, EP6. The results are presented below.
| Analyte | N | Slope | Intercept | % Error | Allowable % Error | Range |
| --- | --- | --- | --- | --- | --- | --- |
| Glucose | 11 | 1.020 | -0.6 | 2.6 | 3.0 | 0 – 788 mg/dL |
| ALP | 6 | 0.926 | 4.7 | 7.1 | 7.5 | 10 – 2079 U/L |
| ALB | 6 | 0.959 | 0.082 | 2.1 | 2.5 | 0 - 6.71 g/L |
| AST | 5 | 0.974 | 0.0 | 2.6 | 5.0 | 7 – 1334 U/L |
| TBILI | 6 | 1.014 | 0.03 | 1.7 | 5.0 | 0 - 20.5 mg/dL |
| DBIL | 5 | 0.987 | 0.0 | 2.8 | 5.0 | 0 – 20 mg/dL |
| CAL | 5 | 0.965 | -0.013 | 0.16 mg/dL | 0.25 mg/dL | 5 – 15 mg/dL |
| CREA | 11 | 1.000 | 0.03 | 3.6 | 3.8 | 0 - 26.2 mg/dL |
| BUN | 6 | 1.007 | 0.0 | 3.0 | 3.6 | 0 – 128 mg/dL |
| TPRO | 10 | 0.977 | 0.1 | 2.3 | 2.5 | 0 - 17.3 g/L |
| PHOS | 5 | 1.084 | -0.1 | 2.3 | 2.7 | 1 – 11 mg/dL |
| CHOL | 11 | 1.017 | 0.0 | 2.7 | 3 | 0 - 904.9 mg/dL |
| TRIG | 10 | 1.018 | 0.0 | 2.8 | 6.3 | 0 – 1277 mg/dL |
| UA | 5 | 0.998 | -0.23 | 2.1 | 4.3 | 2 – 22 mg/dL |
| ALT | 6 | 0.993 | 1.9 | 4.9 | 5.0 | 0 – 545 U/L |
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
See the package insert for each analyte.
d. Detection limit:
See the package insert for each analyte.
e. Analytical specificity:
See the package insert for each analyte.
{6}
f. Assay cut-off: Not applicable
2. Comparison studies:
a. Method comparison with predicate device: The method comparison was performed per - CLSI Method Comparison Standard, EP9. The results are presented below.
| Analyte | N | Slope | Intercept | Corr. R | Sample Range |
| --- | --- | --- | --- | --- | --- |
| Glucose | 60 | 0.935 | -0.2 | 0.9797 | 8 – 220 mg/dL |
| ALP | 60 | 0.94 | -4.2 | 0.9922 | 40 – 516 U/L |
| ALB | 60 | 0.9 | 0.28 | 0.9254 | 2.2 – 5.5 g/L |
| AST | 55 | 0.97 | -1.7 | 0.9732 | 8 – 90 U/L |
| TBILI | 40 | 1.195 | -0.1 | 0.9411 | 0.0 – 1.6 mg/dL |
| DBIL | 40 | 0.891 | 0.15 | 0.9785 | 0.0 – 1.7 mg/dL |
| CAL | 60 | 0.942 | 0.42 | 0.9288 | 5.6 – 13.3 mg/dL |
| CREA | 59 | 0.995 | 0.14 | 0.988 | 0.2 – 7.1 mg/dL |
| BUN | 59 | 1 | 0.18 | 0.9875 | 2.2 – 36.1 mg/dL |
| TPRO | 40 | 1.047 | -0.05 | 0.9952 | 0.4 – 14.3 g/L |
| PHOS | 60 | 1.17 | -0.422 | 0.9758 | 2.7 – 8.7 mg/dL |
| CHOL | 60 | 1.068 | -9.3 | 0.9671 | 108 – 284 mg/dL |
| TRIG | 60 | 1.044 | 21.7 | 0.9404 | 27 – 343 mg/dL |
| UA | 60 | 0.901 | 0.164 | 0.9769 | 2.2 – 13.1 mg/dL |
| ALT | 60 | 0.96 | -0.9 | 0.9914 | 6 – 120 U/L |
b. Matrix comparison: Not applicable
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
{7}
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
See the package insert for each analyte.
N. Instrument Name:
Thermo Electron DataPro™ / DataPro Plus™ Clinical Chemistry Analyzer
O. System Descriptions:
1. Modes of Operation:
- Profiles, batches, STAT procedures.
- Automatic time adjust and dilution with high substrate consumption.
- Automatic dilution for values above high limit.
- Automatic repetition on abnormal low values.
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:
Bar code option
4. Specimen Sampling and Handling:
Sampling
- 48 Sample positions in a rotary tray.
- Use primary or pediatric tubes.
- Bar code reader for sample identification (Optional).
- Sample volume programmable 2 - 100 μL.
- Pre-heater in the probe delivers reagent at the preset temperature.
- Capacitive Level Sensor.
- Inner and outer probe washing system.
- CavroTM diluter syringe with valve assembly.
Reagent Tray
- 48 Reagent positions (Cooled in the Plus model).
- Reagent volume Limits programmable:
- In 0.6cm Cuvette
First Reagent Volume 0 - 700 μL
Second Reagent Volume 0 - 450 μL
Minimum Volume 200 μL
Maximum Volume 700 μL
8
{8}
Total Volume (Sample + R1 + R2) 200 - 700 μL
- Reagents are placed into wedge shaped vials: 45 mL, 30 mL or 18 mL, which can be used in any combination of single or two part reagent systems.
**Reaction Tray**
- Eighty (80) cuvette capacity.
- Double beam, Interferential filters.
- Wavelengths: 340, 380, 405, 450, 505, 550, 600, 650 and 700 nm.
- Bandwidth: 10 nm.
- Photometric range: -0.1 to 3.6 A (-0.1 to 5.5 A with 0.6 cm cuvettes).
- Lamp: Halogen, 6 volts, 20 watts.
5. **Calibration:**
- End point with sample blank or reagent blank.
- Calibration by Factor or Standard.
- Priority programmable per sample (profile) or reagent (batch).
- Calibration curves with two (2) to ten (10) standards.
- Automatic curve adjust.
- Fast and Two-Point Kinetics (0 and 1st order).
6. **Quality Control:**
- Levy Jennings plots, Westgard rules.
- Data import and export to other programs and/or remote terminals.
- Automatic backup protection
**P. Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:**
Software documentation provided demonstrates the DataPro™ / DataPro Plus™ Analyzer was designed and manufactured under well developed software lifecycle processes.
**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.
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.