K083628 · All Medicus Co., Ltd. · NBW · May 1, 2009 · Clinical Chemistry
Device Facts
Record ID
K083628
Device Name
GLUCODR AUTO SYSTEM
Applicant
All Medicus Co., Ltd.
Product Code
NBW · Clinical Chemistry
Decision Date
May 1, 2009
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 862.1345
Device Class
Class 2
Attributes
Pediatric
Indications for Use
The GlucoDr™ auto blood glucose monitoring system is intended for in vitro diagnostic use (i.e., for external use only) for quantitative measurement of glucose in venous, arterial and capillary whole blood. Testing sites include traditional fingertip site along with palm, upper arm, forearm, thigh, and calf. The GlucoDr™ auto blood glucose monitoring system may be used by healthcare professionals or for self testing by diabetic lay users in the mellitus at home as aid in monitoring the effectiveness of diabetes control program. The GlucoDr™ auto blood glucose monitoring system is not intended for the diagnosis of or screening for diabetes mellitus, nor intended for use on neonates. The GlucoDr™ auto control solution is for use with the The GlucoDr™ auto test meters and strips as a quality control check to verify the accuracy of blood glucose test results.
Device Story
System measures glucose via electrical currents generated by reaction of glucose with reagents on gold electrode test strips; reaction involves glucose dehydrogenase and mediators. Meter converts measured current to glucose concentration using internal algorithm. Used by healthcare professionals or patients at home for diabetes management. Output displayed on meter screen; aids in monitoring diabetes control program effectiveness. Includes control solution for accuracy verification.
Clinical Evidence
No clinical data provided; substantial equivalence established via technological comparison and bench testing.
Technological Characteristics
Amperometric glucose monitoring system; gold electrode test strips; glucose dehydrogenase reagent; meter-based algorithm for current-to-glucose conversion; includes control solution for quality verification.
Indications for Use
Indicated for quantitative glucose measurement in venous, arterial, and capillary whole blood for diabetic patients (lay users) and healthcare professionals. Contraindicated for neonates and for diabetes diagnosis or screening.
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.
Predicate Devices
Accu-Chek Aviva System (k043474)
Submission Summary (Full Text)
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k083628
B. Purpose for Submission:
New device
C. Measurand:
Whole blood glucose
D. Type of Test:
Quantitative, glucose dehydrogenase (FAD-GDH)
E. Applicant:
All Medicus, Co. Ltd.
F. Proprietary and Established Names:
GlucoDR auto Blood Glucose Monitoring System
G. Regulatory Information:
| Product Code | Classification | Regulation Section | Panel |
| --- | --- | --- | --- |
| NBW – over the counter glucose test system | II | 862.1345 | 75, Chemistry |
| LFR – Glucose, glucose dehydrogenase | | | |
| JJX – single (specified) analyte controls (assayed and unassayed) | I (reserved) | 862.1660 | |
{1}
H. Intended Use:
1. Intended use(s):
See indications for use below.
2. Indication(s) for use:
The GlucoDr auto blood glucose monitoring system is intended for in vitro diagnostic use (i.e., for external use only) for quantitative measurement of glucose in venous, arterial, and capillary whole blood. Testing sites include traditional fingertip site along with palm, arm, thigh, and calf.
The GlucoDr auto blood glucose monitoring system may be used by healthcare professionals or for self testing by diabetic lay users with diabetes at home as aid in monitoring the effectiveness of diabetes control program.
The GlucoDr auto blood glucose monitoring system is not intended for the diagnosis of or screening for diabetes mellitus nor intended for use on neonates.
The GlucoDr auto control solution is for use with the The GlucoDr auto meters and strips as a quality control check to verify the accuracy of blood glucose test results.
3. Special conditions for use statement(s):
- Not for use on critically ill patients, dehydrated patients or hyperosmolar patients
- Not for neonatal use
- Not for screening or diagnosis of diabetes mellitus
- Alternative site testing is for use at times of steady state only
4. Special instrument requirements:
The GlucoDr auto Blood Glucose Monitoring System
I. Device Description:
The GlucoDr auto Blood Glucose Monitoring System consists of glucose meter, blood glucose test strips and two control materials.
{2}
3
J. Substantial Equivalence Information:
1. Predicate device name(s):
Accu-Chek Aviva System, Roche Diagnostics Corporation
2. Predicate 510(k) number(s):
k043474
3. Comparison with predicate:
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Detection Method | Amperometry | Amperometry |
| Enzyme | Glucose dehydrogenase | Glucose dehydrogenase |
| Sample type | Capillary or venous blood | Capillary or venous blood |
| Test time | 5 seconds | 5 seconds |
| Memory Capacity | 500 results with date and time | 500 results with date and time |
| Control solution | 2 range | 2 range |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Measurement range | 20-600 mg/dL | 10-600 mg/dL |
| Sample Volume | 0.5 ul | 0.6 ul |
| Coding of Strip | Auto Coding | Code Chip |
K. Standard/Guidance Document Referenced (if applicable):
CLSI EP5-A2: Evaluation of Precision Performance of Quantitative Measurement Methods; Approved Guideline-Second Edition (2004)
CLSI EP6-A: Evaluation of Linearity of Quantitative Measurement Procedures, A Statistical Approach: Approved Guideline (2003)
CLSI EP7-A2: Interference Testing in Clinical Chemistry; Approved Guideline (2002)
CLSI EP9-A2: Method Comparison and Bias Estimation Using Patient Samples; Approved Guideline (2002)
ISO 15197: 2003, In vitro diagnostic test systems – Requirements for blood-glucose monitoring systems for self-testing in managing diabetes mellitus
ISO 14971: 2007, Medical devices – Application of risk management to medical devices
EN 13612: 2002, Performance evaluation of in vitro diagnostic medical devices
{3}
EN 13640: 2002, Stability testing of in vitro diagnostic medical devices
EN 61010-2-101: 2002, Safety requirements for electrical equipment for measurement, control and laboratory use. Particular requirements for in vitro diagnostic (IVD) medical equipments FDA Guideline, Review criteria for assessment of portable blood glucose monitoring in vitro diagnostic devices using glucose oxidase, dehydrogenase or hexokinase methodology
## L. Test Principle:
The GlucoDr auto Blood Glucose Monitoring System is based on measurement of electrical currents caused by the reaction of glucose with reagents on the gold electrode strip. Glucose in the blood sample reacts with FAD glucose dehydrogenase and potassium ferricyanide in the test strip, which creates electrical currents. The subsequent electrical currents are proportional to the glucose concentration in the blood and converted to the equivalent glucose concentration by the algorithm programmed in the test meter.
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
The sponsor performed precision studies using venous whole blood with concentrations between 58 and 324 mg/dL (spiked samples). Testing was performed at 3 sites with 10 meters (3 meters used at site 1 and 2 and 4 meters at site 3) and three lots of test strips were tested with 10 replicates of each lot in one day. The results for all three lots are presented in the table below:
| Level | Mean of glucose (mg/dL) | Within-run (SD) | %CV |
| --- | --- | --- | --- |
| 1 | 58 | 1.88 | 3.22 |
| 2 | 103 | 1.95 | 1.89 |
| 3 | 150 | 2.73 | 1.82 |
| 4 | 190 | 3.72 | 1.96 |
| 5 | 324 | 5.95 | 1.84 |
In addition, repeatability of the test strip was tested with control solutions (low, medium and high). Testing was performed at 3 sites with 10 meters (3 meters used at site 1 and 2 and 4 meters at site 3) and three lots of test strips were tested with 10 replicates in one day. The results for all three lots are presented in the table below:
{4}
| Glucose control solution level | Mean of glucose (mg/dL) | Total imprecision (SD) | Total % CV |
| --- | --- | --- | --- |
| Low | 39.8 | 2.32 | 5.82 |
| Medium | 110 | 3.28 | 2.99 |
| High | 311 | 9.20 | 2.96 |
# b. Linearity/assay reportable range:
The linearity of the glucose measurements was demonstrated by comparing prepared blood samples on the GlucoDr auto blood glucose monitoring system and a glucose reference method. The seventeen samples ranged in concentration from a low of approximately $10\mathrm{mg / dL}$ to a high of approximately $600\mathrm{mg / dL}$ . Three GlucoDr meters and three lots of blood glucose test strips were tested in replicates of three. Linear regression of the comparison data yielded the following relationship:
Lot 1 - y = 0.9973x - 1.6265, R² = 0.9996
Lot 2 - y = 1.0018x + 0.0570, R² = 0.9986
Lot 3 - y = 1.0004x + 0.9824, R² = 0.9987
The reportable range for glucose measurements is $20 - 600\mathrm{mg / dL}$
# c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Values for the control materials are assigned by repeat testing over time and analyzing the variation of the results. Expected values for each lot of control solutions are printed on the strip vial. The test strip and control solution stability was assessed by performing real-time and accelerated studies for the shelf life and in use stability. Stability protocols and acceptance criteria were evaluated and found to be acceptable. The claimed shelf life is 18 months and the claimed in-use stability is 90 days for control solution and 4 months in-use shelf life for the test strips when stored at room temperature.
# d. Detection limit:
See linearity/reportable range studies above.
{5}
# e. Analytical specificity:
Endogenous and exogenous substances were tested for interference on this assay at three glucose concentration (58, 163 and $261\mathrm{mg / dL}$ ). Three test strip lots and 4 meters were used in the study. The sponsor defined interference as a change in glucose measurement from the control greater than $10\mathrm{mg / dL}$ for glucose concentration $< 75\mathrm{mg / dL}$ and greater than $10\%$ for glucose concentration $>75\mathrm{mg / dL}$ . The following substances were tested.
| Exogenous Substances | Concentration Showing No Interference (mg/dL) |
| --- | --- |
| Acetaminophen | 6 |
| Ascorbic Acid | 4 |
| Dopamine | 13 |
| Ephedrine | 30 |
| Ibuprophen | 40 |
| L-dopa | 13 |
| Methyl dopa | 13 |
| Salicylate | 50 |
| Tetracycline | 4 |
| Tolazamide | 100 |
| Tolbutamine | 100 |
| Maltose | 20 |
| Endogenous Substances | Concentration Showing No Interference (mg/dL) |
| --- | --- |
| Bilirubin | 4 |
| Creatinine | 30 |
| Citric Acid | 30 |
| Hemoglobin | 500 |
| Oleic Acid | 1.4 |
| Palmitic Acid | 1.0 |
| Protein –Albumin | 6.0 |
| Triglycerides | 300 |
| Uric Acid | 10 |
All substances tested, except for the ones listed below, show no interference at the concentrations tested. The sponsor notes in the labeling that the following substances may affect the test results above concentrations tested; Acetaminophen, Ascorbic Acid, Total bilirubin, Triglyceride and Uric acid.
Hematocrit study:
The effect of hematocrit was evaluated in a study using samples with 5 glucose concentrations (40-60, 80-120, 150-200, 250-300, and $350 - 450\mathrm{mg / dL}$ ) and varying
{6}
hematocrit levels from 20 - 60%. Each glucose level/hematocrit combination was tested on 5 meters using 3 lots of test strips, by comparing the results of samples at each of the varying hematocrit levels to the sample of the same glucose concentration at a normal (40%) hematocrit level. Each glucose level/hematocrit combination was also compared to the corresponding YSI value. The data supports the sponsor's claimed hematocrit range of 20-60%.
## Altitude study:
An altitude study was performed with four whole blood samples spiked to the following concentration 80-120, 180-200, 280-320 and 380-420 mg/dL. The samples were tested at ground level up to 8,200 feet. All samples met the sponsor's acceptability criterion of the difference between the minimum and maximum result at each concentration range is < 10%. The data submitted supports use of the device up to 8,200 feet.
## Temperature and Humidity study:
Temperature and humidity studies were performed and showed that the meter can be used at temperatures from 10 to 40°C and humidity from 35 to 55%; and exposed to temperatures from -10 to 51°C and a relative humidity from 11 to 91%
f. Assay cut-off:
Not applicable
## 2. Comparison studies:
a. Method comparison with predicate device:
The consumer study was performed at three POC sites with a total of 130 lay-users. The lay-users ranged in age, education and were about equally divided between males and females. Each participant performed their own fingerstick and tested their blood using the instructions in the User's manual and package insert. A trained healthcare professional then performed another fingerstick and tested the blood on the same meter. Samples ranged from 31 to 552 mg/dL with samples below 63 mg/dL and above 423 mg/dL adjusted to acquire these extreme ranges. Blood was collected and measured on a YSI analyzer.
System accuracy results for glucose are present in the tables below:
For glucose concentrations < 75 mg/dL Lay-User
| within ± 5 mg/dL | within ± 10 mg/dL | within ± 15 mg/dL |
| --- | --- | --- |
| 9/17 (53%) | 16/17 (94%) | 17/17 (100%) |
For glucose concentrations ≥ 75 mg/dL Lay-User
| within ± 5 % | within ± 10 % | within ± 15 % | within ± 20 % |
| --- | --- | --- | --- |
| 83/113(73.5%) | 107/113(95%) | 113/113(100%) | 113/113(100%) |
{7}
For glucose concentrations $< 75\mathrm{mg / dL}$ Healthcare Professional
| within ± 5 mg/dL | within ± 10 mg/dL | within ± 15 mg/dL |
| --- | --- | --- |
| 10/17 (59%) | 16/17 (94%) | 17/17 (100%) |
For glucose concentrations $\geq 75\mathrm{mg / dL}$ Healthcare Professional
| within ± 5 % | within ± 10 % | within ± 15 % | within ± 20 % |
| --- | --- | --- | --- |
| 85/113(75.2%) | 104/113(92%) | 112/113(99%) | 113/113(100%) |
Alternate site testing:
The consumer study was performed at one POC site with a total of 51 lay-users. The lay-users ranged in age, education and were equally divided between males and females. Each participant performed a self-test on their finger, palm, arm and thigh testing their blood using the instructions in the User's guide. A trained professional then performed testing on the finger, palm, forearm, upper arm, thigh, and calf testing the blood on the same meter.
System accuracy alternative site Professional and Lay-user results for glucose are present in the tables below:
For glucose concentrations $< 75\mathrm{mg / dL}$ Lay-User
| | within ± 5 mg/dL | within ± 10 mg/dL | within ± 15 mg/dL |
| --- | --- | --- | --- |
| Finger | 6/9 (67%) | 9/9 (100%) | 9/9 (100%) |
| Palm | 5/9 (56%) | 9/9 (100%) | 9/9 (100%) |
| Upper Arm | 5/9 (56%) | 8/9 (89%) | 9/9 (100%) |
| Forearm | 6/9 (67%) | 9/9 (100%) | 9/9 (100%) |
| Thigh | 6/9 (67%) | 9/9 (100%) | 9/9 (100%) |
| Calf | 5/9 (56%) | 8/9 (89%) | 9/9 (100%) |
For glucose concentrations $\geq 75\mathrm{mg / dL}$ Lay-User
| | within ± 5 % | within ± 10 % | within ± 15 % | within ± 20 % |
| --- | --- | --- | --- | --- |
| Finger | 22/42 (52%) | 35/42 (83%) | 42/42 (100%) | 42/42 (100%) |
| Palm | 25/42 (60%) | 39/42 (93%) | 41/42 (98%) | 42/42 (100%) |
| Upper Arm | 23/42 (55%) | 36/42 (86%) | 42/42 (100%) | 42/42 (100%) |
| Forearm | 26/42 (62%) | 39/42 (93%) | 42/42 (100%) | 42/42 (100%) |
| Thigh | 25/42 (60%) | 36/42 (86%) | 42/42 (100%) | 42/42 (100%) |
| Calf | 34/42 (81%) | 38/42 (91%) | 41/42 (98%) | 42/42 (100%) |
For glucose concentrations $< 75\mathrm{mg / dL}$ Healthcare Professional
| | within ± 5 mg/dL | within ± 10 mg/dL | within ± 15 mg/dL |
| --- | --- | --- | --- |
| Finger | 5/9 (56%) | 8/9 (89%) | 9/9 (100%) |
| Palm | 5/9 (56%) | 9/9 (100%) | 9/9 (100%) |
| Upper Arm | 6/9 (67%) | 9/9 (100%) | 9/9 (100%) |
{8}
For glucose concentrations $\geq 75\mathrm{mg / dL}$ Healthcare Professional
| | within ± 5 % | within ± 10 % | within ± 15 % | within ± 20 % |
| --- | --- | --- | --- | --- |
| Finger | 26/42 (62%) | 39/42 (93%) | 42/42 (100%) | 42/42 (100%) |
| Palm | 33/42 (79%) | 39/42 (93%) | 42/42 (100%) | 42/42 (100%) |
| Upper Arm | 37/42 (88%) | 42/42 (100%) | 42/42 (100%) | 42/42 (100%) |
| Forearm | 34/42 (81%) | 41/42 (98%) | 42/42 (100%) | 42/42 (100%) |
| Thigh | 31/42 (74%) | 40/42 (95%) | 42/42 (100%) | 42/42 (100%) |
| Calf | 34/42 (81%) | 41/42 (98%) | 42/42 (100%) | 42/42 (100%) |
# b. Matrix comparison:
EDTA venous blood samples from 70 patients were assayed on the GlucoDr auto Blood Glucose Monitoring System and the YSI using two strip lots. Sample ranged from $58.3 - 431\mathrm{mg / dL}$ . The linear regression for each lot is:
Lot $1 - \mathrm{y} = 0.9926\mathrm{x} + 6.3264,\mathrm{r}^2 = 0.9969$
Lot $2 - \mathrm{y} = 1.0022\mathrm{x} + 7.0767,\mathrm{r}^2 = 0.9969$
Lot $1 + \mathrm{Lot}2 = \mathrm{y} = 0.9974\mathrm{x} - 6.7016,\mathrm{r}^2 = 0.9965$
System accuracy results for glucose are present in the tables below for the combined data from each lot:
For glucose concentrations $< 75\mathrm{mg / dL}$
| within ± 5 mg/dL | within ± 10 mg/dL | within ± 15 mg/dL |
| --- | --- | --- |
| 10/16 (62.5%) | 16/16 (100%) | 16/16 (100%) |
For glucose concentrations $\geq 75\mathrm{mg / dL}$
| within ± 5 % | within ± 10 % | within ± 15 % | within ± 20 % |
| --- | --- | --- | --- |
| 50/124(40%) | 103/124(83%) | 122/124(98%) | 124/124(100%) |
Lithium heparin arterial blood samples from 70 patients were assayed on the GlucoDr auto Blood Glucose Monitoring System and the YSI using two strip lots. Sample ranged from $56 - 398\mathrm{mg / dL}$ . The linear regression for each lot is:
Lot $1 - \mathrm{y} = 0.9700\mathrm{x} - 0.1545,\mathrm{r}^2 = 0.9952$
Lot $2 - \mathrm{y} = 0.9792\mathrm{x} - 0.1199,\mathrm{r}^2 = 0.9953$
Lot $1 + \mathrm{Lot}2 = \mathrm{y} = 0.9746\mathrm{x} - 0.1372,\mathrm{r}^2 = 0.9952$
{9}
System accuracy results for glucose are present in the tables below for the combined data from each lot:
For glucose concentrations $< 75\mathrm{mg / dL}$
| within ± 5 mg/dL | within ± 10 mg/dL | within ± 15 mg/dL |
| --- | --- | --- |
| 10/18 (55.6%) | 18/18 (100%) | 18/18 (100%) |
For glucose concentrations $\geq 75\mathrm{mg / dL}$
| within ± 5 % | within ± 10 % | within ± 15 % | within ± 20 % |
| --- | --- | --- | --- |
| 116/122(95%) | 121/122(99%) | 122/122(100%) | 122/122(100%) |
# 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:
The sponsor included the following Expected Values for people without diabetes in their strip labeling:
Status
Range
Fasting and Before meals
70-100 (mg/dL) (3.9-6.1 mmol/L)
2 hours after meals
Less than $140\mathrm{mg / dl}$ (7.8 mmol/L)
Source: ADA Clinical Practice Recommendations 2003
# N. Instrument Name:
The GlucoDr auto Blood Glucose Monitoring System
# O. System Descriptions:
{10}
1. **Modes of Operation:**
Each test strip is single use and must be replaced with a new strip for additional readings.
2. **Software:**
FDA has reviewed applicant’s Hazard Analysis and software development processes for this line of product types:
Yes ☑ or No ☐
3. **Specimen Identification:**
There is no sample identification function with this device. Samples are applied directly to the test strip as they are collected.
4. **Specimen Sampling and Handling:**
This device is intended to be used with capillary whole blood from the fingertip, palm, forearm or thigh and venous and arterial whole blood. For capillary whole blood, since the sample is applied directly to the test strip, there are no special handling or storage issues. For venous whole blood, samples must be tested within 15 minutes of draw and the sample cannot be stored.
5. **Calibration:**
Each vial of test strips has a code number which is used to calibrate the meter. The code number must be verified by turning on the meter using the power button. The code number cannot be changed with a test strip inserted into the port. The user confirms that the code number on the test strip bottle matches the code number in the instrument. No further calibrations are required of the user.
6. **Quality Control:**
The sponsor sells two levels of control solution with this device. To mark the test result as a control, after the test result is displayed the user is instructed to press the +/- buttons to select the attention event icon. After the attention event icon appears on the display press the power button to save. This distinguishes control results from actual blood glucose tests in the memory. An acceptable range for each control level is printed on the test strip vial label. If control results fall outside these ranges, the user is referred to a list of troubleshooting steps and the customer care line.
P. **Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:**
Not applicable
{11}
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 substantial equivalence decision.
12
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.