The Duo-Max Blood pressure and Glucose Monitor, Model HMF-100 consists of a meter with wrist cuff and test strips. The system is intended for use in the quantitative measurement of glucose in whole blood taken from the fingertip. Testing is done outside the body (In Vitro diagnostic use). It is indicated for use at home (over the counter [OTC]) by persons with diabetes mellitus, or in clinical settings by healthcare professionals, as an aid to monitor the effectiveness of diabetes control. It is not intended for use on neonates. Also the system measures systolic and diastolic blood pressure and pulse rate from adult's wrist in the home care environment. The device employs a wrist cuff and the oscillometric metric method of measurement.
Device Story
Duo-Max HMF-100 combines blood pressure (BP) monitor and blood glucose (BG) monitor in single wrist-mounted unit. BP component uses wrist cuff with oscillometric measurement method; BG component uses test strips for capillary whole blood analysis. User interface includes LCD displaying systolic/diastolic BP, pulse rate, date, and time. Device stores 180 BP and 270 BG readings. Used in home care or clinical settings by patients or healthcare professionals. Provides quantitative glucose and BP/pulse data to aid diabetes management and BP monitoring.
Clinical Evidence
Bench testing only. Device conforms to ANSI/AAMI SP-10 (BP), IEC 60601-1 (Safety), and IEC 60601-1-2 (EMC) requirements. No clinical trial data reported.
Technological Characteristics
Wrist-mounted unit with integrated cuff. Oscillometric BP measurement; test strip-based glucose measurement. Memory: 180 BP readings, 270 BG readings. Pulse rate range: 20-199 bpm. Battery-powered. Standards: ANSI/AAMI SP-10, IEC 60601-1, IEC 60601-1-2.
Indications for Use
Indicated for quantitative measurement of capillary whole blood glucose in adults for diabetes management; not for neonates, critically ill, dehydrated, or hyperosmolar patients; not for screening or diagnosis of diabetes. Also indicated for non-invasive measurement of systolic/diastolic blood pressure and pulse rate in adults in home care settings.
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
Blood Glucose and Blood Pressure Monitor System, Model BGP-100 Sein Electronics Co., Ltd (k052108)
Infopia GlucolabTM Blood Glucose Monitoring System (k051285)
Submission Summary (Full Text)
{0}
510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION
DECISION SUMMARY
ASSAY AND INSTRUMENT COMBINATION TEMPLATE
A. 510(k) Number:
k080636
B. Purpose for Submission:
Clearance of a new device
C. Measurand:
Capillary whole blood glucose
D. Type of Test:
Whole blood glucose concentration through a quantitative amperometric assay
(Glucose Oxidase)
E. Applicant:
HuBDIC Co., Ltd.
F. Proprietary and Established Names:
Duo-Max Blood Pressure and Glucose Monitor, Model HMF-100
G. Regulatory Information:
1. Regulation section:
21 CFR § 862.1345, Glucose Test System
21 CFR § 870.1130, Noninvasive Blood Pressure Measurement System
21 CFR § 862.1660, Quality control material (assayed and unassayed)
2. Classification:
Class II
Class I (reserved)
3. Product code:
NBW, CGA, JJX
DXN
4. Panel:
75 (Clinical Chemistry)
74 (Cardiovascular)
H. Intended Use:
1. Intended use(s):
See indications for use below.
2. Indication(s) for use:
{1}
The Blood pressure and glucose monitor, Duo-Max™ consists of a meter with wrist cuff and glucose test strips. The glucose test system is intended for use in the quantitative measurement of glucose in capillary whole blood taken from the fingertip, dorsal hand, ventral palm, upper arm, forearm, calf and thigh. Glucose testing is done outside the body (In Vitro diabetes mellitus, or in clinical settings by healthcare professionals. Glucose testing system is not to be used for the diagnosis or screening of diabetes. It is not intended for use on neonates. Also the blood pressure test system measures systolic and diastolic blood pressure and pulse rate from adult's wrist in the home care environment. The device employs a wrist cuff and the oscillometric metric method of measurement.
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:
Duo-Max Blood Pressure and Glucose Monitor, Model HMF-100
I. Device Description:
HuBDIC's Duo- Max Blood Pressure and Glucose Monitor System, Model HMF-100 combines the function of a blood pressure meter and a blood glucose monitoring system in one unit. Supplies with the meter are test strips, lancets, Lancing device, storage case, batteries and log book.
HMF-100 adopts the wrist type cuff for blood pressure monitoring. The cuff and control unit are combined into a single wrist-mounted assembly. The user interface pane has power switch, timer switch, memory switch and LCD for displaying the systolic and diastolic blood pressure, pulse rate, date and time. This device has the memory function that permits memory and display of the 180 most recent measurement results.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Blood Glucose and Blood Pressure Monitor System, Model BGP-100 Sein Electronics Co., Ltd
Infopia GlucolabTM Blood Glucose Monitoring System
2. Predicate 510(k) number(s):
k052108
k051285
3. Comparison with predicate:
{2}
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate (k052108) |
| Detection method | Amperometry | Amperometry |
| Enzyme | Glucose oxidase
(Aspergillus niger) | Glucose oxidase
(Aspergillus niger) |
| Test range | 20-600 mg/dL | 30-550 mg/dL |
| Hematocrit range | 30-55% | 30-55% |
| Sample volume | 1 μL | 1 μL |
| Glucose test time | 5 seconds | 5 seconds |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Pulse Rate | 20 ~ 199 pulse/min | 40 ~ 199 pulse/min |
| Number of readings stored in memory | 180 (Blood Pressure) | 60 (Blood Pressure) |
| | 270 (Blood Glucose) | 150 (Blood Glucose) |
| Size L x W x H (mm) | 64(W) x 84(W) x | 62(W) x 83(W) x |
| | 31(H)(mm) | 33(H)(mm) |
| Weight | 163g | 192g |
K. Standard/Guidance Document Referenced (if applicable):
- CLSI EP7-A, Interference Testing in Clinical Chemistry; Proposed Guideline
- ISO 15197:2003, In Vitro Diagnostic Test Systems – Requirements for Blood Glucose Monitoring Test Systems for Self Managing Diabetes Mellitus
- AAMI SP10:2002, Manual, Electronic or Automated Sphygmomanometers
L. Test Principle:
Glucose measurement is based on electrical potential caused by the reaction of glucose with the reagents contained on the strip’s electrodes. The glucose in the sample is oxidized by the enzyme glucose oxidase, and the current resulting from this enzymatic reaction is measured and converted to glucose concentration by the meter. The magnitude of the current is proportional to the concentration of glucose in the sample.
Blood pressure: the pressure sensor in the cuff detects small changes in pressure and converts them to electrical signals. The meter analyzes the signals and converts them to standard measurements of pulse rate and systolic and diastolic blood pressure.
M. Performance Characteristics (if/when applicable):
1. Analytical performance:
a. Precision/Reproducibility:
Within-Run
The testing was conducted using venous blood, collected in a heparin blood collection tube. Glucose was added to the blood to prepare 5 different levels of glucose for the testing. The glucose concentration ranges
{3}
were: $30 - 50\mathrm{mg / dL}$ , $51 - 110\mathrm{mg / dL}$ , $111 - 150\mathrm{mg / dL}$ , $151 - 250\mathrm{mg / dL}$ , and $251 - 400\mathrm{mg / dL}$ . For each testing range, the samples were tested 50 times.
| Range (mg/dL) | Assays | Mean (mg/dL) | SD (mg/dL) | CV (%) |
| --- | --- | --- | --- | --- |
| 30~50 | 50 | 43.7 | 1.8 | 4.2 |
| 51~110 | 50 | 86.8 | 2.4 | 2.8 |
| 111~150 | 50 | 138.4 | 4.1 | 3.0 |
| 151~250 | 50 | 215.9 | 5.9 | 2.8 |
| 251~400 | 50 | 373.6 | 10.7 | 2.9 |
# Day-to-Day Precision
Three control solutions of Low, Normal and High were prepared. Each control was tested four times a day, twice in the morning and twice in the afternoon for 20 days.
| Control solution | N | mean (mg/dL) | SD (mg/dL) | CV (%) |
| --- | --- | --- | --- | --- |
| Low | 80 | 50.5 | 1.0 | 2.1 |
| Normal | 80 | 106.6 | 1.9 | 1.7 |
| High | 80 | 306.3 | 2.9 | 1.0 |
# b. Linearity/assay reportable range:
To establish the linearity of the system through the range of 20 to $600\mathrm{mg / dL}$ , 11 glucose adjusted whole blood samples across the range were tested on the meter and compared to the YSI 2300 using 5 replicate measurements. Linear regression yields the following statistics:
| Slope | 1.0031 |
| --- | --- |
| Y-intercept | 0.1625 |
| R² | 0.9999 |
# c. Traceability, Stability, Expected values (controls, calibrators, or methods):
The sponsor claims that the device is traceable to a laboratory analyzer which is calibrated to a NIST traceable glucose standard.
The two control solutions (normal and high levels) consist of buffered aqueous solutions of $\beta$ -D-glucose and non-reactive ingredients. Lot-specific ranges are printed on the test strip bottle label.
Closed Vial Stability of Control Solution: The measured glucose levels of 3 lots of each level of control solution were tested using a real-time stability study. The results showed that during the tested time frame of 847 days at room temperature, the controls were within the specified ranges. The sponsor
{4}
claims a closed vial stability of 26 months.
Opened Vial Stability of Control Solution: The measured glucose levels of 3 lots of each level of control solution were tested during 96 days and were found to be within the specified ranges. The sponsor claims an open vial stability of 90 days.
## d. Detection limit:
The measuring range of the system is 20 - 600 mg/dL. See the linearity study above (section M.1.b.).
## e. Analytical specificity:
Spiked whole blood samples containing three levels of glucose, with and without interfering substances, were prepared to test common endogenous and exogenous substances for interference. Levels tested for each interferant (in mg/dL) are summarized below:
Low glucose sample < (60mg/dL)
| Interference substance | Highest interference Level Tested (mg/dL) | Mean of Test Results | | (mg/dL) Difference |
| --- | --- | --- | --- | --- |
| | | Glucose Level With No Interferant (mg/dL) | Glucose Level With Interferant Added (mg/dL) | |
| Acetaminophen | 20 | 45.0 | 43.4 | -1.6 |
| Bilirubin | 40 | 52.4 | 46.4 | -6.0 |
| Gentistic acid | 50 | 45.0 | 52.0 | 7.0 |
| Uric acid | 20 | 52.4 | 49.2 | -3.2 |
| Levo-Dopa | 4 | 47.6 | 46.0 | -1.6 |
| Creatinine | 30 | 45.0 | 44.2 | -0.8 |
| Methyl-Dopa | 2.5 | 47.6 | 49.2 | 1.6 |
| Tolazamide | 5 | 52.4 | 51.2 | -1.2 |
| Dopamine | 13 | 45.0 | 46.4 | 1.4 |
| Ascorbate | 3 | 45.0 | 48.0 | 3.0 |
| EDTA | 640 | 45.0 | 49.8 | 4.8 |
| Glutathione | 1 | 45.0 | 42.8 | -2.2 |
| Heparin | 1,000 | 45.0 | 43.2 | -1.8 |
| Ibuprofen | 40 | 52.6 | 48.4 | -4.2 |
| Salicylic acid | 50 | 45.0 | 44.2 | -0.8 |
{5}
Mid-level glucose sample (170mg/dL)
| Interference substance | Highest interference Level Tested (mg/dL) | Mean of Test Results | | (%) Difference |
| --- | --- | --- | --- | --- |
| | | Glucose Level With No Interferant (mg/dL) | Glucose Level With Interferant Added (mg/dL) | |
| Acetaminophen | 20 | 171.0 | 168.6 | -1.4 |
| Bilirubin | 40 | 166.2 | 157.2 | -5.4 |
| Gentistic acid | 50 | 171.0 | 181.6 | 6.2 |
| Uric acid | 20 | 166.2 | 161.6 | -2.8 |
| Levo-Dopa | 4 | 167.6 | 164.6 | -1.8 |
| Creatinine | 30 | 171.0 | 168.8 | -1.3 |
| Methyl-Dopa | 2.5 | 167.6 | 171.2 | 2.1 |
| Tolazamide | 5 | 166.2 | 163.4 | -1.7 |
| Dopamine | 13 | 171.0 | 172.8 | 1.1 |
| Ascorbate | 3 | 171.0 | 175.2 | 2.5 |
| EDTA | 640 | 171.0 | 178.2 | 4.2 |
| Glutathione | 1 | 171.0 | 167.4 | -2.1 |
| Heparin | 1,000 | 171.0 | 167.4 | -2.1 |
| Ibuprofen | 40 | 169.2 | 162.8 | -3.8 |
| Salicylic acid | 50 | 171.0 | 168.4 | -1.5 |
| Tetracycline | 0.4 | 171.0 | 169.4 | -0.9 |
| Tolbutamide | 100 | 169.2 | 167.4 | -1.1 |
| Urea | 500 | 171.0 | 184.2 | 7.7 |
| Cholesterol | 500 | 171.0 | 179.8 | 5.1 |
| TG | 3000 | 169.6 | 179.2 | 5.7 |
| Galactose | 50 | 171.0 | 166.6 | -2.6 |
{6}
High glucose sample $> (240\mathrm{mg / dL})$
| Interference substance | Highest interference Level Tested (mg/dL) | Mean of Test Results | | (%) Difference |
| --- | --- | --- | --- | --- |
| | | Glucose Level With No Interferant (mg/dL) | Glucose Level With Interferant Added (mg/dL) | |
| Acetaminophen | 20 | 290.2 | 285.6 | -1.6 |
| Bilirubin | 40 | 289.4 | 273.0 | -5.7 |
| Gentistic acid | 50 | 290.2 | 308.8 | 6.4 |
| Uric acid | 20 | 289.4 | 281.8 | -2.6 |
| Levo-Dopa | 4 | 291.0 | 284.6 | -2.2 |
| Creatinine | 30 | 290.2 | 286.0 | -1.4 |
| Methyl-Dopa | 2.5 | 291.0 | 296.4 | 1.9 |
| Tolazamide | 5 | 289.4 | 284.8 | -1.6 |
| Dopamine | 13 | 290.2 | 293.0 | 1.0 |
| Ascorbate | 3 | 290.2 | 297.0 | 2.3 |
| EDTA | 640 | 290.2 | 301.8 | 4.0 |
| Glutathione | 1 | 290.2 | 284.4 | -2.0 |
| Heparin | 1,000 | 290.2 | 283.2 | -2.4 |
| Ibuprofen | 40 | 289.4 | 278.6 | -3.7 |
| Salicylic acid | 50 | 290.2 | 286.4 | -1.3 |
| Tetracycline | 0.4 | 290.2 | 288.6 | -0.6 |
| Tolbutamide | 100 | 289.4 | 286.8 | -0.9 |
| Urea | 500 | 290.2 | 313.2 | 7.9 |
| Cholesterol | 500 | 288.8 | 304.4 | 5.4 |
| TG | 3000 | 291.0 | 307.4 | 5.6 |
| Galactose | 50 | 290.2 | 281.8 | -2.9 |
| Xylose | 10 | 290.2 | 284.8 | -1.9 |
| Maltose | 300 | 290.2 | 281.0 | -3.2 |
Interference testing showed that the system results in less than $\pm 10\%$ bias (or $\pm 10\mathrm{mg / dL}$ for glucose samples less than $60~\mathrm{mg / dL}$ ) in the presence of high concentrations of interferants, even beyond clinically significant ranges.
{7}
An altitude study was performed with 9 venous blood samples ranging from 30 to 530 mg/dL. Testing was performed at altitudes of sea level and 10,000 feet (using a chamber). The test data showed that the bias versus YSI at 10,000 feet is the same bias versus YSI observed at sea level. These data indicate no additional effect due to altitude up to the claimed altitude of 10,000 feet.
Hematocrit interference was evaluated by adjusting the glucose concentrations and hematocrit levels of venous blood samples. The venous blood samples were spiked to 8 glucose concentrations (40, 70, 110, 180, 250, 350, 450, and 550 mg/dL). The hematocrit levels were adjusted to 30%, 40%, 55%. Each sample was assayed 15 times and the maximum percent bias was calculated compared to the 40% hematocrit samples. The sponsor demonstrated that the bias did not exceed ±15 mg/dL when glucose concentration is ≤75 mg/dL and bias did not exceed ±15% when glucose concentration is >75 mg/dL for hematocrit concentrations within the claimed range of 30% to 55%.
f. Assay cut-off:
Not Applicable.
2. Comparison studies:
a. Method comparison with predicate device:
To demonstrate the accuracy performance of the Duo-Max Blood Pressure and Glucose Monitor, 160 patients samples were tested in duplicate using capillary blood samples from the finger (with samples ranging from 31 to 487 mg/dL) and compared to the results from a laboratory reference method using samples taken at the same time. Samples with blood glucose levels below 50 mg/dL were obtained by glycolysis of patient samples and samples above 400 were obtained by supplementing the samples with glucose. Results are summarized below:
| | Fingerstick vs. Reference |
| --- | --- |
| Samples < 75 mg/dL within ±15 mg/dL YSI | 60/60 (100%) |
| Samples ≥ 75 mg/dL within ±20% YSI | 258/260 (99%) |
| Total | 318/320 (99%) |
A consumer study was performed with 150 lay-users and a technician to see how well results obtained from a lay user compared to results obtained by a technician. The labeling provided to the users was in English only. Each participant performed their own test and tested their blood using the instructions in the user's manual, then a technician performed a test using the same meter. Samples ranged from 50 - 537 mg/dL. Results are summarized below:
{8}
| | Lay User Fingerstick vs. Technician Fingerstick |
| --- | --- |
| Samples < 75 mg/dL within ±15 mg/dL YSI | 25/25 (100%) |
| Samples ≥ 75 mg/dL within ± 20% YSI | 124/125 (99%) |
| Total | 149/150 (99%) |
A study was performed with 100 participants to determine if the performance of the Duo-Max on alternate site (palm, forearm, thigh, and calf) were comparable to fingertip when obtained by lay users). The labeling provided to the users was in English only. Each participant performed their own test and tested their blood using the instructions in the user's manual. Samples ranged from 61 - 485 mg/dL. Results are summarized below:
| | Dorsal Palm vs. Fingerstick | Ventral Palm vs. Fingerstick | Forearm vs. Fingerstick | Upper Arm vs. Fingerstick | Calf vs. Fingerstick | Thigh vs. Fingerstick |
| --- | --- | --- | --- | --- | --- | --- |
| Samples < 75 mg/dL within ±15 mg/dL Fingerstick | 6/6 (100%) | 6/6 (100%) | 6/6 (100%) | 7/7 (100%) | 6/6 (100%) | 8/8 (100%) |
| Samples ≥ 75 mg/dL within ± 20% Fingerstick | 93/94 (99%) | 93/94 (99%) | 93/94 (99%) | 92/93 (99%) | 93/94 (99%) | 91/92 (99%) |
| Total | 99/100 (99%) | 99/100 (99%) | 99/100 (99%) | 99/100 (99%) | 99/100 (99%) | 99/100 (99%) |
b. Matrix comparison:
Not applicable. Capillary whole blood is the only indicated matrix.
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):
The sponsor provided a readability study that indicated that the user manual, test strip labeling, and control solution labeling is at an 8th grade reading level or below.
{9}
4. Clinical cut-off:
Not Applicable.
5. Expected values/Reference range:
The sponsor included the following expected values for normal glucose levels for people without diabetes in their strip labeling:
70 mg/dL (3.9 mmol/L) - 110 mg/dL (6.1 mmol/L)¹
Two hours after meals: less than 140 mg/dL (7.8 mmol/L)²
¹Stedmans Medical Dictionary, 27th Edition, 1999, p 755.
²American Diabetes Association Clinical Practice Recommendations 2004, Diabetes Care, Vol. 27 Supplement 1, p. S9
N. Instrument Name:
Duo-Max Blood Pressure and Glucose Monitor, Model HMF-100
O. System Descriptions:
1. Modes of Operation:
Each test strip is single use and must be replaced with a new strip for additional readings.
Does the applicant’s device contain the ability to transmit data to a computer, webserver, or mobile device?:
Yes ______ or No ☐ X
Does the applicant’s device transmit data to a computer, webserver, or mobile device using wireless transmission:
Yes ______ or No ☐ X
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:
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 finger, palm, and forearm. Since the whole blood sample is applied directly to the test strip there are no special handling or storage issues.
5. Calibration:
A code number is provided with each batch of test strips to calibrate the meter for
{10}
that lot. The code number is associated with the meter by inserting a test strip and entering the code number to match that found on the test strip bottle. No further calibrations are required of the user.
6. **Quality Control:**
The sponsor has two levels of controls available for this meter with one level coming with the kit. When a test strip is inserted into the meter, a control can be run. An acceptable range for each control level is printed on the test strip vial label. The user is referred to a troubleshooting section at the end of the control test instructions of the owner's manual to identify possible reasons control results fall outside these ranges.
P. **Other Supportive Instrument Performance Characteristics Data Not Covered In The "Performance Characteristics" Section above:**
The blood pressure monitoring system was reviewed by the Office of Device Evaluation and found to be acceptable.
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.