HemosIL INR Validate is a tri-level quality control intended to monitor the accuracy of INR (International Normalized Ratio) reporting with designated HemosIL PT reagents on IL Coagulation Systems in conjunction with the ISIweb software. HemosIL ISI Calibrate is a set of four certified plasmas intended to establish a laboratory's instrument/ reagent specific local ISI (International Sensitivity Index) and Mean Normal Prothrombin Time (MNPT) with designated HemosIL PT reagents on IL Coagulation Systems in conjunction with the ISIweb software. ISIweb Software is a web-based service to customers, used in conjunction with HemosIL INR Validate and HemosIL ISI Calibrate with designated HemosIL PT reagents on IL Coagulation Systems; whereby the PT seconds and INR results can be entered and calculated through a web-based interface (ISIweb software).
Device Story
System comprises three components: HemosIL INR Validate (control plasmas), HemosIL ISI Calibrate (calibration plasmas), and ISIweb software. Used on IL Coagulation Systems to manage PT/INR testing. Laboratory technicians input PT seconds and INR results into the web-based ISIweb interface. Software calculates mean INR for controls to verify system accuracy (±15% threshold) or generates calibration curves for local ISI/MNPT assignment using orthogonal regression of LogINR vs. LogPT. If controls exceed thresholds, software triggers recommendation for new local calibration. System ensures standardized INR reporting for patients on vitamin K antagonist therapy, improving clinical decision-making regarding anticoagulant dosage.
Clinical Evidence
Bench testing only. Precision study conducted per CLSI EP05-A2 (20 days, 2 replicates/run, 2 runs/day, N=80 per level) using IL Coagulation Systems (ACL TOP, ACL 10000) and various HemosIL PT reagents. Results demonstrated acceptable within-run and total %CV across all control and calibration levels.
Technological Characteristics
Lyophilized citrated human plasma controls and calibrators. Web-based software (ISIweb) for data entry and calculation. Orthogonal regression algorithm for ISI/MNPT derivation. Connectivity via web interface. No specific material standards cited beyond compliance with CLSI H54-A and ISTH guidelines.
Indications for Use
Indicated for use as quality control and calibration plasmas for monitoring and establishing INR, ISI, and MNPT values in patients undergoing anti-vitamin K therapy, using designated HemosIL PT reagents on IL Coagulation Systems.
Regulatory Classification
Identification
A multipurpose system for in vitro coagulation studies is a device consisting of one automated or semiautomated instrument and its associated reagents and controls. The system is used to perform a series of coagulation studies and coagulation factor assays.
Special Controls
*Classification.* Class II (special controls). A control intended for use with a multipurpose system for in vitro coagulation studies is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 864.9.
{0}
1
# 510(k) SUBSTANTIAL EQUIVALENCE DETERMINATION DECISION SUMMARY
A. 510(k) Number:
k090563
B. Purpose for Submission:
To seek clearance for the following devices:
1. Tri-level quality control plasmas
2. Four-level calibration plasmas
3. ISIweb software
C. Measurand:
Prothrombin Time (PT), INR (International Normalized Ratio), ISI (International Sensitivity Index), and Mean Normal Prothrombin Time (MNPT)
D. Type of Test:
Control and Calibrator plasmas: clotting assay.
ISIweb: calculator/data processing module for clinical use.
E. Applicant:
Instrumentation Laboratory Co.
F. Proprietary and Established Names:
HemosIL® INR Validate
HemosIL® ISI Calibrate
ISIweb Software
G. Regulatory Information:
1. Regulation section:
21 CFR 864.5425; Multipurpose system for in vitro coagulation studies
21 CFR 862.1150; Calibrator
21 CFR 862.2100; Calculator/data processing module for clinical use
2. Classification:
Class II: (Controls and Calibrators)
Class I: (ISIweb)
3. Product code:
GGN; Plasma, Coagulation Control
JIS; Calibrator, primary
JQP Calculator/Data Processing Module, For Clinical Use
4. Panel:
Hematology (81)
H. Intended Use:
1. Intended use(s):
HemosIL INR Validate is a tri-level quality control intended to monitor the accuracy of INR (International Normalized Ratio) reporting with designated HemosIL PT reagents on IL Coagulation Systems in conjunction with the ISIweb software.
HemosIL ISI Calibrate is a set of four certified plasma intended to establish a laboratory’s instrument/reagent specific local ISI (International Sensitivity Index) and Mean Normal Prothrombin Time (MNPT) with designated HemosIL PT reagents on IL Coagulation Systems in conjunction with the ISIweb software.
{1}
ISIweb Software is a web-based service to customers, used in conjunction with HemosIL INR Validate and HemosIL ISI Calibrate with designated HemosIL PT reagents on IL Coagulation Systems, whereby the PT seconds and INR results can be entered and calculated through a web-based interface (ISIweb software).
2. Indication(s) for use:
Same as Intended Use
3. Special conditions for use statement(s):
Prescription Use only
4. Special instrument requirements:
IL Coagulation Systems: ACL TOP Family, ACL Futura Advance, ACL 8/9/10000/Elite/Pro, ACL 100 - 7000
I. Device Description:
1. HemosIL® INR Validate: the control set consists of three-levels of lyophilized citrated control plasmas which have assigned INR reference values in the range of 1.6 - 5.0. Level 1 has an INR range of 1.6 - 2.4, Level 2 of 2.5 - 3.5, and Level 3 of 3.8 - 5.0. The reference INR values for each level are reagent-specific for the IL coagulation systems. The plasmas are collected from human donors on stable anti-vitamin K therapy. The INRs are monitored by running the controls on a local instrument/reagent system using the laboratory's locally established lot-specific MNPT and manufacturer's lot-specific ISI value.
2. HemosIL® ISI Calibrate: The calibrator set contains four-levels of lyophilized citrated calibration plasmas which have assigned INR reference values in the range of 0.9 - 5.0. Level A has an INR range of 0.9 - 1.1, Level B of 1.6 - 2.4, Level C of 2.5 - 3.5, and Level D of 3.8 - 5.0. The reference INR values for each level are reagent-specific for the IL coagulation systems. Level A is collected from normal human pool. Levels B, C, and D are collected from a pool of human donors on stable anti-vitamin K therapy.
3. ISIweb: ISIweb is a web-based service for customers used in conjunction with designated HemosIL PT reagents on IL coagulation systems, whereby the PT and INR results can be entered and calculated.
J. Substantial Equivalence Information:
1. Predicate device name(s):
Pacific Hemostasis INR Control Plasma
HemosIL Calibration Plasma
2. Predicate K number(s):
k010750
k041905
3. Comparison with predicate:
HemosIL® INR Validate
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Indications for Use | HemosIL INR Validate is a tri-level quality control intended to monitor the accuracy of INR reporting with designated HemosIL PT reagents on IL | Pacific Hemostasis INR controls, levels 1-5, are intended for use as controls to check the performance of PT testing. Pacific Hemostasis warrants the INR values of control |
| | in the range of 1.6 - 5.0. Level A has an INR range of 0.9 - 1.1, Level B of 1.6 - 2.4, Level C of 2.5 - 3.5, and Level D of 3.8 - 5.0. The reference INR values for each level are reagent-specific for the IL coagulation systems. Level A is collected from normal human pool. Levels B, C, and D are collected from a pool of human donors on stable anti-vitamin K therapy. | in the range of 1.6 - 5.0. Level B, level C, and level D are collected from normal human pool. Levels B, C, and D are collected from a pool of human donors on stable anti-vitamin K therapy. |
{2}
3
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| | Coagulation systems. | plasma only for use with Pacific Hemostasis brand ThromboPlastTins. |
| Instrument/Reagent Test System | PT reagent-specific INR reference values for IL Coagulation Systems | Instrument/Reagent specific INR reference values |
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Certification | The three control plasmas are certified, with INR reference values traceable to WHO International Reference Thromboplastins and consensus testing from >200 laboratories. | The reference values are calculated by the manufacturer from the mean normal PT (MNPT) for each reagent/instrument combination of ≥ 20 and the thromboplastin ISI, which is directly traceable to the WHO International Reference Thromboplastins. |
| INR Levels | Level 1: 1.6 – 2.4
Level 2: 2.5 – 3.5
Level 3: 3.8 – 5.0 | Level 1: 1 – 1.4
Level 2: 1.5 – 2.0
Level 3: 2.1 – 2.7
Level 4: 2.8 – 3.5
Level 5: 3.6 – 5 |
| Preparation | Prepared using lyophilized citrated plasma from human donors on stable anti-vitamin K therapy (AVK), in which the plasma factors are similar to those levels normally expected in plasma from patients undergoing long-term oral anticoagulant therapy, together with the proteins induced by vitamin K antagonists. | Prepared using lyophilized citrated plasma from healthy donors. The plasma are adjusted during the manufacturing proves to yield the clot times with an INR ranges from 1 to 5.2. |
| Composition | Lyophilized human plasma with buffer, no preservative. | Lyophilized human plasma with buffer and stabilizer. |
## HemosIL® ISI Calibrate
| Similarities | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Indications for Use | HemosIL ISI Calibrate is a set of four certified plasmas intended to establish a laboratory’s instrument/reagent specific local ISI (International Sensitivity | Calibration of coagulation assays on both ELECTRA and IL Coagulation systems |
{3}
4
| Differences | | |
| --- | --- | --- |
| Item | Device | Predicate |
| Indications for Use | HemosIL ISI Calibrate is a set of four certified plasmas intended to establish a laboratory’s instrument/reagent specific local ISI (International Sensitivity Index) and Mean Normal Prothrombin Time (MNPT) with designated HemosIL PT reagents on IL Coagulation Systems in conjunction with the ISIweb software. | Calibration of coagulation assays on both ELECTRA and IL Coagulation systems |
| Certification | The four calibrate plasmas are certified, with INR reference values traceable to WHO International reference thromboplastins and consensus testing from >200 laboratories. ISI values in the consensus testing come from label values traceable to the WHO laboratories. | Recommendation to use international reference thromboplastin (IRP) using the manual tilt-tube technique from at least two different WHO centers with locally determined MNPT. |
| INR Levels | Level A: 0.9 – 1.1
Level B: 1.6 – 2.4
Level C: 2.5 – 3.5
Level D: 3.8 – 5.0 | Calibrate using control plasmas |
| Preparation | Prepared using lyophilized citrated plasmas. Normal (Level A) from normal human pool. Levels B, C, and D from human donors on stable anti-vitamin K therapy. No preservative. | Lyophilized citrated plasma containing buffer and preservatives. The calibration plasma is prepared using citrated plasma from healthy donors by means of a dedicated process to maintain the characteristics of a normal plasma pool. |
| Composition | Lyophilized human plasma with buffer. | Lyophilized plasma with minimal additives recommended for adequate stability. |
K. Standard/Guidance Document Referenced:
CLSI EP05-A2: Evaluation of Precision Performance of Quantitative Measurement
{4}
Methods; Approved Guideline, 2nd Ed.
CLSI H54-A: Procedure for validation of INR and Local Calibration of PT/INR Systems; Approved Guideline.
## L. Test Principle:
### HemosIL® INR Validate:
As determined through the ISIweb software, the PT/INR system is verified if the mean INRs of all controls are within of ± 15% of their assigned INR reference values. If the mean INRs of all the controls are within ± 15% of their assigned INR reference values, the PT/INR system is verified. If the mean INRs of the controls are not within ± 15% of their assigned INR reference values, a new local ISI calibration is recommended using the HemosIL ISI calibrate set. The new local ISI and MNPT is verified by re-running the HemosIL INR Validate controls on the same instrument/reagent system with the local ISI and MNPT
### HemosIL® ISI Calibrate:
To establish a local ISI, the calibrate plasmas are run on the IL instrument/reagent system. The PT (second) data is entered into the ISIweb, which will generate a calibration curve from the PT and the INR reference values by plotting an orthogonal regression of LogINR (x-axis) vs. LogPT (y-axis). From the slope and y-intercept of the curve, the ISI and MNPT are derived as follows:
$$
\mathrm{ISI} = 1/\text{slope} \quad \mathrm{MNPT} = 10^{\mathrm{y\text{-}intercept}}
$$
### ISIweb:
When used in conjunction with HemosIL Validate, the mean INR for each control level will be automatically calculated by ISIweb. The ISIweb will verify whether the mean INR for each level of control is within ± 15% of the assigned INR reference values. When used in conjunction with HemosIL ISI Calibrate, the mean PT and % CV value of each calibrator level is automatically calculated by the ISIweb software. For each level of the calibrator, if the % CV passes specification, ISIweb generates a calibration curve from the PT and INR reference values by plotting an orthogonal regression of LogINR (x-axis) vs. LogPT (y-axis).
## M. Performance Characteristics (if/when applicable):
### 1. Analytical performance:
#### a. Precision/Reproducibility:
- The precision study was performed in accordance with CLSI EP05-A2, Evaluation of Precision Performance of Quantitative Measurement Methods, on one lot. Two replicates per run, two runs per day, 20 days (n=80) per level on three levels of Validate and four levels of Calibrate using HemosIL reagents on representative IL instruments: ACL TOP and ACL 10000. For the HemosIL Validate, levels 1-3 met their within-run % CV specification of ≤6%. For the HemosIL Calibrate, Level A and Levels B-D met their within-run %CV specification of ≤3% and ≤6%, respectively.
{5}
HemosIL INR Validate (Levels 1-3)
| Reagent | Instrument | Level | Mean (Seconds) | Within-Run % CV | Total % CV |
| --- | --- | --- | --- | --- | --- |
| HemosIL RecombiPlasTin | ACL TOP | 1 | 28.1 | 1.2 | 1.5 |
| | ACL 10000 | | 27.2 | 1.0 | 2.1 |
| | ACL TOP | 2 | 43.5 | 1.0 | 2.5 |
| | ACL 10000 | | 41.4 | 1.3 | 3.1 |
| | ACL TOP | 3 | 68.3 | 2.8 | 3.5 |
| | ACL 10000 | | 65.5 | 1.0 | 1.5 |
| HemosIL RecombiPlasTin 2G | ACL TOP | 1 | 22.3 | 2.0 | 2.5 |
| | ACL 10000 | | 21.2 | 0.9 | 1.9 |
| | ACL TOP | 2 | 33.9 | 0.9 | 1.8 |
| | ACL 10000 | | 32.0 | 1.2 | 3.0 |
| | ACL TOP | 3 | 53.2 | 4.1 | 4.4 |
| | ACL 10000 | | 51.4 | 1.2 | 2.0 |
| HemosIL PT-Fibrinogen HS PLUS | ACL TOP | 1 | 24.7 | 1.3 | 2.5 |
| | ACL 10000 | | 24.5 | 0.7 | 1.7 |
| | ACL TOP | 2 | 35.4 | 1.6 | 2.7 |
| | ACL 10000 | | 34.6 | 1.2 | 2.2 |
| | ACL TOP | 3 | 50.5 | 3.5 | 4.2 |
| | ACL 10000 | | 48.0 | 1.5 | 3.4 |
| HemosIL PT-Fibrinogen HS* | ACL 10000 | 1 | 21.2 | 0.9 | 1.9 |
| | ACL 10000 | 2 | 32.0 | 1.2 | 3.0 |
| | ACL 10000 | 3 | 51.4 | 1.2 | 2.0 |
| HemosIL PT-Fibrinogen | ACL TOP | 1 | 16.6 | 0.4 | 2.1 |
| | ACL 10000 | | 17.5 | 0.7 | 2.2 |
| | ACL TOP | 2 | 21.0 | 0.4 | 3.4 |
| | ACL 10000 | | 22.4 | 0.7 | 3.6 |
| | ACL TOP | 3 | 27.5 | 0.4 | 3.9 |
| | ACL 10000 | | 29.8 | 1.9 | 4.1 |
*Application is not currently available for HemosIL PT-Fibrinogen HS on the ACL TOP family.
HemosIL ISI Calibrate (Levels A-D)
| Reagent | Instrument | Level | Mean (Seconds) | Within-Run % CV | Total % CV |
| --- | --- | --- | --- | --- | --- |
| HemosIL RecombiPlasTin | ACL TOP | A | 12.1 | 1.2 | 1.3 |
| | ACL 10000 | | 11.8 | 0.6 | 1.1 |
| | ACL TOP | B | 29.5 | 0.8 | 1.2 |
{6}
| Reagent | Instrument | Level | Mean (Seconds) | Within-Run % CV | Total % CV |
| --- | --- | --- | --- | --- | --- |
| | ACL 10000 | | 27.9 | 1.3 | 2.0 |
| | ACL TOP | C | 43.7 | 0.7 | 1.2 |
| | ACL 10000 | | 42.2 | 0.7 | 1.1 |
| | ACL TOP | D | 68.8 | 4.4 | 4.6 |
| | ACL 10000 | | 66.9 | 0.8 | 2.0 |
| HemosIL RecombiPlasTin 2G | ACL TOP | A | 11.2 | 1.5 | 1.6 |
| | ACL 10000 | | 10.7 | 0.8 | 1.2 |
| | ACL TOP | B | 23.2 | 1.2 | 2.2 |
| | ACL 10000 | | 21.4 | 1.3 | 2.2 |
| | ACL TOP | C | 33.9 | 1.0 | 1.7 |
| | ACL 10000 | | 31.6 | 1.0 | 2.0 |
| | ACL TOP | D | 50.8 | 4.4 | 4.9 |
| | ACL 10000 | | 48.5 | 1.0 | 2.2 |
| HemosIL PT-Fibrinogen HS PLUS | ACL TOP | A | 13.4 | 1.0 | 2.1 |
| | ACL 10000 | | 13.5 | 1.2 | 2.1 |
| | ACL TOP | B | 24.0 | 1.8 | 2.5 |
| | ACL 10000 | | 23.7 | 1.1 | 4.2 |
| | ACL TOP | C | 35.1 | 1.2 | 2.2 |
| | ACL 10000 | | 35.2 | 1.1 | 1.8 |
| | ACL TOP | D | 50.4 | 3.4 | 3.9 |
| | ACL 10000 | | 50.1 | 0.8 | 2.0 |
| HemosIL PT-Fibrinogen HS* | ACL 10000 | A | 10.7 | 0.1 | 1.2 |
| | ACL 10000 | B | 21.4 | 1.3 | 2.2 |
| | ACL 10000 | C | 31.6 | 1.0 | 2.0 |
| | ACL 10000 | D | 48.5 | 1.0 | 2.2 |
| HemosIL PT-Fibrinogen | ACL TOP | A | 11.7 | 0.9 | 1.8 |
| | ACL 10000 | | 11.9 | 0.8 | 1.4 |
| | ACL TOP | B | 16.0 | 0.4 | 2.3 |
| | ACL 10000 | | 16.8 | 0.7 | 2.3 |
| | ACL TOP | C | 20.7 | 0.3 | 2.9 |
| | ACL 10000 | | 22.2 | 0.9 | 3.0 |
| | ACL TOP | D | 26.6 | 0.4 | 3.7 |
| | ACL 10000 | | 28.8 | 0.4 | 3.5 |
*Application is not currently available for HemosIL PT-Fibrinogen HS on the ACL TOP family.
An additional precision study was performed utilizing CLSI H54-A on three lots. Two replicates per run over 3 days $(n = 6)$ for each level of control and calibrator using the following reagent and instruments:
HemosIL PT-Fibrinogen, HemosIL PT-Fibrinogen HS (not available on the
{7}
ACL TOP family), HemosIL PT-Fibrinogen HS PLUS, HemosIL RecombiPlasTin 2G, and HemosIL RecombiPlasTin.
ACL300, ACL 3000, ACL 6000, ACL 10000, ACL Advance, and ACL TOP. For the HemosIL Validate, levels 1-3 met their within-run % CV specification of ≤6%. For the HemosIL Calibrate, Level A and Levels B-D met their within-run % CV specification of ≤3% and ≤6%, respectively.
b. Linearity/assay reportable range:
Not applicable
c. Traceability, Stability, Expected values (controls, calibrators, or methods):
Traceability: The traceability of the tri-level HemosIL Validate and the four-level HemosIL Calibrate with INR reference values are summarized as follows: The House Standard ISI Calibrate INR reference value is derived from the mean INR reference values from combined sources of >200 laboratories and three WHO laboratories. At the WHO laboratories, Human IRP (RTF/95) and Rabbit IRP (RBT/05) were used. The House Standard ISI/MNPT for each instrument/reagent combination are derived from House Standard Calibration curves using the House Standard ISI Calibrate reference INR values and PT (seconds). Reagent-specific INR reference values for each production lot of HemosIL Calibrate and HemosIL Validate are calculated from the mean PT (seconds) and the House Standard ISI/MNPT on the same instrument/reagent combinations as the assignment of the House Standard ISI and MNPT.
Stability:
Reconstituted stability studies were performed to support the reconstituted stability for the HemosIL Validate and HemosIL Calibrate. Two lots were used in the studies for each device. At different time intervals, the stored control and calibrator levels were analyzed in a minimum of four replicates and the mean results were compared to the Time 0 mean results.
- 8 hours at 2-8° C in the original vial
- 30 days at -20° C in the original vial
- 4 hours at 15-25° C on-board IL Coagulation System
A shelf life stability study is ongoing at 2-8° C using three different lots of HemosIL Validate and HemosIL Calibrate plasmas. At different time intervals, the plasmas were run in a minimum of four replicates using the representative IL instrument/PT reagent combinations. The results were compared to the Time 0 mean results. The package insert instructs the end user to use the expiration date as shown on the vial. The results to date are within acceptable limits of ± 10% difference from Time 0 mean results.
d. Detection limit:
Not applicable
e. Analytical specificity:
Not applicable
f. Assay cut-off:
Not applicable
2. Comparison studies:
a. Method comparison with predicate device:
{8}
Not applicable
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):
An external testing was performed to evaluate the performance of the HemosIL Validate and HemosIL Calibrate. Specific instrument/PT reagent combination was used in the study. Data indicate that the INR Validate and ISI Calibrate met performance specification: the mean INR was within ± 15% of the reference value for each level of the plasma controls.
4. Clinical cut-off:
Not applicable
5. Expected values/Reference range:
Not applicable
N. Proposed Labeling:
The labeling is sufficient and it satisfies the requirements of 21 CFR Part 809.10.
O. Conclusion:
The submitted information in this premarket notification is complete and supports a substantial equivalence decision.
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.