DEN170072 · Timpel, Inc. · QEB · Dec 20, 2018 · Anesthesiology
Device Facts
Record ID
DEN170072
Device Name
Enlight 1810
Applicant
Timpel, Inc.
Product Code
QEB · Anesthesiology
Decision Date
Dec 20, 2018
Decision
DENG
Submission Type
Direct
Regulation
21 CFR 868.1505
Device Class
Class 2
Attributes
Real-World Evidence
Real-World Evidence
Submission
Device
Sponsor
RWD Sources
RWE Use Summary
Key Tags
DEN170072 · Dec 20, 2018
Enlight 1810
Timpel, Inc.
Retrospective clinical chart/data review
A retrospective analysis of 39 patients was used to assess the regional distribution of ventilation to the anterior and posterior halves of the lung at different PEEP levels to support the clinical performance of the device.
Retrospective analysis; Ventilation distribution; PEEP levels
Clinical Evidence
Study Design
Population
Comparator
Key Endpoints
Retrospective analysis of 39 patients; Retrospective analysis
39 patients evaluated for regional distribution of ventilation; Sample Size: 39
Not applicable for this study
Proportion of ventilation to the anterior region at the highest and lowest PEEP levels
Indications for Use
ENLIGHT 1810 is a non-invasive, non-radiation medical device that provides information of local impedance variation within a cross-section of a patient's thorax. This information is presented to the clinician user as an adjunctive tool to other clinical information in order to support the user's assessment of variations in regional air content within a cross section of a patient's lungs. It is intended for mechanically ventilated adult patients in a hospital setting, whose thorax perimeter is within the range of 78-122 cm.
Device Story
ENLIGHT 1810 is a non-invasive, non-radiological ventilatory electrical impedance tomograph; operates by measuring local impedance variation within a cross-section of a patient's thorax; provides clinicians with visual information regarding regional air content variations in lungs; used as an adjunctive tool to support clinical assessment of mechanically ventilated adult patients in hospital settings; output assists healthcare providers in monitoring lung ventilation; benefits include non-invasive, radiation-free assessment of regional lung air distribution.
Clinical Evidence
No clinical data provided. The device classification is supported by non-clinical performance testing, including characterization of device parameters (signal-to-noise ratio, voltage accuracy, drift, reciprocity accuracy, amplitude response, position error, ringing), real-time evaluation of local impedance variation, plethysmogram accuracy testing, and use-life testing of reusable components.
Technological Characteristics
Non-invasive electrical impedance tomography system. Components must be biocompatible. Requires electrical, thermal, and mechanical safety testing and electromagnetic compatibility testing. Includes reusable components requiring validated reprocessing. Software-based image generation and analysis. Operates as a prescription device for hospital use.
Indications for Use
Indicated for mechanically ventilated adult patients in a hospital setting with a thorax perimeter of 78-122 cm. Contraindicated for pregnant/lactating women, patients with active implantable devices (pacemakers, ICDs, neurostimulators), and use in MRI suites or environments with flammable anesthetic gases/elevated ambient oxygen.
Regulatory Classification
Identification
A ventilatory electrical impedance tomograph is a prescription non-invasive, non-radiological ventilatory device that provides an assessment of local impedance variation within a cross-section of a patient's thorax.
Special Controls
In combination with the general controls of the FD&C Act, the ventilatory electrical impedance tomograph is subject to the following special controls:
*Classification.* Class II (special controls). The special controls for this device are:(1) The patient-contacting components of the device must be demonstrated to be biocompatible.
(2) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use, including the following:
(i) Characterization of device parameters, including signal-to-noise ratio, voltage accuracy, drift, reciprocity accuracy, amplitude response, position error, and ringing;
(ii) Real time evaluation of local impedance variation;
(iii) Plethysmogram accuracy testing; and
(iv) Use life testing of reusable components.
(3) Performance data must validate reprocessing instructions for any reusable components of the device.
(4) Performance data must demonstrate the electrical, thermal, and mechanical safety and the electromagnetic compatibility of the device.
(5) Software verification, validation, and hazard analysis must be performed.
(6) Labeling must include the following:
(i) Guidance for interpretation of the images generated;
(ii) A warning that the device should be removed before use of a defibrillator, or defibrillator interaction information based on defibrillator performance testing with the device;
(iii) A use life for any reusable components; and
(iv) Instructions for reprocessing any reusable components.
Submission Summary (Full Text)
{0}------------------------------------------------
### DE NOVO CLASSIFICATION REQUEST FOR ENLIGHT 1810
### REGULATORY INFORMATION
FDA identifies this generic type of device as:
Ventilatory electrical impedance tomograph. A ventilatory electrical impedance tomograph is a prescription non-invasive, non-radiological ventilatory device that provides an assessment of local impedance variation within a cross-section of a patient's thorax.
NEW REGULATION NUMBER: 21 CFR 868.1505
CLASSIFICATION: Class II
PRODUCT CODE: QEB
#### BACKGROUND
DEVICE NAME: ENLIGHT 1810
SUBMISSION NUMBER: DEN170072
DATE OF DE NOVO: September 29, 2017
- TIMPEL Inc. CONTACT: R. Simão Álvares, 356 cj. 41 - Pinheiros São Paulo - SP, 05417-020, Brazil
#### INDICATIONS FOR USE
ENLIGHT 1810 is a non-invasive, non-radiation medical device that provides information of local impedance variation within a cross-section of a patient's thorax. This information is presented to the clinician user as an adjunctive tool to other clinical information in order to support the user's assessment of variations in regional air content within a cross section of a patient's lungs.
It is intended for mechanically ventilated adult patients in a hospital setting, whose thorax perimeter is within the range of 78-122 cm.
#### LIMITATIONS
The sale, distribution, and use of the ENLIGHT 1810 are restricted to prescription use in accordance with 21 CFR 801.109.
{1}------------------------------------------------
# WARNINGS AND PRECAUTIONS
- . Remove the Shaper and open the Electrode Belt prior to patient defibrillation. Protection circuitry of the device mav draw part of the energy delivered by the defibrillator if all electrodes are attached to the patient.
- To avoid an electric shock do not touch the Electrode Belt during the ● defibrillation discharge.
- . ENLIGHT 1810 should not be used on pregnant or lactating women since the safety and efficiency for such cases have not been verified.
- ENLIGHT 1810 should not be used on patients with active implantable devices, . such as pacemakers, cardioverter defibrillators, or neurostimulators. There is no scientific evidence of safety for the use of this device on patients with active implantable devices.
- . ENLIGHT 1810 should not be used in environments with elevated levels of ambient oxygen (such as hyperbaric chambers) oxygen-enriched environments or in the presence of flammable anesthetic gases or any flammable agent. The device may, however, be used in patients receiving oxygen-enriched ventilation.
- ENLIGHT 1810 is MR unsafe.
- ENLIGHT 1810 should not be used in areas of explosion hazard. .
- Do not apply the Electrode Belts or Reference Electrode on injured areas of the . skin (e.g., burns, open wounds, rashes, etc.).
- . Do not reuse the Electrode Belts. They are disposable and single patient use. Reusing Electrode Belts on a new patient may result in cross-infection.
# PLEASE REFER TO THE LABELING FOR A MORE COMPLETE LIST OF WARNINGS, PRECAUTIONS AND CONTRAINDICATIONS.
# DEVICE DESCRIPTION
ENLIGHT 1810 is a non-invasive, radiation free medical device intended to provide information on the regional distribution of ventilation in a cross-sectional slice of the thorax.
As the total variation in impedance for the thorax corresponds to the total tidal volume, ENLIGHT 1810 can estimate the percentage of tidal volume in regions of interest (ROI) breath by breath, measuring the contribution of the impedance variation of that ROI to the total impedance of the lung.
Electrical impedance tomography (EIT) is a technique in which the electrical properties of tissues are estimated from surface electrode voltage measurements and used to provide information on Local Impedance Variation (LIV) within a cross section of a patient's thorax. Considerable electrical impedance variations are imposed on lung tissue by variations in the lung's air content. There is a linear relationship between the variations in air content and the percentage change in lung tissue impedance. This linear relationship is explored in Electrical Impedance Tomography, supporting its use as a tool to support the user's assessment of the variations in regional air content within a cross section of a patient's lungs.
The device may be used on adult patients undergoing either fully controlled or assisted mechanical ventilation in the ICU environment.
{2}------------------------------------------------
The system components are shown below:
Image /page/2/Figure/1 description: This image shows a medical setup with a patient connected to various devices. The devices include a Spirometer Flow Sensor, an Addere and Electrode Belt, a Shaper, and a Reference Cable, all connected to the patient's body. On the right side, there is a computer, a Pneumotachograph, a Bioimpedance Measurement System, a Power Supply, and a Device Cart, indicating a comprehensive monitoring and measurement system for the patient's respiratory and physiological functions.
Figure 1. ENLIGHT 1810 System Components
### SUMMARY OF NONCLINICAL/BENCH STUDIES
## BIOCOMPATIBILITY/MATERIALS
ENLIGHT 1810 includes components (flow sensor) that have externally communicating patient contact via gas pathway for permanent duration. The electrode belt, and shaper have surface contact, intact skin.
The complete device in its final, finished form was subjected to biocompatibility testing in accordance with the FDA guidance document, "Use of International Standard ISO 10993-1, 'Biological evaluation of medical devices – Part 1: Evaluation and testing within a risk management process."" The following tests were conducted to assess biocompatibility of the device for the externally communicating components for permanent duration:
- Cytotoxicity ●
- Sensitization ●
- Irritation ●
- Intracutaneous reactivity ●
- Extractables and leachables testing with a risk assessment .
All tests passed. The results demonstrated the biocompatibility of the device.
### SHELF LIFE/REPROCESSING/STERILITY
The following components are single patient use only: the electrode belt, shaper, flow sensor, and reference cable. The Addere and reference electrode are single use only and
{3}------------------------------------------------
must be disposed each time after use.
The surface of the ENLIGHT 1810 hardware undergoes low level cleaning, usually with disinfecting wipes similar to equipment in the ICU. No components are provided sterile.
The cleaning procedures for the single patient use were validated following the recommendations of the FDA Guidance Document "Reprocessing Medical Devices in Health Care Settings: Validation Methods and Labeling". Data supported that 50 reprocessing cycles did not impact device functionality.
# ELECTROMAGNETIC COMPATIBILITY AND ELECTRICAL SAFETY
The ENLIGHT 1810 was tested in accordance with the following consensus standards and conformed with the following electromagnetic compatibility (EMC), electrical, mechanical and thermal safety standards:
- AAMI ANSI ES60601-1:2005/(R)2012 And A1:2012 C1:2009/(R)2012 And ● A2:2010/(R)2012 (Consolidated Text) Medical Electrical Equipment - Part 1: General Requirements For Basic Safety And Essential Performance (IEC 60601-1:2005, MOD)
- ANSI AAMI IEC 60601-1-2:2007/(R)2012 Medical Electrical Equipment Part . 1-2: General Requirements For Basic Safety And Essential Performance -Collateral Standard: Electromagnetic Compatibility - Requirements And Tests (Edition 3)
- The device was also tested for safe exposure to known sources of EMI with ● medical devices such as MRI, diathermy, and RFID.
# MAGNETIC RESONANCE (MR) COMPATIBILITY
The device has not been tested for MRI compatibility and should not be used in an MRI suite.
### SOFTWARE
The De Novo request provided adequate software documentation consistent with a "Moderate" level of software concern as discussed in the FDA Guidance Document "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices," issued May 11, 2005.
Software validation and verification testing demonstrated that the device met its design, implementation, and cybersecurity specifications.
### PERFORMANCE TESTING - BENCH
The non-clinical testing for the device consisted of verification and validation testing of hardware and software.
The following bench tests were performed:
- Verification of the following specifications of the EIT system was performed . based on experimental saline phantom (proposed by Yasin M et al. (2011).
{4}------------------------------------------------
Evaluation of EIT system performance. Physiological measurement, 32(7), 851), The following performance characteristics were studied using an acrylic cylindrical tank filled with saline and the performance computed using experiments with contrast objects placed in this tank:
- о Signal to Noise Ratio: 45 dB-80 dB,
- Voltage Accuracy: 99.45%-100%, O
- Drift: Allan variance converges to zero, o
- o Reciprocity accuracy: 93%-100%,
- Amplitude response: 88%-102%, о
- Position error: <5% of radius, O
- Ringing: 2-5 02. o
- Uniform phantom testing to estimate the plethysmogram results for an acrylic ● cylindrical tank filled with saline: The conductivity of the saline solution is set and measured for different values between 0.09 S/m and 0.892 S/m. The difference image of each case is reconstructed using the same reference voltages and the plethysmogram is computed. Fitting (in a least-squares sense) the set of plethysmogram results as a line, the percentage regression residuals are computed. The testing showed that the percentage error of plethysmogram is below 5%.
- Display of real time information of local impedance variation by application of high frequency current or display an error message if this is not possible.
- . Acquisition Test to verify main functions of the Acquisition Module system: Testing for communication with PIM, command handling, acquisition handling, calibration handling, signal acquisition, hardware handling, file system including configuration recovery and version information of key installed components was completed.
- Reconstruction Library to verify that the Image Reconstruction Library output . matches the results determined analytically: The error between reconstructed output meshes and analytically calculated meshes using the same parameters was measured and verified that the error is below a given threshold.
- . Defibrillation to demonstrate the EIT is safe after undergoing defibrillation shocks if belts/electrodes are not disconnected during RCP/defibrillation maneuvers: Simulations were conducted to estimate energy drawn by EIT equipment. Tests with defibrillator verified energy drawn and if the equipment keeps safety after undergoing defibrillation. The simulation indicated the need to disconnect the patient from ENLIGHT 1810 for defibrillation to avoid loss of treatment efficacy.
- Use Life Testing was conducted to verify the 50 reprocessing cvcles for the single . patient use components.
### PERFORMANCE TESTING - ANIMAL
Animal studies were conducted to assess the ability of EIT to quantify the ventilation distribution to anterior/posterior and right/left regions of the lungs as compared to Xray computed tomography (CT) and compare regional ventilation in 4 regions of interest (Anterior / Posterior and Right / Left). Seven swine animals were used. The lung injury was consistent with severe acute respiratory distress syndrome (PaO2/FiO2 89.9 ± 37.7 mmHg). Agreement between EIT and CT for the
{5}------------------------------------------------
anterior/posterior (bias = -0.02 and limits of agreement = -0.09 to 0.06) as well as for the right/left ROIs (bias = 0.04 and limits of agreement= -0.03 to 0.05%) were observed. The proof-of-concept testing provided supportive data on the qualitative clinical performance of the ENLIGHT 1810 device.
## PERFORMANCE TESTING - HUMAN FACTORS
The Human Factors Validation (HFV) test was performed to validate all safetycritical and associated essential tasks that are required to use the ENLIGHT® 1810. The first objective of this HFV test was to provide objective performance and subjective interview data to validate those representative users can use the ENLIGHT® 1810 safely when used under representative conditions. A second objective was to verify the adequacy of the Instructions for Use (IFU) and Reference Guide to support user performance and to assess the comprehension of warnings provided in these documents to mitigate risks associated with hazards identified in the ENLIGHT®
The intended users of ENLIGHT® 1810 are healthcare professionals responsible for a patient's ventilation, analyzing the monitored physiological parameters and determining the appropriate ventilatory management. There were 15 users per group. The supplementary Human factors/Usability engineering (HF/UE) reports contained the descriptions of Human factors processes and appropriate validating testing results. data collection. root-cause analyses and conclusion to establish that the ENLIGHT®1810 device and the associated labeling and training are adequate for the intended users, its intended uses, and use environments.
# SUMMARY OF CLINICAL INFORMATION
Three clinical studies were conducted to assess the ability of EIT to quantify the ventilation distribution to anterior/posterior and right/left regions of the lungs as compared to X-ray computed tomography (CT) and compare regional ventilation in 4 regions of interior / Posterior and Right / Left).
- 1. Comparison between regional distribution of ventilation: EIT vs. CT
Method: This study evaluated 32/39 healthy volunteers where the ventilation distribution was compared to CT. EIT and CT images were acquired simultaneously in supine, prone and laterals decubitus during 20 seconds of end-expiration and end-inspiration pause. Four thoracic regions of interest (ROI) were defined: anterior, posterior, right, and left. On EIT images, the ROIs represent the division of the thorax in two equal halves both in the anterior/posterior and in the right/left direction. The CT's ROIs were defined based on the midpoint of the lungs in the vertical and horizontal directions.
Endpoints: Evaluated the Ventilation distribution to anterior / posterior and right / left regions of the thorax and assessed the agreement of these distributions to those measured with CT using the same thoracic regions of interest (ROI).
{6}------------------------------------------------
Results: Seven subjects were excluded from the analysis. The statistical evaluations were descriptive, where a Bland-Altman type difference plot was used to compare EIT vs CT with 95% limits of agreement for EIT ventilation distribution to regions of interest in both anterior posterior and right/left. The study showed that in 32 healthy volunteers the anterior/posterior bias was -0.1 and the limits of agreement was -0.11-0.1 and for the right/left ROI the bias was -0.02 and the limits of agreement was -0.09 to 0.06.
- 2. Assessment of Regional Distribution of Ventilation: Right / Left
Methods: This study assessed 21 patients with lung transplants (11 single lung, 10 bilateral transplant). Regional distribution of ventilation to the right and left lungs was assessed with ENLIGHT during 30 cycles of regular, spontaneous breathing in five different body positions: seated, supine, right lateral, left lateral, and prone. CT scans were performed at total lung capacity in spontaneously breathing patients.
Endpoint: Percent ventilation to the 'best lung' according to EIT.
Results: On average, during tidal ventilation and in the supine position, the best lung received 57±11% in bilateral transplants, 79±12% in unilateral transplants for emphysema, and 83±13% in unilateral transplants for fibrosis.
{7}------------------------------------------------
Image /page/7/Figure/0 description: The image shows CT scans and EIT ventilation maps of patients with lung conditions, including emphysema and fibrosis, and a bar graph comparing best lung ventilation across different conditions and body positions. The CT scans and ventilation maps illustrate the distribution of ventilation in patients who underwent bilateral lung transplants, as well as those with single lung transplants. The bar graph titled "Best Lung Ventilation" compares ventilation in unilateral emphysema, unilateral fibrosis, and bilateral transplant cases, considering seated, supine, and prone positions. The ventilation values range from approximately 0.5 to 0.9, with variations observed across different conditions and body positions.
De Novo Summary (DEN170072)
{8}------------------------------------------------
- 3. Assessment of Regional Distribution of Ventilation: Upper / Lower
Methods: This study was a retrospective analysis of 39 patients who were evaluated for the regional distribution of ventilation to the anterior and posterior halves at different PEEP levels.
Endpoint: The proportion of ventilation to the anterior region, obtained using ENLIGHT, at the highest and lowest PEEP levels available for each patient.
Results: The regional distribution of ventilation to the anterior half of the lung was also 35 ± 6% during the highest PEEP and 62± 8% (P< 0.001) during the lowest PEEP.
### Conclusion:
The clinical studies support the use of the subject device as a qualitative tool that provides information of local impedance variation within a cross-section of a patient's thorax. The images in these studies provide qualitative information; however, adequate validation has not been provided for quantitative measures. The clinical studies, support the use of the device as a qualitative tool that should only be used as an adjunct to support the user's assessment of variations in regional air content within a cross section of a patient's lungs based on other clinical information.
### Pediatric Extrapolation
In this De Novo request, existing clinical data were not leveraged to support the use of the device in a pediatric patient population.
# LABELING
The labeling (User Instructions) meets the requirements of 21 CFR 801.109 for prescription devices. The user instructions include the following:
{9}------------------------------------------------
- 1. A description and function of all components of the system and instructions regarding how to use each component;
- 2. A description of how to use the device safely, information on signal acquisition. use of flow sensor, electrode belt and reference electrode;
- 3. The available images screens and their interpretations;
- Cleaning instructions for the main unit, which is reusable; 4.
- 5. Information regarding maintenance and replacement of the main unit;
- 6. A warning that the device should not be used with defibrillator;
- Contraindications listing patient comorbidities that would preclude use of the 7. system; and
- 8. A troubleshooting guide.
### RISKS TO HEALTH
The table below identifies the risks to health that may be associated with use of the ventilatory electrical impedance tomograph and the measures necessary to mitigate these risks.
| Identified Risk | Mitigation Measures |
|---------------------------------|---------------------------------------------------------|
| Adverse tissue reaction | Biocompatibility evaluation |
| Electromagnetic interference | Electromagnetic compatibility testing |
| with other devices | |
| Infection | Reprocessing validation, and |
| | Labeling |
| Inaccurate images due to either | Software verification, validation, and hazard analysis; |
| device hardware or software | Non-clinical performance testing; and |
| failure/malfunction | Labeling |
| Electrical shock injury or | Electrical, thermal, and mechanical safety testing; |
| thermal injury | Software verification, validation and hazard analysis; |
| | Non-clinical performance testing; and |
| | Labeling |
### SPECIAL CONTROLS:
In combination with the general controls of the FD&C Act, the ventilatory electrical impedance tomograph is subject to the following special controls:
- 1. The patient-contacting components of the device must be demonstrated to be biocompatible.
- 2. Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use, including the following:
- Characterization of device parameters, including signal to noise ratio, voltage a. accuracy, drift, reciprocity accuracy, amplitude response, position error, and ringing:
- b. Real time evaluation of local impedance variation;
- Plethysmogram accuracy testing; and C.
- d. Use life testing of reusable components.
{10}------------------------------------------------
- 3. Performance data must validate reprocessing instructions for any reusable components of the device.
- 4. Performance data must demonstrate the electrical, thermal, and mechanical safety and the electromagnetic compatibility of the device.
- 5. Software verification, validation, and hazard analysis must be performed.
- 6. Labeling must include the following:
- a. Guidance for interpretation of the images generated;
- b. A warning that the device should be removed before use of a defibrillator, or defibrillator interaction information based on defibrillator performance testing with the device;
- c. A use life for any reusable components; and
- d. Instructions for reprocessing any reusable components.
### BENEFIT/RISK DETERMINATION
The risks of the device are based on nonclinical laboratory studies as well as data collected in the clinical studies described above. The device exhibited an acceptable safety profile in the clinical study that was conducted. No device-related serious adverse events were observed.
The ENLIGHT 1810 risks include incorrect placement of electrode belts on patient, application of belt over broken skin, electrical current leakage from device to patient, use of contaminated components, device failure, incorrect battery replacement, incorrect interpretation of EIT measurements, use of expired Addere, disconnection of reference electrodes during use, incorrect data feed to the device by the user, skewed data due to EMI interference, misinterpretation of data due to nonstandard thorax profile (malformation, surgery etc.), water between electrode belt and patient's skin and incorrect flow sensor placement. Although these device malfunctions or device-related adverse events were not seen in the clinical studies these risks are associated with most devices utilized in critical care settings.
The device is a qualitative tool that compares ventilation differences between the right and left lung. This is useful in a critical care setting for the evaluation of a sudden change in ventilation such as pneumothorax or mucous plugging and in evaluating the respiratory status if there is a sudden change in the patient's clinical status on a ventilator. Risks include incorrect decision making; however, the labeling clearly states that this is not to be used for sole decision-making and will be used in conjunction with other modalities in the critical care setting.
### Patient Perspectives
This submission did not include specific information on patient perspectives for this device.
### Benefit/Risk Conclusion
In conclusion, given the available information above, the data support that the probable benefits outweigh the probable risks for the ENLIGHT 1810 as an adjunctive tool to other clinical information to support the user's assessment of variations in regional air content within a cross section of a patient's lungs. The device provides benefits and the risks can be mitigated using general controls and the identified special controls.
{11}------------------------------------------------
### CONCLUSION
The De Novo request for the ENLIGHT 1810 is granted and the device is classified under the following:
Product Code: QEB Device Type: Ventilatory electrical impedance tomograph Class: II Regulation: 21 CFR 868.1505
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.