Clinical performance study: 416 lung ultrasound video loops from 157 subjects
>1 (clinicians)
Indications for Use
The intended use of the product is to collect ultrasound image data that may be used by clinicians for diagnostic and procedural purposes. The product shall provide the ability for gathering clinically acceptable images and ultrasound data for the clinical presets and anatomies listed under the indications for use. This product is intended to be installed, used, and operated only in accordance with safety procedures and operating instructions given in the product user information, and only for the purposes for which it was designed. However, nothing stated in the user information reduces the user's responsibility for sound clinical judgement and best clinical procedure.
Device Story
Lumify is a mobile, software-controlled ultrasound system using COTS Android/iOS mobile devices and USB-connected transducers (C5-2, L12-4, S4-1). It acquires B-mode, Color Doppler, Pulsed Wave Doppler, and M-mode images. An AI-based software feature for lung exams automatically detects and counts B-lines and identifies merged (confluent) B-lines in cine loops. The system highlights identified B-lines and merged B-lines (depicted as an inverted T) on the display. Clinicians review, accept, or adjust the automated output (0, 1-2, 3+ B-lines, or merged). Used at point-of-care for assessing lung conditions like pneumonia, pulmonary edema, contusion, and ARDS. The algorithm is locked post-commercialization. Benefits include standardized, automated assessment of lung fluid buildup to assist clinical decision-making.
Clinical Evidence
Clinical performance evaluated using 416 lung ultrasound cine loops from 157 subjects (age 18 to >89). Study compared AI-based merged B-line detection and counting against clinician ground truth. For merged B-line detection, overall sensitivity was 0.83 (95% CI: 0.77, 0.88) and specificity was 0.92 (95% CI: 0.88, 0.96). For B-line counting, overall ICC was 0.91 (95% CI: 0.89, 0.93). Performance verified across C5-2, S4-1, and L12-4 transducers and varying BMI/image quality levels.
Technological Characteristics
Mobile ultrasound system utilizing COTS Android/iOS tablets/phones and USB-connected transducers (C5-2, L12-4, S4-1). Imaging modes: B, Color Doppler, Pulsed Wave Doppler, M-mode. Software-based AI/ML classifier for lung ultrasound analysis (locked algorithm). Complies with IEC 62304 (software lifecycle), IEC 62366-1 (usability), and ISO 14971 (risk management).
Indications for Use
Indicated for diagnostic ultrasound imaging and fluid flow analysis in Fetal/Obstetric, Abdominal, Pediatric, Cephalic, Urology, Gynecological, Cardiac Fetal Echo, Small Organ, Musculoskeletal, Peripheral Vessel, Carotid, Cardiac, and Lung applications. Intended for use by healthcare professionals in transportable environments.
Regulatory Classification
Identification
An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.
{0}------------------------------------------------
May 4, 2023
Image /page/0/Picture/1 description: The image shows the logos of the Department of Health & Human Services and the U.S. Food & Drug Administration (FDA). The Department of Health & Human Services logo is on the left, featuring a stylized human figure. To the right is the FDA logo, with the letters "FDA" in a blue square and the words "U.S. FOOD & DRUG ADMINISTRATION" in blue text.
Philips Ultrasound % Sudipta Chakrabarti Sr. Regulatory Affairs Specialist 22100 Bothell Everett Hwy. BOTHELL WA 98021
Re: K223771
Trade/Device Name: Lumify Diagnostic Ultrasound System Regulation Number: 21 CFR 892.1550 Regulation Name: Ultrasonic pulsed doppler imaging system Regulatory Class: Class II Product Code: IYN, IYO, ITX, QIH Dated: March 30, 2023 Received: March 30, 2023
Dear Sudipta Chakrabarti:
We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.
If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.
Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part
{1}------------------------------------------------
801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4. Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.
For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
# Yanna S. Kang -S
Yanna Kang, Ph.D. Assistant Director Mammography and Ultrasound Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{2}------------------------------------------------
# Indications for Use
Submission Number (if known)
# K223771
Device Name
Lumify Diagnostic Ultrasound System
Indications for Use (Describe)
The Philips Lumify Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B (2D), Color Doppler, Combined (B+Color), Pulsed Wave Doppler (PWD), and M-modes.
It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: Fetal/Obstetric, Abdominal, Pediatric, Cephalic, Urology, Gynecological, Cardiac Fetal Echo, Small Organ, Musculoskeletal, Peripheral Vessel, Carotid, Cardiac, Lung.
The Lumify system is a transportable ultrasound system intended for use in environments where healthcare is provided by healthcare professionals.
Type of Use (Select one or both, as applicable)
> Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
# CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
## *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.*
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
> Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
{3}------------------------------------------------
#### 510(k) Number: K223771
This summary of safety and effectiveness information is submitted in accordance with 21 CFR § 807.92.
#### 1. Submitter's name, address, telephone number, contact person
| Manufacturer: | Philips Ultrasound<br>22100 Bothell Everett Hwy<br>Bothell, WA 98021-8431 |
|--------------------|------------------------------------------------------------------------------------------------------------------------|
| Contact Person: | Sudipta Chakrabarti<br>Sr. Regulatory Affairs Specialist<br>TEL: +1 (203) -213-6862<br>sudipta.chakrabarti@philips.com |
| Secondary Contact: | Tamara Daniels<br>Sr. Regulatory Affairs Manager<br>TEL: +1 (203) -213-6862<br>tamara.daniels@philips.com |
| Date Prepared: | May 1, 2023 |
- 2. Name of the device, including the trade of proprietary name if applicable, the common or usual name, and the classification name, if known:
| Proprietary Name: | Lumify Diagnostic Ultrasound System | | |
|-------------------------|-----------------------------------------------------|----------|--------------|
| Common Name: | Diagnostic ultrasound system and transducers | | |
| Regulation Description: | Classification Name | 21 CFR § | Product Code |
| | <b>Primary</b> | | |
| | System, imaging, pulsed doppler,<br>ultrasonic | 892.1550 | IYN |
| | <b>Secondary</b> | | |
| | System, imaging, pulsed echo,<br>ultrasonic | 892.1560 | IYO |
| | Transducer, ultrasonic, diagnostic | 892.1570 | ITX |
| | Automated Radiological Image<br>Processing Software | 892.2050 | QIH |
| Device Class: | Class II |
|-----------------------|-----------|
| Classification Panel: | Radiology |
{4}------------------------------------------------
#### 3. Indications for Use and Intended Use
There is no change to the intended use and indications for use of the subject device as compared to the predicates.
#### 3.1 Indications for Use
The Philips Lumify Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B(2D), Color Doppler, Combined (B+Color), Pulsed Wave Doppler, and M-modes.
It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: Fetal/Obstetric, Abdominal, Pediatric, Cephalic, Urology, Gynecological, Cardiac Fetal Echo, Small Organ, Musculoskeletal, Peripheral Vessel, Carotid, Cardiac, Lung.
The Lumify system is a transportable ultrasound system intended for use in environments where healthcare is provided by healthcare professionals.
#### 3.2 Intended Use
The intended use of the product is to collect ultrasound image data that may be used by clinicians for diagnostic and procedural purposes. The product shall provide the ability for gathering clinically acceptable images and ultrasound data for the clinical presets and anatomies listed under the indications for use.
This product is intended to be installed, used, and operated only in accordance with safety procedures and operating instructions given in the product user information, and only for the purposes for which it was designed. However, nothing stated in the user information reduces the user's responsibility for sound clinical judgement and best clinical procedure.
#### 4. Device Description Summary
The Philips Lumify Diagnostic Ultrasound System (Lumify) is a mobile, durable, software-controlled medical device, which is intended to acquire high-resolution ultrasound data and to display the data in B (2D), Pulsed Wave Doppler, Color Doppler, Combined (B+ Color), and M modes. It is intended to be used by trained professionals at various settings of patient point of care such as clinical admission, periodic evaluations, and prior to hospitalization discharge,
The Lumify system is compatible with iOS or Android operating systems. The B-lines feature is compatible only with Android operating systems and utilizes:
- A commercial off-the-shelf (COTS) Android mobile device (smart phone or tablet) ●
- The Philips Ultrasound Lumify software running as an application on the COTS device
- The Philips C5-2 Curved array USB transducer
- . The Philips L12-4 Linear array USB transducer
- The Philips S4-1 Sector array USB transducer
- Lumify Micro B Transducer Cable ●
- Lumify Micro C Transducer Cable ●
{5}------------------------------------------------
Image /page/5/Figure/1 description: The image shows a Lumify transducer, a tablet, and a transducer cable. The Lumify transducer is a small, handheld device that is used to create ultrasound images. The tablet is a mobile device that can be used to view the ultrasound images. The transducer cable connects the Lumify transducer to the tablet.
Figure 4-1: Hardware components of Lumify Diagnostic Ultrasound System.
The Lumify system software provides various imaging features, including an Android-specific feature with a guided scan protocol for comprehensive exams and real-time automated B-line assessment during lung exams. B-lines occur when sound waves encounter a mixture of air and water. They are hyperechoic imaging artifacts that appear in a lung exam as long bands of varying widths that originate at the pleural line and extend vertically the length of the ultrasound image. Often, when many B-lines are present and close together, they can merge together and become hard to distinguish from one another and difficult to count accurately. The observation of multiple B-lines merging together is referred to as "merged B-lines" (or otherwise as confluent B-lines, coalescent B-lines, or "white lung" pattern); this can occur as more fluid builds up in the lungs and it becomes increasingly difficult to differentiate between multiple singular B-lines.
The automated B-lines feature is only available in the Lung Preset (which is a specific setting the user selects for ultrasound scanning of the lung) for devices utilizing an Android operating system. The automated B-lines feature also provides a summary page for users to review the highlighted B-lines. The device is a sonographic tool used for assessment of lung involvements in conditions, such as pneumonia, pulmonary edema, lung contusion, and acute respiratory distress syndrome (ARDS) along with clinical and radiological information.
When compared to the predicate device, the subject device has the same software features, but with the addition of an expanded algorithm which includes the detection of merged (confluent) B-lines in the cine loop. In the same manner as the original B-line counting algorithm, the expanded algorithm analyzes lung ultrasound cine video clips (cine loops) acquired using the Lumify Diagnostic Ultrasound System and provides the user the number of B-lines in the loop. The capability of the existing automated B-lines feature (K203406) has been extended to include detection of the presence of merged B-line in cine loops (subject of this submission) and to include support of the expanded Blines feature (including B-line counting) on a previously cleared Lumify C5-2 transducer (K152899). This software enhancement does not alter the intended use of the device but provides additional functionality to clinical workflows during lung related applications. The Lumify L12-4 and S4-1 transducers were cleared for use with the B-line counting feature via K203406.
{6}------------------------------------------------
The Expanded B-lines Software Feature, with the updated merged B-line detection feature, uses machine learning as part of the algorithm design. Relevant image features extracted from a lung ultrasound cine loop are provided to a machine learning classifier that identifies B-lines and/or merged B-lines in each frame. While the user is scanning the ultrasound exam, the software automatically counts the number of B-lines in each frame of the loop and determines whether B-lines are considered to be merged. Identified B-lines and merged B-lines in each frame throughout the loop are highlighted.
After the cine loop is acquired, the software determines whether the loop is considered positive for merged B-line. If so, the software reports an output category "1" (merged B-line) for that loop. Otherwise, if not merged, the software determines the maximum B-line count within the loop, reported as one of three output categories, "0 B-lines", "1-2 B-lines", or "3+ B-lines". In this way, the subject device informs the user of the presence of merged B-lines in the cine loop, where a B-line count may no longer be an appropriate measurement for that loop. The user can review the highlighted B-lines and merged B-lines and can accept or adjust the reported cine loop output category (0, 1-2, 3+, or L) provided by the software in cases where he or she disagrees with the algorithm output (B-line count or presence of merging). The approved result is then saved for reporting. The software can record the results for up to 12 lung zones (8 anterior zones and 4 posterior zones).
The Philips Lumify Diagnostic Ultrasound System highlights merged B-lines in the frames of a cine loop through depiction of a rendered drawing of a bold inverted T (L). The software leverages the Lumify application for image acquisition, visualization, and reporting. The algorithm, that used artificial intelligence/machine learning in its development, is locked (meaning no further adjustments by the algorithm are made and it does not continue to learn once commercialized).
The B-lines algorithm update has no impact on the design, workflow, or intended users of the predicate. This software enhancement does not alter the intended use of the device but provides additional functionality to clinical workflows during lung related applications.
#### 5. Substantially Equivalent Devices
| Predicate Device: | K203406 – Philips Ultrasound – Lumify Diagnostic Ultrasound<br>System |
|-------------------|----------------------------------------------------------------------------------------|
| Reference Device: | K152899 – Philips Ultrasound – Lumify Diagnostic Ultrasound<br>System, C5-2 transducer |
#### 6. Technological Comparison to Predicate Devices
The Lumify Diagnostic Ultrasound System with Merged B-line Counting feature and associated Lumify C5-2 transducer (subject devices) are substantially equivalent to the currently marketed predicate devices (K203406 and K152899, respectively).
The following Table 6.1 provides an overview of the comparison between the subject devices and the currently marketed predicates.
{7}------------------------------------------------
| Standard Feature | Lumify Diagnostic Ultrasound<br>System K223771 (Subject Device) | Lumify Diagnostic Ultrasound<br>System K2030406 (Predicate Device) |
|----------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Scientific Technology | Ultrasound Imaging | Ultrasound Imaging |
| Intended Use | Philips Lumify Diagnostic Ultrasound<br>System is intended for diagnostic<br>ultrasound imaging in B (2D), Pulsed<br>Wave, Color Doppler, Combined<br>(B+Color), and M modes. | Philips Lumify Diagnostic Ultrasound<br>System is intended for diagnostic<br>ultrasound imaging in B (2D), Pulsed<br>Wave, Color Doppler, Combined<br>(B+Color), and M modes. |
| Indications for Use | Lumify Diagnostic Ultrasound<br>System is indicated for diagnostic<br>ultrasound imaging and fluid flow<br>analysis in the following applications:<br>Fetal/Obstetric, Abdominal, Pediatric,<br>Cephalic, Urology, Gynecological,<br>Cardiac Fetal Echo, Small Organ,<br>Musculoskeletal, Peripheral Vessel,<br>Carotid, Cardiac, Lung.<br><br>Lumify is a transportable ultrasound<br>system intended for use in<br>environments where healthcare is<br>provided by healthcare professionals. | Lumify Diagnostic Ultrasound System<br>is indicated for diagnostic ultrasound<br>imaging and fluid flow analysis in the<br>following applications:<br>Fetal/Obstetric, Abdominal, Pediatric,<br>Cephalic, Urology, Gynecological,<br>Cardiac Fetal Echo, Small Organ,<br>Musculoskeletal, Peripheral Vessel,<br>Carotid, Cardiac, Lung.<br><br>Lumify is a transportable ultrasound<br>system intended for use in<br>environments where healthcare is<br>provided by healthcare professionals. |
| Modes of Operations | B (2D), Pulse Wave, Color Doppler,<br>Combined (B+Color), and M modes | B (2D), Pulse Wave, Color Doppler,<br>Combined (B+Color), and M modes |
| Transducers | L12-4<br>S4-1<br>C5-2 | L12-4<br>S4-1 |
| Primary Product Code | IYN | IYN |
| Secondary Product<br>Code | IYO, ITX, QIH | IYO, ITX |
| Principles of Operation<br>(subject merged B-lines<br>Feature) | Automatic counting of B-lines and<br>detection of merged B-lines, with<br>optional manual adjustment of results<br>provided by the software. | Automatic counting of B-lines, with<br>optional manual adjustment of results<br>provided by the software. |
Table 6.1 Technological Comparison of Proposed Subject Device & Predicate Device.
#### 7. Non-Clinical Performance Data
The proposed modification of the Lumify Diagnostic Ultrasound System was tested in accordance with Philips internal procedures. Philips Ultrasound tested the subject device per the following standards to ensure the continued safe and effective performance:
- IEC 62304 Medical device software Software life cycle processes, 2006 + A 2015 ●
- IEC62366-1 Medical devices Part 1: Application of usability engineering to medical devices, ● 2015
- ISO 14971 Medical devices- Application of risk management to medical devices, 2019 ●
Non-clinical verification testing was conducted to address the change and performance test data was provided to support the introduction of the subject software algorithm for the merged B-lines feature. The activities to assure the safe and effective performance of the software revision included, but are not limited to, the following:
{8}------------------------------------------------
- Requirements Review ●
- Risk Analysis and Management
- . Product Specifications
- Design Reviews .
Non-Clinical Verification Testing of requirements, consisted of feature-specific functional testing, transducer compatibility, user interface and workflow testing related to new functionality introduced in B-Lines for this submission as part of the software verification activities for the system and for each transducer supporting the B-lines feature.
Since this is a software only change and no new hardware was added, no acoustic output, cleaning and disinfectant, thermal, electromagnetic and mechanical safety testing were required. Biocompatibility testing is not needed for the subject Lumify Ultrasound System with Automated B-Line Counting. The transducer patient contact materials and manufacturing processes are not impacted by the release of the subject Lumify Diagnostic Ultrasound System with automated B-line counting.
#### 8. Clinical Performance Data
#### Summary of Clinical Tests
There was no clinical investigation needed for this premarket submission of the Lumify Diagnostic Ultrasound System with Expanded B-lines software feature, which is an artificial intelligence-based feature.
#### Artificial Intelligence Summary
A study using previously collected clinical ultrasound images with prospective reads by clinicians was conducted to evaluate the performance (including merged B-lines and B-line counting). The data used for clinical performance study were completely distinct from that used during training of the algorithm, and there was no overlap between the two data sets.
#### Dataset
A study involving review by clinicians of 416 LUS (lung ultrasound) video loops were collected from 157 subjects presenting with shortness of breath in a hospital setting. Each subject may have contributed up to 4 video loops. The study data were collected to ensure full coverage of lung, both posterior and interior as well as left and right lungs. The dataset was representative of videos collected from three different transducers.
The demographic distribution of the performance testing includes the following:
| Gender | Male and Female |
|-----------|-----------------------------------------------|
| Age | 18 to> 89 |
| Ethnicity | Hispanic or Latino and Not Hispanic or Latino |
A pre-defined success criteria for the study was assessed as Artificial Intelligence (AI) agreement to the clinicians (ground truth: majority agreement target was determined through pilot study conducted to assess clinician's agreement and determined to be based on lower confidence limits of 0.746 for both sensitivity and specificity.
The algorithm performance was verified in sub-groups:
- Transducer: C5-2, L12-4, S4-1 ●
{9}------------------------------------------------
- BMI: <30,>=30,>=40 ●
- Image quality: Poor or Good
#### Results
Algorithm performance for merged B-line detection and B-line counting was compared to clinician readings.
For merged B-line detection, the sensitivity, specificity, and accuracy (where confidence interval is abbreviated as CI) were as follows:
| Transducer | Sample size<br>(video loops) | Sensitivity<br>(95% CI) | Specificity<br>(95% CI) |
|------------|------------------------------|-------------------------|-------------------------|
| All | 416 | 0.83 (0.77, 0.88) | 0.92 (0.88, 0.96) |
| C5-2 | 146 | 0.89 (0.79, 0.95) | 0.96 (0.89, 0.99) |
| S4-1 | 150 | 0.81 (0.72, 0.88) | 0.92 (0.80, 0.98) |
| L12-4 | 120 | 0.74 (0.57, 0.88) | 0.89 (0.81, 0.95) |
For B-line counting, the intraclass correlation coefficient (ICC) for maximum B-line count was as follows:
| Transducer | Sample size<br>(video loops) | ICC (95% CI) |
|------------|------------------------------|-------------------|
| All | 416 | 0.91 (0.89, 0.93) |
| C5-2 | 146 | 0.94 (0.91, 0.95) |
| S4-1 | 150 | 0.87 (0.82, 0.90) |
| L12-4 | 120 | 0.91 (0.88, 0.94) |
#### Conclusion
The study demonstrates the safety and efficacy of the Expanded B-Lines Software Feature and confirms the device met the clinical user needs as intended.
#### 9. Sterilization
Not applicable. The ultrasound transducers are not supplied sterile.
#### 10. Conclusion
For testing, all pre-determined acceptance criteria were met. Results of these tests show that the proposed subject device meets its intended use.
The changes made to the subject device do not affect the use of the device, nor do they introduce any new or significantly modified risks. The results of the relevant performance and compatibility tests support a determination that the proposed subject device does not raise new questions of safety or effectiveness. Therefore, the subject device is substantially equivalent to the predicate device (K203406) in terms of indications for use, design, technological characteristics, modes of operations, safety, and effectiveness.
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.