K132402 · Nonin Medical, Inc. · DQA · Feb 21, 2014 · Cardiovascular
Device Facts
Record ID
K132402
Device Name
SENSMART MODEL X-100 UNIVERAL OXIMETRY SYSTEM
Applicant
Nonin Medical, Inc.
Product Code
DQA · Cardiovascular
Decision Date
Feb 21, 2014
Decision
SESE
Submission Type
Traditional
Regulation
21 CFR 870.2700
Device Class
Class 2
Attributes
Pediatric
Indications for Use
Nonin's SenSmart™ Model X-100 Universal Oximetry System is a modular system and is indicated for use in simultaneously measuring, displaying, monitoring, and recording up to six (6) channels of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate or cerebral or somatic hemoglobin oxygen saturation (rSO2) of blood underneath the sensor. Patient populations include adult, pediatric, infant, and neonate through the use of SenSmart compatible sensors. The SenSmart system is intended for use in hospitals, long-term care, medical facilities, sleep laboratories, sub-acute environments, and Emergency Medical Services (EMS), including patient transport. The X-100 SenSmart system may be used for spot-checking and continuous monitoring with patient alarms. The SenSmart pulse oximetry (SpO2) functionality is suitable for use in both motion and non-motion conditions, including patients who are well or poorly perfused.
Device Story
Modular oximetry system measuring SpO2, pulse rate, and rSO2 via sensors. Inputs: optical signals from sensors (up to 6 channels). Processing: signal processor (X-100SP) and hub (X-100H) transmit data to monitor (X-100M) for display, alarm, and memory storage. Used in clinical settings (hospitals, EMS, etc.) by healthcare professionals. Output: real-time physiological data on monitor display; data exportable via SenSmart Download software to Windows PC for record-keeping and reporting. Clinical benefit: continuous or spot-check monitoring of oxygenation status to inform clinical decision-making.
Clinical Evidence
Clinical hypoxia study on 13 healthy volunteers (light-to-dark-skinned) compared device SpO2 to co-oximeter SaO2 (70-100% range). Results: ±2% accuracy in non-motion, ±3% in motion conditions. Usability study with 20 healthcare professionals validated user interface effectiveness, efficiency, and satisfaction. No adverse effects reported.
Technological Characteristics
Modular system with X-100M monitor, X-100SP signal processors, and X-100H hub. Uses Li-ION battery. Connectivity via Bluetooth. Sensors: 8004CA, 8003CA, 8004CB, 8004CB-NA, and 8100S(x). Compliance with IEC 60601-1, IEC 60601-1-2, ISO 80601-2-61, and IEC 60601-1-6.
Indications for Use
Indicated for adult, pediatric, infant, and neonate patients requiring monitoring of SpO2, pulse rate, or rSO2. Suitable for well or poorly perfused patients in motion or non-motion conditions. Used in hospitals, long-term care, medical facilities, sleep labs, sub-acute environments, and EMS.
Regulatory Classification
Identification
An oximeter is a device used to transmit radiation at a known wavelength(s) through blood and to measure the blood oxygen saturation based on the amount of reflected or scattered radiation. It may be used alone or in conjunction with a fiberoptic oximeter catheter.
{0}------------------------------------------------
# 2. "510(k) Summary" as required by section 807.92(c)
| Submitter: | Nonin Medical, Inc.<br>13700 1st Ave. North<br>Plymouth, MN 55441-5443 |
|----------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Phone: | 763-553-9968 |
| Fax: | 763-553-7807 |
| Contact Person: | Brodie Pedersen<br>Senior Regulatory Engineer |
| Date Prepared: | September 13, 2013 |
| Trade Name: | Model X-100 |
| Common Name/<br>Classification Name<br>and Number: | Oximeter<br>Class II, 21 CFR 870.2700 |
| Product Code: | MUD, DQA |
| Predicate Device(s): | Nonin's SenSmart™ Model X-100 Universal Oximetry System is<br>equivalent to the predicate Model 7600 system cleared by the FDA<br>under K113215 on 5/18/2012 including the 8004CB and 8004CB-NA<br>sensors, the Model 7600 cleared by the FDA under K102715 on<br>12/17/2010 including the 8004CA and 8000CA sensors, and Model 7500<br>Digital Pulse Oximeter and cleared by the FDA under K080255 on<br>5/23/2008. |
{1}------------------------------------------------
#### Device Description:
The SenSmart X-100 Oximetry System performs both pulse oximetry and regional oximetry measurements. The SenSmart X-100 Oximetry System works with all Nonin Equanox regional oximetry sensors (Model 8004CA, Model 8003CA, Model 8004CB and Model 8004CB-NA). The SenSmart compatible pulse oximetry Soft Sensor Model 8100S(x) is used with the Model X-100 System. The system consists of the sensor, the X-100SP signal processor (up to 6), extensions cables, the X-100H hub for multiple channels, the X-100M SenSmart Monitor which includes display, alarms, and memory. The SenSmart Download software is included for data storage review and reporting on a Windows PC.
Indications for Use:
## Model X-100
Nonin's SenSmart™ Model X-100 Universal Oximetry System is a modular system and is indicated for use in simultaneously measuring, displaying, monitoring, and recording up to six (6) channels of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate or cerebral or somatic hemoglobin oxygen saturation (rSO2) of blood underneath the sensor. Patient populations include adult, pediatric, infant, and neonate through the use of SenSmart compatible sensors. The SenSmart system is intended for use in hospitals, long-term care, medical facilities, sleep laboratories, sub-acute environments, and Emergency Medical Services (EMS), including patient transport. The X-100 SenSmart system may be used for spot-checking and continuous monitoring with patient alarms. The SenSmart pulse oximetry (SpO2) functionality is suitable for use in both motion and non-motion conditions, including patients who are well or poorly perfused.
#### Model 8100S(x)
Nonin's Model 8100S(X) reusable soft sensor is indicated for noninvasive spot checking and/or continuous monitoring of adult and pediatric patients who are well or poorly perfused, during both motion and non-motion conditions. It is intended for use in environments including the operating room, surgical recovery, critical care, emergency room, long-term care, and mobile environments.
#### SenSmart Download Software
The SenSmart Download Software is an optional accessory for use with Nonin's X-100M SenSmart Monitor only. It is intended for use by healthcare professionals when 1) transferring data from the X-100M to a computer in order to maintain individual records of oximetry data, 2) reviewing data according to user-selected parameters, and 3) generating reports.
4
{2}------------------------------------------------
#### Technological Characteristics:
The Model X-100 system is the Model 7600 platform with the addition of the SpO2 module and sensor from the Model 7500. The Model X-100 provides both modalities of oximetry monitoring in one monitor. The indications for use are combined from the predicate monitors with no changes from the predicates.
The Model X-100 system connectors are modified to prevent misconnection with incompatible components. The Model 8000S(x) connector was modified to create the Model 8100S(x) sensor, consistent with the Model 8004CX regional sensor connector. The Model X-100 system has undergone significant testing and evaluation as described below to assure there is no effect on safety or effectiveness. As shown in Table 1 below, these predicate devices represent the same technical characteristics as the subject device utilizing the same materials, power source and communication technology to provide regional oximetry and pulse oximetry in one device.
| CATEGORY | Identical/<br>Different | Model X-100 | Model 7600 | Model 7500 |
|-----------------------------|-------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| INDICATIONS FOR USE | Similar | Nonin's SenSmart™ Model<br>X-100 Universal Oximetry<br>System is a modular system<br>and is indicated for use in<br>simultaneously measuring,<br>displaying, monitoring, and<br>recording up to six (6)<br>channels of functional<br>oxygen saturation of arterial<br>hemoglobin (SpO2) and<br>pulse rate or cerebral or<br>somatic hemoglobin oxygen<br>saturation (rSO2) of blood<br>underneath the sensor.<br>Patient populations include<br>adult, pediatric, infant, and<br>neonate through the use of<br>SenSmart compatible<br>sensors.<br>The SenSmart system is<br>intended for use in hospitals,<br>long-term care, medical<br>facilities, sleep laboratories,<br>sub-acute environments,<br>and Emergency Medical<br>Services (EMS), including<br>patient transport. The X-100<br>SenSmart system may be<br>used for spot-checking and<br>continuous monitoring with<br>patient alarms. The<br>SenSmart pulse oximetry | Nonin's non-invasive<br>Model 7600 4- Channel<br>Regional Oximeter System<br>is intended for use as an<br>absolute real-time adjunct<br>monitor of regional<br>hemoglobin oxygen<br>saturation of blood<br>underneath the sensor. It<br>is intended for spot-<br>checking or continuous<br>monitoring of adult, or<br>neonate, infant and<br>pediatric patients. It is<br>intended for use in<br>environments including<br>the operating room,<br>surgical recovery, critical<br>care, emergency room,<br>long-term care and mobile<br>environments. | The Nonin Model 7500<br>Digital Pulse Oximeter is<br>a portable tabletop<br>device indicated for use<br>in measuring, displaying,<br>and recording functional<br>oxygen saturation of<br>arterial hemoglobin<br>(SpO2) and pulse rate of<br>adult, pediatric, infant<br>and neonatal patients. It<br>is indicated for spot<br>checking and or<br>continuous monitoring<br>of patients during both<br>motion and non-motion<br>conditions, and for<br>patients who are well or<br>poorly perfused. |
| | ldentical/ | | | |
| CATEGORY | Different | Model X-100 | Model 7600 | Model 7500 |
| | | (SpO2) functionality is<br>suitable for use in both<br>motion and non-motion<br>conditions, including<br>patients who are well or<br>poorly perfused. | | |
| Indications for use | Similar | Nonin's Model 8100S(X)<br>reusable soft sensor is<br>indicated for non-invasive<br>spot checking and/or<br>continuous monitoring of<br>adult and pediatric patients<br>who are well or poorly<br>perfused, during both<br>motion and non-motion<br>conditions. It is intended for<br>use in environments<br>including the operating<br>room, surgical recovery,<br>critical care, emergency<br>room, long-term care, and<br>mobile environments. | NA | Nonin's Model 8000SX-<br>Series Reusable Soft<br>Sensors are indicated for<br>non-invasive spot-<br>checking and/or<br>continuous monitoring of<br>adult and pediatric<br>patients who are well or<br>poorly perfused. It is<br>intended for use in<br>environments including<br>operating room, surgical<br>recovery, critical care,<br>emergency room, long-<br>term care, home use,<br>and mobile<br>environments. |
| Indications for use | Similar | The SenSmart Download<br>Software is an optional<br>accessory for use with<br>Nonin's X-100M SenSmart<br>Monitor only. It is intended<br>for use by healthcare<br>professionals when 1)<br>transferring data from the X-<br>100M to a computer in<br>order to maintain individual<br>records of oximetry data, 2)<br>reviewing data according to<br>user-selected parameters,<br>and 3) generating reports. | eVISION Data<br>Management Software<br>(eVISION) is an optional<br>accessory for use with<br>Nonin's Model 7600<br>Regional Oximeter System.<br>It is intended for use by<br>healthcare professionals<br>when 1) transferring data<br>from the X-100M to a<br>computer in order to<br>maintain individual records<br>of oximetry data, 2)<br>reviewing data according<br>to user-selected<br>parameters, and 3)<br>generating reports. | The nViSiON Data<br>Management Software is<br>an optional accessory for<br>compatible Nonin<br>oximeters: 2120, 2500,<br>3100, 3150, 4000 7500,<br>7800, 8500, 8800, 9600,<br>9700, and 9847. It is<br>intended for use by<br>healthcare professionals<br>when (1) transferring<br>data from pulse<br>oximeters to computers<br>in order to maintain<br>individual records of<br>pulse oximetry data, (2)<br>reviewing data according<br>to user-selected<br>parameters, and (3)<br>generating reports. |
| SYSTEM<br>CONFIGURATIONS | | | | |
| Parts and Accessories | | | | |
| CATEGORY | Identical/<br>Different | Model X-100 | Model 7600 | Model 7500 |
| Sensor Models | Similar | All Nonin smart sensors,<br>8004CA, 8003CA, 8004CB,<br>8004CB-NA, 8100S(x) | All Nonin Regional smart<br>sensors, 8004CA, 8003CA,<br>8004CB, 8004CB-NA | All Nonin DE9 connector<br>pulse oximeter sensors<br>including Model 8000S(x) |
| Download software | Similar | SenSmart Download | evision | nVISION |
| Batteries | Similar | Li ION | Li ION | NiMH |
| Operator's<br>instructions | Similar | CD | CD | CD |
| OVERALL<br>SPECIFICATIONS | | | | |
| SpO2 Range | Similar | 0% to 100% SpO2 | NA | 0% to 100% SpO2 |
| rSO2 Range | Similar | 0% to 100% 1502 | 0% to 100% 1502 | NA |
| Pulse Rate Range | Similar | 18-321 BPM | NA | 18-321 BPM |
| Accuracy | | | | |
| rSOz | Similar | 8004CA 3.9 +/-Arms absolute<br>8004CB 5.9 +/-Ams absolute<br>8003CA 3.6 Ams Trending | 8004CA 3.9 +/-Arms absolute<br>8004CB 5.9 +/-Ams absolute<br>8003CA 3.6 Am, Trending | NA |
| SpOz | Similar | ±2 digits (± 1 Arms) | NA | ±2 digits (± 1 Arms) |
| Low Perfusion SpO2 | Similar | ±2 digits (± 1 Arms) | NA | ±2 digits (± 1 Arms) |
| Pulse Rate | Similar | 20 to 250 BPM ±3 digits | NA | 20 to 250 BPM ±3 digits |
| Low Perfusion Pulse<br>Rate | Similar | 40 to 240 BPM ±3 digits | NA | 40 to 240 BPM ±3 digits |
| Displays | | | | |
| | Similar | LCD Panel 6 Channels | .LCD Panel 4 Channels | 7-Segment 3-Digit LED 1<br>Channel |
| Connectivity | | | | |
| | Identical | Saber Bluetooth Module | Saber Bluetooth Module | N/A |
| Package | Similar | Box | Box | Box |
#### Table 1: Technological Characteristics
{3}------------------------------------------------
.
:
: : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : :
·
·
{4}------------------------------------------------
: : : : : :
:
{5}------------------------------------------------
| Testing: | Nonin's Model X-100 Oximeter system is supported by both laboratory<br>and clinical hypoxia accuracy testing in order to ensure that it has<br>appropriate performance and functional features to fully comply with<br>recognized standards and is substantially equivalent to the predicate<br>device. |
|-----------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Functional and<br>Safety Testing: | Laboratory testing included: software verification, safety testing for<br>electrical, mechanical, biocompatibility analysis, ingress protection,<br>electromagnetic compatibility, device performance, usability evaluation,<br>wireless Bluetooth certification and mechanical durability. These tests<br>have been performed to demonstrate equivalency with the predicate<br>devices and compliance with recognized standards. As shown in the<br>table below the device met the relevant requirements of the applicable<br>recognized standards. |
| | rSO2 Accuracy Testing |
| | The rSO₂ accuracy was demonstrated through detailed device<br>comparison and testing showing how the X-100SP is equivalent to the<br>Model 7600PA pod used with the Model 7600 system regarding rSO2<br>measurements. The regional sensors are identical to those used with<br>the 7600PA. The testing shows via the clinical data how the output<br>from each system is the same when the input signals of the same |
| Test | Reference | Result |
|-------------------------------------------|------------------------------------------------|--------|
| Electrical Safety | IEC 60601-1 | Pass |
| Temperature and Humidity | IEC 60601-1 | Pass |
| Cleaning | IEC 60601-1 | Pass |
| Electromagnetic Immunity and<br>Emissions | IEC 60601-1-2 | Pass |
| Bluetooth Wireless certification | FCC wireless certification Grant | Pass |
| Performance | ISO 80601-2-61<br>IEC 60601-1<br>IEC 60601-1-6 | Pass |
| Ingress Protection | ISO 80601-2-61 | Pass |
| Mechanical Durability | ISO 80601-2-61 | Pass |
| Atmospheric Pressure | IEC 60601-1 | Pass |
| Usability | IEC 60601-1-6 | Pass |
·
{6}------------------------------------------------
## Clinical Testing:
Clinical testing for SpO2 included induced laboratory hypoxia testing on healthy volunteers. A Usability / Human Factors Study was performed to get real user feedback from clinical oximeter users.
### SpO2 Accuracy Testing
Clinical hypoxia accuracy testing conducted during induced hypoxia studies on 13 healthy, nonsmoking, light-to-dark-skinned subjects in an independent research laboratory. The measured arterial hemoglobin saturation value (SpO2) of the device was compared to arterial hemoglobin oxygen (SaO2) value, determined from blood samples with a laboratory co-oximeter. The accuracy of the device is in comparison to the co-oximeter samples measured over the SpO2 range of 70-100%. Accuracy data was calculated using the root-mean-squared (Arms value) for all subjects, per ISO 80601-2-61, Standard Specification for Pulse Oximeters for Accuracy in a non-motion environment demonstrated a specified accuracy of ±2% in non-motion conditions and ±3 in motion conditions on the index finger, middle finger, or ring finger for all data points with an arterial oxygen saturation (SaO2) of greater than or equal to 70%. There were no reported adverse effects during these investigations.
Objectives: The purpose of this study was to verify SpO2 performance accuracy of the Nonin Medical Model X-100SP oximeter with the 8100S(X), pulse oximetry sensors on the finger in stationary (nonmotion) and motion conditions. These aims were achieved by comparing SpO2 measurements with those of arterial blood samples assessed by CO-oximetry. The study was designed in accordance with ISO 80601-2-61. The goal, in its entirety, was to show the SpO2 accuracy performance for the devices. It was expected that the Accuracy Root Mean Square (Arms) performance of the above pulse oximetry systems will meet a specification of ±3% for the range of 70 - 100% SaO2.
Methods: Subjects were connected to a breathing circuit, in which the gas flow delivery was adjusted for subject comfort. This gas circuit provided a gas mixture of medical grade oxygen and nitrogen. The program was run in manual mode, in which the gas mixture was changed by the controller. The program was used to induce hypoxia in a stair-stepped manner which allowed each subject to settle at his or her SpO2 level (e.g. plateau). At each plateau, arterial blood sampling was performed. After drawing a waste sample to clear the arterial line, an arterial sample was drawn. The beginning and end of each draw was noted on the data collection system. This series of waste draw, and arterial draws was repeated multiple times for each plateau. At the end of each plateau, the arterial line was flushed with sterile saline. Subsequently, the program was adjusted to allow the subject to reach a new level of SpO2 and the process was repeated. Samples were run on four (4) CO-oximeters. The SpO2 values at each draw were paired with the average of the three Radiometer CO-oximeters (ALB80Flex OSM).
9
{7}------------------------------------------------
On one hand (the hand without the arterial line), two types of motion were evaluated. These included tapping and rubbing. Both were induced using a motion simulator, occurring at a frequency of 1 Hz, and moving the fingers approximately 1-2 inches. Subjects alternated between starting with rubbing or tapping. Subsequently, the motion type alternated for each stable plateau.
Conclusions: The X-100SP (software rev. 12085) with 8100S(X) sensors demonstrated a specified accuracy of ±2% in non-motion conditions and ±3 in motion conditions on the index finger, middle finger, or ring finger for all data points with an arterial oxygen saturation (SaO2) of greater than or equal to 70%.
USABILITY: The testing performed for this Usability / Human Factors Study was to acquire user feedback from clinical oximeter users.
The primary objective of this study was to collect data which demonstrates the usability of the Nonin Model X-100 SenSmart™ system user interface. The usability components to be tested in this study included operator effectiveness, efficiency, and operator satisfaction. These were assessed by recording the proportion of users who properly performed each task, the time it took to perform each step, and the operator's perception of the system, respectively. Operator effectiveness was the primary objective. Efficiency and operator satisfaction were secondary objectives. Secondary endpoints are descriptive in nature.
Methods: Each user was asked about their knowledge of regional and pulse oximetry. They were trained on system use through an in-service conducted by Nonin personnel. The training included a demonstration of the functions of the system. A minimum of two days after training, each user returned to demonstrate system use. The users were presented with two case scenarios that used specific functions of the system. Users had the benefit of Instructions for Use and In-Service materials as well as the opportunity to contact their clinical education specialist as would be the case with normal clinical use. An observer was present to watch the user perform each task and document whether the tasks were performed appropriately, and whether the user had difficulty using the system. User responses and body language were also documented. The users then completed a questionnaire regarding the various aspects of using the Model X-100 system.
Usability validation was conducted with 20 health care professionals who performed the use case scenarios. A list of effectiveness endpoints which were met and unmet was provided. Lists of modifications to the device, in-service and accompanying documentation were provided. On average, users agreed or strongly agreed with all statements about . system set-up except the ease of changing from %baseline to absolute
{8}------------------------------------------------
alarm limits. On average users also agreed or strongly agreed with all statements about system use.
Conclusion: The Model X-100 has been found to be suitable to provide operator effectiveness, efficiency, and operator satisfaction for the intended users, uses and environments.
Conclusion:
Nonin's SenSmart™ Model X-100 Universal Oximetry System is substantially equivalent to the Model 7600 cleared by the FDA under K113215 on 5/18/2012 including the 8004CB and 8004CB-NA sensors, the Model 7600 cleared by the FDA under K102715 on 12/17/2010 including the 8004CA and 8000CA sensors and Model 7500 Digital Pulse Oximeter and cleared by the FDA under K080255 on 5/23/2008.
Nonin's Model 8100S(x) reusable soft sensor is substantially equivalent to Nonin's Model 8000S(x) reusable soft sensor cleared by the FDA with Model 7500 Digital Pulse Oximeter under K080255 on 5/23/2008 and in K092101 on 10/21/2009.
Nonin's SenSmart Download Software is substantially equivalent to Nonin's eVISION Data Management Software cleared by the FDA in K092678. This software like eVISION is an optional accessory to the SenSmart Model X-100 Universal Oximeter system.
The positive results of testing, lead to the conclusion that the revised indications for use and labeling are substantially equivalent to the predicate device and do not raise new questions of safety and effectiveness.
{9}------------------------------------------------
Image /page/9/Picture/1 description: The image shows the logo for the Department of Health & Human Services USA. The logo is a circular seal with the words "DEPARTMENT OF HEALTH & HUMAN SERVICES USA" written around the perimeter. Inside the circle is an abstract image of an eagle.
Public Health Service
Food and Drug…
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.