(232 days)
EchoGo Amyloidosis 1.0 is an automated machine learning-based decision support system, indicated as a screening tool for adult patients aged 65 years and over with heart failure undergoing cardiovascular assessment using echocardiography.
When utilised by an interpreting physician, this device provides information alerting the physician for referral to confirmatory investigations.
EchoGo Amyloidosis 1.0 is indicated in adult patients aged 65 years and over with heart failure. Patient management decisions should not be made solely on the results of the EchoGo Amyloidosis 1.0 analysis.
EchoGo Amyloidosis 1.0 takes a 2D echocardiogram of an apical four chamber (A4C) as its input and reports as an output a binary classification decision suggestive of the presence of Cardiac Amyloidosis (CA).
The binary classification decision is derived from an AI algorithm developed using a convolutional neural network that was pre-trained on a large dataset of cases and controls.
The A4C echocardiogram should be acquired without contrast and contain at least one full cardiac cycle. Independent training, tune and test datasets were used for training and performance assessment of the device.
EchoGo Amyloidosis 1.0 is fully automated without a graphical user interface.
The ultimate diagnostic decision remains the responsibility of the interpreting clinician using patient presentation, medical history, and the results of available diagnostic tests, one of which may be EchoGo Amyloidosis 1.0.
EchoGo Amyloidosis 1.0 is a prescription only device.
The provided text describes the acceptance criteria and a study proving that the EchoGo Amyloidosis 1.0 device meets these criteria.
Here's a breakdown of the requested information:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are not explicitly stated as clear, quantitative thresholds in a "table" format within the provided text. Instead, the document describes the study that was conducted to demonstrate performance against generally accepted metrics for such devices (e.g., sensitivity, specificity, PPP, NPV, repeatability, reproducibility).
However, based on the results presented in the "10.2 Essential Performance" and "10.4 Precision" sections, we can infer the achieved performance metrics. The text states: "All measurements produced by EchoGo Amyloidosis 1.0 were deemed to be substantially equivalent to the predicate device and met pre-specified levels of performance." It does not, however, explicitly list those "pre-specified levels."
Here's a table summarizing the reported device performance:
| Metric | Reported Device Performance (95% CI) | Notes |
|---|---|---|
| Essential Performance | ||
| Sensitivity | 84.5% (80.3%, 88.5%) | Based on native disease proportion (36.7% prevalence) |
| Specificity | 89.7% (87.0%, 92.4%) | Based on native disease proportion (36.7% prevalence) |
| Positive Predictive Value (PPV) | 82.7% (78.8%, 86.5%) | At 36.7% prevalence |
| Negative Predictive Value (NPV) | 90.9% (88.8%, 93.2%) | At 36.7% prevalence |
| PPV (Inferred) | 15.6% (11.0%, 20.8%) | At 2.2% prevalence |
| NPV (Inferred) | 99.6% (99.5%, 99.7%) | At 2.2% prevalence |
| No-classifications Rate | 14.0% | Proportion of data for which the device returns "no classification" |
| Precision | ||
| Repeatability (Positive Agreement) | 100% | Single DICOM clip analyzed multiple times |
| Repeatability (Negative Agreement) | 100% | Single DICOM clip analyzed multiple times |
| Reproducibility (Positive Agreement) | 85.5% (82.4%, 88.2%) | Different DICOM clips from the same individual |
| Reproducibility (Negative Agreement) | 79.9% (76.5%, 83.2%) | Different DICOM clips from the same individual |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 1,164 patients
- 749 controls
- 415 cases
- Data Provenance: Retrospective case:control study, collected from multiple sites spanning nine states in the USA. The data also included some "Non-USA" origin (as seen in the subgroup analysis table, but the overall testing data seems to be primarily US-based based on the description).
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not explicitly state the number of experts or their specific qualifications (e.g., radiologists with X years of experience) used to establish the ground truth for the test set. It mentions that clinical validation was conducted to "assess agreement with reference ground truth" but does not detail how this ground truth was derived or by whom.
4. Adjudication Method for the Test Set
The document does not specify an adjudication method (e.g., 2+1, 3+1, none) used for the test set's ground truth establishment.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No, the document does not describe an MRMC comparative effectiveness study where human readers improve with AI vs. without AI assistance. The study described is a standalone performance validation of the algorithm against a defined ground truth.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done
Yes, a standalone performance study was done. The results presented (sensitivity, specificity, PPV, NPV) are for the algorithm's performance without a human-in-the-loop. The device is described as "fully automated without a graphical user interface" and is a "decision support system" that "provides information alerting the physician for referral." The performance metrics provided are directly from the algorithm's output compared to ground truth.
7. The Type of Ground Truth Used
The document states: "The clinical validation study was used to demonstrate consistency of the device output as well as to assess agreement with reference ground truth." However, it does not specify the nature of this "reference ground truth" (e.g., expert consensus, pathology, outcomes data).
8. The Sample Size for the Training Set
The training data characteristics table shows the following sample sizes:
- Controls: 1,262 (sum of age categories: 118+197+337+388+222)
- Cases: 1,302 (sum of age categories: 122+206+356+389+229)
- Total Training Set Sample Size: 2,564 patients
9. How the Ground Truth for the Training Set Was Established
The document states: "The binary classification decision is derived from an AI algorithm developed using a convolutional neural network that was pre-trained on a large dataset of cases and controls." It mentions that "Algorithm training data was collected from collaborating centres." However, it does not explicitly describe how the ground truth labels (cases/controls) for the training set were established. It is implied that these were clinically confirmed diagnoses of cardiac amyloidosis (cases) and non-amyloidosis (controls), but the method (e.g., biopsy, clinical diagnosis based on multiple tests, expert review) is not detailed.
{0}------------------------------------------------
Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo is in blue and includes the letters "FDA" in a square and the words "U.S. FOOD & DRUG ADMINISTRATION".
November 15, 2024
Ultromics Limited Jaco Jacobs Chief Regulatory and Compliance Officer 4630 Kingsgate Cascade Way, Oxford Business Park Oxford, OX4 2SU United Kingdom
Re: K240860
Trade/Device Name: EchoGo Amyloidosis (1.0) Regulation Number: 21 CFR 870.2200 Regulation Name: Adjunctive Cardiovasular Status Indicator Regulatory Class: Class II Product Code: SDJ Dated: November 13, 2024 Received: November 13, 2024
Dear Jaco Jacobs:
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 (the 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 available 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.
{1}------------------------------------------------
Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).
Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30. Design controls; 21 CFR 820.90. Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).
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 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-device-advicecomprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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-regulatory
{2}------------------------------------------------
assistance/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,
Stephen C. Browning -S
LCDR Stephen Browning Assistant Director Division of Cardiac Electrophysiology, Diagnostics, and Monitoring Devices Office of Cardiovascular Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health
Enclosure
{3}------------------------------------------------
Indications for Use
Submission Number (if known)
Device Name
EchoGo Amyloidosis (1.0)
Indications for Use (Describe)
EchoGo Amyloidosis 1.0 is an automated machine learning-based decision support system, indicated as a screening tool for adult patients aged 65 years and over with heart failure undergoing cardiovascular assessment using echocardiography.
When utilised by an interpreting physician, this device provides information alerting the physician for referral to confirmatory investigations.
EchoGo Amyloidosis 1.0 is indicated in adult patients aged 65 years and over with heart failure. Patient management decisions should not be made solely on the results of the EchoGo Amyloidosis 1.0 analysis.
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."
{4}------------------------------------------------
Image /page/4/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
1 Submitter
| Company | Ultromics Limited4630 Kingsgate Cascade Way, Oxford Business Park South, Oxford,Oxfordshire, United Kingdom, OX4 2SU |
|---|---|
| Contact | Dr. Jaco Jacobs |
| Date Prepared | 15 Nov 2024 |
2 Subject Device
| Product Trade Name | EchoGo Amyloidosis |
|---|---|
| Model Number | 1.0 |
| 510(k) | K240860 |
| Manufacturer | Ultromics Limited |
| Medical Speciality | Cardiology |
| Regulation | 21 CFR 870.2200 - Cardiovascular Monitoring Devices |
| Product Code | SDJ - Adjunctive Cardiac Amyloidosis Status Indicator |
| Regulatory Class | II |
EchoGo Amyloidosis is the product trade name and 1.0 is the model number. For the avoidance of doubt, in this submission we combine the product trade name and model number and refer to the subject device as EchoGo Amyloidosis 1.0.
3 Predicate Device
| Predicate Device | EchoGo Heart Failure |
|---|---|
| 510(k) | K222463 |
| Manufacturer | Ultromics Limited |
{5}------------------------------------------------
Image /page/5/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
4 Device Description
EchoGo Amyloidosis 1.0 takes a 2D echocardiogram of an apical four chamber (A4C) as its input and reports as an output a binary classification decision suggestive of the presence of Cardiac Amyloidosis (CA).
The binary classification decision is derived from an AI algorithm developed using a convolutional neural network that was pre-trained on a large dataset of cases and controls.
The A4C echocardiogram should be acquired without contrast and contain at least one full cardiac cycle. Independent training, tune and test datasets were used for training and performance assessment of the device.
EchoGo Amyloidosis 1.0 is fully automated without a graphical user interface.
The ultimate diagnostic decision remains the responsibility of the interpreting clinician using patient presentation, medical history, and the results of available diagnostic tests, one of which may be EchoGo Amyloidosis 1.0.
EchoGo Amyloidosis 1.0 is a prescription only device.
5 Comparison of Intended Use
5.1 Indications for Use
We discuss similarities and differences of the subject and predicate devices.
5.1.1 Subject Device
EchoGo Amyloidosis 1.0 is an automated machine learning-based decision support system, indicated as a screening tool for adult patients aged 65 years and over with heart failure undergoing cardiovascular assessment using echocardiography.
When utilised by an interpreting physician, this device provides information alerting the physician for referral to confirmatory investigations.
EchoGo Amyloidosis 1.0 is indicated in adult populations over 65 years of age with heart failure. Patient management decisions should not be made solely on the results of the EchoGo Amyloidosis 1.0 analysis.
5.1.2 Predicate Device
EchoGo Heart Failure 1.0 is an automated machine learning-based decision support system, indicated as a diagnostic aid for patients undergoing routine functional cardiovascular assessment using echocardiography. When utilised by an interpreting clinician, this device provides information that may be useful in detecting heart failure with preserved ejection fraction (HFpEF).EchoGo Heart Failure 1.0 is indicated in adult populations over 25 years of age. Patient management
{6}------------------------------------------------
Image /page/6/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular icon on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular icon is a gradient of blue and green, creating a swirling effect.
decisions should not be made solely on the results of the EchoGo Heart Failure 1.0 analysis. EchoGo Heart Failure 1.0 takes as input an apical 4-chamber view of the heart that has been captured and assessed to have an ejection fraction ≥50%.
6 Discussion
Both subject and primary predicate devices are software-only devices and automated machine learning-based decision support system, indicated for patients undergoing routine cardiovascular assessment using echocardiography.
Both subject and primary predicate are indicated to provide information that may be useful for healthcare professionals in forming a diagnostic work up decisioning. The subject device is intended to be used "as a screening tool for patients undergoing routine cardiovascular assessment using echocardiography" and the primary predicate device is intended to be used "as diagnostic aid for patients undergoing routine functional cardiovascular assessment".
Both subject and primary predicate are intended to provide information on the cardiovascular state of patients. Both subject and primary predicate are used for "patients undergoing routine cardiovascular assessment using echocardiography ".
Both subject and primary predicate devices are indicated in adult populations. The subject device "EchoGo Amyloidosis 1.0 is indicated in adult populations over 65 years of age" and the primary predicate is indicated in adult populations over 25 years of age".
For both subject and primary predicate devices, the patient management decisions should not be made solely on device recommendations.
For purposes of substantial equivalence, the term intended use means the general purpose of the device or its function and encompasses the indications for use. The term indications for use describes the disease the device is intended to serve as a diagnostic aid including a description of the patient population for which the device is intended. Both devices are intended as adjunctive aids for cardiovascular states or conditions and both devices can be used on adult populations. It follows that both devices have intended use of providing adjunctive information on the cardiovascular condition of a patient.
Ultromics believes that general controls and special controls of the predicate device are sufficient to ensure the safety and effectiveness of the subject device.
7 Technological Characteristics
A full comparison of the technological characteristics of the subject and predicate devices follows:
- Both devices takes as input a DICOM file consisting of an echocardiogram from medical devices, such as Medical Ultrasound Equipment or Picture Archiving and Communication System (PACS). Both devices therefore receive as input data that is the output of a preceding medical device (e.g. Medical Ultrasound Equipment or PACS) .
{7}------------------------------------------------
Image /page/7/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
- The output of both devices is based on an artificial intelligence (AI) model developed using a convolutional neural network that produces a classification result.
- Both device reports a classification decision as suggestive or not suggestive of a specific cardiac condition. Both devices are adjunctive cardiovascular status indicators.
- The subject device reports a classification decision as suggestive or not suggestive of the presence of cardiac amyloidosis (CA), while the predicate device reports a classification decision as suggestive or not suggestive of the presence of heart failure with preserved ejection fraction (HFpEF).
- Both subject and primary predicate takes as input an apical 4-chamber view of the heart that has been captured. The subject device takes as input an apical 4-chamber view of the heart that has been captured, while the predicate device takes as input an apical 4chamber view of the heart that has been captured and assessed to have an ejection fraction ≥50%.
- Subject device includes application programming interfaces for input and output for interfacing with external applications and medical devices. This includes the DICOM network interfaces that were also present in the predicate device.
- Subject device allows deployment options permitting functionality to be distributed and replicated, ensuring the scalability, robustness and non-clinical performance of the device.
| Characteristic | Subject DeviceEchoGo Amyloidosis 1.0 | Predicate DeviceEchoGo Heart Failure(K222463) |
|---|---|---|
| Regulation | 21 CFR 870.2200 | 21 CFR 870.2200 |
| Generic Device Type | Adjunctive cardiovascular statusindicator | Adjunctive cardiovascular statusindicator |
| SaMD | Yes | Yes |
| Characteristic | Subject DeviceEchoGo Amyloidosis 1.0 | Predicate DeviceEchoGo Heart Failure(K222463) |
| Indications for Use | EchoGo Amyloidosis 1.0 is anautomated machine learning-baseddecision support system, indicatedas a screening tool for adultpatients over 65 years of age withheart failure undergoing routinecardiovascular assessment usingechocardiography.When utilised by an interpretingphysician, this device providesinformation alerting the physicianfor referral to confirmatoryinvestigations.EchoGo Amyloidosis 1.0 is indicatedin adult populations over 65 yearsof age with heart failure. Patientmanagement decisions should notbe made solely on the results ofthe EchoGo Amyloidosis 1.0analysis. | EchoGo Heart Failure 1.0 is anautomated machine learning-based decision support system,indicated as a diagnostic aid forpatients undergoing routinefunctional cardiovascularassessment usingechocardiography.When utilised by an interpretingclinician, this device providesinformation that may be useful indetecting heart failure withpreserved ejection fraction(HFpEF).EchoGo Heart Failure 1.0 isindicated in adult populationsover 25 years of age. Patientmanagement decisions should notbe made solely on the results ofthe EchoGo Heart Failure 1.0analysis.EchoGo Heart Failure 1.0 takes asinput an apical 4-chamber view ofthe heart that has been capturedand assessed to have an ejectionfraction ≥50%. |
| Population | Adults over the age of 65 | Adults over the age of 25 |
| Anatomical Site | Cardiovascular | Cardiovascular |
| Users | Interpreting clinician | Interpreting clinician |
| Machine Learning-Based Algorithm | Yes | Yes |
| Operating platform | Hosted on Ultromics' platform oron third party infrastructure. | Hosted on Ultromics' platform oron third party infrastructure. |
| Interoperability | Interoperability testing conductedwith a device conformant with theDICOM Standard (NEMA PS 3.1 -3.20 2022d [Rec# 12-349]) | Interoperability testing conductedwith a device conformant with theDICOM Standard (NEMA PS 3.1 -3.20 2022d [Rec# 12-349]) |
| Characteristic | Subject DeviceEchoGo Amyloidosis 1.0 | Predicate DeviceEchoGo Heart Failure(K222463) |
| Software | Complies with IEC 62304:2015 andGPSV. Developed under an FDAQSR and ISO 13485:2016 compliantQMS incorporating riskmanagement per ISO 14971:2019.Software verification and validationtesting conducted. | Complies with IEC 62304:2015 andGPSV. Developed under an FDAQSR and ISO 13485:2016 compliantQMS incorporating riskmanagement per ISO 14971:2019.Software verification andvalidation testing conducted. |
| Risk Management | In accordance with ISO 14971:2019 | In accordance with ISO 14971:2019 |
| Cybersecurity | Post-market Management ofCybersecurity in Medical Devices.Content of Premarket Submissionsfor Management of Cybersecurity inMedical Devices.Cybersecurity for NetworkedMedical Devices Containing Off-the-Shelf (OTS) Software:Guidance for Industry. | Post-market Management ofCybersecurity in Medical Devices.Content of PremarketSubmissions for Management ofCybersecurity in Medical Devices.Cybersecurity for NetworkedMedical Devices Containing Off-the-Shelf (OTS) Software:Guidance for Industry. |
| Usability | Complies with IEC 62366-1:2020and general use of FDA guidancedocuments on usabilityengineering. Formative andsummative evaluations conductedwith clinicians specialising incardiology, with knowledge/experience in echocardiography(N=18). | Complies with IEC 62366-1:2020and general use of FDA guidancedocuments on usabilityengineering. Formative andsummative evaluations conductedwith accredited cardiacphysiologists (N=2) andcardiologists (N=5). |
| Pre-clinicalPerformance Testing | No animal studies were conducted. | No animal studies wereconducted. |
| Bench PerformanceTesting | Technical validation, numericalstability, and regression testing. | Technical validation, numericalstability, and regression testing. |
| Clinical PerformanceTesting | Validated on a validation cohortincluding 12 US sites and 3International sites representative ofthe intended use population. | Validated on a US cohortpopulation, comprising 8independent clinical sitesrepresentative of the intended usepopulation. |
The following table summarises technological characteristics.
{8}------------------------------------------------
Image /page/8/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a blue and green circular icon to the left of the company name, which is written in dark blue, bold, sans-serif font. The icon is a gradient of blue and green, with the colors blending together in a circular shape.
{9}------------------------------------------------
Image /page/9/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
Any technological differences between the subject and predicate devices raise no new concerns with regards to safety and efficacy. In addition, Ultromics is of the view that general controls
{10}------------------------------------------------
Image /page/10/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
alongside special controls introduced under the primary product code of the predicate are sufficient to ensure safety and efficacy of the EchoGo Amyloidosis 1.0 device.
8 Special Controls
Special controls for regulation 21 CFR 870.2200 follows.
| Control | Description | Evidence |
|---|---|---|
| 1 | Software description, verification, and validation based on comprehensive hazard analysis: | |
| a | Full characterization of technical parameters of the software, including any proprietary algorithm(s); | A.22.1 ADP EchoGo Amyloidosis 1.0:Algorithmic Design PlanA.22.2 ADS EchoGo Amyloidosis 1.0:Algorithm Design SpecificationA.22.3 ADR EchoGo Amyloidosis 1.0:Algorithmic Design Report |
| b | Description of the expected impact of all applicable acquisition hardware characteristics on performance and any associated hardware specifications; | A.7.1 EchoGo Amyloidosis 1.0 IFU:Clinician ManualA.23.2 PTR EchoGo Amyloidosis 1.0:Clinical Performance Testing Report |
| c | Specification of acceptable data quality control measures | |
| d | Mitigation of impact of user error or failure of any components (data detection and analysis, data display, and storage) on accuracy of patient reports | 1. Data Validation for Prediction Safety2. Fault Tolerance (Component Failure)3. Prevention of MisreportingA.13.1 SDS EchoGo Amyloidosis 1.0:Software Design SpecificationA.13.2 SDS Ultromics Image ProcessingLibrary 2.0: Software DesignSpecificationA.13.3 SDS Ultromics Repository Library2.0: Software Design SpecificationA.13.4 SDS Ultromics Dicom Library 2.0:Software Design SpecificationA.13.5 SDS Ultromics Reporting Library3.0: Software Design SpecificationA.11.2 SRS EchoGo Amyloidosis 1.0:Software Requirement Specification |
| Control | Description | Evidence |
| 2 | Scientific justification for the validity of thestatus indicator algorithm(s) must beprovided. Verification of algorithmcalculations and validation testing of thealgorithm using a data set separate fromthe training data must demonstrate thevalidity of modelling. | A.22.1 ADP EchoGo Amyloidosis 1.0:Algorithmic Design PlanA.22.2 ADS EchoGo Amyloidosis 1.0:Algorithm Design SpecificationA.22.3 ADR EchoGo Amyloidosis 1.0:Algorithmic Design ReportA.7.1 EchoGo Amyloidosis 1.0 IFU:Clinician ManualA.23.1 PTP EchoGo Amyloidosis 1.0:Clinical Performance Testing PlanA.23.2 PTR EchoGo Amyloidosis 1.0:Clinical Performance Testing Report |
| 3 | Usability assessment must be provided todemonstrate that risk of misinterpretationof the status indicator is appropriatelymitigated. | A.22.8.1 HFUEP EchoGo Amyloidosis 1.0:Human Factors and UsabilityEngineering PlanA.22.8.2 USER EchoGo Amyloidosis 1.0 :Usability Engineering ReportA.22.8.9 UATP EchoGo Amyloidosis 1.0:User Acceptance Testing PlanA.22.8.11 UATR EchoGo Amyloidosis 1.0:User Acceptance Testing Report |
| 4 | Clinical data must be provided in support of the intended use and include thefollowing | |
| a | Output measure(s) must be compared to anacceptable reference method todemonstrate that the output measure(s)represent(s) the predictive measure(s) thatthe device provides in an accurate andreproducible manner. | A.23.1 PTP EchoGo Amyloidosis 1.0:Clinical Performance Testing PlanA.23.2 PTR EchoGo Amyloidosis 1.0:Clinical Performance Testing Report |
| b | The data set must be representative of theintended use population for the device. Anyselection criteria or limitations of thesamples must be fully described andjustified. | |
| c | Agreement of the measure(s) with thereference measure(s) must be assessedacross the full measurement range. | |
| Control | Description | Evidence |
| d | Data must be provided within the clinicalvalidation study or using equivalentdatasets to demonstrate the consistency ofthe output and be representative of therange of data sources and data qualitylikely to be encountered in the intendeduse population and relevant use conditionsin the intended use environment. | A.22.2 ADS EchoGo Amyloidosis 1.0:Algorithm Design SpecificationA.22.3 ADR EchoGo Amyloidosis 1.0:Algorithmic Design ReportA.7.1 EchoGo Amyloidosis 1.0 IFU:Clinician ManualA.23.1 PTP EchoGo Amyloidosis 1.0:Clinical Performance Testing PlanA.23.2 PTR EchoGo Amyloidosis 1.0:Clinical Performance Testing Report |
| 5 | Labeling must include the following: | |
| a | The type of input data used, includingspecification of compatible hardware fordata acquisition | A.7.1 EchoGo Amyloidosis 1.0 IFU:Clinician ManualA.8.1 ADMAN EchoGo Amyloidosis 1.0:Administration Manual - Overview |
| b | A description of what the device measuresand outputs to the user | A.8.2 ADMAN EchoGo Amyloidosis 1.0:Administration Manual - InputAPI:Specification and UsageA.8.3 ADMAN EchoGo Amyloidosis 1.0:Administration Manual - ConfigurationSettingsA.8.4 ADMAN EchoGo Amyloidosis 1.0:Administration Manual - Installation,Management and DecommissioningA.8.5 ADMAN EchoGo Amyloidosis 1.0:Administration Manual - OutputAPI:Specification and UsageA.8.6 ADMAN EchoGo Amyloidosis 1.0:Administration Manual - SecurityA.8.7 ADMAN EchoGo Amyloidosis 1.0:Administration Manual -TroubleshootingA.21.3 DICOM EchoGo Amyloidosis 1.0:DICOM Conformance Statement |
| c | Warnings identifying acquisition or otherfactors that may impact output measures | A.7.1 EchoGo Amyloidosis 1.0 IFU:Clinician Manual |
| d | Guidance for interpretation of the outputmeasures, including warning(s) specifyingadjunctive use of the results | |
| Control | Description | |
| e | Key assumptions made in the calculationand determination of results | |
| f | The measurement performance of thedevice for all presented parameters, withappropriate confidence intervals, and thesupporting evidence for this performance | |
| g | A detailed description of the patientsstudied in the clinical validation (e.g., age,gender, race/ethnicity, clinical stability) aswell as procedural details of the clinicalstudy. |
{11}------------------------------------------------
Image /page/11/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
{12}------------------------------------------------
Image /page/12/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
{13}------------------------------------------------
Image /page/13/Picture/0 description: The image shows the Ultromics logo. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green.
9 Consensus Standards
The following consensus standards will be used in the design and manufacture of EchoGo Amyloidosis 1.0 .
| Standard | Recognition Number |
|---|---|
| ISO 14971:2019 - Medical Devices - Application of Risk Management toMedical Devices | 5-125 |
| IEC 62304:2015 - Medical Device Software - Software Life CycleProcesses | 13-79 |
| IEC 62366-1:2020 - Medical Devices - Application of UsabilityEngineering to Medical Devices | 5-129 |
| NEMA PS 3.1 - 3.20 2022d - Digital Imaging and Communications inMedicine (DICOM) Set | 12-349 |
| IEC ISO 10918-1:1994 - Digital Compression and Coding of Continuous-tone Still Images | 12-261 |
| ISO 14155:2020 - Clinical investigation of medical devices for humansubjects - Good clinical practice | 2-282 |
Ultromics Limited cites conformity to the voluntary standards above. In addition, EchoGo Amyloidosis 1.0 will be designed and manufactured under a QMS that fully conforms to US Quality System (QS) regulation (21 CFR Part 820) and ISO 13485:2016.
{14}------------------------------------------------
Image /page/14/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
10 Performance Data
10.1 Software Verification and Validation
EchoGo Amyloidosis 1.0 software was developed and tested in accordance with Ultromics' Design Control processes and has been subjected to extensive safety and performance testing. Nonclinical verification and validation test results established that the device meets its design requirements and intended use. A description for the patient characteristics within the training data is provided in the table below.
Software verification was conducted at unit, module, and system integration levels. Risk management analysis generated multiple risk mitigation measures and verification activities. Regression- and numerical stability testing were conducted to ensure the device meets algorithmic specifications. Formative and summative usability assessments were conducted to validate labelling and mitigate against the device outputs being misinterpreted by the clinical user. Cybersecurity and data security testing were conducted to verify that data and patient protected health information security measures are included in the design of the software.
Software verification and validation testing were conducted, and documentation was provided as recommended by FDA's Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices. The software device documentation was evaluated at the Enhanced Documentation level, as specified in the FDA's Content of Premarket Submissions for Device Software Functions guidance.
EchoGo Amyloidosis 1.0 passed all software verification and validation tests.
10.2 Essential Performance
Device performance was validated using bench- and clinical performance testing.
Algorithm training data was collected from collaborating centres. The clinical characteristics of the training data are provided in the table below. The training dataset included both controls and cases across a broad age range, consisting of males and females, with most participants aged between 61-80 years. Racial demographics included 79.7-80.6% White, 13.3% Black, 2.3-3.0% Asian, and 3.7-4.0% Other. An independent clinical validation study was conducted to complile a clinical test dataset (testing data). For testing and intended use, the data comprised male and female patients aged 65+ years with heart failure (HF). The testing dataset included both controls and cases, consisting of male and female participants, with most individuals aged between 71-80 years. Racial demographics included 58.4-66.0% White, 24.6-26.8% Black, 1.9-11.8% Asian, and 5.2-5.3% Other. The data was intended to be representative of the intended use population and containing a range of data sources and data quality likely to be encountered in the intended use population and relevant use conditions in the intended use environment (see table below). The clinical validation study was used to demonstrate consistency of the device output as well as to assess agreement with reference ground truth.
{15}------------------------------------------------
Image /page/15/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
| Variable | Training data | Testing Data (65+ years with HF) | ||
|---|---|---|---|---|
| Controls | Cases | Controls | Cases | |
| Age, years, median (IQR) | ||||
| <50 | 118 (9.4%) | 122 (9.4%) | - | - |
| 51-60 | 197 (15.6%) | 206 (15.8%) | - | - |
| 61-70 | 337 (26.7%) | 356 (27.3%) | 105 (14.0%) | 75 (18.1%) |
| 71-80 | 388 (30.7%) | 389 (29.9%) | 285 (38.1%) | 214 (51.6%) |
| >80 | 222 (17.6%) | 229 (17.6%) | 359 (47.9%) | 126 (30.4%) |
| Sex, n(%) | ||||
| Male | 921 (73%) | 948 (72.8%) | 355.0 (47.4%) | 333.0 (80.8%) |
| Female | 341 (27%) | 354 (27.2%) | 394.0 (52.6%) | 79.0 (19.2%) |
| Race, n(%) | ||||
| Black | 161 (13.3%) | 165 (13.3%) | 172.0 (26.8%) | 100.0 (24.6%) |
| White | 965 (79.7%) | 997 (80.6%) | 424.0 (66.0%) | 237.0 (58.4%) |
| Asian | 36 (3.0%) | 29 (2.3%) | 12.0 (1.9%) | 48.0 (11.8%) |
| Other | 49 (4.0%) | 46 (3.7%) | 34.0 (5.3%) | 21.0 (5.2%) |
| Patient Characteristics | ||||
| Hypertension,n(%) | 723 (57.3%) | 337 (25.9%) | 581.0 (91.1%) | 170.0 (74.6%) |
| Diabetes Mellitus,n(%) | 358 (28.4%) | 146 (11.2%) | 272.0 (42.4%) | 54.0 (23.7%) |
| Coronary ArteryDisease, n(%) | 175 (13.9%) | 106 (8.1%) | 201.0 (40.7%) | 66.0 (41.5%) |
| Height, cm,median (IQR) | 173 (166, 180) | 173 (166, 179) | 167.5 (160.0,175.0) | 172.72 (167.6,177.8) |
{16}------------------------------------------------
Image /page/16/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular icon on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular icon is a gradient of blue and green, creating a swirling effect.
| Variable | Training data | Testing Data (65+ years with HF) |
|---|---|---|
| Weight, Kg, median (IQR) | 88.9 (75.9, 103.3) 79.7 (68.0, 90.5) | 80.0 (68.5, 95.0) 77.11 (67.95, 89.2) |
| Body Mass Index, Kg/m2, median (IQR) | 29.4 (25.8, 33.8) 26.3 (23.6, 29.4) | 28.8 (24.0, 33.0) 26.1 (22.9, 29.1) |
| Left Ventricular Ejection Fraction, (%) median (IQR) | 63.0 (56.0, 68.0) 55.0 (44.0, 63.0) | 61.0 (55.0, 66.0) 55.0 (45.6, 62.8) |
The essential performance of EchoGo Amyloidosis 1.0 was not evaluated on patients with prior heart transplantation.
Device performance was determined according to a retrospective case:control study including multiple sites spanning nine states in the USA. The final testing data cohort for patients >65 years of age with evidence of heart failure amounted to 1,164 patients, comprising 749 controls and 415 cases. A summary of the device performance for this population is provided in the table below. The EchoGo Amyloidosis 1.0 device correctly identified 310 true positives, and 569 true negatives, alongside 65 false positives and 57 false negatives. This equates to a sensitivity of 84.5% (95% C1: 80.3%, 88.5%), a specificity of 89.7% (95% Cl: 87.0%, 92.4%), a PPV of 82.7% (95% Cl: 78.8%, 86.5%) and NPV of 90.9% (95% CI: 88.8%, 93.2%).
| Statistic | Outcome(95% CI) |
|---|---|
| Sensitivity | 84.5%(80.3%, 88.5%) |
| Specificity | 89.7%(87.0%, 92.4%) |
| Positive Predictive Value at2.2% prevalence* | 15.6%(11.0%, 20.8%) |
| Negative Predictive Value at2.2% prevalence* | 99.6%(99.5%, 99.7%) |
| Positive Predictive Value at36.7% prevalence** | 82.7%(78.8%, 86.5%) |
{17}------------------------------------------------
Image /page/17/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of green and blue, creating a swirling effect.
| Statistic | Outcome(95% CI) |
|---|---|
| Negative Predictive Value at36.7% prevalence** | 90.9%(88.8%, 93.2%) |
| Repeatability | |
| Positive Agreement | 100% |
| Negative Agreement | 100% |
| Reproducibility | |
| Positive Agreement | 85.5%(82.4%, 88.2%) |
| Negative Agreement | 79.9%(76.5%, 83.2%) |
| No-classifications | |
| Proportion of data | 14.0% |
*Estimate based on inferred disease prevalence of 2.2% using data re-sampling.
**Estimate based on native disease proportion within the collected testing dataset (36.7% prevalence).
A breakdown of the device performance by relevant patient sub-groups in a population of patients >65 years of age with evidence of heart failure is provided in table below:
| Variable | Sensitivity | Specificity | PPV Inferred at 2.2%Prevalence |
|---|---|---|---|
| Data Origin | |||
| USA | 83.3% (78.3%, 87.8%) | 89.7% (87.0%, 92.4%) | 15.4% (12.4%, 19.7%) |
| Non-USA | 90.3% (83.0%, 97.7%) | N/A | N/A |
| Age Category(years) | |||
| >80 | 80.6% (72.1%, 88.9%) | 89.2% (85.2%, 92.9%) | 14.4% (10.8%, 20.7%) |
| Variable | Sensitivity | Specificity | PPV Inferred at 2.2% Prevalence |
| 71-80 | 88.3% (83.2%, 92.9%) | 91.5% (87.6%, 95.1%) | 19.0% (13.7%, 29.4%) |
| 61-70 | 79.4% (66.7%, 89.8%) | 86.7% (78.3%, 94.5%) | 11.8% (7.6%, 25.2%) |
| BMI Category(kg/m2) | |||
| >35 | 68.8% (38.5%, 92.3%) | 93.3% (87.9%, 97.9%) | 18.8% (9.5%, 42.1%) |
| 30-35 | 69.4% (52.0%, 84.6%) | 92.7% (87.2%, 97.3%) | 17.6% (10.2%, 36.3%) |
| 25-30 | 84.7% (76.9%, 92.3%) | 91.9% (87.5%, 95.8%) | 19.0% (13.1%, 30.2%) |
| 18.5-25 | 88.7% (81.3%, 95.0%) | 83.3% (76.1%, 89.6%) | 10.7% (7.7%, 16.4%) |
| <18.5 | 100.0% (100.0%, 100.0%) | 66.7% (28.6%, 100.0%) | 6.3% (3.1%, 100.0%) |
| Sex | |||
| Female | 73.9% (61.8%, 85.5%) | 90.5% (86.7%, 93.8%) | 14.9% (10.6%, 21.7%) |
| Male | 87.5% (83.2%, 91.2%) | 88.9% (84.9%, 92.8%) | 15.1% (11.5%, 21.7%) |
| Race | |||
| White | 84.8% (79.1%, 90.4%) | 91.4% (87.9%, 94.5%) | 18.1% (13.7%, 25.8%) |
| Black | 85.9% (77.8%, 93.6%) | 82.8% (75.5%, 90.1%) | 10.1% (7.2%, 16.3%) |
| Asian | 84.1% (70.6%, 94.4%) | 100.0% (100.0%, 100.0%) | 100.0% (100.0%, 100.0%) |
| Other | 78.9% (56.2%, 100.0%) | 93.3% (80.8%, 100.0%) | 21.0% (8.1%, 100.0%) |
| History ofAFib | |||
| AFib | 83.2% (75.3%, 90.5%) | 91.8% (87.4%, 95.6%) | 18.6% (12.8%, 30.3%) |
| SR | 83.5% (74.7%, 91.8%) | 90.8% (87.1%, 94.2%) | 17.0% (12.4%, 24.8%) |
| Hypertension | |||
| Y | 82.2% (75.6%, 88.9%) | 91.2% (88.4%, 94.0%) | 17.3% (13.5%, 23.5%) |
| N | 86.3% (73.2%, 95.0%) | 90.4% (81.0%, 97.6%) | 16.8% (8.9%, 45.9%) |
| Variable | Sensitivity | Specificity | PPV Inferred at 2.2% Prevalence |
| DiabetesMellitus | |||
| Y | 79.2% (63.9%, 91.7%) | 93.9% (90.2%, 97.2%) | 22.6% (14.7%, 39.8%) |
| N | 84.7% (78.1%, 90.8%) | 89.3% (85.4%, 92.8%) | 15.1% (11.5%, 21.2%) |
| CoronaryArteryDisease | |||
| Y | 84.7% (73.9%, 93.8%) | 91.1% (85.9%, 95.6%) | 17.7% (11.8%, 30.0%) |
| N | 87.8% (79.7%, 95.3%) | 91.9% (88.0%, 95.3%) | 19.6% (14.1%, 29.5%) |
| AorticStenosis | |||
| Y | 85.7% (50.0%, 100.0%) | 88.6% (79.7%, 95.5%) | 14.5% (7.5%, 32.4%) |
| N | 83.3% (72.7%, 92.7%) | 90.5% (85.6%, 94.6%) | 16.4% (11.2%, 25.6%) |
| HFpEF | |||
| Y | 85.4% (80.8%, 90.1%) | 92.2% (89.1%, 95.0%) | 19.7% (14.8%, 27.3%) |
| N | 82.0% (69.4%, 91.8%) | 89.7% (76.0%, 100.0%) | 15.1% (6.9%, 100.0%) |
| Manufacturer | |||
| Philips | 81.9% (76.2%, 87.5%) | 86.5% (81.3%, 91.0%) | 12.0% (9.0%, 16.9%) |
| GE | 88.8% (82.0%, 95.5%) | 90.4% (85.6%, 95.2%) | 17.2% (12.1%, 29.6%) |
| Siemens | 83.3% (0.0%, 94.7%) | N/A | 18.1% (12.2%, 29.2%) |
| ACUSON | 100.0% (100.0%, 100.0%) | N/A | 15.4% (11.5%, 21.5%) |
| LeftVentricularEjectionfractionCategory (%) | |||
| >65 | 82.5% (70.5%, 93.0%) | 91.6% (86.8%, 95.5%) | 18.1% (12.2%, 29.2%) |
| Variable | Sensitivity | Specificity | PPV Inferred at 2.2% Prevalence |
| 50-65 | 86.1% (79.6%, 91.5%) | 89.3% (85.3%, 92.9%) | 15.4% (11.5%, 21.5%) |
| 40-50 | 86.2% (76.0%, 94.5%) | 90.0% (78.6%, 100.0%) | 16.2% (8.1%, 100.0%) |
| <40 | 82.0% (69.4%, 91.8%) | 89.7% (76.0%, 100.0%) | 15.1% (6.9%, 100.0%) |
| LeftVentricularPosteriorWallThicknessCategory(mm) | |||
| >16 | 94.2% (89.0%, 98.0%) | 84.2% (75.0%, 92.9%) | 11.8% (7.7%, 22.6%) |
| 14-16 | 88.5% (80.8%, 95.1%) | 86.4% (79.3%, 93.4%) | 12.7% (8.7%, 23.0%) |
| 12-14 | 79.5% (68.5%, 89.5%) | 86.8% (80.5%, 92.8%) | 11.9% (8.2%, 19.9%) |
| 10-12 | 80.0% (66.7%, 92.1%) | 96.7% (93.2%, 99.3%) | 35.2% (20.9%, 71.7%) |
| 8-10 | 50.0% (27.8%, 73.7%) | 94.2% (86.0%, 100.0%) | 16.3% (6.1%, 100.0%) |
| 6-8 | 60.0% (0.0%, 100.0%) | 100.0% (0.0%, 100.0%) | 100.0% (0.0%, 100.0%) |
| Inter-VentricularSeptumThicknessCategory(mm) | |||
| >16 | 93.7% (89.1%, 97.6%) | 87.1% (80.0%, 93.5%) | 14.0% (9.6%, 24.3%) |
| 14-16 | 81.6% (72.7%, 90.1%) | 88.4% (81.8%, 94.3%) | 13.7% (9.1%, 24.4%) |
| 12-14 | 85.9% (75.5%, 95.6%) | 90.2% (84.2%, 95.4%) | 16.4% (10.5%, 30.1%) |
| 10-12 | 52.2% (29.4%, 75.0%) | 92.9% (85.7%, 98.5%) | 14.3% (5.9%, 45.0%) |
| 8-10 | 60.0% (25.0%, 100.0%) | 95.0% (81.2%, 100.0%) | 21.3% (5.3%, 100.0%) |
| 6-8 | 60.0% (0.0%, 100.0%) | 100.0% (0.0%, 100.0%) | 100.0% (0.0%, 100.0%) |
| Variable | Sensitivity | Specificity | PPV Inferred at 2.2%Prevalence |
| LeftVentricularMass Indexed(g/m2) | |||
| >95 | 85.0% (79.8%, 90.4%) | 89.2% (85.3%, 92.9%) | 15.0% (11.4%, 21.2%) |
| <95 | 78.3% (64.5%, 90.9%) | 95.0% (89.1%, 100.0%) | 26.0% (13.5%, 100.0%) |
| Image Zoom | |||
| Zoomed -Yes | 86.7% (76.6%, 95.7%) | 83.3% (70.0%, 94.4%) | 10.5% (6.1%, 25.6%) |
| Zoomed - No | 84.3% (79.8%, 88.7%) | 86.2% (80.6%, 91.7%) | 12.1% (8.9%, 18.5%) |
{18}------------------------------------------------
Image /page/18/Picture/0 description: The image contains the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
{19}------------------------------------------------
Image /page/19/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
{20}------------------------------------------------
Image /page/20/Picture/0 description: The image contains the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
{21}------------------------------------------------
Image /page/21/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of green and blue, creating a sense of depth and movement.
10.3 Uncertainty ("No Classification") Stratification
When input studies demonstrate a higher than acceptable level of uncertainty (above the predetermined uncertainty threshold), they are reported with a "no classification" output report. EchoGo Amyloidosis 1.0 demonstrated a "no classification" rate of 14.0% during the pivotal clinical investigation.
The primary outcome statistics of the clinical performance study excluded uncertain predictions, per the intended use. For completeness, the below table demonstrates the performance of EchoGo Amyloidosis 1.0 when the uncertainty metrics are disregarded and the predictions with high uncertainty (suggestive of cardiac amyloidosis or not suggestive of cardiac amyloidosis) are included in the performance calculations. We show how incrementally including uncertain predictions affects the performance assessment, demonstrating how the use of uncertainty metrics tempers erroneous device outputs.
| Proportionof UncertainData AddedBack (%) | Sensitivity | Specificity | PPV | NPV |
|---|---|---|---|---|
| 20 | 85.0 (80.7, 88.9) | 86.7 (83.6, 89.7) | 78.4 (73.8, 83.3) | 91.0 (88.4, 93.5) |
| 40 | 85.3 (81.1, 89.2) | 83.9 (80.8, 87.0) | 75.1 (70.2, 79.9) | 91.0 (88.4, 93.5) |
| 60 | 85.7 (81.7, 89.4) | 81.2 (78.0, 84.4) | 71.9 (67.2, 76.8) | 91.0 (88.4, 93.5) |
| 80 | 86.1 (82.1, 89.7) | 78.8 (75.5, 82.2) | 69.3 (64.5, 74.0) | 91.0 (88.4, 93.5) |
{22}------------------------------------------------
Image /page/22/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, with the blue on the bottom and the green on the top.
| Proportionof UncertainData AddedBack (% ) | Sensitivity | Specificity | PPV | NPV |
|---|---|---|---|---|
| 100 | 86.4 (82.6, 89.9) | 76.4 (73.3, 79.9) | 66.9 (62.6, 71.7) | 91.0 (88.4, 93.5) |
For full transparency, and to represents the worst case scenario for spectrum bias, please see the below table that demonstrates the impact on device performance of including the "No-Classification" reports into the denominator when calculating Sensitivity and Specificity (i.e. this approach assumes the uncertain output is incorrect).
| Variable | Proportion ofUncertain Reports | Sensitivity*(including uncertainportion) | Specificity*(including uncertainportion) |
|---|---|---|---|
| All data | 14.0% | 72.8% (67.7%, 77.8%) | 76.0% (72.5%, 79.3%) |
| Age Category (years) | |||
| >80 | 16.7% | 69.0% (61.0%, 77.1%) | 73.5% (69.0%, 78.1%) |
| 71-80 | 11.0% | 80.8% (75.6%, 86.1%) | 79.6% (75.0%, 84.3%) |
| 61-70 | 15.0% | 66.7% (56.0%, 77.3%) | 74.3% (65.9%, 82.6%) |
| BMI Category (kg/m2) | |||
| >35 | 9.9% | 61.1% (38.6%, 83.6%) | 84.2% (78.0%, 90.4%) |
| 30-35 | 16.4% | 58.1% (43.4%, 72.9%) | 77.4% (71.0%, 83.8%) |
| 25-30 | 13.3% | 73.5% (65.3%, 81.6%) | 79.7% (74.6%, 84.7%) |
| 18.5-25 | 15.2% | 78.2% (70.5%, 85.9%) | 68.9% (61.8%, 75.9%) |
| <18.5 | 23.8% | 100.0% (100.0%,100.0%) | 42.9% (16.9%, 68.8%) |
| Sex | |||
| Female | 16.3% | 64.6% (54.0%, 75.1%) | 75.1% (70.9%, 79.4%) |
| Male | 12.4% | 77.8% (73.3%, 82.2%) | 76.9% (72.5%, 81.3%) |
| Race | |||
| Variable | Proportion of Uncertain Reports | Sensitivity* (including uncertain portion) | Specificity* (including uncertain portion) |
| White | 13.2% | 73.0% (67.3%, 78.6%) | 79.7% (75.9%, 83.5%) |
| Black | 19.1% | 79.0% (71.0%, 87.0%) | 61.6% (54.4%, 68.9%) |
| Asian | 6.7% | 77.1% (65.2%, 89.0%) | 100.0% (100.0%, 100.0%) |
| Other | 10.9% | 71.4% (52.1%, 90.8%) | 82.4% (69.5%, 95.2%) |
| History of AFib | |||
| AFib | 14.4% | 71.2% (63.3%, 79.1%) | 78.6% (73.7%, 83.5%) |
| SR | 13.6% | 73.1% (64.6%, 81.6%) | 78.1% (73.6%, 82.6%) |
| Hypertension | |||
| Y | 14.1% | 70.6% (63.7%, 77.4%) | 78.3% (75.0%, 81.7%) |
| N | 10.4% | 75.9% (64.8%, 86.9%) | 82.5% (72.6%, 92.3%) |
| Diabetes Mellitus | |||
| Y | 15% | 70.4% (58.2%, 82.5%) | 79.0% (74.2%, 83.9%) |
| N | 12.1% | 73.0% (66.4%, 79.6%) | 79.2% (75.1%, 83.3%) |
| Coronary ArteryDisease | |||
| Y | 14.6% | 75.8% (65.4%, 86.1%) | 76.6% (70.8%, 82.5%) |
| N | 11.7% | 77.4% (68.9%, 85.9%) | 81.2% (76.8%, 85.7%) |
| Aortic Stenosis | |||
| Y | 18.1% | 66.7% (35.9%, 97.5%) | 72.9% (64.0%, 81.8%) |
| N | 13.6% | 71.4% (61.3%, 81.5%) | 78.4% (73.0%, 83.9%) |
| HFpEF | |||
| Y | 11.9% | 75.2% (70.6%, 79.8%) | 81.3% (77.7%, 84.9%) |
| Variable | Proportion of Uncertain Reports | Sensitivity* (including uncertain portion) | Specificity* (including uncertain portion) |
| N | 12.6% | 74.6% (64.2%, 85.0%) | 72.2% (57.6%, 86.9%) |
| Manufacturer | |||
| Philips | 17.0% | 71.5% (66.1%, 77.0%) | 68.8% (63.7%, 73.9%) |
| GE | 10.5% | 79.8% (72.9%, 86.8%) | 80.6% (74.7%, 86.4%) |
| Siemens | 10.0% | 75.0% (56.0%, 94.0%) | N/A |
| ACUSON | 0.0% | 100.0% (100.0%,100.0%) | N/A |
| Left VentricularEjection fractionCategory (%) | |||
| >65 | 18.0% | 69.1% (58.1%, 80.1%) | 74.6% (69.2%, 80.0%) |
| 50-65 | 12.9% | 76.0% (70.0%, 82.0%) | 77.3% (73.2%, 81.4%) |
| 40-50 | 10.3% | 78.9% (69.4%, 88.4%) | 78.3% (66.3%, 90.2%) |
| <40 | 12.6% | 74.6% (64.2%, 85.0%) | 72.2% (57.6%, 86.9%) |
| Left VentricularPosterior WallThickness Category(mm) | |||
| >16 | 12.9% | 83.7% (77.5%, 89.9%) | 71.1% (61.7%, 80.5%) |
| 14-16 | 13.1% | 78.7% (71.0%, 86.4%) | 73.6% (66.0%, 81.2%) |
| 12-14 | 13.9% | 72.5% (62.7%, 82.3%) | 72.7% (66.0%, 79.3%) |
| 10-12 | 12.1% | 69.2% (56.7%, 81.8%) | 85.4% (80.5%, 90.2%) |
| 8-10 | 14.9% | 42.3% (23.3%, 61.3%) | 80.3% (70.4%, 90.3%) |
| 6-8 | 17.6% | 42.9% (6.2%, 79.5%) | 90.0% (71.4%, 108.6%) |
| Inter-VentricularSeptum ThicknessCategory (mm) | |||
| Variable | Proportion ofUncertain Reports | Sensitivity*(including uncertainportion) | Specificity*(including uncertainportion) |
| >16 | 12.2% | 83.6% (78.2%, 89.1%) | 74.8% (67.5%, 82.1%) |
| 14-16 | 20.2% | 71.4% (63.1%, 79.8%) | 65.6% (58.0%, 73.1%) |
| 12-14 | 10.1% | 78.6% (69.0%, 88.2%) | 80.4% (74.0%, 86.8%) |
| 10-12 | 15.0% | 46.2% (27.0%, 65.3%) | 78.2% (70.2%, 86.3%) |
| 8-10 | 16.7% | 50.0% (21.7%, 78.3%) | 79.2% (62.9%, 95.4%) |
| 6-8 | 18.2% | 50.0% (10.0%, 90.0%) | 80.0% (44.9%, 115.1%) |
| Left Ventricular MassIndexed (g/m2) | |||
| >95 | 12.2% | 75.2% (69.7%, 80.7%) | 77.9% (73.6%, 82.3%) |
| <95 | 17.1% | 66.7% (54.1%, 79.2%) | 77.6% (69.3%, 85.8%) |
| Image Zoom | |||
| Zoomed - Yes | 10.1% | 81.0% (71.3%, 90.6%) | 71.4% (59.6%, 83.3%) |
| Zoomed - No | 16.3% | 74.1% (69.5%, 78.7%) | 67.1% (61.2%, 73.0%) |
{23}------------------------------------------------
Image /page/23/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
{24}------------------------------------------------
Image /page/24/Picture/0 description: The image shows the logo for Ultromics. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
{25}------------------------------------------------
Image /page/25/Picture/0 description: The image shows the logo for ULTROMICS. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
*Performance analysis when including the cases where the truth is positive/negative and the device provides an uncertain result, where the uncertain outputs are included in the denominator when calculating sensitivity/specificity.
10.4 Precision
We compared the device output classification from a single Digital Imaging and Communications in Medicine (DICOM) clip analyzed multiple times (repeatability), and the device output classification from different DICOM clips from the same individual (reproducibility). Repeatability demonstrated 100% positive and negative agreement statistics. Reproducibility demonstrated an average percent of positive agreement of 85.5% (82.4%, 88.2%), the average percent of negative agreement was 79.9% (76.5%, 83.2%).
All measurements produced by EchoGo Amyloidosis 1.0 were deemed to be substantially equivalent to the predicate device and met pre-specified levels of performance. We therefore consider EchoGo Amyloidosis 1.0 to be 'substantially equivalent to the predicate device and is therefore deemed to be safe and effective.
{26}------------------------------------------------
Image /page/26/Picture/0 description: The image shows the Ultromics logo. The logo consists of a circular graphic on the left and the word "ULTROMICS" in bold, dark blue letters on the right. The circular graphic is a gradient of blue and green, creating a swirling effect.
11 Conclusions
The subject device, EchoGo Amyloidosis 1.0 is as safe and as effective as the predicate device, EchoGo Heart Failure, previously cleared under K222463.
Ultromics concludes that the predicate and subject devices have intended use as well as same technological characteristics, so no new concerns raised with regards to safety and effectiveness.
Furthermore, Ultromics believe special controls introduced under the 21 CFR 870.2200 regulation are sufficient to ensure device benefits outweigh the risks. These include software verification and validation including a comprehensive hazard analysis; validation testing of the AI algorithm using a data set separate from the training data to demonstrate the validity of the device output; a usability assessment; clinical data in support of the intended use; as well as labelling consistent with the intended use. Performance data is provided as part of this PMN application to demonstrate that EchoGo Amyloidosis 1.0 performs as intended in the specified use conditions and that it is as safe and effective as the predicate device and therefore substantially equivalent to K222463.
§ 870.2200 Adjunctive cardiovascular status indicator.
(a)
Identification. The adjunctive cardiovascular status indicator is a prescription device based on sensor technology for the measurement of a physical parameter(s). This device is intended for adjunctive use with other physical vital sign parameters and patient information and is not intended to independently direct therapy.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Software description, verification, and validation based on comprehensive hazard analysis must be provided, including:
(i) Full characterization of technical parameters of the software, including any proprietary algorithm(s);
(ii) Description of the expected impact of all applicable sensor acquisition hardware characteristics on performance and any associated hardware specifications;
(iii) Specification of acceptable incoming sensor data quality control measures; and
(iv) Mitigation of impact of user error or failure of any subsystem components (signal detection and analysis, data display, and storage) on accuracy of patient reports.
(2) Scientific justification for the validity of the status indicator algorithm(s) must be provided. Verification of algorithm calculations and validation testing of the algorithm using a data set separate from the training data must demonstrate the validity of modeling.
(3) Usability assessment must be provided to demonstrate that risk of misinterpretation of the status indicator is appropriately mitigated.
(4) Clinical data must be provided in support of the intended use and include the following:
(i) Output measure(s) must be compared to an acceptable reference method to demonstrate that the output measure(s) represent(s) the predictive measure(s) that the device provides in an accurate and reproducible manner;
(ii) The data set must be representative of the intended use population for the device. Any selection criteria or limitations of the samples must be fully described and justified;
(iii) Agreement of the measure(s) with the reference measure(s) must be assessed across the full measurement range; and
(iv) Data must be provided within the clinical validation study or using equivalent datasets to demonstrate the consistency of the output and be representative of the range of data sources and data quality likely to be encountered in the intended use population and relevant use conditions in the intended use environment.
(5) Labeling must include the following:
(i) The type of sensor data used, including specification of compatible sensors for data acquisition;
(ii) A description of what the device measures and outputs to the user;
(iii) Warnings identifying sensor reading acquisition factors that may impact measurement results;
(iv) Guidance for interpretation of the measurements, including warning(s) specifying adjunctive use of the measurements;
(v) Key assumptions made in the calculation and determination of measurements;
(vi) The measurement performance of the device for all presented parameters, with appropriate confidence intervals, and the supporting evidence for this performance; and
(vii) A detailed description of the patients studied in the clinical validation (
e.g., age, gender, race/ethnicity, clinical stability) as well as procedural details of the clinical study.