Search Results

EndoTool IV 3.1 is a glucose management software system used by healthcare professionals in all inpatient care settings for adult and pediatric patients aged two years and above who weigh 12 kgs. or more. EndoTool adjusts and maintains a patient's glucose level within a configurable clinician-determined target range by recommending patient-specific intravenous insulin dosing, carbohydrate dosing for recovery or supplementation, and subcutaneous dosing for the transition from IV dosing.

EndoTool IV 3.1 logic is not a substitute for but rather an adjunct to clinical reasoning. No medical decision should be based solely on the recommended guidance provided by this software system.

EndoTool IV 3.1 is a software system for glucose management which uses the current and cumulative qlucose values provided by the user to calculate and recommend intravenous insulin or carbohydrate doses, to adjust and maintain the patient's glucose level within a provider-ordered target range. In addition, the application can recommend a subcutaneous Basal transition insulin dose when IV insulin therapy is no longer required.

The provided text is a 510(k) summary from the FDA, detailing the premarket notification for the "EndoTool IV 3.1" device. While it outlines the device's purpose, comparison to a predicate device, and general statements about software verification and validation, it does not contain the specific information required to answer your questions regarding acceptance criteria and a study proving the device meets those criteria.

The document states:

• "Software verification and validation testing was conducted per IEC 62304."
• "Clinical testing was not required to demonstrate the safety and effectiveness of the EndoTool IV 3.1. Instead, substantial equivalence is based upon benchtop performance testing."

This indicates that the validation was primarily software-focused and benchtop (likely simulated data or internal testing against predefined rules) rather than clinical. It does not provide:

• A table of acceptance criteria and reported device performance.
• Sample sizes for a test set, its provenance, or whether it was retrospective/prospective.
• Information on experts used for ground truth, their qualifications, or adjudication methods.
• Details of a Multi-Reader Multi-Case (MRMC) study or its effect size.
• Results from a standalone algorithm performance study.
• The type of ground truth used (e.g., expert consensus, pathology, outcomes data).
• Sample size for the training set or how its ground truth was established.

Therefore, based solely on the provided document, I cannot fulfill your request as the essential information about specific performance data, test methodologies, and ground truth establishment is not present. The document focuses on demonstrating substantial equivalence to a predicate device based on similar indications for use, technological characteristics, and conformance to a general software standard (IEC 62304).

Ask a specific question about this device

EndoTool SubQ 2.1 is a software application for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin to be administered subcutaneously to manage blood glucose levels in patients with hyperglycemia including adult and pediatric patients (age 2 years and above and 12 kg or more). The software is designed to recommend the insulin dose(s) and when indicated a carbohydrate dosed on the prescribing healthcare Provider's nutritional regimen, insulin regimen, target glucose range, and patient specific characteristics.

EndoTool SubQ 2.1 logic is not a substitute for clinical reasoning but an aid for trained healthcare professionals based on obtained glucose readings and entered clinical data. Final dose recommendations for a patient must be made only after consideration of the full clinical status of the patient. No medical decision should be made based solely upon the results provided by this software program.

EndoTool SubQ 2.1 is a software application for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin to be administered subcutaneously to manage blood glucose levels in patients with hyperglycemia including adult and pediatric patients (age 2 years and above and 12 kg or more). The software is designed to recommend the insulin dose(s) and when indicated a carbohydrate dose based on the prescribing healthcare Provider's nutritional regimen, insulin regimen, target glucose range, and patient specific characteristics.

The EndoTool® SubQ 2.1 Glucose Management system includes security, software, and technical support features. Each user has an individual User Identification (ID) and Password to access portions of the application. EndoTool SubQ 2.1 is designed to safeguard the confidentiality, integrity, and availability of electronic protected health information of patients according to the Health Insurance Portability and Accountability Act (HIPAA) privacy rules.

EndoTool SubQ 2.1 is packaged in a user friendly, stand-alone program. The application is installed on Windows Server 2008 R2 or newer. The end-user should access the application using a compatible web browser, such as Internet Explorer 9 and higher, or Google Chrome 58 and higher. The application was developed for use on Personal Computers (PCs), network servers, and terminal server environments. As EndoTool SubQ 2.1 data is time sensitive, it is also imperative that all PCs and servers be set with the correct date and time using UTC.

EndoTool SubQ can utilize barcode scanning in Code 39 format (also known as Alpha39, Code 3 of 9, Code 3/9, Type 39, USS Code 39, or USD-3) for patient identification/verification.

The provided text does not contain detailed information about specific acceptance criteria for the output of the EndoTool SubQ 2.1 software or a study demonstrating that the device meets such criteria. Instead, it focuses on demonstrating substantial equivalence to a predicate device through comparison of technological characteristics and general software verification and validation activities.

Here's an analysis of the information that is available and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

Not available in the provided text. The document states that "Software verification and validation testing was conducted per IEC 62304 and FDA's software validation guidance to demonstrate the performance of the device is substantially equivalent to the predicate." It then lists types of testing performed (requirements-based, module and integration, data integration, algorithm test cases, static analysis, regression testing), but it does not provide specific quantitative acceptance criteria (e.g., target accuracy, precision, or other performance metrics for insulin dose recommendations) or the reported performance values against these criteria.

2. Sample size used for the test set and data provenance

Not explicitly available. The document mentions "Algorithm test cases (automated and manual)" as part of performance testing, which implies a test set was used. However, the size of this test set, the nature of the data (e.g., patient records, simulated data), and its provenance (country of origin, retrospective or prospective collection) are not specified.

3. Number of experts used to establish the ground truth for the test set and their qualifications

Not available. Since the details of the "Algorithm test cases" are not provided, there is no information on how ground truth was established for these cases, nor the number or qualifications of any experts involved.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

Not available. This information is dependent on the details of how the ground truth was established, which is not provided.

5. If a multi-reader, multi-case (MRMC) comparative effectiveness study was done, and its effect size

No, a MRMC comparative effectiveness study was not explicitly mentioned and does not appear to have been performed. The document focuses on the software's performance and its substantial equivalence to a predicate device, not on comparing human reader performance with and without AI assistance. The device is described as "an aid for trained healthcare professionals," not a tool to enhance human reading of medical images or data in a comparative effectiveness study context.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

Yes, implicitly. The "Algorithm test cases (automated and manual)" would involve evaluating the algorithm's output independently. The device's description as a "software application for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin" implies standalone algorithmic calculations. However, the performance metrics from this standalone evaluation are not provided.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

Not explicitly available. For "Algorithm test cases," the ground truth would likely be a clinically validated optimal insulin dose or a set of expected outcomes based on established medical protocols for various patient scenarios. However, the specific method of establishing this ground truth is not detailed.

8. The sample size for the training set

Not available. The document describes a software application that calculates insulin doses. While such applications often involve algorithms that might be "trained" or developed based on data, there is no mention of a distinct "training set" or its size in the context of machine learning or AI. The software is described as having an "algorithm" and being "designed to recommend the insulin dose(s)", suggesting it operates based on predefined logic and parameters rather than a continuously learning model with a training phase.

9. How the ground truth for the training set was established

Not applicable/Not available. As above, the concept of a "training set" and establishing ground truth for it is not explicitly discussed for this type of software, which appears to be rule-based or algorithmic rather than a machine learning model requiring labeled training data.

In summary: The provided document is a 510(k) summary focused on demonstrating substantial equivalence of EndoTool SubQ 2.1 to a predicate device, EndoTool SubQ (K180366). It outlines general software validation practices and a comparison of features but lacks the specific performance data, acceptance criteria, and details of clinical studies that would typically be described for a diagnostic AI device requiring quantitative performance metrics against a defined ground truth. The device is a "Predictive Pulmonary-Function Value Calculator" (Regulation Name) but its "Indications for Use" clearly state its function is for "calculat[ing] and recommend[ing] an individual patient's next dose of insulin... to manage blood glucose levels." This discrepancy might be a clerical error in the regulatory classification.

Ask a specific question about this device

EndoTool IV is a glucose management software system, designed for use by healthcare professionals in all patient care settings to recommend intravenous and subcutaneous transition dosing, as well as carbohydrates. Evaluating current and cumulative glucose levels, the software adjusts and maintains the glucose level within a configurable clinician-determined target range. The system is indicated for use in adult and pediatric patients ages 2 years and above, who weigh 12 kgs. or more. EndoTool IV logic is not a substitute for, but rather an adjunct to clinical reasoning. No medical decision should be based solely on the recommended guidance provided by this software system.

EndoTool IV is a software system for glucose management which uses the current and cumulative glucose values provided by the user to calculate and recommend intravenous insulin or carbohydrate doses, to adjust and maintain the patient's glucose level within a provider-ordered target range. In addition, the application can recommend a subcutaneous Basal transition insulin therapy is no longer required.

The provided text describes the 510(k) premarket notification for the EndoTool IV System, a glucose management software. However, it does not include specific acceptance criteria or details of a study proving the device meets those criteria, particularly in the context of clinical performance or human-AI interaction.

The document states that the device is a software-only device and that clinical testing was not required to demonstrate safety and effectiveness. Instead, substantial equivalence to a predicate device (EndoTool IV 1.10, K200443) is based upon benchtop performance testing (Software Verification and Validation Testing).

Therefore, many of the requested details about acceptance criteria, sample sizes for test and training sets, expert involvement, adjudication methods, MRMC studies, standalone performance, and ground truth types are not available in the provided document because the nature of the device and the regulatory pathway chosen (510(k) based on substantial equivalence to a predicate, with bench testing for software verification) did not require them.

Below is a table summarizing the information that is available and explicitly stating what is not available based on the provided text.

Acceptance Criteria and Device Performance (Based on available information for EndoTool IV System)

Given that this is a software-only device and substantial equivalence was determined based on benchtop performance testing (software verification and validation), the "acceptance criteria" discussed are likely related to software quality, functional correctness, and adherence to design specifications, rather than clinical performance metrics in a patient population. The document states that the device performs "as well as the predicate device" in terms of its indications for use and overall performance.

1. Table of acceptance criteria and the reported device performance

• Requirements-based, module, and integration tests
• Endo-Tool regression testing (requirements-based for risk-related requirements, automated algorithm test cases for complete application)
• Static analysis of the software code. |
  | User Interface and Functionality: Interface and functionality are as designed and equivalent to the predicate. | "The predicate and subject device are equivalent in design. The subject device is an updated version of the predicate software with minor changes to the interface and functionality." All listed features (e.g., user inputs, alarm advisories, GUI interface) are present and function as intended. |
  | Safety Warnings/Precautions: Appropriate warnings and controls are implemented. | New warning/controls regarding low potassium added (compared to predicate). Warnings, precautions, and labeling are present and equivalent to the predicate. |
  | Compatibility: Operates on specified systems and browsers. | Compatible with "All" operating systems (as vague as stated) and specific browsers (Internet Explorer, Microsoft Edge, Google Chrome, Mozilla Firefox). Hardware requirements are server, PC, printer, barcode scanner (optional). |

2. Sample size used for the test set and the data provenance:

• Not explicitly stated in terms of patient data or clinical samples. The "test set" likely refers to software test cases and simulated data used for verification and validation.
• Data Provenance: Not applicable in the context of clinical data for this 510(k) submission, as clinical studies were not required. The "data" used would be input data for software testing, derived from theoretical scenarios, and potentially representative patient profiles (though specifics are not provided).
• Retrospective/Prospective: Not applicable as clinical studies were not conducted.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not applicable for this type of software verification and validation. The "ground truth" for software functionality is established by its specification and requirements, and verified through testing against those requirements. This does not typically involve a panel of clinical experts adjudicating cases for a test set.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

• Not applicable. As no clinical test set requiring expert interpretation or adjudication was used, this method is not relevant to the data provided.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No, an MRMC study was NOT done. The document explicitly states: "Clinical testing was not required to demonstrate the safety and effectiveness of the EndoTool IV." The device is a "Drug Dose Calculator," which provides recommendations and is an adjunct to clinical reasoning, but the document does not describe it as an AI-powered diagnostic tool requiring human-AI comparative effectiveness studies.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

• Yes, in essence. The entire basis for this 510(k) is the "Software Verification and Validation Testing," which represents the standalone performance of the algorithm against its requirements and specifications. The document states it's "a software system for glucose management which uses the current and cumulative glucose values... to calculate and recommend..." This is the "algorithm only" performance.
• No specific performance metrics (e.g., accuracy, precision relative to a ground truth clinical outcome) are provided because clinical studies were not performed. The performance is deemed "as well as the predicate device" based on software verification.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• Not applicable in the clinical sense. The "ground truth" for software validation testing is typically the expected output based on the defined algorithms and inputs, derived from mathematical models, clinical guidelines incorporated into the algorithm, or predefined correct outputs for specific test cases. This is not derived from expert consensus on patient cases, pathology, or outcomes data in the way a diagnostic AI would require for clinical validation.

8. The sample size for the training set:

• Not applicable/Not stated. This device is presented as an update to a predicate software system, and the filing focuses on demonstrating substantial equivalence based on engineering and software validation. There is no mention of a machine learning component requiring a "training set" of data in the common AI/ML sense. It is a rule-based or algorithm-based system ("Algorithm B" is mentioned).

9. How the ground truth for the training set was established:

• Not applicable. As there is no mention of an ML training set, the establishment of its ground truth is not relevant here. The "ground truth" for the core algorithms would be embedded in established medical principals for glucose management.

Ask a specific question about this device

By evaluating current and cumulative blood glucose levels, EndoTool IV 1.10 - a glycemic management software support program - is designed for use by healthcare professionals in all patient care settings to recommend intravenous and subcutaneous transition dosing, as well as dextrose, to adjust and maintain the blood glucose level within a configurable clinician- determined target range. The EndoTool Drug Delivery Calculator is indicated for use in adult and pediatric patients ages 2 years and above and who weigh 12 kgs. or more. EndoTool IV 1.10 logic is not a substitute for, but rather an adjunct to clinical reasoning. No medical decision should be based solely on the recommended guidance provided by this software program.

EndoTool IV is a software device for blood glucose management which evaluates current and cumulative blood glucose values to recommend intravenous insulin or dextrose/carbohydrate dose, to adjust and maintain the blood glucose level within a provider-ordered target range. In addition, the application will recommend a subcutaneous Basal transition insulin dose when IV insulin therapy is no longer required.

The provided document is a 510(k) summary for the EndoTool IV 1.10 device, a glycemic management software support program. It states that the device is substantially equivalent to a predicate device (EndoTool Glucose Management System, K132547).

Based on the provided text, the device is a software-only device that calculates blood glucose management recommendations. The 510(k) summary explicitly states that clinical studies and animal studies were not required, and performance testing was limited to software verification and validation testing in accordance with IEC 62304 and FDA software validation guidance. Therefore, much of the requested information regarding acceptance criteria for a clinical study, human reader performance, types of ground truth for training/test sets, and sample sizes for training/test sets, is not available in this document as such studies were not conducted for the clearance of this specific iteration of the device.

Here's what can be extracted from the provided text:

1. A table of acceptance criteria and the reported device performance

The document does not provide a specific table of acceptance criteria tied to quantitative device performance metrics (e.g., accuracy, precision) in the way one might expect for a diagnostic or therapeutic device that undergoes clinical trials. Instead, the acceptance criteria are implicit in the software verification and validation testing objectives: ensuring the software meets its requirements and functions correctly as intended.

2. Sample size used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

• Sample Size for Test Set: Not applicable/not specified. The testing described is software verification and validation, not a clinical study with a patient test set.
• Data Provenance: Not applicable. No clinical data was used for performance testing.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Not applicable. As no clinical test set was used, no human experts were involved in establishing ground truth for performance evaluation of the algorithm against patient data. Software testing relies on defined requirements and expected computational outputs as its "ground truth."

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not applicable. No clinical test set.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No. The document explicitly states: "Clinical testing was not required to demonstrate the safety and effectiveness of the EndoTool IV." Therefore, no MRMC study or assessment of human reader improvement with AI assistance was conducted or reported here.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Yes, in the sense that the software's internal logic and calculations were verified through "Automated algorithm test cases" and "Static analysis of the software code." However, this is against predetermined computational correctness, not against clinical outcomes or human performance. The device is intended to provide "recommended guidance" and is "not a substitute for, but rather an adjunct to clinical reasoning," implying it's always intended to be used with a human in the loop. The "standalone" performance here refers to its computational correctness rather than its diagnostic or therapeutic performance in isolation from clinical context.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• For the software verification and validation, the "ground truth" is defined by the software requirements and expected computational outputs based on those requirements. It is a mathematical/logic-based ground truth, not a clinical one derived from patient outcomes or expert consensus on clinical data.

8. The sample size for the training set

• Not applicable/not specified. This device is described as a software program that calculates doses based on input data, not as a machine learning model that undergoes a "training" phase on a dataset of patient outcomes. Its logic is presumably rule-based or uses established physiological models.

9. How the ground truth for the training set was established

• Not applicable. No training set described.

Ask a specific question about this device

EndoTool SubQ is a software application for use by trained healthcare professionals to calculate and recommend an individual patient's next dose of insulin to be administered subcutaneously to manage blood glucose levels in patients with Diabetes Mellitus in both adult and pediatric patients (age 2 years and above and 12 kg or more). The software is designed to recommend the insulin dose(s) (and when indicated a carbohydrate dose) based on the prescribing healthcare provider's nutritional regimen, insulin regimen, target glucose range, and patient specific characteristics.

The EndoTool SubQ is not a substitute for clinical reasoning, but is an aid for trained healthcare professionals to manage patients. The System is based on obtained glucose readings and clinical data entered by the medical staff. Final dose decisions for a patient must be made only after consideration of the full clinical status of the patient. No medical decision should be made based solely on the recommendations provided by this software program.

Monarch Medical Technology's EndoTool SubQ Glucose Management System is a glucose management software solution for healthcare institutions. This system uses proprietary control technology to provide patient-specific glycemic control across a broad population of adult and pediatric patients using basal/bolus insulin therapy. This system is designed to correctly dose subcutaneous insulin (and amount of carbohydrates if and when indicated to treat hypoglycemia) to achieve patient-specific, sustained control with different nutritional and insulin regimens, selected by the patient's physician responsible for glycemic control.

EndoTool SubQ Glucose Management System is designed to be used following a physician order with physician set optional diet, insulin regimen, basal/bolus distribution, initial total daily dose of insulin, and glucose target range. The primary user of the EndoTool SubQ Glucose Management System is the bedside caregiver (e.g. nurse) who will use the system to enter clinical data (e.g. food intake and scheduled blood glucose readings). With confirmation of previous data entered, the system makes the next dose calculation of subcutaneous insulin and the next time for a scheduled glucose determination.

The provided text is a 510(k) summary for the EndoTool SubQ™ device, a software application designed to recommend insulin doses for managing blood glucose levels in diabetic patients. However, the document does not contain explicit acceptance criteria and a detailed study report that proves the device meets specific performance metrics. It primarily focuses on demonstrating substantial equivalence to predicate devices based on intended use, technological characteristics, and general functionality.

Therefore, I cannot provide a table of acceptance criteria and reported device performance, nor can I detail specific study parameters such as sample size, data provenance, expert qualifications, adjudication methods, or effects of AI assistance. The document refers to "Requirements-based testing for all functionality" and "Automated algorithm test case execution" but does not provide the results or details of these tests.

Specifically, the document states:

• Test Summary: "Testing included the following: 1) Requirements-based testing for all functionality. 2) Requirements-based testing for all risk-related requirements. 3) Integration testing to ensure that data flows correctly into and out of the database. 4) Automated algorithm test case execution. 5) Off The Shelf (OTS) software embedded in the application was included in the technical verification protocols. Each OTS component was tested to ensure that it functioned as intended."
• Test Summary Conclusion: "The performance of the EndoTool SubQ Glucose Management System is substantially equivalent to that of the Glytec Glucommander G+ Enterprise System (K113853) and EndoTool IV Glucose Management System (K132547) and raises no new safety or effectiveness issues and performs as well as the predicate."

This indicates that testing was performed, but the results, acceptance criteria, and detailed methodology are not included in this summary.

Therefore, most of the requested information cannot be extracted from this document.

Ask a specific question about this device

By evaluating current and cumulative blood glucose levels, the EndoTool Glucose Management Sysstem (EGMS) - a glycemic management software support program is designed for use by healthcare professionals in all patient care settings to recommend intravenous and subcutaneous transition dosing, as well as dextrose, to adjust and maintain the blood glucose level within a configurable clinician- determined target range.

The EndoTool Drug Delivery Calculator is indicated for use in adult and pediatric patients ages 2 years and above and who weigh 12 kgs. or more.

The EGMS logic is not a substitute for, but rather an adjunct to clinical reasoning. No medical decision should be based solely on the recommended guidance provided by this software program.

The EGMS includes: security features, software upgrades, data backup capabilities, and technical support. Each user has an individual User ldentification (ID) and Password in order to access portions of the application. Software upgrades are accessible through the EndoTool Portal website and the technical support is made easier by the use of Microsoft .Net technologies. EndoTool is designed to safeguard the confidentiality, integrity, and availability of electronic protected health information of patients according to the Health Insurance Portability and Accountability Act (HIPAA) privacy rules. EndoTool is packaged in a user friendly, stand-alone program using Microsoft .Net technologies. The application requires Windows XP or Windows 7. The application was developed for use on Personal Computers (PCs), network servers, and terminal server environments.

The provided text does not contain detailed information about the acceptance criteria or a specific study proving the device meets them beyond a general statement that "Clinical user validation studies demonstrated that the EGMS performs safely and effectively, as intended." Therefore, I cannot fully complete the requested table or answer all questions.

Here's what can be extracted and what information is missing:

1. A table of acceptance criteria and the reported device performance

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample size for the test set: Not specified.
• Data provenance: Not specified (e.g., country of origin, retrospective or prospective).

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not specified.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not specified.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• A MRMC comparative effectiveness study is not explicitly mentioned. The document states "Clinical user validation studies demonstrated that the EGMS performs safely and effectively, as intended," but does not detail the study design to determine if it was an MRMC study or if it measured improvement with AI assistance.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• The document implies human-in-the-loop performance as it states, "The EGMS logic is not a substitute for, but rather an adjunct to clinical reasoning. No medical decision should be based solely on the recommended guidance provided by this software program." This suggests it is not a standalone algorithm without human intervention, but the specifics of a standalone performance study are not detailed.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

• Not specified.

8. The sample size for the training set

• Not specified.

9. How the ground truth for the training set was established

• Not specified.

Summary of available information:

The provided 510(k) summary for the EndoTool Glucose Management System (K132547) presents a high-level overview. It mentions "Clinical user validation studies" that "demonstrated that the EGMS performs safely and effectively, as intended." However, it does not provide any specific details regarding:

• Quantitative acceptance criteria (e.g., specific accuracy, precision, or safety metrics).
• The methodology or results of these studies.
• Sample sizes for training or testing sets.
• The provenance or characteristics of the data used.
• How ground truth was established.
• Details about expert involvement or adjudication.
• Whether MRMC or standalone performance studies were conducted.

The document primarily focuses on regulatory compliance (IEC 62304, ISO 14971) and substantial equivalence to predicate devices, rather than detailed performance study results.

Ask a specific question about this device