Search Results

Ask a specific question about this device

The SOZO Pro has the following uses:

For adult human patients at risk of lymphedema:

A bioimpedance spectroscopy device for use on adult human patients, utilizing impedance ratios that are displayed as an L-Dex ratio that supports the measurement of extracellular volume differences between the limbs and is presented to the clinician on an L-Dex scale as an aid to their clinical assessment of lymphedema.

The use of the device to obtain an L-Dex score is only indicated for patients who will have or who have had lymph nodes, from the axillary and/or pelvic regions, either removed, damaged or irradiated.

The SOZO Pro is intended for adult patients living with heart failure.

This device is intended for use, under the direction of a physician, for the monitoring of patients with fluid management problems suffering from heart failure. Data from the device should be considered in conjunction with other clinical data.

The SOZO Pro may be used as an adjunct to existing methods by aiding clinicians who are using Subjective Global Assessment (SGA) tools to assess patients at risk of protein-calorie malnutrition (PCM).

The SOZO Pro may be further used to estimate the following body composition parameters in humans to track clinically relevant body composition parameters over time:

• Fat mass

• Fat-free mass

• Total body water

• Intracellular fluid

• Extracellular fluid

• Skeletal muscle mass

• The following outputs are also presented:

• Body Mass Index (BMI)

• Basal metabolic rate (BMR; based on Mifflin St. Jeor's algorithm) displayed in calories per day

• Protein and mineral (also known as 'dry lean mass') represents the content of a body that is not fat or fluid; calculated by subtracting total body water weight from fat-free mass weight.

The SOZO Pro device measures current (I), voltage (V) and phase angle (Phi), and from these values calculates resistance (R), reactance (Xc), and impedance (Z), which are used to estimate the above body composition parameters. The device' software will also display the Cole plot, subject height, weight, age and sex.

The SOZO Pro system consists of a connected hand and footplate with built-in stainless-steel electrodes, paired with an Android tablet over Bluetooth connection. An app ("SOZOapp"), supplied with the tablet, controls the functionality of the hardware, and supplies the bioimpedance measurement data to a database ("MySOZO") managed on an external cloud- hosted database. Patient weight is measured with load cells located in the SOZO Pro foot unit or can be hand entered.

Bioimpedance measurements require the patient's weight to be measured by a scale embedded in the base of the system or for the weight of the patient to be entered manually. Following the collection of the patient weight, the patient contacts the SOZO Pro with their bare hands and feet on stainless steel electrodes. The impedance measurement takes about 30 seconds, during which the SOZO Pro® system applies small levels of electrical energy (200μA RMS) to the body across 256 frequencies spaced from 3kHz to 1000kHz and measures the resulting voltage levels.

The provided text describes the SOZO Pro device, a bioimpedance spectroscopy device, and its 510(k) submission to the FDA. However, it does not contain the specific details about acceptance criteria, a comparative study with a human-in-the-loop, the exact sample sizes for test and training sets, the number and qualifications of experts for ground truth, or adjudication methods for all the stated indications for use.

Based on the information available, here's what can be extracted and inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the device went through "appropriate testing per design controls to confirm functionality and performance of the indications." While specific numerical acceptance criteria (e.g., accuracy percentages, thresholds) are not explicitly provided in this document, the general categories of testing and the reported outcomes are:

2. Sample Sizes Used for the Test Set and Data Provenance

• Test Set Sample Size: Not explicitly stated for any of the performance tests. The document mentions "fixed loads" for functional performance, implying a controlled, non-patient-specific test, and "a variety of pacemakers" for compatibility. For the software V&V, it states the software was "verified and validated," which implies testing, but sample size is not quantified.
• Data Provenance: Not explicitly stated. The document is a 510(k) summary for a device manufactured by ImpediMed Limited in Australia. The testing is likely conducted by the manufacturer, but the origin of the data used for performance comparison (e.g., patient data) is not specified. It does not indicate if it was retrospective or prospective.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Experts

• Not explicitly stated. The document focuses on technical performance and validation against engineering standards and a predicate device, rather than diagnostic accuracy studies involving expert human readers and a ground truth derived from clinical experts.

4. Adjudication Method for the Test Set

• Not applicable/Not explicitly stated. Since there's no mention of a human-in-the-loop diagnostic study or expert consensus for ground truth establishment, adjudication methods are not detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• No, not explicitly stated or implied. The submission emphasizes substantial equivalence to a predicate device primarily through technical and functional comparisons, not through a comparative effectiveness study showing improvement in human reader performance with AI assistance. The document states, "The SOZO Pro is intended for use, under the direction of a physician, for the monitoring of patients with fluid management problems suffering from heart failure. Data from the device should be considered in conjunction with other clinical data." This indicates it's an aid, not a standalone diagnostic that would typically undergo such a comparative study for its primary clearance.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Yes, implied. The "Functional performance" section, where it states "performance testing was undertaken using fixed loads and comparing modified SOZO Pro to predicate SOZO measurements to demonstrate that outputs remained consistently accurate and precise," suggests standalone performance evaluation. The device measures impedance, resistance, reactance, and then calculates body composition parameters. The validation of these calculations against a known standard (fixed loads, predicate device performance) represents a standalone performance assessment.

7. The Type of Ground Truth Used

• Reference to Predicate Device and Engineering Standards: For most of the performance claims, the ground truth appears to be:

  • The performance of the predicate SOZO device (K203473).
  • Compliance with IEC 60601 (Electrical Safety/EMC), ISO 62304 (Software V&V), ISO 10993 (Biocompatibility), NIST Handbook 44 and EU Directive 2014/31/EU (Weight Scale).
  • Fixed loads for functional performance testing.
  • ISO 14117 for pacemaker/ICD compatibility.

  There is no mention of "expert consensus," "pathology," or "outcomes data" as ground truth for the device's diagnostic or monitoring capabilities beyond aiding clinical assessment.

8. The Sample Size for the Training Set

• Not applicable/Not stated. This device does not appear to be an AI/ML device that requires a distinct "training set" in the conventional sense for a deep learning model. It's a bioimpedance spectroscopy device that measures physical parameters and applies algorithms (e.g., Mifflin St. Jeor for BMR). The "software updates were included to integrate the scale and weight measurement capabilities," but this doesn't imply a self-learning algorithm that would require a training dataset.

9. How the Ground Truth for the Training Set Was Established

• Not applicable. As it does not appear to be an AI/ML device with a training set, this information is not relevant or provided. The algorithms it uses (e.g., for body composition) are likely fixed formulas validated against general physiological principles and existing scientific literature.

Ask a specific question about this device

Monitoring of the following parameters and their relative of relative of relative changes in fluid volume in adult patients:

• Bioelectrical Impedance
• ECG Amplitude
• PPG Amplitude
• Skin Temperature

The Zynex Monitoring System, Model CM-1600, simultaneously monitors various parameters of a patient's body. These parameters include Bioelectrical Impedance, Electrocardiogram (ECG) Amplitude, Photoplethysmography (PPG) Amplitude, and Skin Temperature. A Relative Index value is calculated as a combination of the changes in these parameters and is represented by a single number. The CM-1600 System is comprised of two (2) subsystems, the Wearable and the Monitor. The CM-1600 Wearable is designed and developed by Zynex Monitoring Solutions, and it collects physiological parameters and transmits those parameters to the CM-1600 Monitor via wireless communication. The CM-1600 Monitor is a Zynex-branded, third-party all-in-one medical grade tablet.

The provided text is a 510(k) summary for the Zynex Monitoring System, Model CM-1600. It describes the device, its intended use, a comparison to a predicate device, and performance data provided in support of substantial equivalence.

However, the provided document does not contain information regarding an AI/ML device, expert ground truth establishment, or specific details on studies proving the device meets acceptance criteria related to AI/ML performance metrics (like sensitivity, specificity, or AUC). The device described, the Zynex Monitoring System, Model CM-1600, monitors physiological parameters such as Bioelectrical Impedance, ECG Amplitude, PPG Amplitude, and Skin Temperature and calculates a "Relative Index" as a combination of changes in these parameters. This appears to be a traditional medical monitoring device, not a device incorporating artificial intelligence or machine learning for diagnostic or interpretive purposes.

Therefore, many of the requested points, such as AI/ML acceptance criteria, sample size for AI/ML test sets, expert adjudication methods, MRMC studies, or ground truth establishment for AI/ML models, cannot be answered from the provided text because the text does not describe an AI/ML device or studies typically associated with its validation.

The available information related to device performance and validation is summarized below:

Device: Zynex Monitoring System, Model CM-1600

Intended Use: Monitoring of Bioelectrical Impedance, ECG Amplitude, PPG Amplitude, and Skin Temperature, and their relative changes in fluid volume in adult patients. It provides numerical values to aid diagnosis by a physician; it is the physician's responsibility to make proper judgments based on these measurements.

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

The document does not specify "acceptance criteria" in terms of numerical performance thresholds (like accuracy percentages or error rates) for the physiological measurements themselves. Instead, it relies on demonstrating compliance with recognized standards and substantial equivalence to a predicate device through various performance tests.

Note: The document states "Animal Testing: No Testing Required" and "Clinical Testing: No Testing Required", indicating these were not part of the performance data submitted for this 510(k) clearance.

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

The document does not detail specific sample sizes for "test sets" in the way one would for an AI/ML algorithm. The performance testing (V&V/Predicate Testing) demonstrates that the device meets applicable requirements and is substantially equivalent to the predicate device. This typically involves engineering and functional validation, not data-driven performance assessments on patient cohorts for diagnostic accuracy. No information is provided regarding data provenance (country of origin, retrospective/prospective). Since clinical testing was not required/conducted, there isn't patient-specific data being referred to in this context.

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

Not applicable. The document does not describe the establishment of a "ground truth" by experts for diagnostic purposes or for validating an AI/ML model. The device provides raw physiological parameters and a "Relative Index," which are direct measurements or calculations, not interpretations requiring expert consensus for ground truth.

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

Not applicable. There is no mention of a test set requiring adjudication in the context of diagnostic or interpretive performance.

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

Not applicable. This is not an AI-assisted diagnostic device, and no MRMC study was mentioned or conducted.

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

Not applicable. The device provides physiological measurements and a calculated index. There isn't an "algorithm only" component that generates a diagnosis or interpretation independent of human interpretation for which standalone performance would be relevant in the context of AI/ML.

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

Not applicable. For this type of physiological monitoring device, "ground truth" would relate to the accuracy of its direct measurements (e.g., how accurately it measures bioelectrical impedance or temperature) against a calibrated standard, not against expert consensus on a diagnosis, pathology, or outcomes data, as these are beyond the scope of a monitoring device providing raw or relative change data.

8. The sample size for the training set

Not applicable. The document does not describe the use of a "training set" for an AI/ML model for this device.

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

Not applicable. As no training set for an AI/ML model is mentioned, the method for establishing its ground truth is not discussed.

Ask a specific question about this device

The Bodyport Cardiac Scale is intended for use, under the direction of a physician, for the non-invasive monitoring and management of patients with fluid management related health conditions. The device is intended to be used to measure and track body weight, peripheral impedance, pulse rate, and center of pressure. The device is intended to be used in the home or clinic environment.

Intended users are people over 21 years of age who can stand for the measurement and weigh less than 180 kg (397 lbs).

The device does not generate any real-time alarms for consideration by the user at home or by a healthcare professional. Data from the device should be used in the context of all clinical data to make determinations of a patient's status.

The Bodyport Cardiac Scale is a non-invasive cardiovascular monitor and body weight scale that measures body weight, peripheral impedance, pulse rate, and center of pressure through the feet of a user standing on its surface. The device is powered by four (4) AA alkaline batteries.

The device is comprised of a physical platform on which the user stands with bare feet. Four electrodes located on the top surface of the platform are used to measure of the user's lower body (foot-to-foot). The impedance signal is obtained by applying a small, safe battery-generated current (

The provided text is a 510(k) summary for the Bodyport Cardiac Scale. It outlines the device's intended use, technological characteristics, and performance data used to demonstrate substantial equivalence to a predicate device. However, it does not provide explicit acceptance criteria in a table format or detailed results from a study proving that the device meets specific performance criteria for AI/algorithm-driven features.

The document states:

• "Performance Bench Testing: Measurement accuracy and linearity of the Bodyport Cardiac Scale were compared to the predicate device to determine substantial equivalence."
• "Clinical Data: Pulse Rate: Clinical testing demonstrated the accuracy of the pulse rate measurement from the Bodyport Cardiac Scale compared to a reference single lead ECG heart rate measurement. For this study, adult subjects, with a range of peripheral impedances and pulse rates, were analyzed. Peripheral Impedance: Analysis of clinical data demonstrated the clinical utility of peripheral impedance in the monitoring of patients with fluid management conditions. This analysis included clinical data from patients with heart failure, as an example patient population with fluid management related health conditions, and healthy subjects, as a control population. Additional testing demonstrated the correlation between impedances measured through hand-to-foot and foot-to-foot body segments. For this study, adult subjects, with a range of peripheral impedances, were analyzed."

Without access to the specific study reports referenced, it's not possible to populate all the requested information about acceptance criteria and study details. The document provides a high-level summary of the types of tests performed but lacks the granular data required.

Here's an attempt to answer the questions based only on the provided text, highlighting what is not available:

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

The document does not explicitly present acceptance criteria in a table or precise reported performance metrics for the device's measurements (body weight, peripheral impedance, pulse rate, center of pressure) against specific numerical targets. It generally states that "Measurement accuracy and linearity... were compared to the predicate device to determine substantial equivalence." and "Clinical testing demonstrated the accuracy of the pulse rate measurement...".

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

• Sample Size for Pulse Rate Study: "adult subjects, with a range of peripheral impedances and pulse rates, were analyzed." (Specific number of subjects not provided).
• Sample Size for Peripheral Impedance Utility Study: "patients with heart failure, as an example patient population with fluid management related health conditions, and healthy subjects, as a control population." (Specific numbers not provided).
• Sample Size for Peripheral Impedance Correlation Study: "adult subjects, with a range of peripheral impedances, were analyzed." (Specific number not provided).
• Data Provenance: Not specified (e.g., country of origin, retrospective or prospective). The context of a 510(k) submission for a US device often implies US-based studies, but it is not explicitly stated.

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)

• The document mentions "reference single lead ECG heart rate measurement" for pulse rate, implying a gold standard measurement, not subjective expert opinion.
• For peripheral impedance, "clinical utility" and "correlation" were analyzed. It does not mention experts establishing ground truth or their qualifications.

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

• This concept is not relevant as the "ground truth" for the measured parameters (pulse rate, impedance, weight, center of pressure) would typically be established by validated reference instruments or objective clinical data, not expert consensus or adjudication in this context.

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 comparative effectiveness study involving human readers with and without AI assistance was not performed or described. The device is a "Cardiac Scale" that measures physiological parameters; it is not an AI-driven diagnostic imaging interpretation tool where human-in-the-loop performance would typically be evaluated in an MRMC study. The device's role is to provide data for physicians to use in context.

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

• Yes, the performance data presented (accuracy of pulse rate, utility/correlation of impedance, accuracy/linearity of weight/center of pressure) would represent the standalone performance of the device's measurement algorithms. It measures the parameters directly.

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

• Pulse Rate: "reference single lead ECG heart rate measurement." This is an objective, instrumental ground truth.
• Peripheral Impedance: For utility, it involved "patients with heart failure... and healthy subjects" which implies clinical diagnoses/outcomes as context for utility. For correlation, it involved comparison between "hand-to-foot and foot-to-foot body segments," likely referring to an instrumental comparison.
• Body Weight & Center of Pressure: Not specified beyond "compared to the predicate device to determine substantial equivalence," which implies a reference standard or validated measurement.

8. The sample size for the training set

• The document does not describe any specific training set for an AI/ML model. It describes "clinical testing" and "analysis of clinical data" but does not differentiate between training and test sets in the context of a machine learning pipeline. The device's function appears to be direct measurement and calculation, not an AI model trained on a large dataset to make a diagnosis or prediction.

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

• Not applicable, as no explicit training set for an AI/ML model is described. The device's functionalities (measuring impedance, pulse rate, weight, center of pressure) are based on established physiological principles and signal processing, not explicitly a supervised machine learning model requiring a ground-truthed training set in the typical AI/ML sense.

Ask a specific question about this device

The SOZO Body Fluid Analyzer is intended for adult patients living with heart failure. This device is intended for use, under the direction of a physician, for the noninvasive monitoring of patients with fluid management problems suffering from heart failure. Data from the device should be considered in conjunction with other clinical data.

The SOZO system consists of a connected hand and footplate with built-in stainless steel electrodes, paired with an Android tablet over Bluetooth connection. An app ("SOZOapp"), supplied with the tablet, controls the functionality of the hardware and supplies the bioimpedance measurement data to a database ("MySOZO") managed on an external cloudhosted database.

Measurements require the patient to make contact with bare hands and feet on stainless steel electrodes. The measurement takes about 30 seconds, during which the SOZO® system applies small levels of electrical energy (200uA RMS) to the body across 256 frequencies spaced from 3kHz to 1000kHz and measures the resulting voltage levels.

The provided text is a 510(k) summary for ImpediMed Limited's SOZO device. It outlines the regulatory review process, device description, technological characteristics, and performance data. However, it does not contain the specific details about acceptance criteria, the study design (like sample sizes for test and training sets, data provenance), ground truth establishment, expert qualifications, or MRMC comparative effectiveness studies that would typically be found in a clinical study report or a more detailed performance section of a 510(k) submission.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (ImpediMed Limited's SOZO, K193410) through technical and safety testing, rather than a clinical performance study evaluating the diagnostic accuracy or effectiveness of a new AI-driven diagnostic feature.

The key change described in this 510(k) is a software modification: "Modification to SOZOapp Fluid Analysis module, renaming it as the 'HF-Dex' module and incorporating a set of normative reference ranges to aid the clinician in their fluid management of patients living with heart failure." This suggests the change is primarily about presenting existing data with new reference points for clinical interpretation, not necessarily about a new algorithm for fluid analysis that would require extensive clinical validation as requested in the prompt.

Given the information provided, I cannot fulfill all parts of your request. The document describes:

• Performance Data in general terms: "The SOZO system has gone through appropriate testing per design controls to confirm functionality and performance of the indications." This refers to:
  • Electrical safety/EMC (IEC 60601)
  • Software V&V (ISO 62304)
  • Biocompatibility (ISO 10993)
  • Functional performance: "performance testing was undertaken using both fixed loads and human volunteers comparing modified to predicate SOZO measurements to demonstrate that outputs remained consistently accurate and precise." This last point is the closest to a performance study, but it's focused on accuracy and precision of measurements (bioimpedance parameters, extracellular fluid, intracellular fluid, and total body water) compared to the predicate device, not on the diagnostic accuracy of the "HF-Dex" module for managing heart failure fluid.

Therefore, many sections of your request cannot be answered from the provided text.

Here's what can be extracted and inferred, along with the limitations:

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

The document broadly states: "The software was verified and validated to meet acceptance criteria and perform as intended." And for functional performance: "to demonstrate that outputs remained consistently accurate and precise." However, specific quantitative acceptance criteria and the corresponding reported numerical performance (e.g., specific accuracy percentages, precision values, or ranges) are not provided.

Missing Information for a Detailed AI/Diagnostic Performance Study:

Since the document describes a software modification primarily related to displaying normative reference ranges and not a new diagnostic algorithm requiring an AI performance study, the following information is not present:

2. Sample size used for the test set and the data provenance: Not applicable in the context of this 510(k) summary, as it doesn't describe a clinical performance study for a new diagnostic algorithm. The "human volunteers" for functional performance testing are mentioned, but no sample size or provenance is given.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, as there's no diagnostic test set with ground truth described.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable.

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: Not applicable. This change isn't an AI-assistance feature in the sense of image interpretation or complex diagnostic aid, but rather new reference ranges for an existing measurement.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The "HF-Dex" module seems to be a display enhancement to an existing measurement device, and its performance is tied to the underlying bioimpedance measurements, which are assessed against the predicate's measurement accuracy, not as a standalone diagnostic algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For the functional performance of the bioimpedance measurements, the ground truth indirectly relies on the established accuracy and precision of the predicate device (K193410) and potentially comparison to known physical properties via "fixed loads." For the "HF-Dex" module providing normative ranges, the "ground truth" would be the clinical standard or source of those normative ranges, which is not detailed here.

8. The sample size for the training set: Not applicable. This document does not describe a machine learning algorithm that requires a training set. The "HF-Dex" module incorporates "normative reference ranges," which implies pre-defined medical standards or clinical data, not a learned model from a training set.

9. How the ground truth for the training set was established: Not applicable.

In summary, this 510(k) notification focuses on demonstrating that modifications to an existing device (SOZO) – specifically, a software update incorporating new normative reference ranges – do not raise new safety or effectiveness concerns and maintain substantial equivalence to the predicate. It does not describe a clinical performance study of a new diagnostic algorithm involving AI or a comprehensive test set with established ground truth as you've outlined in your request.

Ask a specific question about this device

The SOZO Body Fluid Analyzer is intended for adult patients living with heart failure.

This device is intended for use, under the direction of a physician, for the noninvasive monitoring of patients with fluid management problems suffering from heart failure. Data from the device should be considered in conjunction with other clinical data.

The SOZO system consists of a connected hand and footplate with built-in stainless steel electrodes, paired with an Android tablet over Bluetooth connection. An app ("SOZOapp"), supplied with the tablet, controls the functionality of the hardware and supplies the bioimpedance measurement data to a database ("MySOZO") managed on an external cloudhosted database.

Measurements require the patient to make contact with bare hands and feet on stainless steel electrodes. The measurement takes about 30 seconds, during which the SOZO™ system applies small levels of electrical energy (200µA RMS) to the body across 256 frequencies spaced logarithmically from 3kHz to 1000kHz and measures the resulting voltage levels.

The provided text describes the SOZO Body Fluid Analyzer and its clearance via a 510(k) premarket notification. The document focuses on showing substantial equivalence to a predicate device rather than presenting a detailed study proving device performance against specific acceptance criteria for heart failure monitoring. However, it does mention that "The SOZO system has gone through appropriate testing per design controls to confirm functionality and performance of the indications." and "The software was verified and validated to meet acceptance criteria and perform as intended."

Based on the provided text, a direct, comprehensive study with specific acceptance criteria and detailed performance metrics for the device's clinical indication (monitoring heart failure patients with fluid management problems) is not explicitly detailed. The document primarily focuses on demonstrating substantial equivalence through:

• Software V&V: "The software was verified and validated to meet acceptance criteria and perform as intended." - This refers to internal software development and testing, not a clinical performance study.
• Electrical safety/EMC: Tested per IEC 60601.
• Biocompatibility: Tested per ISO 10993.
• Functional performance: Tested design reliability by repeatedly placing weights.

Given the scope of the provided text, I cannot provide detailed acceptance criteria directly linked to clinical performance for heart failure monitoring, nor a study proving those criteria are met for the full clinical indication. The document states "Performance data demonstrates that the modified SOZO is as safe and effective as its predicate," but does not elaborate on what specific performance data was collected for heart failure monitoring.

Therefore, the following information is based on the limited details provided in the text regarding "acceptance criteria" and "performance," largely inferring from the context of a 510(k) submission focused on demonstrating substantial equivalence to a predicate device, rather than a de novo clinical validation for the heart failure indication against quantitative performance targets.

1. Table of Acceptance Criteria and Reported Device Performance

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

The document does not specify a distinct "test set" in the context of clinical performance data for heart failure monitoring. The performance data mentioned (software V&V, electrical safety, biocompatibility, functional performance) appear to be part of engineering design verification and validation processes. No clinical test set size or data provenance (e.g., country of origin, retrospective/prospective) for clinical effectiveness in heart failure monitoring is provided.

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

Not applicable as a clinical test set with externally established ground truth for heart failure monitoring is not described in the provided text.

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

Not applicable.

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

Not applicable. The SOZO Body Fluid Analyzer is described as a non-invasive monitoring device for fluid management, not an AI-assisted diagnostic imaging tool that would typically involve human readers.

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

The device is a "Body Fluid Analyzer" that provides data "under the direction of a physician" and "in conjunction with other clinical data." This indicates it's a device intended for clinical use with human interpretation, not a standalone AI algorithm for diagnosis. The phrase "algorithm only" performance would not be directly applicable in the way it is for an AI-driven image analysis tool, for example.

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

For the engineering and software validation, the 'ground truth' would be the design requirements and specifications themselves. For clinical performance related to its indication (monitoring fluid management in heart failure), the text does not specify how clinical ground truth was established, as it primarily relies on substantial equivalence to a predicate device rather than a new clinical trial.

8. The sample size for the training set

Not applicable. The document does not describe a machine learning model that would require a "training set" in the context of its primary claim, but rather a bioimpedance-based measurement device.

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

Not applicable.

Ask a specific question about this device

Monitoring of the following parameters and their relative changes, indicative of relative changes in fluid volume in adult patients.

• Bioelectrical Impedance
• Heart Rate
• ECG Amplitude
• PPG Amplitude

Cardiac Monitor, Model 1500 and accessories monitor a patient's parameters. These parameters include: Bioelectrical Impedance, Heart Rate, ECG Amplitude, and Skin Temperature.

The Cardiac Monitor, Model 1500, is intended to be used in a professional medical environment such as hospitals, clinics and research institutions. The Cardiac Monitor, Model 1500, is a standalone device intended for desktop use. Measurements are to be performed under uninterrupted patient surveillance by the operator.

The user of the Cardiac Monitor, Model 1500, shall be a qualified operator. The operator shall have knowledge of the system and data interpretation, obtained via medical education, system manuals and/or specific courses. The device does not report any diagnosis but provides numerical values. It is the physician's responsibility to make proper judgments based on these numbers.

The provided text is related to a 510(k) submission for the Zynex Medical Cardiac Monitor, Model 1500. However, it does not contain specific acceptance criteria, reported device performance data, details of clinical studies, sample sizes for test or training sets, ground truth establishment, expert qualifications, or adjudication methods that would be required to fully answer the request.

The document primarily focuses on regulatory compliance, outlining the device's indications for use, its comparison to predicate devices, and adherence to general medical device safety standards. It emphasizes that the device provides numerical values and that a physician is responsible for making judgments based on these numbers, explicitly stating: "The device does not report any diagnosis, but provides numerical values. It is the physician's responsibility to make proper judgments based on these numbers." This indicates that the device itself is not making diagnostic claims that would typically require validation against a clinical ground truth for diagnostic accuracy.

Therefore, many of the requested items cannot be extracted from this document because the information is not present. The device is not an AI/ML device that would typically undergo the kind of detailed performance studies described in the prompt (e.g., MRMC studies, standalone algorithm performance against a clinical ground truth). Instead, it's a monitoring device whose performance is assessed against established safety and electrical standards.

Here's a breakdown of what can be inferred or explicitly stated based on the provided text, and what cannot be answered:

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

• Acceptance Criteria: Not explicitly stated as pass/fail thresholds for specific performance metrics in a clinical study. The document focuses on compliance with general medical device standards.
• Reported Device Performance: No specific numerical performance metrics (e.g., accuracy, sensitivity, specificity, or error rates) are reported for the Cardiac Monitor, Model 1500. The document states that the device "met all applicable requirements" of the listed standards and is "substantially equivalent" to its predicates.

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

• Not Applicable / Not Provided: The document does not describe a clinical performance study with a "test set" in the context of an AI/ML device validating diagnostic accuracy. The evaluation appears to be based on adherence to safety standards and comparison to predicate devices' design and methodology.

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 Applicable / Not Provided: There is no mention of experts establishing ground truth for a test set, as the device is for monitoring and not making diagnostic claims itself.

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

• Not Applicable / Not Provided: No adjudication method is mentioned because no clinical test set for diagnostic claims is described.

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: No MRMC study was done, as this is a physiological monitoring device, not an AI-assisted diagnostic tool for human readers.

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

• Not Applicable: This is a hardware monitoring device, not an algorithm. Its "performance" is based on the accuracy and reliability of its physiological measurements, which are then interpreted by a qualified operator/physician. The document notes that "Operation is to be performed as uninterrupted patient surveillance by the operator" and "The device does not report any diagnosis, but provides numerical values. It is the physician's responsibility to make proper judgments based on these numbers."

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

• Not Applicable / Not Provided: Ground truth in the context of diagnostic accuracy is not relevant here. The device's "ground truth" would be the actual physiological parameters measured, validated through calibration and comparison to established measurement techniques, but specific details are not in this document.

8. The sample size for the training set

• Not Applicable / Not Provided: This device is not an AI/ML algorithm that requires a "training set."

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

• Not Applicable / Not Provided: Not an AI/ML device requiring a training set.

Ask a specific question about this device

The ReDS System is intended for use by qualified healthcare practitioners, under the direction of a physician, in hospitals, hospital-type facilities and home environments, for the non-invasive monitoring and management of patients with fluid management problems in a variety of medically accepted clinical applications. The ReDS System is indicated for patients:

• With fluid management problems
• Taking diuretic medication
• Living with heart failure
• Recovering from a coronary artery disease-related event

The ReDS System ("ReDS" or "ReDS System") is a non-invasive thoracic base wave impedance monitor that provides measurement of patient lung fluid content. ReDS™ technology measures wave impedance of biological tissues. Low power electromagnetic (EM) signals are emitted into the body, and intercepted by sensors on the body. The wave impedance is a function of the distributed tissue conductivity and capacitance properties, and is representative of tissue fluid content.

The system consists of a Sensor Unit connected to a bedside console, as well as a cloud application. The Sensor Unit encases two sensors and an attachment mechanism. The Bedside Console is an enclosure housing the electronic modules, an embedded computer and a touch-screen display. The device software provides the management of the device as well as analysis of the measured signals, graphic display of readings, reporting, and communications functionality to enable remote patient monitoring.

The provided document is a 510(k) summary for the ReDS System V2.7, seeking substantial equivalence to a predicate device, the ReDS Wearable System V2.6. As such, the study described focuses on demonstrating that the new device (V2.7) performs equivalently to the existing cleared device (V2.6), rather than establishing de novo performance criteria against a specific medical condition's ground truth.

Therefore, the acceptance criteria and study design are framed around equivalence to a predicate device, not necessarily absolute clinical accuracy or performance based on an independent ground truth outside of this comparison.

Here's an analysis of the document to address your request:

Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by demonstrating "substantial equivalence" to the predicate device (ReDS V2.6). The performance reported is in terms of this equivalence, rather than specific numerical thresholds for diagnostic accuracy against a disease state.

Study Details:

The document describes a comparison study to demonstrate substantial equivalence, rather than a de novo clinical trial establishing absolute accuracy against a gold standard for a specific disease or outcome.

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

   • Test Set (Clinical Data): The document states "Clinical data was provided to further assess the ReDS System V2.7 equivalency to ReDS System V2.6." However, it does not specify the sample size for this clinical test set.
   • Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective for the clinical testing.

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

   • Given that this is an equivalence study between two versions of the same device, and not a study validating the device's accuracy against a specific physiological ground truth (e.g., direct measurement of lung fluid volume), the concept of "experts establishing ground truth for the test set" in the traditional sense (e.g., radiologists annotating images) is not directly applicable here.
   • The "ground truth" for this study is essentially the performance of the predicate device (ReDS V2.6). The clinical study aimed to show that V2.7's performance was equivalent to V2.6's.

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

   • Not applicable in the context of this equivalence study. There is no mention of independent reviewers or an adjudication process for clinical "ground truth" labels, as the study's goal was to compare the two device versions.

4. 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 comparative effectiveness study was not conducted or described. The ReDS System measures lung fluid content; it is not described as an AI-assisted diagnostic imaging tool where human readers "improve with AI assistance." The device is a direct measurement system.

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

   • The ReDS System itself is a standalone device that measures lung fluid content algorithmically. It's described as a "non-invasive thoracic base wave impedance monitor that provides measurement of patient lung fluid content." The "clinical data" section (Page 5) effectively serves as a standalone performance assessment in comparison to the predicate device. The performance of the algorithm within V2.7 was assessed as part of the overall device performance against V2.6.

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

   • For the clinical study's "ground truth," the performance of the predicate device (ReDS V2.6) was implicitly used as the reference point for comparison. The study aimed to show that the new device (V2.7) did not significantly differ in its measurements or clinical utility from the established V2.6.
   • The document does not detail a separate, independent "gold standard" for fluid assessment (e.g., invasive measurements, specific clinical outcomes data) against which both devices were tested. The core claim is equivalence to the predicate.

7. The sample size for the training set:

   • Not applicable / Not explicitly stated. This document describes the validation of a medical device hardware and software system, not the training of a machine learning model. While an internal algorithm exists (which was updated with a "stricter signal quality assessment mechanism" in V2.7), the summary does not suggest a discrete "training set" in the common machine learning sense. The development of the algorithm would have involved internal data sets, but these are not reported as a "training set" in the context of this 510(k) summary.

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

   • Not applicable. As above, the summary does not detail a machine learning training process or corresponding ground truth establishment.

Ask a specific question about this device

The Cardiovascular Analyzer is intended to obtain Pulse Wave Velocity (PWV) and Pulse Rate (PR) through a combination of impedance plethysmography and weight measurements in adults 18 years of age and older. The Cardiovascular Analyzer also measures Body Weight and calculates BMI.

The Cardiovascular Analyzer is designed to perform non-invasive physiologic measurements for PWV, PR, and BW, and to calculate BMI. The Cardiovascular Analyzer uses strain gauge sensors to measure BW and the ballistocardiogram (BCG). The BCG provides an indication of the arterial pulsation in the aortic arch. The Cardiovascular Analyzer also uses impedance plethysmography (IPG) sensing to estimate the PR and arterial pulsation in the legs. PWV is then calculated using the subject's sternal height (measured with a height rod) and the Pulse Transit Time (PTT) derived from the BCG and IPG signals.

The Cardiovascular Analyzer is comprised of the following key components and accessories: Scale Platform, Console, USB Cable, Isolated Power Supply and Power Cord, Height Rod, Visual Guide Accessory and Console Wall Mount.

The device uses two sensing modalities (load cells and impedance electrodes) to perform the following three measurements: PWV, PR and BW. BMI is calculated using BW and the operator-entered subject's overall height measurement.

The provided text details the 510(k) premarket notification for the PhysioWave Cardiovascular Analyzer. However, it does not explicitly provide a table of acceptance criteria and the reported device performance. It states that "The comparison tests demonstrated very high correlation of all measured and calculated parameters between the new device and the comparison devices and satisfactorily passed the acceptance criteria." but does not list these criteria or the specific results.

Therefore, the following response will extract the available information and highlight what is not explicitly stated in the document.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly provide a table of acceptance criteria with corresponding device performance values. It generally states that the device "satisfactorily passed the acceptance criteria" for comparison tests against predicate and reference devices.

However, the primary parameters measured by the Cardiovascular Analyzer are:

• Pulse Wave Velocity (PWV)
• Pulse Rate (PR)
• Body Weight (BW)
• Body Mass Index (BMI) (calculated)

The study indicated "very high correlation of all measured and calculated parameters between the new device and the comparison devices."

2. Sample Size Used for the Test Set and Data Provenance

The document does not specify the sample size used for the clinical performance testing or side-by-side equivalence testing. It also does not explicitly state the country of origin of the data or whether the study was retrospective or prospective.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

The document does not provide information on the number of experts used to establish ground truth or their qualifications.

4. Adjudication Method for the Test Set

The document does not describe any adjudication method used for the test set.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study. The focus is on the device's performance compared to predicate devices and a "gold standard" ECG monitor and patient scale.

6. Standalone (Algorithm Only) Performance

The testing included "side-by-side equivalence testing was performed for the BW, BMI, PR and PWV functions of the CA device against the comparison devices." This suggests a standalone evaluation of the device's measurements. The device has "automated algorithms to determine PTT based on the proximal and distal pulse measurements, to compute PWV, and also compute PR based upon the periodicity of the distal pulse." The software verification and validation section also indicates testing of the software's predetermined specifications.

7. Type of Ground Truth Used

The ground truth for the comparison tests was established by:

• Primary Predicate Device: AtCor Medical SphygmoCor® XCEL (K122129) for PWV and PR.
• Secondary Predicate Device / Gold Standard: Detecto Solo® scale (510(k)-exempt) for BW and BMI.
• Gold Standard: FDA-cleared ECG monitor for PR (implied for accuracy comparison, though not explicitly stated as "ground truth" for the CA in the same way as the predicates for specific parameters).

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set.

9. How the Ground Truth for the Training Set Was Established

The document does not provide information on how ground truth was established for a training set. The device was likely developed using established algorithms and physical principles (ballistocardiogram and impedance plethysmography), and then validated against existing cleared devices and gold standards.

Ask a specific question about this device

The SOZO Fluid Status Monitor is intended for adult patients living with heart failure.

This device is intended for use, under the direction of a physician, for the noninvasive monitoring of patients with fluid management problems suffering from heart failure. Data from the device should be considered in conjunction with other clinical data.

The SOZO™ system consists of a connected hand and footplate with built-in stainless steel electrodes, paired with an Android tablet over Bluetooth connection. An app ("SOZOapp"), supplied with the tablet, controls the functionality of the hardware and supplies the bioimpedance measurement data to a database ("SOZOhub") contained within the hospital/facility network.

Measurements require the patient to make contact with bare hands and feet on stainless steel electrodes. The measurement takes about 30 seconds, during which the SOZO™ system measures small quantities of electrical energy (200uA RMS) across 256 frequencies, spaced logarithmically from 3kHz to 1000kHz. Established algorithms are used to analyze data and calculate extracellular fluid impedance levels for left and right sides of the body, and present the impedance levels for the clinician to review. These scores facilitate the clinician's monitoring and management of patients with fluid management problems in a variety of medically accepted clinical applications.

The provided text is a 510(k) Summary for the ImpediMed SOZO™ system. While it details the device's technical characteristics, intended use, and various validations (electrical safety, software V&V, biocompatibility, functional performance), it does not contain a specific performance study with acceptance criteria and reported device performance for its primary intended use of monitoring fluid status in heart failure patients.

The document focuses on demonstrating substantial equivalence to a predicate device (ImpediMed Limited's IMED-Z, K142503) by highlighting similar technological characteristics and showing that minor differences do not raise new safety or effectiveness issues.

Here's a breakdown of what is and isn't available based on the provided text:

1. Table of acceptance criteria and the reported device performance:

The document mentions "Comparative performance" but this is for demonstrating correlation between the new SOZO system and the predicate IMED-Z system using a "test fixture" (not human subjects).

Missing Information (Crucial for its Primary Indication):

The document does not provide acceptance criteria or performance data for the SOZO system's ability to accurately monitor fluid status in heart failure patients in a clinical setting. It states the purpose of the 510(k) is to clear design changes and indications, and relies on the "substantial equivalence" framework without presenting new clinical performance data for its intended use.

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

• Test set for fluid status monitoring: Not applicable, as no human subject clinical performance study is described for its intended use.
• Comparative performance (test fixture): The "test fixture" represents "multiple fixed impedance loads," but the exact number of these simulated 'humans' or specific impedance loads is not stated. This is an engineering verification, not a clinical test.

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

Not applicable, as no human subject clinical performance study is described. The "ground truth" for the comparative performance was the output of the predicate/reference device on a test fixture.

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

Not applicable, as no human subject clinical performance study is described.

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:

Not applicable. The SOZO device is a bioimpedance measurement system that directly provides impedance levels, not an AI-assisted diagnostic tool interpreted by human readers in the sense of an MRMC study.

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

The device itself is a standalone measurement device. The "Comparative performance" section is the closest to a standalone evaluation, comparing the SOZO's output to another device's output on a test fixture. This is an algorithm-only comparison, but not against a clinical "ground truth" for fluid status monitoring.

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

For the comparative performance: The "ground truth" was the measurements from the predicate/reference device (IMED-Z/ZOE) on a test fixture. This is a technical (device vs. device) comparison, not a clinical ground truth (e.g., fluid volume measured by another gold standard method, or clinical outcomes).

8. The sample size for the training set:

Not applicable. This device is described as using "Established algorithms" to analyze data and calculate impedance levels. It's not a machine learning model that would typically have a "training set" in the context of supervised learning for classification or prediction. The algorithms are based on bioimpedance principles rather than trained on a large dataset of patient outcomes.

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

Not applicable, as there is no mention of a training set for machine learning. The algorithms are described as "established" for bioimpedance analysis.

Ask a specific question about this device