Search Results

The RespArray™ patient monitor is intended to be used for monitoring, storing, reviewing of, and to generate alarms for, multiple physiological parameters of adults, pediatrics and neonates. The monitors are intended for use by trained healthcare professionals in hospital environments. The monitor is for prescription use only.

The monitored physiological parameters include: ECG, respiration (RESP), temperature (TEMP), oxygen saturation of arterial blood (SpO2), pulse rate (PR), non-invasive blood pressure (NIBP), and carbon dioxide (CO2).

The arrhythmia detection and ST Segment analysis are intended for adult patients.

The SpO2 (Nellcor™) module is intended to be used for spot-check or continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR), in motion and no motion conditions, and in patients who are well or poorly perfused.

The Microstream™ capnography module is intended for continuous non-invasive monitoring of carbon dioxide concentration of the expired and inspired breath (etCO2) and respiration rate (RR). The monitor also provides the clinician with integrated pulmonary index (IPI), apnea per hour (A/hr) and oxygen desaturation index (ODI) values. IPI is not intended for patients up to the age of one year. A/hr and ODI are intended for ages 22 and up.

The monitors are not intended for MRI environments.

The RespArray patient monitor (hereinafter called RespArray) can perform long-time continuous monitoring of multiple physiological parameters. Also, it is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormity so that doctors and nurses can deal with them in time.

The provided text is a 510(k) summary for the Edan Instruments Patient Monitor (RespArray). It focuses on establishing substantial equivalence to a predicate device, primarily through non-clinical performance and software verification/validation.

Crucially, the document explicitly states: "Clinical data: Not applicable." This means there was no clinical study conducted to prove the device meets specific acceptance criteria in a human-use setting, particularly relating to diagnostic accuracy where AI assistance or expert consensus would be relevant.

Therefore, many of the requested items, such as multi-reader multi-case studies, ground truth establishment for a test set, and sample sizes for clinical test sets, are not applicable to this submission as per the document's contents.

Here's a breakdown based on the provided text:

Acceptance Criteria and Reported Device Performance

The acceptance criteria discussed are primarily related to electrical safety, electromagnetic compatibility (EMC), and general performance of the physiological parameter measurements (ECG, RESP, NIBP, TEMP, SpO2, CO2). The document states that the device was found to comply with relevant standards and that bench testing shows it meets its accuracy specification and relevant consensus standards.

Table of Acceptance Criteria and Reported Device Performance (as inferred from the text):

Study Proving Device Meets Acceptance Criteria:

The study proving the device meets the acceptance criteria is described as "Non-clinical data" including:

• Electrical safety and electromagnetic compatibility (EMC) assessments.
• Performance testing-Bench
• Software Verification and Validation Testing.

Detailed Information on the Study:

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

   • Sample Size: Not explicitly quantified in terms of number of patients or physiological measurements. The testing was "bench" testing, meaning laboratory-based tests on the device's functionality and accuracy against reference standards, rather than patient-derived data.
   • Data Provenance: Not applicable in the context of clinical data. For testing against standards, it implies standardized test setups and simulated physiological signals/conditions.

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

   • Not applicable. No experts were used for ground truth establishment as it was non-clinical bench testing against established engineering and medical device performance standards. There's no "ground truth" of a diagnostic nature being established by human experts in this context.

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

   • Not applicable. Adjudication is relevant for human-interpreted diagnostic data. This study relies on objective measurements against engineering specifications and international standards.

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, not applicable. The device is a patient monitor, not an AI-assisted diagnostic tool that interprets medical images/signals for improved human reader performance. The submission explicitly states "Clinical data: Not applicable."

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

   • Yes, in essence. The "Performance testing-Bench" and "Software Verification and Validation Testing" evaluate the device's inherent algorithms and functionality in a standalone manner (without a human in the loop for diagnostic interpretation, but rather for operational functionality and accuracy of physiological measurements). However, this is not in the context of a diagnostic AI algorithm.

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

   • Reference standards and engineering specifications. The "ground truth" for the non-clinical tests is derived from established international and national standards for medical electrical equipment, specific performance criteria for various physiological measurement modules, and the device's own accuracy specifications validated through bench testing.

7. The sample size for the training set:

   • Not applicable for a clinical training set. This is not an AI/ML device in the sense of learning from a large dataset of patient cases. The device's algorithms are designed and verified, not "trained" on patient data in a machine learning sense.

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

   • Not applicable. As above, no clinical training set or associated ground truth establishment process is described or relevant for this type of device submission.

In summary, the provided 510(k) focuses on demonstrating substantial equivalence through adherence to recognized performance and safety standards via non-clinical bench testing and software validation, rather than clinical studies involving human patients or complex AI diagnostic algorithms requiring expert review and adjudication.

Ask a specific question about this device

PA&PR series:
The PA&PR series are a neuromuscular electrical stimulator indical supervision for adjunctive therapy in the treatment of medical diseases and conditions.
As a powered muscle stimulator, PA&PR series are indicated for the following conditions:

• · Relaxation of muscle spasms,
• · Prevention or retardation of disuse atrophy,
• · Increasing local blood circulation,
• · Immediate post-surgical stimulation of calf muscles to prevent venous thrombosis,
• · Maintaining or increasing range of motion,
• · Muscle re-education.
  Environments of Use: Clinics, hospital. Patient population: Adults
  S&Q series:
  The S&O series are a neuromuscular electrical stimulator indical supervision for adjunctive therapy in the treatment of medical diseases and conditions.
  As a powered muscle stimulator, S&Q series are indicated for the following conditions:
• · Relaxation of muscle spasms,
• · Prevention or retardation of disuse atrophy,
• · Increasing local blood circulation,
• · Immediate post-surgical stimulation of calf muscles to prevent venous thrombosis,
• · Maintaining or increasing range of motion,
• · Muscle re-education.
  As a transcutaneous electrical nerve stimulator for pain relief, S&Q series are indicated for the following conditions:
  · Symptomatic relief and management of chronic (long-term), intractable pain,
• · Adjunctive treatment in the management of post-surgical pain and post traumatic acute pain.
  Environments of Use: Clinics, hospital and home environments.
  Patient population: Adults

Subject device have four series, which are PA series, PR series, Q series and S series. These four series are all electrical stimulating devices.

This document is an FDA 510(k) clearance letter for the "Stimulation System" manufactured by Edan Instruments, Inc. It asserts substantial equivalence to a predicate device, STIWELL med4 (K080950).

The provided text does not contain acceptance criteria for an AI-powered device, nor does it describe a study proving such a device meets acceptance criteria.

Instead, this document is a regulatory submission for a medical device (neuromuscular and transcutaneous electrical nerve stimulators) that appears to be hardware-based, with "software/firmware/microprocessor control" mentioned generally, but not as the primary component being evaluated for AI performance. The document focuses heavily on bench testing (electrical safety, EMC, performance to standards) and comparison to a predicate device's physical and electrical specifications, not on AI performance metrics like accuracy, sensitivity, or specificity.

Therefore, I cannot fulfill your request for:

• A table of acceptance criteria and reported device performance for an AI device.
• Sample sizes, data provenance, ground truth establishment, or expert involvement related to AI performance.
• MRMC studies or standalone AI performance.

The document's "Performance Data" section explicitly states: "Clinical data: Not applicable." This further confirms that no clinical studies (which would be necessary to prove performance of an AI system in a clinical context) were conducted or presented for this submission.

In summary, the provided text does not describe an AI medical device or its performance criteria/study.

Ask a specific question about this device

The iX series Patient Monitors including iX10, iX12, iX15 are intended to be used for monitoring, storing, and reviewing of, and to generate alarms for, multiple physiological parameters of adults and pediatics (including neonates). The monitors are intended for use by trained healthcare professionals in hospital environments.

The monitored physiological parameters include: ECG, respiration (RESP), temperature (TEMP), functional oxygen saturation of arterial hemoglobin (SpO2), pulse rate (PR), non-invasive blood pressure (NIBP), invasive blood pressure (IBP), carbon dioxide (CO2), cardiac output (C.O.), and Anaesthesia gas (AG).

The arrhythmia detection and ST Segment analysis are intended for adult patients.

The NIBP monitoring supports iCUFS algorithm and iFAST algorithm is intended for adult, pediatric and neonatal patients. The iFAST algorithm is intended for adult and pediatic patients (≥3 years of age). Both measurement algorithms are also intended for use with pregnant women, including pre-eclamptic patients. NIBP MAP is not applicable to pregnant women.

The Spot Temp with T2A module can only measure temperature of adult and pediatric (> 1 year of age) patients. The monitors are not intended for MRI environments.

The cardiac output (C.O.) is only intended for adult patients.

The iX series Patient Monitors including iX10, iX12, iX15 can perform long-time continuous monitoring of multiple physiological parameters. Also, it is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormalities so that doctors and nurses can respond to the patient's situation as appropriate.

This document describes the premarket notification (510(k)) for the Edan Instruments, Inc. Patient Monitor (iX10, iX12, iX15) and its equivalence to a predicate device.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the new device were generally established by compliance with various international standards for medical electrical equipment and specific performance characteristics. The reported device performance indicates that the device meets these standards and its specified accuracy.

For the Quick Temp Module (T2A), the provided text details specific clinical study results. Other parameters were tested for compliance with relevant standards through non-clinical testing.

2. Sample Size for Test Set and Data Provenance

For the Quick Temp Module (T2A) Predict Mode clinical accuracy study:

• Sample Size: 142 valid cases for sublingual and axillary temperature measurements.
• Data Provenance: Clinical investigation (prospective study). No country of origin is explicitly stated, but the company is based in China.

For other parameters, specific sample sizes for non-clinical (bench) testing are not provided, but the document states "Edan has conducted functional and system level testing to validate the performance of the results of the bench testing show that the subject device meets its accuracy specification and meet relevant consensus standards."

3. Number of Experts and their Qualifications for Ground Truth

The document does not specify the number or qualifications of experts used to establish ground truth for the clinical study of the Quick Temp Module (T2A). It only mentions that the study compared the new module against the "direct mode of F3000 Temp Module of M3A Vital signs monitor," implying the predicate device served as a reference for accuracy.

For other non-clinical tests, the ground truth is implicitly defined by the specifications and performance requirements outlined in the referenced international standards.

4. Adjudication Method for the Test Set

The document does not describe a specific adjudication method (e.g., 2+1, 3+1) for the clinical study or any other test sets.

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

No multi-reader multi-case (MRMC) comparative effectiveness study is mentioned in the provided text. The device is a patient monitor, and its performance evaluation typically focuses on the accuracy and reliability of its physiological parameter measurements, not on improving human reader performance with AI assistance.

6. Standalone (Algorithm Only) Performance Study

Yes, standalone performance was evaluated for the components of the device. The non-clinical data section describes extensive functional and system-level testing to validate the performance against relevant consensus standards. This includes specific tests for algorithms like cardiac rhythm and ST segment measurement. The clinical study for the Quick Temp Module (T2A) also assesses the standalone performance of that specific module.

7. Type of Ground Truth Used

• For the Quick Temp Module (T2A) clinical study: The ground truth was established by comparison to a reference device's direct temperature measurement mode ("direct mode of F3000 Temp Module of M3A Vital signs monitor"). This is a form of reference standard comparison (using a predicate device as the reference).
• For other parameters (e.g., ECG, NIBP, SpO2, CO2, AG): The ground truth for non-clinical testing is implicitly based on the specifications and performance requirements outlined in the referenced international consensus standards (e.g., IEC 60601 series, ISO 80601 series, AAMI standards).

8. Sample Size for the Training Set

The document does not provide information about a training set since this is a patient monitoring device and not a machine learning algorithm as typically understood in the context of large-scale image-based diagnostics. The "algorithms" mentioned (e.g., arrhythmia detection, NIBP algorithms) are likely engineered signal processing algorithms rather than deep learning models requiring large training datasets.

9. How Ground Truth for Training Set was Established

Not applicable, as no training set for a machine learning model is described in the provided text. The algorithms for the patient monitor's functions are developed and validated against established physiological principles and engineering standards.

Ask a specific question about this device

The device is intended to be used for measuring, storing, and to generate prompts for, multiple physiological parameters of adults and pediatrics (including neonates). The device is intended for use by trained healthcare professionals in hospital environments. Parameters include: NIBP, SpO2, PR (pulse rate), TEMP. The F3000 Quick Temp module is not intended for neonates. The device is not intended for MRI environments.

The iM3s series vital signs monitors including iM3s\iM3As\iM3Bs\ iHM3s are intended to be used for measuring, storing, reviewing of, and generating prompts for multiple physiological parameters of adults and pediatrics.

The provided documentation describes the FDA 510(k) clearance for the Edan Instruments Vital Signs monitor, Model: iM3s, iM3As, iM3Bs, iHM3s. However, the document primarily focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance testing and software verification/validation, rather than detailing a clinical study with specific acceptance criteria for AI/algorithm performance.

Therefore, many of the requested details regarding acceptance criteria, sample size, expert involvement, and ground truth establishment for a study proving device performance in an AI/algorithm context are not applicable or not provided in this specific FDA clearance document. The device is a vital signs monitor, not explicitly described as incorporating AI for diagnosis or interpretation that would necessitate an MRMC study or detailed ground truth establishment in the context of AI performance.

The document states "Clinical data: Not applicable," further confirming the absence of a clinical study for this clearance.

Here's a breakdown based on the information available in the document:

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

The document refers to compliance with consensus standards for device performance, where the "acceptance criteria" are implied by adherence to these standards and the "reported device performance" is that the device "meets its accuracy specification and meet relevant consensus standards." Specific numerical acceptance criteria are mentioned for the measurement accuracy of SpO2, PR, and NIBP, and various temperature modules.

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

• The document explicitly states "Clinical data: Not applicable." The "test set" for performance was conducted through "Non-clinical data" including "Electrical safety and electromagnetic compatibility (EMC)" and "Performance testing-Bench."
• No specific sample sizes (e.g., number of patients/measurements) for "bench" testing are provided.
• Data provenance (e.g., country of origin, retrospective/prospective) is not applicable given no clinical study.

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 ground truth or expert-adjudicated test set was used. Device performance was assessed against established engineering and safety standards.

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

• Not applicable as no clinical test set requiring adjudication was used.

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 MRMC study was performed as this device is a vital signs monitor, not an AI-assisted diagnostic device requiring human reader improvement assessment. Clinical data was deemed "Not applicable."

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

• The performance assessment focused on the device's ability to accurately measure vital signs according to specifications and consensus standards (e.g., IEC 80601-2-30 for NIBP, ISO 80601-2-56 for temperature, ISO 80601-2-61 for pulse oximetry). This is essentially a "standalone" performance evaluation of the measurement algorithms within the device against physical standards, but not in the context of an AI-driven diagnostic algorithm.

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

• For the non-clinical performance testing, the "ground truth" would be the reference measurements from calibrated and traceable sources, as specified by the relevant international standards (e.g., simulated physiological signals/conditions, calibrated temperature sources, etc.).

8. The sample size for the training set:

• Not applicable. This document describes the clearance of a vital signs monitor, not an AI/machine learning algorithm requiring a separate training set.

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

• Not applicable, as no AI training set is described.

Ask a specific question about this device

MFM-CMS central monitoring system (hereinafter referred to as MFM-CMS) supports centralized management of patients' clinical data provided by EDAN medical devices. Clinicians can obtain patient clinical data via MFM-CMS. The indications for use of the MFM-CMS central monitoring system include:

• · Viewing patient real-time clinical data and alarms.
• · Storing and reviewing patient clinical data and alarms.
• · Printing real-time and history patient data.
• · Configuring local settings as well as synchronizing settings to a remote device through network.
• · Accessing patient clinical data between several departments.

MFM-CMS is intended to be used only in clinical or hospital environment by well-trained healthcare professionals.

MFM-CMS is indicated for use when monitoring adult and/or pediatric and/or neonate patients as indicated by labeling of the medical device providing the data.

MFM-CMS is a central monitoring system product, which can connect and manage information from EDAN medical devices. MFM-CMS offers central management for monitoring information from the medical devices. All these collected information can be displayed, printed, alarmed and recorded.

The provided text is a 510(k) summary for the Edan Instruments, Inc. MFM-CMS Central Monitoring System. It describes the device, its intended use, and a comparison to predicate devices, but does not contain information related to specific acceptance criteria, reported device performance in those criteria, sample sizes, expert qualifications, or ground truth establishment for a diagnostic AI device.

The submission is for a "Central Monitoring System" (MFM-CMS), which supports centralized management of patient clinical data from other EDAN medical devices. It is classified as an "Arrhythmia detector and alarm (including ST-segment measurement and alarm)" with product code MHX. However, the summary focuses on the system's ability to display, store, review, and print data, and manage settings, rather than its performance as an arrhythmia detector itself.

Therefore, many of the requested details cannot be extracted from this document, as they are typically found in the clinical validation studies of algorithms that perform diagnostic or interpretative tasks.

Here's an analysis based on the information available in the document:

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

This information is not provided in the document. The submission focuses on functional changes and comparison to predicates, not specific performance metrics like sensitivity, specificity, or accuracy for an arrhythmia detection algorithm. The "Performance" section within the comparison table refers to features like "Bi-directional Configuration" and "Data Review," not numerical performance criteria.

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

This information is not provided. The document states "Clinical testing: Not applicable. Clinical testing is not required to establish substantial equivalence to the predicate device." This indicates that no clinical test set was used to validate the device's performance in a diagnostic capacity.

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)

This information is not provided, as no clinical test set for diagnostic accuracy was utilized.

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

This information is not provided, as no clinical test set for diagnostic accuracy was utilized.

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

There is no indication that an MRMC study was done. The device is a "Central Monitoring System" and is not described as an AI-powered diagnostic tool that assists human readers.

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

This information is not provided, as the document does not describe the MFM-CMS as a standalone diagnostic algorithm. Its primary function is a central data management system. Although it is classified under "Arrhythmia detector and alarm," the detailed description of its updates and comparison to predicates emphasizes data handling and system functionality rather than algorithm performance for arrhythmia detection.

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

This information is not provided, as no clinical validation study is described.

8. The sample size for the training set

This information is not provided. As the submission focuses on software updates and functional equivalence, details about training sets for an AI algorithm are not relevant or discussed.

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

This information is not provided, as no clinical validation study or AI training is described.

Summary of what is available in the document:

The document describes the MFM-CMS as a central monitoring system that connects to other EDAN medical devices to manage patient clinical data. The submission is for an updated version (K232694) of an existing device (K120727), with the primary predicate being the BeneVision Central Monitoring System (K220058).

Key changes and comparisons:

The main changes to the software include:

• Add distributed function.
• Add license authorization.
• Support department management, device management, and user management.
• Support time synchronization function.
• Support data automatic dump function.
• Replace the software development platform.
• Supports simultaneous login of multiple clients.
• Support domain account to log in to the CMS client.

The comparison table highlights similarities and differences in intended use, operating system support, data review features, calculations, telemetry support, print capabilities, and network connectivity between the subject device and its predicate.

Performance Data (as per the document):
The document states:

• Non-clinical test: Biocompatibility testing and Electrical safety & electromagnetic compatibility (EMC) are "Not applicable."
• Software Verification and Validation Testing: Conducted in accordance with FDA guidance for software in medical devices.
• Bench Testing: Functional and system-level testing was conducted to validate performance, and results "show that the subject device meets relevant consensus standards" (e.g., IEC 60601-1-8:2006 + Am1:2012 for alarm systems).
• Clinical testing: "Not applicable. Clinical testing is not required to establish substantial equivalence to the predicate device."

Conclusion: The submission concludes that "The bench testing data and software verification and validation demonstrate that MFM-CMS Central Monitoring System is substantially equivalent to the predicate devices."

In essence, this FDA 510(k) summary focuses on demonstrating that the updated MFM-CMS system maintains the safety and effectiveness of its predicate devices through non-clinical testing and software verification, rather than providing a detailed performance study of a diagnostic algorithm against specific clinical acceptance criteria.

Ask a specific question about this device

The SA-20 Series recorder combines ambulatory ECG Holter and BP monitor. It is intended to acquire, store and display ambulatory ECG signals from adult and pediatric patient. It is capable of measuring systolic and diastolic blood pressures of adults and pediatrics (> 12 years) over a preprogrammed period of time. These measurements are displayed and stored in the recorder. It is intended to be used by trained personnel under the direction of doctors.

Holter ECG and ABP System (Model: SA-20, SA-19, SA-18, SA-15, SA-16) is composed of the recorder, NIBP cuff, lead wire. The ambulatory blood pressure adopts the principle of the oscillometric method for non-invasive blood pressure measurement. ECG signals are obtained by placing electrodes on the patient's surface to record the potential change signal of the human heart and then processing the data to form an ECG waveform and store it in the Recorder to monitor the ECG signal.

The provided text describes the Holter ECG and ABP System and its performance data to establish substantial equivalence to predicate devices. However, the document does not contain an acceptance criteria table or specific details of a study directly proving the device meets acceptance criteria in the format often associated with AI/ML algorithm validation (e.g., sensitivity, specificity, AUC).

Instead, the document focuses on non-clinical performance testing to demonstrate the device's adherence to relevant industry standards and functional specifications, ensuring its safety and effectiveness are comparable to the predicate devices.

Here's a breakdown of the information that can be extracted or inferred based on common medical device submission practices, acknowledging that explicit details on some points are missing:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present a formal "acceptance criteria" table in terms of diagnostic performance metrics (e.g., sensitivity, specificity for disease detection). Instead, the performance evaluations are based on compliance with established medical device standards. The "reported device performance" is the successful compliance with these standards.

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

The document states, "Clinical data: Not applicable," implying that the assessment for this 510(k) submission did not involve a clinical trial or a test set derived from patient data in the typical sense of evaluating diagnostic accuracy. The testing was primarily bench-based and software verification. Therefore, there's no "sample size for a test set" or "data provenance" related to patient data for diagnostic performance evaluation.

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 for diagnostic performance was used. The "ground truth" for the non-clinical testing was defined by the specifications and requirements of the referenced industry standards.

4. Adjudication method for the test set

Not applicable, as no clinical test set for diagnostic performance was used.

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 device is a Holter ECG and ABP system (hardware for acquisition, storage, and display of physiological signals), not an AI/ML diagnostic algorithm designed to assist human readers or perform automated interpretations beyond basic parameter measurements.

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

Not applicable. This is not an AI/ML algorithm in the context of diagnostic interpretation. It is a device for signal acquisition and measurement. The "algorithm" for NIBP (oscillometric method) and ECG signal processing is inherent to the device's function, but it's not described as a standalone diagnostic algorithm requiring performance evaluation against a specific ground truth like an AI model would be.

7. The type of ground truth used

For the performance testing, the "ground truth" was the specifications and requirements defined by the referenced international and national consensus standards (e.g., IEC 60601 series, ANSI AAMI standards). The device's measurements (ECG signals, blood pressure) are verified against the expected outputs and accuracy tolerances dictated by these standards.

8. The sample size for the training set

Not applicable. This is not an AI/ML algorithm that requires a training set of patient data.

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

Not applicable. This is not an AI/ML algorithm that requires a training set.

Summary of the Study that Proves the Device Meets Acceptance Criteria (based on the document):

The "study" proving the device meets its "acceptance criteria" is a series of non-clinical performance tests and software verification and validation activities designed to demonstrate compliance with recognized medical device standards.

1. Electrical Safety and EMC Testing: The device was tested against ANSI AAMI ES 60601-1 and IEC 60601-1-2 to ensure it is electrically safe and does not cause or succumb to electromagnetic interference.
2. Performance Testing (Bench): Functional and system-level bench testing was conducted to validate the device's performance against the accuracy specifications and requirements outlined in:
   • IEC 60601-2-47: For ambulatory electrocardiographic systems (ECG Holter functionality).
   • IEC 80601-2-30: For automated non-invasive sphygmomanometers (ABP functionality).
   • ANSI AAMI EC53: For ECG trunk cables and patient leadwires.
   • IEC 60601-1-11: For devices used in the home healthcare environment.
     These tests would involve simulating physiological signals or using calibrated equipment to ensure the device accurately acquires, processes, and displays ECG and ABP data within acceptable error margins defined by these standards.
3. Software Verification and Validation: This involved rigorous testing of the device's embedded software to ensure it functions as intended, is free from critical bugs, and meets specified requirements, following FDA guidance for software in medical devices.

The conclusion drawn from these "non-clinical data" is that the "subject devices are as safe and as effective as the predicate device," thus establishing substantial equivalence for market clearance.

Ask a specific question about this device

The SE-1200 Pro&SE-1201 Pro 12-lead electrocardiographs are intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The electrocardiographs are only intended to be used in hospitals or healthcare facilities by doctors and trained healthcare professionals. The cardiogram recorded by the electrocardiograph can help users to analyze and diagnose heart disease. However, the interpreted ECG with measurements and interpretive statements is offered to clinicians on an advisory basis only.

SE-1201 Pro&SE-1200 Pro (2 models: SE-1201 Pro and SE-1200 Pro) features a LCD touch screen, an operation panel, user-programmable reports, and the ability to operate on either battery or AC power. It is capable of simultaneous acquisition, display, and print of 12-lead ECG. It uses algorithm to generate measurements, data presentations, graphical presentations and interpretative statements. The record can be saved in flash memory or send to PC.

The provided document is a 510(k) premarket notification for Electrocardiograph models SE-1200 Pro and SE-1201 Pro. It aims to demonstrate substantial equivalence to previously cleared predicate devices.

However, the document makes a clear statement regarding clinical data: "Clinical data: Not applicable." This indicates that no clinical study was conducted to prove the device meets specific acceptance criteria based on human performance or diagnostic accuracy. Instead, the submission relies on non-clinical data, including electrical safety, electromagnetic compatibility (EMC), and performance testing (bench).

Therefore, I cannot provide the information requested in your prompt regarding acceptance criteria, study details, expert involvement, or MRMC studies, as the submission explicitly states that clinical data was not applicable.

The device's performance demonstration relies on:

1. Electrical safety and electromagnetic compatibility (EMC): Conformity to standards like ANSI AAMI ES 606601-1:2005/(R) 2012, IEC 60601-1-2:2014, and IEC 60601-2-25 Edition 2.0 2011-10.
2. Performance testing (bench): Functional and system-level testing to validate accuracy specifications and compliance with relevant consensus standards (e.g., IEC 60601-2-25).
3. Software Verification and Validation Testing: Documentation provided as recommended by FDA guidance for software in medical devices.

The conclusion states that "The bench testing data and software verification and validation demonstrate that Electrocardiograph SE-1201 Pro&SE-1200 Pro is substantially equivalent to the predicate devices." This substantial equivalence is based on the technical and non-clinical performance characteristics, not on a clinical effectiveness study involving human subjects or interpretation.

Ask a specific question about this device

The RespArray™ patient monitor is intended to be used for monitoring, storing, of, and to generate alarms for, multiple physiological parameters of adults, pediatrics and neonates. The monitors are intended for use by trained healthcare professionals in hospital environments.
The monitor is for prescription use only.
The monitored physiological parameters include: ECG, respiration (RESP), temperature (TEMP), oxygen saturation of arterial blood (SpO2), pulse rate (PR), non-invasive blood pressure (NIBP), and carbon dioxide (CO2).
The arrhythmia detection and ST Segment analysis are intended for adult patients.
The SpO2 (NellcorTM) module is intended to be used for spot-check or continuous non-invasive monitoring of functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR), in motion conditions, and in patients who are well or poorly perfused.
The MicrostreamTM capnography module is intended for continuous non-invasive monitoring of carbon dioxide concentration of the expired and inspired breath (etCO2) and respiration rate (RR).
The monitor also provides the clinician with integrated pulmonary index (IPI), apnea per hour (A/hr) and oxygen desaturation index (ODI) values. IPI is not intended for patients up to the age of one year. Allr and ODI are intended for ages 22 and up.
The monitors are not intended for MRI environments.

The RespArray patient monitor (hereinafter called RespArray) can perform long-time continuous monitoring of multiple physiological parameters. Also, it is capable of storing, displaying, analyzing and controlling measurements, and it will indicate alarms in case of abnormity so that doctors and nurses can deal with them in time.

The provided text is a 510(k) Premarket Notification summary for the "Patient Monitor: RespArray" device. This type of submission focuses on demonstrating substantial equivalence to legally marketed predicate devices, rather than conducting new clinical trials for de novo clearance or PMA approval. Therefore, the details requested about acceptance criteria, specific study design (like MRMC studies, sample sizes, expert ground truth establishment for AI/algorithm performance), and training set information are not typically found in these types of submissions, as the FDA review here centers on comparing the new device's specifications and performance to an existing, already cleared device.

The document primarily highlights the device's technical specifications and how they compare to a predicate device (Edan Instruments, Inc, Patient Monitor Model X8, X10, X12 - K192514), along with compliance with relevant electrical safety, EMC, and performance standards. It explicitly states "Clinical data: Not applicable."

Given this, I will extract the information that is present in the document and indicate where the requested information is not applicable or not provided within the scope of a 510(k) submission focused on substantial equivalence.

Analysis of the Provided Document for Device Acceptance Criteria and Study Proof

The provided document is a 510(k) premarket notification. For devices cleared via a 510(k), the primary "acceptance criterion" is often substantial equivalence to a legally marketed predicate device, demonstrated through comparative testing and adherence to recognized standards. Direct, explicit "acceptance criteria" presented as quantitative performance targets with a detailed study to prove they are met (as might be seen in AI/ML clearances for algorithms with novel functionalities) are typically not included in this type of submission for a patient monitor.

The "study" that proves the device meets the acceptance criteria is primarily non-clinical performance testing (bench testing) and software verification/validation to show that the device performs as intended and is as safe and effective as its predicate.

Here's a breakdown of the requested information based on the provided document:

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

The document does not provide a table of explicit acceptance criteria/performance targets with quantitative results in the way one might expect for a new AI/ML algorithm. Instead, it demonstrates performance by stating compliance with recognized consensus standards and by comparing the subject device's specifications to those of its predicate device, showing "similar design features and performance specifications."

The closest representation of "performance" and "acceptance" is the "Predicate Device Comparison" table (pages 5-6). This table implicitly acts as the performance comparison against the predicate device that serves as the "acceptance" benchmark for substantial equivalence.

The document concludes that "the subject and predicate devices have similar design features and performance specifications. The technological differences between the subject and predicate devices do not raise different questions of safety or effectiveness."

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

The document states "Clinical data: Not applicable." Therefore, there isn't a "test set" in the sense of patient data used for clinical validation of, for example, an AI algorithm's performance. The "testing" primarily refers to non-clinical bench testing.

• Sample size: Not applicable for patient data test set. For bench testing, samples would be physical devices, components, or simulated signals, but a "sample size" in terms of patient numbers is not provided.
• Data provenance (e.g., country of origin of the data, retrospective or prospective): Not applicable, as no clinical data test set was used/provided.

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

Not applicable. Since no clinical data test set was described and "Clinical data: Not applicable" is stated, there was no need for expert ground truth establishment for a test set. This type of information would be relevant for AI/ML device clearances where human expert annotation is part of the ground truth creation.

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

Not applicable, as no clinical test set requiring adjudication of ground truth was 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. The document explicitly states "Clinical data: Not applicable." MRMC studies are typically for evaluating the impact of AI algorithms on human reader performance, which is not the scope of this 510(k) submission for a patient monitor.

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

The device is a patient monitor with various physiological parameter measurements and alarms. Its "performance" is inherent in its ability to accurately measure these parameters and detect events like arrhythmias. The non-clinical bench testing demonstrated its standalone performance by showing compliance with relevant standards (e.g., IEC 60601-2-27 for ECG, IEC 80601-2-30 for NIBP, ISO 80601-2-61 for pulse oximeter).

While not explicitly called "standalone algorithm performance" in the AI/ML sense, the "Performance testing-Bench" section (page 8) confirms that "Edan has conducted functional and system level testing to validate the performance of the results of the bench testing show that the subject device meets its accuracy specification and meet relevant consensus standards." This demonstrates the device's functional performance in isolation.

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

For the non-clinical bench testing, the "ground truth" would be established by:

• Reference instruments or calibrated signals (e.g., precise electrical signals for ECG, known pressure values for NIBP, calibrated gas mixtures for CO2).
• Standardized measurement protocols defined by the cited IEC/ISO standards.
• Accuracy specifications found within those standards or the device's own specifications.

There's no mention of expert consensus, pathology, or outcomes data as "ground truth" because this is a measurement and alarm device, not a diagnostic imaging AI algorithm, and no clinical data was used for validation in this submission.

8. The sample size for the training set

Not applicable. This device is a patient monitor, not an AI/ML algorithm that undergoes a distinct training phase on a dataset. The underlying algorithms for parameter measurement (e.g., NIBP oscillometric algorithm, arrhythmia detection) are established engineering designs, not typically "trained" in the machine learning sense with large datasets.

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

Not applicable, as there is no specific "training set" for an AI/ML algorithm described. The "ground truth" for the development and calibration of the monitor's measurement algorithms would have been established through engineering principles, laboratory testing with calibrated instruments, and referencing physiological models and data, but this is part of the device's fundamental design and not a separate "training set" as understood in current AI/ML contexts.

Ask a specific question about this device

The iSE series electrocardiograph is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The electrocardiograph is only intended to be used in hospitals or healthcare facilities by doctors and trained healthcare professionals. The cardiogram recorded by the electrocardiograph can help users to analyze and diagnose heart disease. However, the interpreted ECG with measurements and interpretive statements is offered to clinicians on an advisory basis only. The electrocardiograph is capable of network communications and supports the informatized management of workflows in hospital and healthcare facilities.

iSE-1210 and iSE-1810 Electrocardiograph can support ECG Data Sampling of maximum 12 leads and maximum 18 leads separately. iSE series electrocardiograph uses algorithm to generate measurements, data presentations, graphical presentations and interpretative statements. The electrocardiograph is only intended to be used in hospitals or healthcare facilities by doctors and trained healthcare professionals.

The provided text is a 510(k) Premarket Notification summary for the Edan Instruments, Inc. Electrocardiograph (iSE series). It focuses on establishing substantial equivalence to previously cleared devices.

Based on the provided document, here's a breakdown of the acceptance criteria and the study that proves the device meets them:

Key Takeaway: This 510(k) summary does not include a clinical study with real patient data to prove the device's diagnostic performance against a ground truth for conditions like heart disease. Instead, it relies heavily on non-clinical bench testing, electrical safety, EMC, human factors, and software verification/validation to demonstrate that the new device (iSE series) is as safe and effective as its predicate devices, primarily in its ability to acquire and process ECG signals according to established industry standards. The interpretation of ECGs with measurements and interpretive statements is explicitly stated as advisory only.

Therefore, the acceptance criteria and study described will pertain to the technical performance and safety of the ECG acquisition and processing rather than the diagnostic accuracy of an AI algorithm in interpreting ECGs for specific heart conditions.

Acceptance Criteria and Device Performance

The document does not present a formal table of acceptance criteria with corresponding performance results in the format requested for diagnostic performance. Instead, it states that the device meets "accuracy specification" and "relevant consensus standards" through non-clinical bench testing.

Based on the "Performance Specifications" table (Table 1) and the "Performance testing-Bench" section, we can infer some performance aspects that were likely tested against standards.

Inferred Acceptance Criteria and Reported Device Performance (based on technical specifications and implied testing):

Study Details (Based on the provided document)

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

   • Test Set Sample Size: Not specified for any performance testing beyond "Functional and system level testing" and "usability testing." No specific number of patient ECGs are mentioned for any diagnostic validation.
   • Data Provenance: The document does not specify the country of origin for any data (if patient data was used implicitly in some "accuracy specification" bench testing, which is unlikely given the context). The studies mentioned (Electrical safety, EMC, performance bench testing, human factors, software verification) are non-clinical bench and lab-based studies. There is no mention of prospective or retrospective patient data collection.

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

   • Not Applicable. For non-clinical bench testing, the "ground truth" is typically defined by engineering specifications, calibration standards, and validated test equipment rather than expert human interpretation of medical data.
   • The interpretative statement for the ECGs is offered "on an advisory basis only," indicating that the device's interpretation is not intended to replace a physician's diagnosis.

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

   • Not Applicable. The studies described are technical performance tests against standards, not human reader studies requiring adjudication of medical diagnoses.

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 study was not conducted or reported. The device's interpreted ECGs are advisory, and there's no claim of AI assistance for human readers in the diagnostic process. The "algorithm" mentioned (SEMIP V1.92) generates measurements, data presentations, graphical presentations, and interpretative statements, but its performance is not assessed in a comparative effectiveness study with human readers.

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

   • Partially Yes, for technical performance. The bench testing (e.g., meeting accuracy specifications, sampling frequency, frequency response) can be considered a standalone performance assessment of the device's ability to acquire and process ECG signals according to engineering and industry standards. However, this is distinct from a standalone diagnostic performance study typically seen for AI/CADe devices. The document explicitly states "Clinical data: Not applicable." This confirms that no standalone clinical diagnostic performance study was performed or needed for this 510(k) submission, as the device's interpretations are advisory.

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

   • Technical Specifications/Industry Standards. For the non-clinical tests, the "ground truth" for the device's performance is compliance with established electrical safety, EMC, and ECG technical performance standards (e.g., IEC 60601 series). There is no "ground truth" of patient diagnosis (e.g., pathology, outcomes, expert consensus on disease states) used as this device is broadly an ECG acquisition and processing device, with its interpretive statements being advisory.

7. The sample size for the training set:

   • Not applicable / Not specified. The document makes no mention of AI model training or a training set. The "algorithm" (SEMIP V1.92) is mentioned as generating interpretive statements, but its development process (e.g., use of a training set, machine learning) is not described or evaluated in this 510(k) summary. Given the nature of a foundational ECG device and the "advisory basis only" statement for interpretations, it's highly likely this algorithm is rule-based or statistical rather than a deep learning model requiring a large training set of annotated ECGs for diagnostic purposes.

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

   • Not applicable. As no training set is mentioned or evaluated in the provided document, the process for establishing its ground truth is not described.

Ask a specific question about this device

The SE-1202 12-lead electrocardiograph is intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The electrocardiograph is only intended to healthcare facilities by doctors and trained healthcare professionals. The cardiogram recorded by the electrocardiograph can help users to analyze and diagnose heart disease. However, the interpreted ECG with measurements is offered to clinicians on an advisory basis only.

CONTRAINDICATIONS:
SEMIP algorithm is not intended for interpretive statements of neonatal patients from birth to 28 days.

The SE-1202 electrocardiograph features a 10.1" LCD touch screen, an operation panel, user-programmable reports, and the ability to operate on either battery or AC power. It is capable of simultaneous acquisition, display, and print of 12-lead ECG. It uses algorithm to generate measurements, data presentations, graphical presentations and interpretative statements. The record can be saved in flash memory or send to PC.

The provided document is a 510(k) Premarket Notification from Edan Instruments, Inc. for their Electrocardiograph SE-1202. It establishes substantial equivalence to a predicate device (Edan Instruments, Inc, Electrocardiograph: SE-12, SE-12 Express, SE-1200, and SE-1200 Express, K171942).

The document does not contain details about a study addressing specific acceptance criteria for an AI/algorithm's performance as typically required for devices with interpretive or diagnostic AI functionalities. Instead, it focuses on the performance of the electrocardiograph hardware and its ability to meet general electrical safety, EMC, and basic functional standards (e.g., heart rate range, noise, filter specifications).

The device's software includes an algorithm (SEMIP or Glasgow) that generates measurements, data presentations, graphical presentations, and "interpretative statements." However, the document explicitly states that these interpretations are "offered to clinicians on an advisory basis only." Furthermore, it contraindicates the SEMIP algorithm for neonatal patients.

Given that the core of the request is about acceptance criteria and a study that proves the device meets specific acceptance criteria related to its performance, and the document explicitly states "Clinical data: Not applicable," it indicates there wasn't a clinical study designed to test the interpretive algorithm's performance against detailed criteria for accuracy, sensitivity, or specificity in a diagnostic context. The "Performance validation via EDAN proprietary database" is mentioned, but no specifics about this validation, its acceptance criteria, or its results are provided.

Therefore, many of the requested details cannot be extracted from this document, as it describes a device where the interpretive statements are advisory and clinical data showing performance of these interpretive features in a diagnostic capacity was not deemed necessary for this 510(k) clearance.

However, I will extract what is available and clearly state what information is not present.

Here's an analysis of the acceptance criteria and the study as described in the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on demonstrating equivalence to a predicate device through technical specifications and compliance with general medical device standards, rather than defining and meeting specific analytical or clinical performance acceptance criteria for an AI/algorithm's diagnostic accuracy. The "acceptance criteria" here are more about meeting safety, EMC, and basic functional parameters of the ECG device itself, and showing the interpretive algorithm's presence but framing its output as advisory.

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

• Sample Size: Not specified for any performance testing related to the interpretive algorithm. The document mentions "Performance validation via EDAN proprietary database" but does not give details on the size or characteristics of this database.
• Data Provenance: Not specified (e.g., country of origin). The document indicates it's an "EDAN proprietary database," suggesting it's internal.
• Retrospective or Prospective: Not specified.

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

• This information is not provided in the document. Given that the interpretive statements are "advisory" and no clinical data was submitted, detailed ground truth establishment by experts for evaluative purposes is not described.

4. Adjudication Method for the Test Set

• This information is not provided in the document.

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

• No. The document explicitly states "Clinical data: Not applicable." Therefore, an MRMC study was not performed or submitted for this 510(k). As a result, no effect size of human readers improving with AI vs. without AI assistance is reported.

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

• The document mentions "Performance validation via EDAN proprietary database" for the algorithm. However, specific details of this "standalone" performance (e.g., metrics like sensitivity, specificity, accuracy for specific arrhythmias or findings) are not provided, nor are the acceptance criteria for these metrics. The focus of the submission is on substantial equivalence of the overall device, not on analytical performance of the interpretive algorithm in isolation for diagnostic claims.

7. The Type of Ground Truth Used

• For the "Performance validation via EDAN proprietary database," the type of ground truth is not specified. Given the nature of ECG interpretation, it would typically involve cardiologist consensus or perhaps correlation with other diagnostic modalities for specific findings, but this document does not describe it.

8. The Sample Size for the Training Set

• This information is not provided. The document notes the use of "SEMIP or Glasgow" algorithms. These tend to be well-established, rule-based or statistical algorithms, rather than deep learning models that would have a distinct "training set" in the modern sense. If newer machine learning components were integrated, their training data size is not disclosed.

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

• This information is not provided. For established algorithms like SEMIP or Glasgow, their development likely involved expert consensus and large ECG databases over time, but the specific method for their training data's ground truth is not detailed here.

Ask a specific question about this device