Search Results

Fetal & Maternal Monitor (Model: F15A, F15A Air) is intended for providing Non-Stress testing or fetal monitoring for pregnant women from the 28th week of gestation. It is intended to be used only by trained and qualified personnel in antepartum examination rooms, labor and delivery rooms.

Fetal & Maternal Monitor (Model: F15A, F15A Air) is intended for real time monitoring of fetal and maternal physiological parameters, including non-invasive monitoring and invasive monitoring:

Non-invasive physiological parameters:

• Maternal heart rates (MHR)
• Maternal ECG (MECG)
• Maternal temperature (TEMP)
• Maternal oxygen saturation (SpO2) and pulse rates (PR)
• Fetal heart rates (FHR)
• Fetal movements (FM)
• FTS-3

Note: SpO2 and PR are not available in F15A Air.

Invasive physiological parameters:

• Uterine activity
• Direct ECG (DECG)

The F15A series fetal and maternal monitor can monitor multiple physiological parameters of the fetus/mother in real time. F15A series can display, store, and print patient information and parameters, provide alarms of fetal and maternal parameters, and transmit patient data and parameters to Central Monitoring System.

F15A series fetal and maternal monitors mainly provide following primary feature:

Non-invasive physiological parameters:

• Maternal heart rates (MHR)
• Maternal ECG (MECG)
• Maternal temperature (TEMP)
• Maternal oxygen saturation (SpO2) and pulse rates (PR)
• Fetal heart rates (FHR)
• Fetal movements (FM)
• FTS-3

Note: SpO2 and PR are not available in F15A Air.

Invasive physiological parameters:

• Uterine activity
• Direct ECG (DECG)

The provided FDA 510(k) clearance letter and summary for the Fetal & Maternal Monitor (F15A, F15A Air) do not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and the study that proves the device meets them.

The document focuses primarily on demonstrating substantial equivalence to a predicate device (Edan Instruments, Inc., F9 Express Fetal & Maternal Monitor, K173042) through comparison of intended use, technological characteristics, and conformance to various safety and performance standards. It mentions "functional and system level testing to validate the performance of the devices" and "results of the bench testing show that the subject device meets relevant consensus standards," but it does not specify quantitative acceptance criteria for each individual physiological parameter (e.g., FHR accuracy, SpO2 accuracy) nor the specific results of those tests beyond stating that they comply with standards.

Specifically, the document does not include information on:

• A table of acceptance criteria with specific quantitative targets for each parameter and the reported device performance values against those targets. It only states compliance with standards.
• Sample sizes used for a "test set" in the context of clinical performance evaluation (it mentions "bench testing," but this is typically laboratory-based and doesn't involve patient data in a "test set" sense for AI/algorithm performance validation).
• Data provenance for such a test set (e.g., country of origin, retrospective/prospective).
• Number or qualifications of experts used to establish ground truth.
• Adjudication methods.
• Multi-Reader Multi-Case (MRMC) studies or human reader improvement data with AI assistance.
• Standalone (algorithm-only) performance, as this is a monitoring device, not a diagnostic AI algorithm.
• Type of ground truth (beyond "bench testing" which implies engineered signals or controlled environments).
• Sample size for a training set or how ground truth for a training set was established. This device is a traditional medical device, not an AI/ML-driven diagnostic or interpretative algorithm in the way your request implies.

Therefore, based solely on the provided text, I can only address what is present or infer what is missing.

Here's a breakdown based on the available information:

Analysis of Acceptance Criteria and Performance Testing based on Provided Document

The provided 510(k) summary focuses on demonstrating substantial equivalence to a predicate device (F9 Express Fetal & Maternal Monitor, K173042) by showing that the new device (F15A, F15A Air) has the same intended use and fundamentally similar technological characteristics, with any differences not raising new safety or effectiveness concerns.

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

The document does not provide a specific table with quantitative acceptance criteria for each physiological parameter (e.g., FHR accuracy, SpO2 accuracy) and the corresponding reported performance values obtained in testing. Instead, it states that the device was assessed for conformity with relevant consensus standards. For example, it lists:

• IEC 60601-2-37:2015: Particular requirements for the basic safety and essential performance of ultrasonic medical diagnostic and monitoring equipment (relevant for FHR).
• ISO 80601-2-61:2017+A1:2018: Particular requirements for basic safety and essential performance of pulse oximeter equipment (relevant for SpO2).
• ISO 80601-2-56:2017+A1:2018: Particular requirements for basic safety and essential performance of clinical thermometers for body temperature measurement (relevant for TEMP).
• IEC 60601-2-27:2011: Particular requirements for the basic safety and essential performance of electrocardiographic monitoring equipment (relevant for MECG/DECG).

Acceptance Criteria (Inferred from standards compliance): The acceptance criteria are implicitly the performance requirements specified within these listed consensus standards. These standards set limits for accuracy, precision, response time, and other performance metrics for each type of measurement.

Reported Device Performance: The document states: "The results of the bench testing show that the subject device meets relevant consensus standards." This implies that the measured performance statistics (e.g., accuracy, bias, precision) for each parameter fell within the acceptable limits defined by the respective standards. However, the specific measured values are not provided in this summary.

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

The document mentions "Bench Testing" which implies laboratory-based testing using simulators, controlled signals, or phantoms, rather than a "test set" involving patient data. There is no information provided regarding:

• Sample size (e.g., number of recordings, duration of recordings, number of simulated cases) for the bench tests for each parameter.
• Data provenance (e.g., country of origin, retrospective or prospective) as this is not a study involving patient data collection for performance validation.

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 is not applicable and not provided. For a traditional physiological monitor, ground truth for bench testing is typically established using:

• Calibrated reference equipment/simulators: e.g., ECG simulators to generate known heart rates, SpO2 simulators to generate known oxygen saturation levels.
• Physical standards/phantoms: e.g., temperature baths at known temperatures.
• Known physical properties: e.g., precise weights for pressure transducers.

Clinical experts are not involved in establishing ground truth for bench performance of these types of physiological measurements.

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

This is not applicable and not provided. Adjudication methods are relevant for human expert review of complex clinical data (e.g., medical images for AI validation) to establish a consensus ground truth. For bench testing of physiological monitors, ground truth is objectively determined by calibrated instruments or defined physical parameters.

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

This is not applicable and not provided. An MRMC study is typically performed to evaluate the diagnostic accuracy of AI-assisted human interpretations versus unassisted human interpretations for AI-driven diagnostic devices. The Fetal & Maternal Monitor is a physiological monitoring device, not an AI-assisted diagnostic imaging or interpretation system. It measures and displays physiological parameters; it does not provide AI-driven assistance for human "readers" to interpret complex clinical information.

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

The device is a monitor that directly measures physiological parameters. It is not an "algorithm only" device in the sense of an AI model providing a diagnostic output. Its performance (e.g., FHR accuracy) is its standalone performance, as it directly measures these parameters. The document states "functional and system level testing to validate the performance of the devices," which would represent this type of standalone performance for the measurement functionalities. However, specific quantitative results are not given, only compliance with standards.

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

As explained in point 3, the ground truth for bench testing of physiological monitors is established using calibrated reference equipment/simulators and physical standards.

8. The sample size for the training set

This is not applicable and not provided. This device is a traditional physiological monitor, not a machine learning model that requires a "training set." Its algorithms for parameter measurement are based on established physiological principles and signal processing techniques, not on statistical learning from large datasets.

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

This is not applicable and not provided for the same reasons as point 8.

Ask a specific question about this device

The monitors are intended to be used for monitoring, storing, recording, and reviewing of, and to generate alarms for, multiple physiological parameters of adults and pediatrics (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), and cardiac output (C.O.).

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

The NIBP monitoring supports iCUFS algorithm and iFAST algorithm. The iCUFS algorithm is intended for adult, pediatric and neonatal patients. The iFAST algorithm is intended for adult and pediatric 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 CX&UX series Patient Monitor including CX10/CX12/CX15/UX10/UX12/UX15 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.

Minor differences from the predicate device are limited to some modifications of monitoring parameter specifications. These updates do not change the fundamental scientific technology of the cleared predicate device and thus do not raise any questions about the safety and effectiveness of the subject device.

The provided FDA 510(k) clearance letter details the device's technical specifications and comparisons to predicate devices, along with the non-clinical performance data and adherence to various IEC and ISO standards. However, it explicitly states: "Clinical data: The subject device did not require new clinical studies to support substantial equivalence."

This means that the submission for this Patient Monitor device (CX10, CX12, CX15, UX10, UX12, UX15) relies on demonstrating substantial equivalence to a legally marketed predicate device (Edan Instruments, Inc., Patient Monitor Model iX10, iX12, iX15, K232962) through non-clinical performance testing and software verification/validation, rather than new clinical trials or studies involving human patients.

Therefore, the requested information regarding acceptance criteria and studies that prove the device meets acceptance criteria through clinical performance (e.g., sample size for test set, expert involvement, MRMC studies, ground truth establishment for test/training sets, effect size of human reader improvement with AI) cannot be extracted from this document, as such clinical studies were explicitly not required for this 510(k) submission.

The document focuses on demonstrating that the new device's technical specifications and performance are similar to the predicate device, and that it complies with relevant safety and performance standards through bench testing.

Here's what can be extracted from the provided text regarding acceptance criteria and the type of study performed, specifically focusing on the non-clinical aspects:

Device: Patient Monitor (CX10, CX12, CX15, UX10, UX12, UX15)

The acceptance criteria for this device are implicitly tied to its performance meeting the standards and accuracy specifications of the predicate device and relevant international standards. Since no new clinical studies were conducted, the "proof" comes from non-clinical bench testing and software validation.

1. Table of Acceptance Criteria and Reported Device Performance (Non-Clinical/Bench Testing)

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

• Sample Size: Not applicable in terms of human subjects or patient data test sets, as "new clinical studies" were not required. The "test set" refers to bench testing and functional system-level validation. The specific number of test cycles or a detailed breakdown of test cases for bench testing is not provided in this summary.
• Data Provenance: The data primarily originates from Edan Instruments Inc. (Shenzhen, Guangdong, China) through internal engineering and quality assurance processes for non-clinical bench testing and software validation. It is not patient data, so concepts like "retrospective or prospective" do not apply.

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

• Not applicable for clinical ground truth: Since no clinical studies were performed requiring human interpretation or diagnosis for a test set, no medical experts (e.g., radiologists) were used to establish ground truth in this context.
• Internal experts: Bench testing and software validation would have involved engineers and quality assurance professionals, whose qualifications are implicit in the quality system (21 CFR Part 820) but not specified in detail here.

4. Adjudication Method for the Test Set:

• Not applicable: Adjudication methods (e.g., 2+1, 3+1) are relevant for clinical studies involving multiple readers. This was not a clinical study. Bench testing relies on established technical specifications and standard compliance.

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

• No: No MRMC study was performed as no new clinical studies were required or conducted. Therefore, there's no effect size of human readers improving with AI assistance. The device is a patient monitor, not an AI-assisted diagnostic tool.

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

• Yes (for the technical components): The "performance testing-Bench" effectively represents a standalone evaluation of the device's functional components (ECG, NIBP, SpO2, etc.) and software against defined technical specifications and standards. The "software verification and validation testing" also represents a standalone evaluation of the algorithm and software functions. The specific algorithms (e.g., iCUFS, iFAST for NIBP, arrhythmia analysis logic) are tested independently for their accuracy against known inputs or reference standards as part of bench testing.

7. The Type of Ground Truth Used:

• Technical/Reference Standards: For the bench testing, the "ground truth" would be derived from:
  • Reference standards/simulators: Calibrated medical equipment, physiological simulators, and test signals (e.g., known ECG waveforms, simulated blood pressure readings, temperature standards) are used to provide the "true" values against which the device's measurements are compared.
  • Defined specifications: The device's internal design specifications and the requirements of the referenced IEC/ISO standards serve as the "ground truth" for compliance testing.
• Not clinical ground truth: No expert consensus, pathology, or outcomes data from real patients were used for establishing ground truth for this submission.

8. The Sample Size for the Training Set:

• Not applicable: The device is a patient monitor, not a machine learning/AI algorithm that typically undergoes a distinct "training" phase with a large dataset. Its functionality is based on established physiological measurement principles and programmed algorithms. Any internal calibration or algorithm refinement would be part of the product development process, not a dedicated "training set" in the AI/ML sense.

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

• Not applicable: As there was no "training set" in the context of an AI/ML model, the concept of establishing ground truth for it does not apply to this 510(k) submission.

In summary, this 510(k) clearance relies on demonstrating that the new Patient Monitor is substantially equivalent to a previously cleared predicate device, primarily through robust non-clinical bench testing and software validation, proving compliance with established medical device standards and functional specifications. No new clinical studies with patient data were required or conducted for this specific submission.

Ask a specific question about this device

The Acclarix AX8 Series Diagnostic Ultrasound System is intended for use by a qualified physician or allied health professional for ultrasound evaluations in hospitals and clinics.
The Acclarix AX8 Series Diagnostic Ultrasound System clinical applications include Abdominal, Gynecology, Obstetric, Cardiac, Small parts, Urology, Peripheral vascular, Musculoskeletal, Pediatric, Neonatal, Adult Cephalic, Thoracic/Pleural and Trans-esophageal Cardiac.
The Modes of Operation for Acclarix AX8 Series include B mode, M mode, Doppler mode, Harmonic Imaging, Elastography Imaging, Contrast imaging and their combination modes.
The Acclarix AX9 Series Diagnostic Ultrasound System is intended for use by a qualified physician or allied health professional for ultrasound evaluations in hospitals and clinics.
The Acclarix AX9 Series Diagnostic Ultrasound System clinical applications include Abdominal. Gynecology, Obstetric, Cardiac, Small parts, Urology, Peripheral vascular, Musculoskeletal, Pediatric, Neonatal, Adult Cephalic, Thoracic/Pleural and Trans-esophageal Cardiac.
The Modes of Operation for Acclarix AX9 Series include B mode, M mode, Doppler mode, Harmonic Imaging, Elastography Imaging, Contrast imaging and their combination modes.

The Acclarix AX8 Series & Acclarix AX9 Series Diagnostic Ultrasound System is a software controlled Diagnostic Ultrasound System, which consists of a main unit along with associated transducers. It is intended for use by a qualified physician or allied health professional for ultrasound evaluations in hospitals and clinics. This system is a Track 3 device to acquire and display ultrasound data in various imaging modes.

The provided text focuses on the 510(k) summary for the Edan Instruments Inc. Acclarix AX8 and AX9 Series Diagnostic Ultrasound Systems. It primarily addresses the substantial equivalence to a predicate device and outlines non-clinical performance data. It explicitly states "Clinical data: Not applicable," which means that no clinical studies were performed to establish acceptance criteria or demonstrate device performance against clinical metrics.

Therefore, I cannot provide the requested information regarding acceptance criteria and a study proving the device meets them because such a study involving clinical data and performance metrics is explicitly stated as "Not applicable" in the document.

However, I can extract information about the non-clinical testing performed:

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

Since no clinical acceptance criteria or performance metrics were reported, this table cannot be created as requested in the context of clinical performance. The document only states that the device complies with certain electrical safety, EMC, and performance standards.

Regarding the other requested information, the document states "Clinical data: Not applicable." Therefore, the following points cannot be addressed from the given text:

• 2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective): Not applicable due to lack of clinical data.
• 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 due to lack of clinical data.
• 4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable due to lack of clinical data.
• 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 device is a diagnostic ultrasound system, and the document doesn't mention AI assistance or MRMC studies.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The device is an ultrasound system, not an AI algorithm intended for standalone performance.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): Not applicable due to lack of clinical data.
• 8. The sample size for the training set: Not applicable as no clinical training data is mentioned.
• 9. How the ground truth for the training set was established: Not applicable as no clinical training data is mentioned.

Ask a specific question about this device

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