Search Results

V9 Patient Monitor is intended to be used for monitoring, displaying, storing and alarming of multiple physiological parameters of patients, including Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Carbon dioxide (CO2) and Temperature (Temp).

V9 Patient Monitor is used to monitor vital signals for patients and is intended to be used in controlled, hospital environments. It is applicable for adult, pediatric and neonatal patiented for helicopter transport, hospital ambulance or home use.

The V9 Patient Monitor can provide the monitoring of physiological parameters such as the Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Carbon dioxide (CO2) and Temperature (Temp). The V9 Patient Monitor is a portable device, consists of main unit and accessories, including NIBP cuff, Temperature sensor, CO2 sensor and SpO2 sensor.

It consists of main unit and accessories, including NIBP cuff, Temperature sensor, CO2 sensor and SpO2 sensor.

All modules, boards and accessories used in V9 Patient Monitor has already been cleared by FDA, referring to Table 1. In which, two NIBP and three SpO2 modules are optional for proposed device.

The provided text is a 510(k) summary for the Shenzhen Biolight Meditech Co., Ltd. V9 Patient Monitor. This document is a premarket notification to the FDA to demonstrate that the device is substantially equivalent to a legally marketed predicate device. As such, it focuses on comparing the proposed device to a predicate and confirming compliance with relevant standards, rather than detailing the full scope of acceptance criteria and a specific study proving those criteria are met for this new device in the way a clinical trial report would.

However, I can extract the information that is present and highlight what is not present given the nature of a 510(k) summary.

Here's an analysis based on your request:

Acceptance Criteria and Study Details for Guangdong Biolight Meditech Co., Ltd. V9 Patient Monitor

The V9 Patient Monitor is intended for monitoring, displaying, storing, and alarming for multiple physiological parameters: Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Carbon dioxide (CO2), and Temperature (Temp).

The primary method for demonstrating acceptance criteria is by showing Substantial Equivalence (SE) to a predicate device (V6 Vital Signs Monitor, K153135) and compliance with recognized national and international standards for medical electrical equipment. No new clinical studies were conducted for this submission (as stated in point 6). Instead, the manufacturer relies on the previous clearance of its individual modules and compliance with established performance standards for each physiological parameter.

1. Table of Acceptance Criteria and Reported Device Performance

Since this is a 510(k) demonstrating substantial equivalence based on previously cleared modules and compliance with standards, specific performance metrics for the new combined device (V9 Patient Monitor) are not presented in a direct "acceptance criteria vs. performance" table in the way one might see for a novel device undergoing clinical trials. Instead, the "acceptance criteria" are compliance with specific IEC/ISO standards, and the "reported device performance" is the assurance that the device meets these standards.

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

• Sample Size for Test Set: Not applicable in the context of this 510(k). No new clinical data or human subject test sets were used. The "tests" referred to are non-clinical (engineering and performance assessment against standards) and rely on the prior clearances of the individual modules.
• Data Provenance: Not applicable for the reasons above.

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

• Number of Experts: Not applicable. No "ground truth" established by experts for a test set for this new device. The compliance with standards is assessed through engineering tests.

4. Adjudication method for the test set

• Adjudication Method: Not applicable. No clinical test set requiring adjudication was performed for this submission.

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 device is a patient monitor, not an AI-assisted diagnostic tool involving "human readers" or image interpretation. Therefore, no MRMC comparative effectiveness study was done, and the concept of "human readers improve with AI vs without AI assistance" is not applicable.

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

• This device is a patient monitor, which relies on sensors and processing algorithms to measure and display physiological parameters. While it contains algorithms, the submission doesn't detail their standalone performance in terms of "algorithm only" studies as would be seen for a complex AI diagnostic system. The performance is assessed by the device's ability to accurately measure and display parameters according to established medical device standards. The "standalone" performance is integrated into the compliance testing against the IEC/ISO standards mentioned above.

7. The type of ground truth used

• The "ground truth" in this context is defined by the established performance requirements and test methodologies outlined in the referenced IEC and ISO standards (e.g., accuracy requirements for NIBP, SpO2, CO2, Temp as defined in their respective standards). Compliance ensures the device's measurements are consistent with these industry-accepted benchmarks. For the previously cleared modules, their "ground truth" would have been established during their initial clearance process, likely through comparison to highly accurate reference methods or clinical data as appropriate for each module.

8. The sample size for the training set

• Sample Size for Training Set: Not applicable. This document does not describe the development of a novel algorithm requiring a training set in the AI sense. The device integrates previously cleared modules.

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

• Ground Truth for Training Set: Not applicable for the reasons mentioned above.

Ask a specific question about this device

Central Monitoring System Software is intended to conduct centralized monitoring of adult, pediatrics and neonatal patient's vital sign information from compatible bedside monitors. The software collects, stores, displays and alarms the information provided on the bedside monitoring parameters include Electrocardiogram(ECG), Heart Rate(HR), Respiration(RESP), Pulse Oxygen Saturation(SpO2), Pulse Rate(PR), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure(IBP), Impedance Cardiograph(ICG), TEMP(Temperature), Carbon dioxide (CO2), Anesthetic Gas (AG), Fetal Heart Rate (FHR), Uterine contraction (TOCO) and Fetal Movement (FM) etc. It is intended to be used in the hospital or medical institutions, and it is not intended for home use.

M6000C central monitoring system software, the risk management object, can central monitor significant vital sign parameters of multi-patients, including ECG/HR, RESP, SpO2, PULSE, NIBP, IBP, ICG, TEMP, CO2, AG, FHR, TOCO and FM. It is connected by network with bedside units and receives data from bedside units. Then, the data are displayed on the screen or recorded or printed as per needs. When the monitored data exceed a set value, the central monitoring system software will start alarm system and gives out alarm to remind doctors and nurses for attention.

Here's a breakdown of the acceptance criteria and study information based on the provided text:

Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria or a direct comparison of the device's performance against such criteria. Instead, it focuses on non-clinical testing to verify design specifications and compliance with voluntary standards. The "Performance testing" mentioned is general and doesn't provide specific numerical results or target metrics.

Detailed Study Information:

1. A table of acceptance criteria and the reported device performance:
   (See table above)

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

   • Sample Size for Test Set: Not specified. The document mentions "Performance testing" but does not detail the number of test cases, patient data, or scenarios used in these tests.
   • Data Provenance: Not specified. It's unclear if the tests used simulated data, existing patient data, or newly acquired data. The country of origin is also not mentioned.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
   Not applicable. The document describes non-clinical performance and software verification testing, which typically do not involve expert-established ground truth in the same way clinical studies or diagnostic AI algorithms do. The "performance testing" seems to focus on functional verification rather than accuracy against a clinical reference standard.

4. Adjudication method for the test set:
   Not applicable, as no external experts or adjudication process against a ground truth is described for the functional and performance testing.

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 submission explicitly states: "No clinical study is included in this submission." Therefore, no MRMC study or AI assistance evaluation was performed.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
   Yes, in a sense. The described "Performance testing" and "Software verification and validation testing" are evaluations of the device (software) itself, without direct human-in-the-loop involvement in the performance assessment against a clinical outcome. These tests confirm the software's functionality, compatibility, and data processing capabilities, rather than its diagnostic or interpretative accuracy in a clinical context.

7. The type of ground truth used:
   Not explicitly stated as "ground truth" in the diagnostic sense. For the functional and performance tests, the "ground truth" would be the expected behavior or output of the software and system based on its design specifications and standard requirements. For example, for data latency, the ground truth would be the defined acceptable latency rate. For compatibility, it would be successful communication with specified bedside monitors.

8. The sample size for the training set:
   Not applicable. This device is a Central Monitoring System, which collects, stores, displays, and alarms vital sign information. It is not an AI/ML algorithm that is "trained" on a dataset in the typical sense. It performs rule-based monitoring and alarm generation.

9. How the ground truth for the training set was established:
   Not applicable, as there is no training set for this type of monitoring system.

Ask a specific question about this device

Truscope Ultra Patient monitors are intended to be used for monitoring, reviewing, storing and alarming of multiple physiological parameters including ECG (3-lead or 5-lead selectable), arrhythmia detection, ST segment analysis, Heart Rate (HR), Respiration Rate (RESP), Temperature (TEMP), Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure (IBP), Carbon dioxide (CO2), Anesthetic Gas (AG), Impedance Cardiograph (ICG), Cerebral Index (CSI), Bispectral Index (BIS), Total Hemoglobin(SpHb), Carboxyhemoglobin (SpCO), Methemoglobin(SpMet).

The arrhythmia detection. ST segment analysis only applied to a single adult patient.

The monitors are to be used in healthcare facilities by clinical physicians or appropriate medical staff under the direction of physician. It is not intended for helicopter transport, hospital ambulance, or home use.

Not Found

This document is a 510(k) premarket notification letter from the FDA regarding the "Truscope Ultra Patient Monitors". It primarily addresses the substantial equivalence determination for the device and its intended use. It does not contain information about acceptance criteria or specific study data to prove device performance.

Therefore, I cannot fulfill your request for the following information based on the provided text:

1. A table of acceptance criteria and the reported device performance
2. Sample sized used for the test set and the data provenance
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
4. Adjudication method for the test set
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, and its effect size
6. If a standalone performance study was done
7. The type of ground truth used
8. The sample size for the training set
9. How the ground truth for the training set was established

This document is an administrative approval from the FDA, confirming that the device is substantially equivalent to a predicate device, and lists its general indications for use. It does not delve into the detailed technical studies or performance data that would typically be reviewed during the 510(k) submission process itself.

Ask a specific question about this device

The device is intended to measure diastolic, systolic blood pressure and the pulse rate of an adult patient via non-invasive technique in which an inflatable cuff is wrapped around the upper arm. It is intended to be used at home. The intended arm circumference is 17cm22cm, 22cm32cm, 32cm~42cm.

The subject device is a battery driven automatic on-invasive blood pressure monitor. It can automatically complete the inflation, deflation and measurement, which can measure systolic and diastolic blood pressure and the pulse rate of adult at upper arm within its claimed range and accuracy via the oscillometric technique. User can select the unit of the measurement: mmHg or KPa. All the models included in this submission follow the same software, same measurement principle and same specifications. The WBP100 does not have LCD display but has Bluetooth; WBP201 does not have Bluetooth but has LCD display, and WBP202 has LCD display and Bluetooth. The difference will not affect the safety and effectiveness of the subject device.

This document describes a 510(k) submission for an Electronic Sphygmomanometer (Model: WBP100, WBP201, WBP202) by Guangdong Biolight Meditech Co., Ltd. The submission aims to demonstrate substantial equivalence to a predicate device (K131558).

Here's an analysis of the provided text to answer your questions regarding acceptance criteria and the study proving the device meets them:

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

The document explicitly states that the clinical study was conducted to evaluate if the device meets the accuracy requirements of ISO 81060-2:2013, "Non-Invasive Sphygmomanometers - Part 2: Clinical Validation Of Automated Measurement Type."

While the document references this standard as the acceptance criterion, it does not provide a table of the specific numerical acceptance criteria (e.g., mean difference, standard deviation) from ISO 81060-2:2013, nor does it present the reported device performance with those specific numbers. It only states that the device "meets the accuracy requirements."

To fully answer this question, one would need to refer to ISO 81060-2:2013 to determine its specific accuracy criteria and then examine the full clinical study report (which is not provided in this excerpt) for the device's measured performance against those criteria.

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

• Sample Size for Test Set: The document mentions a "clinical study" but does not explicitly state the sample size used for the test set (i.e., the number of subjects enrolled in the clinical validation). ISO 81060-2:2013 typically specifies minimum sample sizes for clinical validation (e.g., usually 85 subjects for Phase 1 and Phase 2 combined, or similar, depending on the specific method).
• Data Provenance: The document does not specify the country of origin of the data or whether the study was retrospective or prospective. Clinical validation studies for medical devices are typically prospective in nature.

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

For non-invasive blood pressure monitors, the "ground truth" for blood pressure measurements in a clinical validation study typically involves simultaneous auscultatory measurements by trained observers using a mercury sphygmomanometer, often with a "double stethoscope" setup to ensure independent readings.

The document does not specify the number of experts (observers) used or their qualifications (e.g., "trained observers" or "physicians with X years of experience"). ISO 81060-2:2013 outlines detailed requirements for the training and procedures for these observers to ensure accurate reference measurements.

4. Adjudication method for the test set:

In the context of blood pressure validation studies, "adjudication" usually refers to managing discrepancies between simultaneous reference measurements (e.g., if two observers get slightly different readings). ISO 81060-2:2013 specifies procedures for this, often involving taking the average of the two observer readings if they are within a certain range, or a third observer if they are too disparate.

The document does not explicitly state the adjudication method used for the test set, but it would have followed the methodology defined in ISO 81060-2:2013.

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 device is an Electronic Sphygmomanometer, a direct measurement device, not an AI-powered diagnostic imaging tool that would typically involve human readers. Therefore, an MRMC comparative effectiveness study is not applicable to this type of device, and the concept of "human readers improving with AI assistance" does not apply.

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

The device itself is an automated non-invasive sphygmomanometer. Its operation is inherently "standalone" in the sense that the device's algorithm performs the measurement and calculation of blood pressure without human intervention during the measurement process. The clinical validation outlined by ISO 81060-2:2013 evaluates this automated performance against reference measurements. So, the clinical study is effectively a standalone performance assessment of the automated device.

7. The type of ground truth used:

The ground truth for non-invasive blood pressure measurement devices validated against ISO 81060-2:2013 is typically established by simultaneous, direct auscultatory measurements performed by trained human observers using a calibrated reference device (e.g., mercury sphygmomanometer). This is considered the "gold standard" for clinical validation of these devices. It is not pathology or outcomes data.

8. The sample size for the training set:

This device is a hardware product with a measurement algorithm, not a machine learning model that requires a "training set" in the conventional sense of AI development. The "algorithm" here refers to the oscillometric method's logic and the device's internal programming for calculating BP. Therefore, the concept of a separate "training set" for an AI model does not apply to this medical device submission as described.

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

As mentioned above, the concept of a "training set" and establishing ground truth for it does not apply in the context of this traditional medical device validation. The "ground truth" is relevant for the clinical validation (test set) to ensure the accuracy of the device's measurements against accepted reference methods.

Ask a specific question about this device

Central Monitoring System Software is intended to conduct centralized antepartum and intrapartum monitoring of pregnant women's vital sign information from compatible bedside monitors. The software collects, stores, displays and alarms the information provided on the bedside monitor. The monitoring parameters include Electrocardiogram(ECG), Heart Rate(HR), Respiration(RESP), Pulse Oxygen Saturation(SpO2), Pulse Rate(PR), Non-invasive Blood Pressure (NIBP), Invasive Blood Pressure(IBP), Impedance Cardiograph(ICG), TEMP(Temperature), Carbon dioxide (CO2), Anesthetic Gas (AG), Fetal Heart Rate (FHR), Uterine contraction (TOCO) and Fetal Movement (FM). It is intended to be used in the hospital or medical institutions, and it is not intended for home use.

The Central Monitoring System Software-only device that is intended to conduct centralized antepartum and intrapartum monitoring of pregnant women's vital sign information from compatible bedside monitors connected by a wired or wireless network. The Central Monitoring System consists of two models: M6000C and Truscope CNS. Both models provide functions including collecting, storing, displaying, and alarming (e.g. when the monitored data exceeds a set value, the device will alarm to alert medical personnel) the information which is received from the bedside monitor(s). Multiple patients can be monitored simultaneously. Parameters monitored include ECG/HR, RESP, SpO2, PULSE, NIBP, IBP, ICG, TEMP, CO2, AG, FHR, TOCO and FM.

The provided document does not contain details about specific acceptance criteria related to a numerical performance target (e.g., sensitivity, specificity, accuracy) for the Central Monitoring System Software, nor does it describe a study that proves the device meets such criteria in terms of clinical performance.

Instead, the document focuses on non-clinical testing to demonstrate:

• Compatibility with various bedside monitors.
• Acceptable data latency rates for the clinical environment.
• Software verification and validation testing, following FDA guidance.
• Compliance with voluntary standards (IEC 62366:2007 and IEC 62304:2006).

Therefore, I cannot populate a table of acceptance criteria and reported device performance directly from this text in the way that would typically be done for a diagnostic AI device requiring performance metrics. The information needed for almost all of your specific questions (sample size, data provenance, number of experts, etc.) is also not present because the study described is not a clinical performance study with defined ground truth.

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

1. Table of acceptance criteria and the reported device performance

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

• Sample Size: Not specified. The performance testing mentioned is non-clinical and focuses on system functionality and compatibility rather than clinical data performance.
• Data Provenance: Not applicable, as there is no mention of clinical data or patient-specific test sets.

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

• Number of Experts: Not applicable.
• Qualifications: Not applicable.

4. Adjudication method for the test set

• Adjudication Method: Not applicable.

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

• No, an MRMC comparative effectiveness study was not done. The device is a "Central Monitoring System Software" for displaying and alarming vital sign data, not an AI diagnostic tool designed to assist human readers in interpretation.

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

• The described tests are for the standalone functionality of the software system (e.g., collecting, storing, displaying, alarming data) and its compatibility, not for an "algorithm only" in the sense of an AI diagnostic prediction. Its function is to operate independently of real-time human interpretation, presenting data from other devices.

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

• Type of Ground Truth: For the non-clinical tests, the "ground truth" would be the expected functional behavior and performance defined by the design specifications and relevant standards. For example, for data latency, the ground truth would be the maximum acceptable delay. For compatibility, it would be successful data exchange with target bedside monitors. No clinical ground truth (e.g., pathology, expert consensus on a diagnosis) is relevant or mentioned.

8. The sample size for the training set

• Sample Size: Not applicable. There is no mention of a machine learning or AI model being trained, so no training set is described.

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

• How Ground Truth Established: Not applicable, as there is no training set described.

In summary: This 510(k) summary focuses on the functional and technical performance of software that collects, displays, and alarms vital sign data from other monitors. It is not an AI diagnostic device that requires clinical performance metrics like sensitivity or specificity derived from interpreting medical images or complex data, and therefore, the types of studies and ground truth requested in questions 2-9 are not applicable to the information provided.

Ask a specific question about this device

The vital signs monitor is intended to be used for monitoring, reviewing, storing and alarming of multiple physiological parameters of patients, including Pulse Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Carbon dioxide (CO2) and Temperature (Temp).

This vital signs monitor is used to monitor vital signals for use in hospital environments including out-patient department, wards and NICU. It is not intended for helicopter transport, hospital ambulance or home use. And it is applicable for adult, pediatric and neonatal patients.

The Vital Signs Monitor is a portable device intended for use by health care professionals. The monitor could provide the monitoring of physiological parameters such as the Oxygen Saturation (SpO2), Pulse Rate (PR), Non-invasive Blood Pressure (NIBP), Carbon dioxide (CO2) and Temperature (Temp).

The following lists the detailed features of the subject device.

• LCD/LED display
• SpO2, Pulse Rate NIBPCO2 and TEMP measurement
• Infrared ear temp or fast temp module for Temp measurement
• Nellcor or Masimo or BLT SpO2 module
• Display numeric and waveform information simultaneously .
• Nurse call feature
• . Built-in Lithium-ion Battery
• Suitable for adult, pediatric and neonate patients .
• Visual and audible alarm

The document describes a 510(k) premarket notification for the V6 Vital Signs Monitor. The submission focuses on demonstrating substantial equivalence to a predicate device rather than presenting a performance study with acceptance criteria in the context of AI/ML devices.

Therefore, many of the requested categories for acceptance criteria and study details for an AI-powered device are not applicable to this submission. This document describes a traditional medical device (vital signs monitor) which is evaluated based on its compliance with established electrical safety, EMC, and performance standards for each physiological parameter.

Here's an analysis based on the provided document, highlighting applicable information and noting where information for AI/ML performance would typically be found but isn't present here:

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

The document provides a comparison of the proposed device (Vital Signs Monitor V6) and its predicate devices, especially regarding technical specifications and compliance with standards. It does not present specific "accepted criteria" in terms of performance metrics like sensitivity, specificity, or AUC, as would be typical for an AI/ML diagnostic or assistive device. Instead, it demonstrates compliance with recognized medical device standards and equivalence to a predicate.

For the newly added F3000 Temperature Module, a "Clinical Electronic Thermometers testing" was conducted pursuant to guidance. The table below focuses on the reported accuracy of the temperature measurement, which can be interpreted as a performance metric for that specific function.

Note: The "acceptance criteria" here are largely derived from the predicate device's performance or standard requirements that both devices are expected to meet. For NIBP, SpO2, and CO2, the document only states that compliance with relevant IEC standards (IEC80601-2-30 for NIBP, IEC80601-2-61 for pulse oximeter) was demonstrated, but does not provide specific accuracy ranges within the provided text.

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

The document states: "No clinical study is included in this submission." This implies that for the substantial equivalence claim, the manufacturer relied on non-clinical testing and comparison to the predicate device, rather than a clinical study with a dedicated test set on human subjects to evaluate performance like sensitivity or specificity. For the temperature module, it mentions "Clinical Electronic Thermometers testing" but does not detail sample size or data provenance.

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. There is no clinical study data presented for expert-established ground truth.

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

Not applicable. There is no clinical study data presented requiring adjudication.

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 vital signs monitor, not an AI-assisted diagnostic tool for human readers.

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

The device is a standalone vital signs monitor. Its "performance" is evaluated by its ability to accurately measure physiological parameters and comply with relevant international standards. The non-clinical tests mentioned demonstrate the device's standalone performance in meeting design specifications and standard requirements.

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

For the non-clinical tests and equivalence claims of the vital signs monitor, the "ground truth" would be established by:

• Reference instruments and calibration standards for objective measurements (e.g., for SpO2, NIBP, temperature).
• Compliance with the technical requirements and performance specifications outlined in international standards (e.g., IEC 60601 series, IEC80601 series).

For the temperature module, "Clinical Electronic Thermometers testing" likely involved comparison to highly accurate reference thermometers in a controlled clinical setting, but specific details are not provided.

8. The sample size for the training set

Not applicable. This device does not appear to involve an AI/ML algorithm that would require a "training set" in the conventional sense for a diagnostic product. Its functionality is based on established hardware and software algorithms for physiological parameter measurement rather than machine learning on a dataset.

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

Not applicable, as there is no mention of a training set for an AI/ML algorithm.

Ask a specific question about this device

Electronic Thermometer is intended for measuring and monitoring human body temperature orally and/or under arm for adult, pediatric and infant. It can be used in healthcare facility and home.

The proposed device, Electronic Thermometer, is a handheld device with battery power supply, intended for measuring and monitoring human body temperature orally and/or under arm for adult, pediatric and infant. It can be used in healthcare facility and home. There is no specific use of this device other than temperature measurements, including conversion of temperatures. The proposed device is available in two models, which are WT1 and WT2. Similarities between models: a. Both of them incorporate a temperature sensitive sensor b. Both of them can measure and monitor human body temperature under arm; C. Neither the WT1 nor WT2 has display function, the measured or monitored temperature will be transmitted to a mobile application, Temp Sitter, installed under iOS system via the blue tooth to display the measured and monitored temperature; Differences between models: a. WT1 has an automatic power on/off feature; b. WT1 can be used with an adhesive tape, which could be fix the thermometer under arm for measuring and monitoring; c. WT2 can be used with a designated probe cover; d. WT2 can be used for measurement of oral temperature.

Here's an analysis of the provided text regarding the acceptance criteria and study information for the Electronic Thermometer (Models WT1 and WT2), formatted as requested.

Electronic Thermometer (Models WT1 and WT2)

1. Table of Acceptance Criteria and Reported Device Performance

Based on the provided document, the acceptance criteria are generally established by compliance with recognized standards and the reported performance is directly stated in the comparison table.

Notes on Acceptance Criteria: The document primarily relies on non-clinical testing against recognized national and international standards (ISO, IEC) to demonstrate substantial equivalence. The detailed accuracy claims are a performance specification that needs to be verified by testing.

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

The document explicitly states: "No clinical study is included in this submission."
Therefore, there is no information about:

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

The "test set" in this context refers to non-clinical tests (e.g., biocompatibility testing, electrical safety testing, EMC testing), which are performed on device samples, not human participants or clinical data. The precise number of device units or samples used for each non-clinical test (e.g., for biocompatibility or electrical safety) is not specified in this summary.

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 studies were performed, and thus no clinical ground truth was established by experts for a test set. Non-clinical tests establish "ground truth" based on standard protocols, calibrated equipment, and laboratory measurements.

4. Adjudication Method for the Test Set

Not applicable as no clinical studies were performed. Adjudication methods are typically employed in clinical trials or studies where human readers/experts independently assess cases, and a process is needed to resolve discrepancies.

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 an electronic thermometer, not an AI-assisted diagnostic tool involving human readers or interpretation of medical images/data. Therefore, an MRMC study is not relevant to this device.

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

The device itself is a standalone electronic thermometer. The performance described (accuracy, precision, response time) is for the device operating independently to measure temperature. There isn't an "algorithm" in the sense of AI or image processing, but the device's measurement functionality itself operates in a standalone manner to generate a temperature reading. The companion mobile application "Temp Sitter" serves for display and potentially trend monitoring, but the temperature measurement occurs directly by the physical device. The compliance with standards like ISO 80601-2-56 reflects this standalone performance.

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

For the non-clinical tests that were performed:

• Accuracy and Response Time: Ground truth would be established using calibrated reference thermometers and temperature sources as per the methodologies outlined in ISO 80601-2-56 or similar standards.
• Biocompatibility: Ground truth is established by laboratory testing results (e.g., cell viability assays for cytotoxicity, skin patch tests for sensitization, observation of tissue reactions for irritation) against specified limits.
• Electrical Safety and EMC: Ground truth is established by laboratory measurements taken by specialized equipment as per the IEC standards.

8. The Sample Size for the Training Set

Not applicable as no AI or machine learning algorithm requiring a "training set" is mentioned or implied for this device.

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

Not applicable, as no training set was used.

Ask a specific question about this device

The Fingertip Pulse Oximeter is intended to measure functional arterial oxygen saturation (SpO2) and pulse rate of adult, child and adolescent patients in hospital, hospital type facilities, as well as in the home care environment. The oximeter is not suitable to monitor patient continuously for long term.

The proposed devices, Fingertip Pulse Oximeters M70, M70A, M70C and M70D are fingertip devices, which can display %SpO3, pulse rate value, waveform pulse amplitude bar indication. The five models share the same configuration, intended use, safety and performance, the only difference is extrinsic feature. The proposed devices, Fingertip Pulse Oximeters M70, M70A, M70C and M70D are modified versions of the predicate device, M70, cleared under K081712. The oximetry technology including the sensor was unchanged.

The provided text describes a 510(k) premarket notification for Fingertip Pulse Oximeters M70, M70A, M70B, M70C, M70D by Guangdong Biolight Meditech Co., Ltd. The submission aims to demonstrate substantial equivalence to legally marketed predicate devices.

While the document outlines performance specifications and compliance with standards, it does not contain a detailed study report that proves the device meets specific acceptance criteria in the format typically required for an AI/ML medical device submission. This document focuses on the substantial equivalence argument based on performance specifications and compliance with general medical device standards, rather than a dedicated clinical study with a defined test set, ground truth experts, or MRMC analysis often seen for novel AI/ML device evaluations.

However, I can extract the relevant information from the document to construct an answer based on the provided text, interpreting "acceptance criteria" as the claimed performance specifications and "study" as the non-clinical tests and substantial equivalence comparison.

Here's an analysis based on the information provided:

Acceptance Criteria and Device Performance for Fingertip Pulse Oximeters M70, M70A, M70B, M70C, M70D

The device, Fingertip Pulse Oximeter, is intended to measure functional arterial oxygen saturation (SpO2) and pulse rate. The "acceptance criteria" can be inferred from the device's claimed performance specifications that are stated to be compliant with ISO 80601-2-61.

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document states that the subject device models have more accurate pulse rate and SpO2 specifications than the predicate device K141128. This implies the listed specifications are the target "acceptance criteria" for the new devices.

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

The document states, "Non clinical tests were conducted to verify that the proposed device met all design specifications as was Substantially Equivalent (SE) to the predicate device. The test results demonstrated that the proposed device complies with the following standards: ... ISO 80601-2-6: 2011, Medical Electrical Equipment - Part 2-61: Particular Requirements For Basic Safety And Essential Performance Of Pulse Oximeter Equipment."

• Sample Size for Test Set: The exact sample size for the non-clinical tests is not specified in the provided text. The document refers to compliance with ISO 80601-2-61, which would dictate the methodology and sample sizes for testing SpO2 accuracy (e.g., typically requires human subject studies with induced hypoxia). However, the specific study details are not presented.
• Data Provenance: The document does not specify the country of origin of data or whether the tests were retrospective or prospective. It only mentions "Non clinical tests were conducted." Given the nature of a 510(k) for a pulse oximeter, human subject testing would typically be prospective to determine SaO2 accuracy.

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

This information is not provided in the document. For pulse oximeters, the 'ground truth' for oxygen saturation (SaO2) is typically established by co-oximetry of arterial blood samples, performed by trained medical personnel. It is not typically established by 'experts' in the sense of radiologists or other clinicians interpreting outputs for AI/ML devices.

4. Adjudication Method for the Test Set

This information is not provided in the document. It's not applicable in the context of typical pulse oximetry accuracy testing, where the reference method itself (co-oximetry) serves as the ground truth.

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

There was no MRMC comparative effectiveness study performed or reported. This type of study is typically relevant for AI/ML devices that aim to assist human readers in diagnostic tasks, demonstrating how AI impacts human performance. A pulse oximeter is a standalone measurement device.

6. Standalone (Algorithm Only) Performance

The document describes the performance of the device itself (algorithm + hardware), which is inherently "standalone" in mechanical terms, as it provides direct SpO2 and pulse rate readings. However, it's not an "algorithm-only" performance as typically evaluated for AI/ML, but rather the performance of the integrated medical device. The "non-clinical tests" and compliance with ISO 80601-2-61 essentially represent the standalone performance evaluation.

7. Type of Ground Truth Used

For pulse oximeter accuracy, the ground truth for arterial oxygen saturation (SaO2) is typically established by co-oximetry of arterial blood samples. This is implied by compliance with ISO 80601-2-61, which sets out requirements for determining SpO2 accuracy through human subject testing with induced hypoxia and comparison against arterial blood gas analysis. The document does not explicitly state this, but it is the standard method for establishing ground truth for oximeters.

8. Sample Size for the Training Set

The document is for a traditional pulse oximeter and does not describe an AI/ML algorithm or a "training set." Therefore, this information is not applicable and not provided.

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

As there is no mention of an AI/ML algorithm or a "training set," this information is not applicable and not provided.

Ask a specific question about this device

Digital Electrocardiographs are intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The obtained ECG records can help users to analyze and diagnose heart disease. Digital Electrocardiographs shall be used in healthcare facilities by doctors and/or trained healthcare professionals.

Digital Electrocardiographs, E30, E65, E70 and E80, are intended to acquire ECG signals from adult and pediatric patients through body surface ECG electrodes. The obtained ECG records can help users to analyze and diagnose heart disease. There is no specific contraindication identified for the proposed devices.

The proposed devices acquire ECG electrical signals from patient body surface by ECG electrodes. After been amplified, filtered and transferred, the ECG signal waveforms are displayed on the LCD and recorded on the paper through thermal printer.

The components of the proposed devices, Digital Electrocardiograph, include: (1) chest electrodes (2) limb electrodes, (3) cable and (4) Batteries;

The provided text is a 510(k) Summary for a Digital Electrocardiograph. It describes the device's intended use, comparison to a predicate device, and non-clinical tests conducted to establish substantial equivalence. However, it does not contain any information regarding specific acceptance criteria for device performance, a study proving the device meets these criteria, or details about sample sizes, ground truth establishment, or expert involvement as requested.

The summary primarily focuses on demonstrating substantial equivalence to a predicate device by comparing intended use, technological characteristics, and compliance with general safety and performance standards (like IEC 60601-1 and AAMI EC11).

Therefore, based only on the provided text, I cannot fulfill most of your request.

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

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

• Information in text: The document states the device complies with certain standards (IEC 60601-1, IEC 60601-1-2, AAMI / ANSI EC11:1991/(R)2007, ISO 10993-5, ISO 10993-10). These standards define performance requirements, but the specific acceptance criteria and reported device performance against these criteria are not detailed in the summary. The text only mentions "Non clinical tests were conducted to verify that the proposed device met all design specifications" and that it "complies with the following standards."

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

• Information in text: Not available.

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)

• Information in text: Not available. The device "can help users to analyze and diagnose heart disease," implying human interpretation, but no details of an expert-adjudicated test set are provided.

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

• Information in text: Not available.

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

• Information in text: Not available. This device is an electrocardiograph for acquiring ECG signals, not an AI-assisted diagnostic tool discussed in the context of MRMC studies.

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

• Information in text: Not available. The device is described as acquiring signals
  and assisting users in analysis and diagnosis, not a standalone automated diagnostic algorithm.

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

• Information in text: Not available.

8. The sample size for the training set

• Information in text: Not available. (No mention of a training set for an algorithm).

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

• Information in text: Not available. (No mention of a training set for an algorithm).

Summary of available information related to performance/acceptance criteria:

Further Details:

• Test Set Sample Size & Provenance: Not provided.
• Experts for Ground Truth & Qualifications: Not provided.
• Adjudication Method: Not provided.
• MRMC Comparative Effectiveness Study: Not conducted/reported.
• Standalone Performance Study: Not conducted/reported.
• Type of Ground Truth Used: Not provided.
• Training Set Sample Size: Not applicable/provided (device is for signal acquisition, not an AI diagnostic algorithm with a training set).
• Training Set Ground Truth Establishment: Not applicable/provided.

The document focuses on demonstrating substantial equivalence to an existing legally marketed device (predicate device) by showing similar intended use, technological characteristics, and compliance with recognized performance and safety standards for electrocardiographs. It does not provide the kind of detailed clinical study data often found for AI/CADe devices.

Ask a specific question about this device

M800 handheld monitor is intended for continuously monitoring or spot checking of SpO2, PR, ECG and HR of adult, pediatric and neonatal patients in hospital type facilities as well as in the home care environment.

The proposed device, M800 is a handheld patient monitor for continuously monitoring and spot checking of SpO2, PR, ECG and HR of adult, pediatric and neonatal patients.

The proposed device includes three display modes for monitoring results, data review function, and audio and visual alarming function.

It consists of four functional modules, which are power supply module, parameter measurement module, main control and human-device interface.

The provided text describes the M800 Handheld Monitor and its substantial equivalence to a predicate device (M Series Patient Monitor K100046), rather than detailing a study proving the device meets specific acceptance criteria with defined metrics.

However, based on the information provided, we can infer the "acceptance criteria" are compliance with established medical device standards and the "study" is the non-clinical testing performed to demonstrate this compliance and substantial equivalence to the predicate device.

Here's an analysis based on the provided text, addressing the requested points where information is available or can be reasonably inferred:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are primarily defined by compliance with various IEC, ISO, and AAMI/ANSI standards for medical electrical equipment and specific monitoring functions (pulse oximetry, ECG). The "reported device performance" is the claim of compliance with these standards and the listed technical specifications being "Same" or "Similar" to the predicate device.

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

The document does not specify a "test set" in the context of clinical data for performance evaluation. The non-clinical tests relate to engineering and safety standards. Therefore, specific sample sizes for patients or data provenance (country of origin, retrospective/prospective) are not mentioned as this was likely an engineering verification and validation effort against standards, not a clinical trial with patient data.

3. Number of Experts Used to Establish Ground Truth and Qualifications

Not applicable. This was not a study involving expert-established ground truth on clinical data. The "ground truth" for the non-clinical tests would be the compliance requirements of the referenced standards.

4. Adjudication Method for the Test Set

Not applicable. No clinical test set or adjudication method is mentioned.

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

No. The document makes no mention of an MRMC comparative effectiveness study or human readers improving with AI assistance. The device is a patient monitor, not an AI diagnostic tool.

6. Standalone (Algorithm Only) Performance Study

Yes, in essence. The "non-clinical tests" described are a form of standalone performance evaluation, confirming the device's adherence to technical standards and specifications directly, without human interpretation in the loop. The device itself is a measurement tool, and its performance is assessed against known physical or electrical standards.

7. Type of Ground Truth Used

The ground truth used for these non-clinical tests would be the requirements and specifications within the referenced international and national medical device standards (IEC 60601-1, IEC 60601-1-2, ISO 9919, IEC 60601-2-27, AAMI/ANSI EC13). For example, for an SpO2 accuracy test, the ground truth would be a precisely calibrated oxygen saturation level from a reference device or method.

8. Sample Size for the Training Set

Not applicable. This device is not described as utilizing an AI or machine learning algorithm that would require a "training set" of data. Its functionality is based on established physiological measurement principles.

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

Not applicable, as there is no mention of a training set or AI/ML components for this device.

Ask a specific question about this device