Search Results
Found 9 results
510(k) Data Aggregation
(438 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
The Aulisa Oximeter Module (2nd Gen.) is indicated for spot-checking and/or continuous monitoring SpO2 and pulse rate of adult and pediatric patients during non-motion and under well-perfused conditions in hospitals, medical facilities, home care, and subacute environments. The parameters derived by the Aulisa Oximeter Module (2nd Gen.) are transmitted to a commercially available mobile device that runs an Aulisa-developed application for display and review.
The Aulisa Oximeter Module (2nd Gen.) is a wireless, wrist-worn Sensor Module (SM) specifically designed to continuously measure and display a patient's pulse rate and oxygen saturation (SpO2). It uses non-invasive red and infrared technology to measure the vital signs and sends the data to an Aulisa-developed software application as cleared through previous Premarket Notification 510(k) submissions under Guardian Angel Rx GA1000 Series Digital Vital Sign Monitoring System (K162580) & Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System (K203208) using Bluetooth technology. If the physiological data sent from the subject device to the software application falls outside of pre-set limits or when a technical error is detected, both auditory and visual alarm signals are generated through the software application while the subject device backlight of the vital sign will turn to RED colour as a visual alarm signal, to alert the caregiver.
The sensor module uses Bluetooth technology to interact with a commercial, third-party mobile device whether under iOS or Android operating system, such as iPad, iPhone, Google Pixel ... etc. which is not part of this submission. The vital-signs are transmitted to mentioned mobile device that runs Aulisa-developed application for displayed and reviewed. The software application can be download from an official APP store, such as iOS APP store or Google Play.
The provided text is a 510(k) Summary for the Aulisa Oximeter Module (2nd Gen.). This document primarily focuses on demonstrating substantial equivalence to predicate devices, rather than detailing the full study design and results of performance evaluations in the granular detail requested.
However, based on the information provided, here's an attempt to extract the relevant details for the requested categories:
1. Table of Acceptance Criteria and Reported Device Performance
The document mentions "The SpO2 accuracy data were calculated using the Accuracy root-mean-square (ARMS) and the results which indicated that the subject device had an ARMs less than 3 digits during steady-state conditions over the range of 70-100% were in compliance with the specified performance claimed by the manufacturer." This is the primary performance claim related to SpO2 accuracy.
| Acceptance Criteria (Metric) | Acceptance Criteria (Threshold) | Reported Device Performance |
|---|---|---|
| SpO2 Accuracy (ARMS) | Less than 3 digits | Less than 3 digits |
| SpO2 Range for Accuracy | 70-100% | 70-100% |
| Pulse Rate Accuracy | ± 3 digits (or ± 3%) | ± 3 digits (30-290 bpm) or ± 3% (30-290 bpm) |
| Pulse Rate Range for Accuracy | 30-290 bpm | 30-290 bpm |
| Electrical Safety | Pass IEC 60601-1, IEC 60601-1-11 | Pass |
| Temperature and Humidity | Pass IEC 60601-1, IEC 60601-1-11 | Pass |
| Atmospheric Pressure (Altitude) | Pass IEC 60601-1 | Pass |
| Electromagnetic Immunity and Emissions | Pass IEC 60601-1-2 | Pass |
| Performance (General) | Pass ISO 80601-2-61 | Pass |
| Mechanical Durability | Pass IEC 60601-1, IEC 60601-1-11 | Pass |
| Biocompatibility (Cytotoxicity, Sensitization, Irritation) | Pass ISO 10993-5, ISO 10993-10, ISO 10993-23 | Pass |
| Software V&V | Pass FDA Guidance | Pass |
| Security Testing | Pass FDA Guidance | Pass |
| Wireless Coexistence Testing | Pass ANSI C63.27 | Pass |
| Clinical Testing (General) | Pass FDA Guidance | Pass |
| Usability Testing | Pass FDA Guidance | Pass |
| Bench Testing | Pass Manufacturer's specifications | Pass |
| Durability and Performance | Pass Manufacturer's specifications | Pass |
| Battery Life Testing | Pass Manufacturer's specifications | Pass |
2. Sample size used for the test set and the data provenance
- Sample Size: The document only states "The clinical evaluation for SpO2 accuracy was conducted on healthy male and female, light to dark skinned subjects." It does not specify the number of subjects (sample size).
- Data Provenance: The document does not explicitly state the country of origin. It describes the test as a "clinical evaluation," implying a prospective study.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided in the document. For an oximeter, "ground truth" for SpO2 is typically established by arterial blood gas analysis, which does not involve experts in the same way as, for example, image interpretation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
This information is not applicable/provided as the "ground truth" for SpO2 accuracy in oximetry is typically established by a direct comparison to a reference standard (e.g., co-oximetry of arterial blood samples), not by expert 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
This is not applicable. The Aulisa Oximeter Module is a device for directly measuring physiological parameters (SpO2 and pulse rate), not an AI-assisted diagnostic tool that requires human readers for interpretation. Its performance is evaluated against reference standards, not human readers.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, the SpO2 accuracy evaluation (against ISO 80601-2-61 and FDA Guidance) would be considered a standalone performance test of the device's ability to measure SpO2. The device directly measures and outputs these values, so its performance is inherently "standalone."
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The ground truth for SpO2 accuracy in oximetry studies is typically established using arterial blood gas analysis (specifically, co-oximetry) as the reference standard, allowing for precise measurement of arterial oxygen saturation. This is implied by the reference to ISO 80601-2-61, which outlines these methodologies.
8. The sample size for the training set
This information is not applicable/provided. This device is a hardware oximeter module that directly measures physiological signals and processes them to derive SpO2 and pulse rate. It does not appear to involve a machine learning model that would require a separate "training set" in the common sense of AI/ML development. Its "training" would be more akin to calibration and algorithm refinement based on engineering principles and physiological models.
9. How the ground truth for the training set was established
As per point 8, this is not applicable.
Ask a specific question about this device
(412 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
The Aulisa Infant Oximeter Module (2nd Gen.) is indicated for spot-checking and/or continuous monitoring SpO2 and pulse rate of infant patients during non-motion and under well-perfused conditions in hospitals, medical facilities, home care, and subacute environments. The parameters derived by the Aulisa Oximeter Module (2nd Gen.) are transmitted to a commercially available mobile device that runs an Aulisa-developed application for display and review.
The Aulisa Infant Oximeter Module (2nd Gen.) is a wireless, foot-worn Sensor Module (SM) specifically designed to continuously measure and display a patient's pulse rate and oxygen saturation (SpO2). It uses non-invasive red and infrared technology to measure the vital signs and sends the data to an Aulisa-developed software application as cleared through previous Premarket Notification 510(k) submissions under Guardian Angel Rx GA1001 Series Digital Vital Sign Monitoring System (K182822) & Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System (K203208) using Bluetooth technology. If the physiological data sent from the subject device to the software application falls outside of pre-set limits or when a technical error is detected, both auditory and visual alarm signals are generated through the software application while the subject device flashes LED light as a visual alarm signal, to alert the caregiver. The sensor module uses Bluetooth technology to interact with a commercial, third-party mobile device whether under iOS or Android operating system, such as iPad, iPhone, Google Pixel ... etc. which is not part of this submission. The vital-signs are transmitted to mentioned mobile device that runs Aulisa-developed application for displayed and reviewed. The software application can be download from an official APP store, such as iOS APP store or Google Play. The subject device contains an Oximeter Box and an Oximeter Sensor resulting in device configuration and model names as listed below.
The provided text describes the acceptance criteria and performance study for the Aulisa Infant Oximeter Module (2nd Gen.) (GA-OM0018).
Here's the breakdown of the information requested:
1. A table of acceptance criteria and the reported device performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| SpO2 Accuracy (No motion, 70-100%) | ± 3 digits |
| Pulse Rate Accuracy (No motion) | ± 3 digits (30-290 bpm) |
| Electrical Safety | Pass (IEC 60601-1, IEC 60601-1-11) |
| Temperature and Humidity | Pass (IEC 60601-1, IEC 60601-1-11) |
| Atmospheric Pressure (Altitude) | Pass (IEC 60601-1) |
| Electromagnetic Immunity and Emissions | Pass (IEC 60601-1-2) |
| Performance (Pulse Oximeter Standard) | Pass (ISO 80601-2-61) |
| Mechanical Durability | Pass (IEC 60601-1, IEC 60601-1-11) |
| Biocompatibility | Pass (Skin contact: ISO 10993-5, ISO 10993-10, ISO 10993-23) |
| Software V&V | Pass (FDA Guidance) |
| Security Testing | Pass (FDA Guidance) |
| Wireless Coexistence Testing | Pass (ANSI C63.27) |
| Clinical Testing (Pulse Oximeters) | Pass (FDA Guidance) |
| Usability Testing | Pass (FDA Guidance) |
| Bench Testing | Pass (Manufacturer's specifications) |
| Durability and Performance Testing | Pass (Manufacturer's specifications) |
| Battery Life Testing | Pass (Manufacturer's specifications) |
2. Sample size used for the test set and the data provenance
- Sample Size: The document does not explicitly state the exact number of subjects used in the clinical evaluation. It mentions "healthy male and female, light to dark skinned subjects."
- Data Provenance: The study was a clinical evaluation conducted on human subjects. The details on the specific country of origin are not provided, but it pertains to the validation of a device manufactured by "Taiwan Aulisa Medical Devices Technologies, Inc." The study is prospective in nature, as it is a "clinical evaluation for SpO2 accuracy was conducted on healthy male and female..."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not provide information about experts establishing ground truth for the test set or their qualifications. The clinical evaluation describes measuring SpO2 and pulse rate on subjects, which implies comparison against a reference oximeter or arterial blood gas measurements, but doesn't detail the expert review process for ground truth.
4. Adjudication method for the test set
The document does not describe any adjudication method (e.g., 2+1, 3+1) for the test set.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
A Multi-Reader, Multi-Case (MRMC) comparative effectiveness study was not conducted as this device is a pulse oximeter for direct physiological measurement, not an AI-assisted diagnostic tool that involves human readers interpreting cases.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The primary clinical testing described is a standalone performance evaluation of the device's SpO2 accuracy against a reference method (likely arterial blood gas measurements, standard for pulse oximeter accuracy testing per ISO 80601-2-61), without a human-in-the-loop aspect being assessed. The device itself automatically measures and transmits data.
7. The type of ground truth used
The ground truth for SpO2 accuracy in the clinical evaluation was established by comparing the device's measurements against a reference method, typically arterial blood gas measurements (which are the gold standard for SpO2 calibration and accuracy testing in pulse oximetry, as implied by compliance with ISO 80601-2-61). The reported metric is Accuracy root-mean-square (ARMS).
8. The sample size for the training set
The document does not specify a separate "training set" or its sample size. For pulse oximeters, the development and verification typically involve laboratory calibration and then human clinical studies for validation. If any internal model training occurred, those details are not provided in this 510(k) summary.
9. How the ground truth for the training set was established
As no specific training set is mentioned for data-driven model training, the method for establishing its ground truth is not applicable or provided in this document. The device's performance is validated through clinical evaluation in accordance with established standards for pulse oximeters.
Ask a specific question about this device
(245 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
Aulisa Temperature Module (TM0002) is a battery-operated electronic device with indication for use in continuously measuring and monitoring armpit body temperature of adults, pediatrics, and infants and transmission of the measuring result via wireless signal. Aulisa Temperature Module (TM0002) is a non-invasive and reusable device for single patient use with intended environments of use are hospitals, medical facilities, home care, and subacute environments. The parameters derived by the Aulisa Temperature Module (TM0002) are transmitted to a commercially available mobile device that runs an Aulisa-developed application for display and review.
The Aulisa Temperature Module (TM0002) is indicated for continuous armpit body temperature monitoring of adults, pediatrics, and infants which measures body temperature and sends the physiological data to an Aulisa-developed software application as cleared through previous Premarket Notification 510(k) submissions under Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System (K203208) using Bluetooth technology. If the physiological data sent from the subject device to the software application falls outside of pre-set limits or when a technical error is detected, both auditory and visual alarm signals are generated through the software application to alert the caregiver. The sensor module uses Bluetooth technology to interact with a commercial, thirdparty mobile device whether under iOS or Android operating system, such as iPad, iPhone, Google Pixel ... etc. which is not part of this submission. The vital-signs are transmitted to mentioned mobile device that runs Aulisa-developed application for display and review. The software application can be downloaded from an official APP store, such as iOS APP store or Google Play. The Subject Device is reusable, and its intended environments of use are hospitals, medical facilities, home care, and subacute environments.
Here's an analysis of the provided information regarding the acceptance criteria and study proving the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criterion (Standard/Requirement) | Reported Device Performance |
|---|---|
| Electrical Safety (IEC 60601-1, IEC 60601-1-11) | Pass |
| Temperature and Humidity (IEC 60601-1, IEC 60601-1-11) | Pass |
| Atmospheric Pressure (Altitude) (IEC 60601-1) | Pass |
| Electromagnetic Immunity and Emissions (IEC 60601-1-2) | Pass |
| Performance (Temperature Measurement Accuracy) (ISO 80601-2-56, ASTM E1112) | Pass |
| Under 37°C: ± 0.2°C | |
| 37.1~39.0°C: ± 0.1°C | |
| 39°C and above: ± 0.2°C | |
| Mechanical Durability (IEC 60601-1, IEC 60601-1-11) | Pass |
| Biocompatibility (ISO 10993-5, ISO 10993-10) | Pass |
| Wireless Coexistence Testing (ANSI C63.27) | Pass |
| Software V&V (Guidance for the Content of Premarket Submissions for Device Software Functions) | Pass |
| Security Testing (Cybersecurity in Medical Devices, Quality System Considerations and Content of Premarket Submissions) | Pass |
| Usability Testing (Applying Human Factors and Usability Engineering to Medical Devices) | Pass |
| Clinical Electronic Thermometer (Enforcement Policy for Clinical Electronic Thermometers, Guidance on the Content of Premarket Notification [510(K)] Submissions for Clinical Electronic Thermometers) | Pass |
| Bench Testing (Durability and Performance testing, Battery Life Testing) | Pass |
Note on Performance (Temperature Measurement Accuracy): The document explicitly states the specific accuracy values for different temperature ranges, which are considered "Pass" when measured against the standards ISO 80601-2-56 and ASTM E1112. These are the acceptance criteria for the accuracy.
2. Sample Size Used for the Test Set and Data Provenance
The provided document does not specify the sample size used for the test set for any of the reported performance tests. It also does not specify the data provenance (e.g., country of origin, retrospective or prospective) for the accuracy or other performance tests. It only states that "Clinical accuracy testing was conducted to ISO 80601-2-56."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts
The document does not provide information regarding the number of experts used or their qualifications for establishing ground truth. For temperature measurement, the ground truth is typically established by reference thermometers or established methods defined within the testing standards (ISO 80601-2-56 and ASTM E1112), rather than expert consensus in the way it would be for image interpretation.
4. Adjudication Method for the Test Set
The document does not mention any adjudication method like 2+1 or 3+1. For objective performance tests like temperature accuracy, adjudication methods for expert consensus are generally not applicable. The standards themselves define the criteria for "passing" the test.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance
This section is not applicable to the Aulisa Temperature Module (TM0002). This device is a clinical electronic thermometer and not an AI-assisted diagnostic tool that would involve human readers interpreting cases. Therefore, an MRMC comparative effectiveness study or analysis of human reader improvement with AI assistance would not be relevant.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was Done
The device is a hardware module that measures temperature and transmits it. Its "performance" as a standalone device is covered by the performance testing (e.g., accuracy, electrical safety, etc.) which are conducted independent of a human interpreting its output. The output is displayed via an application, but the core measurement accuracy is inherent to the device itself. The document states that "The output temperature of the Subject Device is derived directly from input signal without any adjustment," implying its core function is standalone.
7. The Type of Ground Truth Used
For the core performance claims (e.g., temperature accuracy), the ground truth is established through reference standards as defined by ISO 80601-2-56 and ASTM E1112. These standards specify how to establish laboratory-controlled "true" temperatures to compare against the device's readings. This is a form of scientific/methodological ground truth rather than expert consensus or pathology.
8. The Sample Size for the Training Set
The document does not mention a training set sample size. This is because the Aulisa Temperature Module (TM0002) is a direct measurement device rather than a machine learning or AI-based device that would require a "training set." Its accuracy is based on its sensor technology and calibration, not learned from data.
9. How the Ground Truth for the Training Set Was Established
As there is no mention of a training set for this device, the question of how its ground truth was established is not applicable.
Ask a specific question about this device
(590 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
The Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System (Model GA2000) is indicated for use in measuring, recording, and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR), The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The Oximeter Module(s) is indicated for spot-checking and/or continuous monitoring of SpO2 and PR of adults and pediatrics during non-motion and under well-perfused conditions.
The Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System (Model GA2001) is indicated for use in measuring, recording, and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate (PR). The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The Oximeter Module(s) is indicated for spot-checking and/or continuous monitoring of SpO2 and PR of pediatrics and infants during non-motion and under well-perfused conditions.
The Guardian Angel Rx GA2000 Series Digital Vital Sigm Monitoring System (Model GA2002) is indicated for use in measuring, recording, and displaying body temperature. The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The Thermometer Module is indicated for continuous armpit body temperature monitoring of adults, pediatrics, and infants.
The Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System (Model GA2100) is indicated for use in measuring, recording, and displaying function of arterial hemoglobin (SpO2) and pulse rate (PR) and body temperature. The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The Oximeter Module(s) is indicated for spot-checking and/or continuous monitoring of SpO2 and PR of adults and pediatrics during non-motion and under well-perfused conditions.
The Thermometer Module is indicated for continuous armpit body temperature monitoring of adults, pediatrics, and infants.
The Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System (Model GA2101) is indicated for use in measuring, recording, and displaying function of arterial hemoglobin (SpO2) and pulse rate (PR) and body temperature. The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The Oximeter Module(s) is indicated for spot-checking and/or continuous monitoring of SpO2 and PR of pediatrics and infants during non-motion and under well-perfused conditions.
The Thermometer Module is indicated for continuous armpit body temperature monitoring of adults, pediatrics, and infants.
The subject device is a digital vital sign monitoring system that measures and displays a patient's vital signs, i.e. pulse rate, oxygen saturation (SpO2) and body temperature. It is also equipped with an audio/video camera to monitor the patient in real time. In addition, the subject device provides visual and auditory alarms that alert the caregiver when a patient's vital signs fall outside of pre-set limits or when a technical error is detected. During a physiological alarm event, the vital sign data along with the audio/video data are recorded automatically by the subject device. The caregiver can review the historical data whenever needed.
The sensor module(s) of the subject device detects vital signs and sends out the data to the Receiver/Transponder using Bluetooth technology. The Receiver/Transponder then transmits, via a customer Wi-Fi network, the physiological data along with audio/video signals obtained by an embedded camera to an Aulisa-supplied tablet (i.e. the Display Unit).
The subject device contains a total of three Aulisa sensor modules, Adult/Pediatric Oximeter Module, Infant Oximeter Module, and Thermometer Module. The three Aulisa sensor modules connect to the Receiver/Transponder either independently or simultaneously, resulting in five system configurations and system model names as listed below.
The provided document describes the Guardian Angel Rx GA2000 Series Digital Vital Sign Monitoring System. Here's a breakdown of the acceptance criteria and the study information:
1. Table of Acceptance Criteria and Reported Device Performance
The document presents acceptance criteria primarily for the functional oxygen saturation (SpO2), pulse rate (PR), and body temperature measurements.
| Feature | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Pulse Oximetry (SpO2) | Accuracy (No Motion): ± 3 digits (70-100%) | SpO2 accuracy calculated using root-mean-square (A-rms) was less than 3 digits during steady-state conditions over the range of 70-100%. |
| Pulse Rate (PR) - GA2000/GA2100 | Accuracy (No Motion): ± 3% (30-290 bpm) | The document states SpO2 accuracy was compliant with specified performance; PR accuracy is implicitly covered by consistency with predicate. (Explicit PR accuracy result for the subject device is not separately stated beyond the criteria). |
| Pulse Rate (PR) - GA2001/GA2101 | Accuracy (No Motion): ± 3 digits (18-300 bpm) | The document states SpO2 accuracy was compliant with specified performance; PR accuracy is implicitly covered by consistency with predicate. (Explicit PR accuracy result for the subject device is not separately stated beyond the criteria). |
| Body Temperature (GA2002/GA2100/GA2101) | Accuracy: 89.6°F-107.6°F: ± 0.2°F (32°C-42°C: ± 0.1°C) | The output temperature is derived directly from the input signal without adjustment, implying it meets this specification. |
| Electrical Safety | IEC 60601-1, IEC 60601-1-11 | Pass |
| Temperature and Humidity | IEC 60601-1 | Pass |
| Atmospheric Pressure (Altitude) | IEC 60601-1 | Pass |
| Defibrillation Protection | IEC 60601-1 | Pass |
| Electromagnetic Immunity and Emissions | IEC 60601-1-2 | Pass |
| Performance | ISO 80601-2-61, ASTM E1112, IEC 60601-1-8, IEC 60086 series | Pass |
| Mechanical Durability | IEC 60601-1, IEC 60601-1-11 | Pass |
| Biocompatibility | ISO 10993-5, ISO 10993-10 | Pass |
| Software V&V | FDA Guidance | Pass |
| Bench testing for Accuracy | Manufacturer's specifications | Pass |
| Security Testing | - | Pass |
| Wireless Coexistence Testing | ANSI C63.27 | Pass |
| Durability and Performance testing | Manufacturer's specifications | Pass |
| CR2025 Battery Life Testing | Manufacturer's specifications | Pass |
2. Sample Size and Data Provenance for Test Set
The "clinical evaluation for SpO2 accuracy" was conducted on a test set of "healthy male and female, light to dark skinned subjects."
The document does not specify the exact sample size used for this SpO2 clinical test set.
The data provenance (country of origin, retrospective/prospective) is not specified in the provided text.
3. Number of Experts and Qualifications for Ground Truth
For the SpO2 clinical evaluation, there is no mention of experts establishing ground truth. Instead, the "functional oxygen saturation (SpO2) measurements of the subject device were validated in accordance with ISO 80601-2-61." This standard typically involves comparison against an invasive co-oximeter reference measurement, which is considered the ground truth. There are no experts involved in establishing this physiological ground truth for SpO2.
For body temperature, "the output temperature of the subject device is derived directly from input signal without any adjustment," implying that the ground truth for temperature measurement would be based on a calibrated reference thermometer, also not requiring experts for ground truth establishment.
4. Adjudication Method
The document does not mention an adjudication method for the test set. Given the nature of physiological measurements (SpO2 and temperature), adjudication by multiple experts is typically not part of the validation process, as the ground truth is established through direct physiological measurement by a gold-standard device.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not mentioned in the document. This type of study is more common for diagnostic imaging AI devices where human interpretation needs to be evaluated with and without AI assistance. The Guardian Angel Rx GA2000 Series is a vital sign monitoring system, not an imaging interpretation aid.
6. Standalone Performance Study
Yes, a standalone performance study was done for the algorithm (device-only performance).
The clinical evaluation for SpO2 accuracy was conducted to determine the device's accuracy in measuring SpO2 (A-rms less than 3 digits from 70-100%).
Similarly, the body temperature measurement accuracy and various other technical tests (electrical safety, EMC, mechanical durability, etc.) represent standalone performance evaluations of the device.
7. Type of Ground Truth Used
- For SpO2: The ground truth for SpO2 accuracy was established through comparison with a reference standard as specified by ISO 80601-2-61. This standard typically mandates the use of an invasive co-oximeter for arterial blood gas analysis as the reference ground truth.
- For Body Temperature: The ground truth for body temperature measurement would be a highly accurate and calibrated reference thermometer, as the device's output is derived directly from input signal without any adjustment.
8. Sample Size for the Training Set
The document does not specify any sample size for a training set. This device functions as a sensor and measurement system, rather than an AI/ML model that would require a separate "training set" in the conventional sense. Its performance is validated against physiological standards and predicate devices.
9. How Ground Truth for Training Set was Established
As no training set is mentioned or implied for an AI/ML model, the establishment of its ground truth is not applicable in this context. The validation for this vital sign monitor relies on direct comparison to established physiological measurement standards in a test setting.
Ask a specific question about this device
(60 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
The Aulisa Multiple Patient Digital Vital Sign Monitoring System, MP1000, is intended to provide remote central monitoring and display of information as recorded by multiple Aulisa single-patient monitoring systems, on a central remote screen. The system can be used in a hospital type and clinic environment.
The Aulisa Multiple Patient Digital Vital Sign Monitoring System, MP1000, operates through an Aulisa-developed software installed on a standard personal computer. The system interlinks multiple Aulisa single-patient monitoring systems to display the information as recorded by each single-patient monitoring system on a central remote screen. The system uses standard off-theshelf communication and IT hardware for data transmission.
The information transmitted from single-patient monitoring systems to the MP1000 system includes the physiological parameters and alarm indications. Adjusting alarm settings can only be performed on the Aulisa Display Unit of the single-patient monitoring system. If configured, the MP1000 screen can also be accessed through remote devices, such as other PCs. In addition, patient history data and report files can be viewed, exported, and/or printed.
The provided document is a 510(k) summary for the Aulisa Multiple Patient Digital Vital Sign Monitoring System, MP1000. It describes the device, its intended use, and a comparison with a predicate device. However, it does not contain detailed information about specific acceptance criteria for a performance study (i.e., quantitative metrics like accuracy, sensitivity, specificity, or error rates) or the study that proves the device meets those criteria.
Instead, the document states:
- "Aulisa Multiple Patient Digital Vital Sign Monitoring System is a medical device stand-alone software; all testing was completed and the software has been verified and validated per FDA's Guidance for Industry and FDA Staff, Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."
- "Further, risk management assessment on the subject device was performed per ISO 14971, Medical Devices- Risk Management to verify that it does not raise any new safety and effectiveness issues in comparison to its predicate device."
- "Test results indicate that the subject device complies with its predetermined specifications and the applicable guidance document and standards."
This indicates that software verification and validation, along with risk management, were performed to demonstrate substantial equivalence, rather than a clinical performance study with defined acceptance criteria for diagnostic performance metrics. The device primarily functions as a remote display system that duplicates data from individual monitoring units, implying that its performance is largely contingent on the accuracy of the connected single-patient monitoring systems, which are not the subject of this 510(k) submission's performance section.
Therefore, for your request, I cannot extract the specific details you've asked for directly from this document, as it does not describe a performance study in the typical manner of an AI/diagnostic device (e.g., measuring sensitivity, specificity against ground truth).
Specifically, the document does NOT include information on:
- A table of acceptance criteria and reported device performance: No quantitative performance metrics or acceptance criteria are listed.
- Sample size for the test set and data provenance: Not applicable as no specific diagnostic performance study is detailed.
- Number of experts used to establish ground truth and qualifications: Not applicable.
- Adjudication method for the test set: Not applicable.
- MRMC comparative effectiveness study or effect size: Not applicable.
- Standalone (algorithm only) performance: Not applicable as it's a data display system, not a diagnostic algorithm.
- Type of ground truth used: Not applicable.
- Sample size for the training set: Not applicable (this is not an AI/ML device in the sense of a trained model).
- How ground truth for the training set was established: Not applicable.
The "Summary of Performance Testing" section (5.8) indicates that software verification and validation were performed according to FDA guidance for software in medical devices, and risk management per ISO 14971. This type of testing ensures the software functions as intended, is reliable, and does not pose undue risks, rather than establishing diagnostic accuracy against a clinical ground truth. The device's primary function is to "display of information as recorded by multiple Aulisa single-patient monitoring systems," not to interpret or derive new diagnostic information.
Ask a specific question about this device
(50 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
The Guardian Angel Rx GA2001 Digital Vital Sign Monitoring System is indicated for use in measuring and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate. It is indicated for spot-checking and/or continuous monitoring of pediatrics and infants during non-motion and under well-perfused conditions. The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The subject device is a digital vital sign monitoring system that measures and displays a patient's pulse rate and oxygen saturation (SpO₂). It is also equipped with an audio/video camera to monitor the patient in real time. In addition, the subject device provides visual and auditory alarms that alert the caregiver when a patient's pulse rate and/or SpO2 falls outside of preset limits or when a technical error is detected. During a physiological alarm event, the pulse rate and SpO2 data along with the audio/video data are recorded automatically by the subject device. The caregiver can review the historical data whenever needed.
The system consists of a self-contained foot-worn Sensor Module, a Receiver/Transponder with an embedded audio/video camera and a portable, table-top wireless Display Unit.
It uses non-invasive red and infrared technology to measure the pulse rate and SpO2. The measurements are taken by the Sensor Module and are transmitted to the Receiver/Transponder which delivers the measurements along with audio/video signals to the Display Unit for display, wherein Bluetooth technology is used to transmit data between the Sensor Module and the Receiver/Transponder, and data is transmitted from the Receiver/Transponder to the Display Unit via the Wi-Fi 802.11 band.
Here's an analysis of the acceptance criteria and study information for the Guardian Angel Rx GA2001 Digital Vital Sign Monitoring System, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance:
The document explicitly states acceptance criteria for SpO2 and Pulse Rate accuracy.
| Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| SpO2 Accuracy (no motion, 70-100%) | ± 3 digits | Arms below 3% |
| Pulse Rate Accuracy (18-300 bpm) | ± 3 digits | Not explicitly stated with a performance metric, but the device is stated to meet the ± 3 digits (18-300 bpm) accuracy as per the comparison table and the clinical study confirms SpO2 accuracy, implying overall accuracy. |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size (Test Set): "Over 200 data points were collected." The clinical study focused on collecting data points for SpO2 accuracy.
- Data Provenance: The study was conducted on "healthy subjects" and involved "controlled induced hypoxia." The country of origin for the study is not explicitly stated within the provided text. It is a prospective study as data was "collected" to verify accuracy.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:
The document does not specify the number of experts used or their qualifications for establishing the ground truth. This is common in pulse oximetry studies where ground truth for SpO2 is typically established using a co-oximeter connected to an arterial blood gas sample, which is a direct measurement, not an expert visual interpretation.
4. Adjudication Method for the Test Set:
The document does not mention any adjudication method for the test set. Given the nature of pulse oximetry accuracy studies, where ground truth is typically derived from direct physiological measurements (co-oximetry) rather than subjective interpretation, an adjudication process involving multiple experts is generally not applicable or necessary for the primary accuracy endpoint.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done:
No, an MRMC comparative effectiveness study was not conducted. The study described is a clinical accuracy study for a device measuring physiological parameters, not an interpretive task that would typically involve multiple readers (like radiologists reviewing images). Therefore, there is no effect size of human readers improving with or without AI assistance reported.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:
Yes, the clinical study described is a standalone performance study. It directly assessed the accuracy of the device's SpO2 measurements against a reference standard without human interpretation being part of the primary measurement endpoint.
7. The Type of Ground Truth Used:
The ground truth for SpO2 accuracy was established through controlled induced hypoxia in healthy subjects. This typically involves simultaneously measuring arterial oxygen saturation using a laboratory co-oximeter (considered the gold standard) from arterial blood samples while comparing it to the device's readings. While "co-oximetry" isn't explicitly named, "controlled induced hypoxia" is the standard method for generating a wide range of accurately known SpO2 values.
8. The Sample Size for the Training Set:
The document does not provide information regarding a "training set" or its sample size. This device appears to be a hardware-based physiological monitoring system, not an AI/ML-driven solution that would typically involve a distinct training set for an algorithm. The clinical data mentioned is for performance verification.
9. How the Ground Truth for the Training Set Was Established:
As no training set is mentioned for an AI/ML model, the establishment of ground truth for a training set is not applicable here. The "clinical study" described serves as the validation/test set for the device's accuracy.
Ask a specific question about this device
(148 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
The Guardian Angel Rx GA1001 Digital Vital Sign Monitoring System is indicated for use in measuring and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate. It is indicated for spot-checking and/or continuous monitoring of pediatrics and infants during non-motion and under well-perfused conditions. The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The subject device is a digital vital sign monitoring system that measures and displays a patient's pulse rate and oxygen saturation (SpO2). The subject device consists of a selfcontained foot-worn sensor module (SM) and a portable, table-top wireless display unit (DU). It uses non-invasive red and infrared technology to measure the pulse rate and SpO2. The measurements taken by the SM are wirelessly transmitted to the DU for display using Bluetooth technology. The subject device also provides visual and auditory alarms that alert the caregiver when a patient's pulse rate and/or SpO2 falls outside of preset limits or when a technical error is detected.
Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:
Device: Guardian Angel Rx GA1001 Digital Vital Sign Monitoring System
Purpose: Measures and displays functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate. Primarily for pediatrics and infants during non-motion and well-perfused conditions.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Stated) | Reported Device Performance |
|---|---|
| Pulse Oximetry Accuracy (SpO2): Accuracy (Arms) below 3% over the range of 70%-100% SpO2 | Arms is below 3%, compliant with FDA guidance on Pulse Oximeters - Premarket notification submissions [510(k)]. |
| Electrical Safety: Compliance with IEC 60601-1, IEC 60601-1-11, IEC 60601-1-8 | Device complies with these standards. |
| Electromagnetic Compatibility (EMC): Compliance with IEC 60601-1-2 | Device complies with this standard. |
| Biocompatibility: Meet requirements of ISO 10993-1 (Cytotoxicity, Sensitization, Irritation) | Biocompatibility evaluation conducted, including Cytotoxicity, Sensitization, and Irritation tests. (Implicitly passed as it supports substantial equivalence). |
| Software Verification & Validation: Documentation provided as recommended by FDA guidance. | Software verification and validation testing conducted and documentation provided. (Implicitly passed). |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set (Clinical Study): "Over 200 data points were collected."
- Data Provenance:
- Country of Origin: Not explicitly stated, but the applicant is "Taiwan Aulisa Medical Devices Technologies, Inc." This suggests the clinical study could have been conducted in Taiwan or another location consistent with the applicant's operations.
- Retrospective or Prospective: "Clinical data were collected... to verify the accuracy of the subject device on healthy subjects over the range of 70%-100% SpO2 through controlled induced hypoxia." This indicates a prospective clinical study.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
This device is an oximeter, not an AI/imaging device requiring expert interpretation for ground truth. The ground truth for SpO2 accuracy is established through controlled induced hypoxia measurements against a reference standard (likely arterial blood gas measurements, though not explicitly stated, this is the standard for pulse oximetry accuracy). Therefore, the concept of "experts establishing ground truth" in the context of interpretation (like radiologists for imaging) does not apply here. The expertise required would be in conducting the induced hypoxia study and accurate blood gas analysis.
4. Adjudication Method for the Test Set
Not applicable. The ground truth for pulse oximetry accuracy is derived from physiological measurements (e.g., arterial blood gas analysis under controlled hypoxia), not subjective expert judgment requiring adjudication.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
No, an MRMC comparative effectiveness study was not done. This type of study is relevant for AI-assisted diagnostic tools where human readers interpret cases with and without AI assistance (e.g., radiologists reading medical images). The Guardian Angel Rx GA1001 is a vital sign monitoring system, not an AI-powered diagnostic imaging tool.
6. If a Standalone (algorithm only without human-in-the-loop performance) was done
The clinical study described (measuring SpO2 accuracy through controlled induced hypoxia) is a standalone performance evaluation of the device. It assesses the device's ability to accurately measure SpO2 directly, without human interpretation as part of the primary measurement function. The performance metric "Arms is below 3%" directly reflects the algorithm's (and hardware's) accuracy compared to the reference standard.
7. The Type of Ground Truth Used
The ground truth used for the clinical study was established through controlled induced hypoxia on healthy subjects. In the context of pulse oximetry, this typically involves comparing the device's SpO2 readings to simultaneously measured arterial oxygen saturation (SaO2) values obtained from arterial blood gas (ABG) analysis. The sO2 (and corresponding SaO2) values from the ABG are considered the "ground truth."
8. The Sample Size for the Training Set
The document does not provide information regarding a separate training set or its sample size. For hardware devices with embedded algorithms like pulse oximeters, the "training" (calibration and refinement of algorithms) typically happens during development and might use internal data or general physiological models. The provided study describes the validation/test set used for regulatory submission.
9. How the Ground Truth for the Training Set Was Established
As no information is provided about a distinct "training set" in the context of machine learning, the method for establishing its ground truth is not detailed. For traditional medical device algorithms, the "ground truth" for development and calibration would be established through established scientific principles, extensive physiological data, and potentially iterative testing against reference methods (like ABG) during the R&D phase.
Ask a specific question about this device
(116 days)
Taiwan Aulisa Medical Devices Technologies, Inc.
The Guardian Angel Rx GA2000 Digital Vital Sign Monitoring System is indicated for use in measuring and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate of adult and pediatric patients. It is indicated for spot-checking and/or continuous monitoring of patients during non-motion and under well-perfused conditions. The intended environments of use are hospitals, medical facilities, home care, and subacute environments. This system is a reusable device.
The subject device is a digital vital sign monitoring system that measures and displays a patient's pulse rate and oxygen saturation (SpO₂). It is also equipped with an audio/video camera to monitor the patient in real time. In addition, the subject device provides visual and auditory alarms that alert the caregiver when a patient's pulse rate and/or SpO2 falls outside of preset limits or when a technical error is detected. During a physiological alarm event, the pulse rate and SpO2 data along with the audio/video data are recorded automatically by the subject device. The careqiver can review the historical data whenever needed.
The system consists of a self-contained wrist-worn Sensor Module (SM), a Receiver/ Transponder (RT) with an embedded audio/video camera and a portable, table-top wireless Display Unit (DU).
It uses non-invasive red and infrared technology to measure the pulse rate and SpO2. The measurements are taken by the SM and are transmitted to the RT which delivers the measurements along with audio/video signals to the DU for display, wherein Bluetooth technology is used to transmit data between the SM and the RT, and data is transmitted from the RT to the DU via the Wi-Fi 802.11 band.
The provided text describes the acceptance criteria and a study for the Guardian Angel Rx GA2000 Digital Vital Sign Monitoring System, which measures functional oxygen saturation (SpO2) and pulse rate.
Here's an organized breakdown of the information:
1. Table of Acceptance Criteria and Reported Device Performance:
The document states that the device's accuracy was verified through a clinical study. The acceptance criterion for SpO2 accuracy is explicitly mentioned in relation to the FDA guidance.
| Parameter | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| SpO2 Accuracy | Ams (Accuracy root-mean-square) less than 3 digits (70%-100% SpO2 range) as per FDA guidance on Pulse Oximeters - Premarket notification submissions [510(k)] | Ams is less than 3 digits, compliant with FDA guidance on Pulse Oximeters. |
| Pulse Rate | Not explicitly stated as an acceptance criterion in the provided text, but measured. | Pulse rate measurements were taken. (Specific accuracy value not provided within the criteria section in this document excerpt). |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size for Test Set: "healthy adult subjects" (number not specified, but stated "Over 200 data points were collected").
- Data Provenance: The study involved "healthy adult subjects" and used "controlled induced hypoxia." The country of origin for the data is not specified within the provided text. It is a prospective study as it involved collecting new data on subjects under controlled conditions.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Experts:
The document does not mention the use of experts or their qualifications for establishing ground truth in this context. For pulse oximetry accuracy studies, the "ground truth" (reference measurement of arterial oxygen saturation, SaO2) is typically established through co-oximetry of arterial blood samples, not expert interpretation.
4. Adjudication Method for the Test Set:
Not applicable. The ground truth for pulse oximetry accuracy is derived from direct physiological measurements (co-oximetry), not subjective expert judgment that would require adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
A MRMC comparative effectiveness study was not conducted. This device is a vital sign monitor, and its performance is evaluated based on the accuracy of its physiological measurements against a reference standard, not human interpretation of images or other data. Therefore, an MRMC study related to human reader improvement with AI assistance is not relevant to this type of device.
6. Standalone Performance (Algorithm Only without Human-in-the-Loop Performance):
Yes, the clinical study directly assesses the standalone performance of the device (the oximeter) in measuring SpO2 and pulse rate against a reference standard, without human interpretation of the device's output to determine diagnosis. The Ams value reported represents the algorithm's performance.
7. Type of Ground Truth Used:
The ground truth used was established via physiological measurements during controlled induced hypoxia. While not explicitly detailed in this excerpt, for pulse oximeters, the gold standard for SpO2 "ground truth" is typically fractional arterial oxygen saturation (SaO2) measured by a co-oximeter from arterial blood samples.
8. Sample Size for the Training Set:
The provided text does not specify a training set size. This type of device (an oximeter) typically relies on established physiological principles and signal processing algorithms derived from extensive research and development in pulse oximetry, rather than a "training set" in the machine learning sense for a new AI algorithm. While there's internal algorithm development, the document refers to a clinical study for verification of accuracy, not for training a model.
9. How the Ground Truth for the Training Set Was Established:
As no explicit training set is mentioned in the context of a machine learning model, this question is not fully applicable based on the provided text. The device's underlying technology and ground truth for its development would be based on the established physiological relationship between light absorption and oxygen saturation, validated through extensive physiological studies over decades of pulse oximetry development.
Ask a specific question about this device
(169 days)
TAIWAN AULISA MEDICAL DEVICES TECHNOLOGIES, INC.
The Guardian Angel GA1000 Digital Vital Sign Monitoring System is indicated for use in measuring and displaying functional oxygen saturation of arterial hemoglobin (SpO2) and pulse rate of adult and pediatric patients. It is indicated for spot-checking and / or continuous monitoring of patients during non-motion and under well-perfused conditions. The intended environment of use is hospital. This system is a reusable device.
Aulisa's GA1000 is a digital vital sign monitoring system that measures and displays a patient's pulse rate and oxygen saturation level. The system includes a self-contained wrist-worn Sensor Module and a portable, table-top wireless Display Unit. The Guardian Angel GA1000 Digital Vital Sign Monitoring System is also equipped with an alarm system that alerts the caregiver when a patient's pulse rate is too low or too high and when the patient's SpO2 is too low or too high.
Guardian Angel GA1000 Digital Vital Sign Monitoring System contains the following components.
- Sensor Module ●
- Display Unit ●
- Finger Sensor ●
- Sensor Module wristband ●
- Sensor Module Charging Adaptor ●
- Display Unit Charging Adaptor ●
- . Display Unit Stand
The GA1000 measures SpO2 and pulse rate based on transmittance technology, measuring the absorbance of red and infrared light passed through the tissue.
The GA1000 uses Bluetooth v4.0 to transmit data between the wrist-worn Sensor Module and the wireless Display Unit. Both the Sensor Module and the Display Unit is Bluetooth® 4.0 compatible.
The GA1000 uses non-invasive red and infrared LED sensors to measure the functional blood oxygen saturation and pulse rate. The measurements are wirelessly transmitted to the Display Unit, which displays the measurements using a Liquid-Crystal-Display (LCD) panel. The system provides adjustable visual and audio oxygen saturation, and pulse rate alarms through the LCD panel and speakers. Additional alarms are featured, including low battery on the Sensor Module, Sensor Cable disconnection, Sensor Module disconnection, Sensor Cable Probe fault, Sensor Probe detached from patient, Display Unit battery low.
Here's an analysis of the acceptance criteria and study information for the Guardian Angel GA1000 Digital Vital Sign Monitoring System, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Standard / Guidance) | Reported Device Performance (Guardian Angel GA1000) |
|---|---|
| SpO2 Accuracy (Declared Range: 70-100%, No Motion) | Adults/Pediatrics: 3 digits (Specific sensor types: SC100M, ENSC100M; Adults: SC100L, ENSC100L) |
| Pulse Rate Accuracy (No Motion) | Adults/Pediatrics: ±3% (Specific sensor types: SC100M, SC100L, ENSC100M, ENSC100L) |
| SpO2 Accuracy in induced hypoxia (70-100% SpO2) | Arms of each sensor is below 3% (compliant with FDA guidance on Pulse Oximeter - Premarket notification submissions [510(k)]: Guidance for Industry and Food and Drug Administration staff, Issued March 4th, 2013) |
| Electrical Safety (IEC 60601-1:2005) | Compliant with IEC 60601-1 |
| Biocompatibility (ISO 10993-10: 2010, ISO 10993-5:2009) | Biocompatible for patient contact materials; compliant with ISO 10993-5 and ISO 10993-10 |
| Electrical Safety & EMC (IEC 60601-1-2:2007) | Compliant with IEC 60601-1-2 |
| Alarm System (IEC 60601-1-8:2006) | Compliant with IEC 60601-1-8 |
| Wireless Coexistence (FDA Guidance Radio Frequency Wireless Technology in Medical Devices (2013)) | Tested for Radio Frequency Compatibility and Emissions/Immunity Tests |
| Software Verification (IEC 62304:2006, FDA Guidance Off-The-Shelf Software Use in Medical Devices (1999)) | Compliant with IEC 62304 and FDA Guidance Off-The-Shelf Software Use in Medical Devices (1999) |
| Pulse Oximetry Testing (ISO 80601-2-61:2011, FDA Pulse Oximeters Guidance (2013)) | Compliant with ISO 80601-2-61 and FDA Pulse Oximeters Guidance (2013) |
| Functional Test | Performed |
| Push, Impact, and Drop Test | Performed |
| Particulate and Water Ingress Test | Performed |
| Temperature and Humidity Test | Performed |
| Battery Life Test | Performed |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for SpO2 Accuracy (Clinical Testing): "Over 200 data points were collected for each sensor." This implies the sample size refers to the number of data points, not necessarily individual subjects.
- Data Provenance: The study was conducted on "healthy adult subjects." The document does not specify the country of origin of the data, but the submitting company is based in Taiwan. The study was prospective in nature, involving induced hypoxia.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
The document does not provide information on the number or qualifications of experts used to establish the ground truth for the clinical test set. For pulse oximetry, the ground truth for SpO2 is typically established using a co-oximeter on arterial blood samples, which is a laboratory measurement rather than an expert consensus process.
4. Adjudication Method for the Test Set
The document does not specify an adjudication method for the clinical test set. For pulse oximetry accuracy during induced hypoxia, the comparison is typically made between the device reading and the gold standard co-oximetry reading, rather than relying on expert adjudication.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed. This type of study is more common for diagnostic imaging AI systems where human readers interpret medical images. The Guardian Angel GA1000 is a vital sign monitoring device.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
Yes, a standalone performance study was conducted. The clinical testing described for SpO2 accuracy (induced hypoxia study) and the various non-clinical tests (electrical safety, EMC, software, etc.) evaluate the device's performance in isolation, without human intervention in the core measurement and algorithm functionality.
7. Type of Ground Truth Used
For the clinical testing of SpO2 accuracy, the ground truth was established through controlled induced hypoxia conditions, implying comparison against a reference method such as co-oximetry from arterial blood samples (though co-oximetry is not explicitly named, it's the standard for this type of testing).
8. Sample Size for the Training Set
The document does not specify the sample size for any training set. As this device appears to be primarily an embedded system for measuring vital signs, it may not rely on a "training set" in the same way a machine learning-based AI diagnostic tool would. If there is any internal algorithm tuning or calibration, the details are not provided.
9. How the Ground Truth for the Training Set Was Established
Since no training set information is provided, the method for establishing its ground truth is also not specified.
Ask a specific question about this device
Page 1 of 1