Search Results
Found 1 results
510(k) Data Aggregation
(156 days)
The EPAD is intended for use in monitoring neurological status by recording somatosensory evoked potentials (SSEP) or assessing the neuromuscular junction (NMJ).
The EPAD system consists of the following components/accessories:
EPAD Headbox EPAD Headbox Power Supply EPAD Tablet Computer (includes power supply and USB cable) Stimulator Left Blue Cable Assembly (110 inches) Stimulator Right Yellow Cable Assembly (110 inches) Acquisition Left Red Cable Assembly (91 inches) Acquisition Right White Cable Assembly (92 inches) Stimulator Left Blue Short Cable Assembly (67 inches) Stimulator Right Yellow Short Cable. Assembly (67 inches) Acquisition Left Red Short Cable Assembly (44 inches) Acquisition Right White Short Cable Assembly (72 inches) Adapter Cable for EPAD Headbox (for leakage current testing)
Upper Limb Electrodes package
Lower Limb Electrodes package
The EPAD Headbox contains a complete data acquisition system that has built-in amplifiers, analog to digital converters, and digital signal processors. User interface is via tablet touchscreen computer provided with the EPAD System and running the Android operating system. The EPAD software application is preloaded onto the tablet. Data can be transferred to an external computer for archiving purposes. Communication between the EPAD Headbox and tablet is via Bluetooth wireless or USB connection.
Electrode cables are provided for left and right stimulation and left and right acquisition, color coded for correct connection to the EPAD Headbox: Custom cutaneous electrodes for stimulus and acquisition are provided by SafeOp for use with the EPAD. A total of 11 electrodes are applied for full patient monitoring (upper and lower limbs). The SafeOp electrodes are wet qel, single patient use, disposable, and biocompatible for short term (<24 hours) use on intact skin.
Here's a breakdown of the acceptance criteria and study information for the EPAD™ device, based on the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
The 510(k) summary for the EPAD™ primarily establishes substantial equivalence through a comparison with predicate devices and nonclinical testing that confirms safety and performance against established standards. Direct "acceptance criteria" for diagnostic performance (like sensitivity/specificity) are not explicitly stated for a clinical study comparing the AI's diagnostic ability to a gold standard. Instead, the acceptance is based on meeting technical specifications and demonstrating safety and effectiveness.
However, we can infer performance criteria from the non-clinical testing performed and the comparison to predicate devices. The "reported device performance" refers to the results of these tests.
| Category | Acceptance Criteria (Inferred/Stated from Predicates/Standards) | Reported Device Performance | Study proving compliance |
|---|---|---|---|
| Alert Algorithm Performance | Ability to detect waveform changes of reduced amplitude (>50%) and increased latency (>10%) under minimal, moderate, and extreme noise conditions. | The EPAD was able to detect waveform changes of reduced amplitude (>50%) and increased latency (>10%) under all noise conditions (minimal, moderate, and extreme). | Alert Algorithm Testing |
| Software Efficacy | All software requirements are fulfilled and all software hazards mitigated with no unresolved anomalies. | All software requirements have been fulfilled and all software hazards have been mitigated. There are no unresolved anomalies in the EPAD software. | Software verification and validation testing |
| Biocompatibility | Safe for short-term (<24 hours) contact with intact skin (meeting ISO 10993-1 requirements for cytotoxicity, sensitization, and irritation/intracutaneous reactivity). | Electrodes are safe for short-term (<24 hours) contact with intact skin. Specific testing included cytotoxicity, sensitization, and irritation/intracutaneous reactivity, meeting ISO 10993-1. | Biocompatibility testing on patient-contacting materials |
| Shelf Life (Electrodes) | 15-month shelf life with all functional tests passed following accelerated aging (including Impedance monitoring, visual inspection, ANSI/AAMI EC12:2000 Section 5.2.2 for Disposable ECG Electrodes tests, Electrode Impedance values on forearm, and Electrode evoked potential responses). | All tests conducted following accelerated aging of the electrodes in their final packaging were passed, establishing a 15-month shelf life. This included impedance monitoring, visual inspection, ANSI/AAMI EC12:2000 tests, electrode impedance values on forearm, and electrode evoked potential responses. | Accelerated aging testing |
| Electrical Safety | Compliance with UL60601-1, IEC 60601-1-1, IEC 60601-1-2, and IEC 60601-2-40 standards. | All tests passed with no need for device modifications for UL60601-1, IEC 60601-1-1, IEC 60601-1-2, and IEC 60601-2-40. | Electrical Safety and Electromagnetic Compatibility Testing |
| EMC | Compliance with IEC 60601-1-2 standard. | All tests passed with no need for device modifications for IEC 60601-1-2. | Electrical Safety and Electromagnetic Compatibility Testing |
| FCC Certification | Compliance with FCC regulations under 47 CFR Part 15 for Bluetooth wireless technology. | All tests passed related to FCC Certification for the Bluetooth wireless technology. | FCC Certification Testing (conducted by tablet manufacturer) |
| Signal Quality | Acceptable noise level peak-to-peak, CMRR adjustment, LF/HF filter performance, DC offset, cross-talk, gain, and impedance circuit qualification on each channel. | Tests validate the quality of waveform signals from Headbox to Tablet, including noise level peak-to-peak, CMRR adjustment, filter performance (LF, HF), DC offset, cross-talk, gain, and impedance circuit qualification. All test results met the test protocol acceptance criteria. (Specific quantitative results not provided in summary). | EPAD Signal Quality Tests (Functional Performance Testing) |
| Wireless Coexistence | No observed decline in data transmission between the EPAD Headbox and Tablet in the presence of multiple simultaneously transmitting wireless devices. | There was no observed decline in data transmission between the EPAD Headbox and Tablet under the test conditions (multiple wireless devices transmitting simultaneously). | Wireless Coexistence Testing (Functional Performance Testing) |
| Electrode Functional | Meet requirements per AAMI/ANSI EC12:2000: Disposable ECG Electrodes (Section 5.2.2: 10-Hz AC impedance, individual pair; Combined offset instability and internal noise; DC voltage offset, Bias test). | EPAD electrodes meet functional test requirements per AAMI/ANSI EC12:2000: Disposable ECG Electrodes (specifically Section 5.2.2 tests: 10-Hz AC impedance, combined offset instability and internal noise, and DC voltage offset/bias test). | Accelerated aging testing (as part of shelf-life) and likely separate functional performance testing specifically for electrodes. |
| Max Voltage | Within acceptable range compared to predicates (similar expected max current). Protektor 32 has 400VDC with 4kΩ load. | 380 VDC with 3.8 kΩ load impedance. Deemed substantially equivalent as "Slightly lower maximum driving voltage but same expected maximum current." | (Comparison to Predicate) |
| Pulse Duration | Within range offered by predicates and appropriate for EPAD modes. Predicates range from 0.05 msec to 1.0 msec. | Choose from 0.1, 0.2 or 0.3 msec settings. Deemed appropriate for EPAD modes. | (Comparison to Predicate) |
| Repetition Rate | Within range offered by predicates and appropriate for EPAD modes. Predicates range from 0.1 Hz to 1000 Hz. | 0.1 to 50 Hz. Deemed appropriate for EPAD modes. | (Comparison to Predicate) |
| Timebase | Within range offered by predicates and appropriate for EPAD modes. Protektor 32 has 0.5 ms/division to 500 ms/division. | 2 ms/division to 10 ms/division. Deemed appropriate for EPAD modes. | (Comparison to Predicate) |
| Sensitivity | Within range offered by predicates and appropriate for EPAD modes. Protektor 32 has 0.1 µV/division to 5 mV/division. | 0.5 µV/division to 20 µV/division. Deemed appropriate for EPAD modes. | (Comparison to Predicate) |
| High Frequency Filter | Appropriate for EPAD modes (SSEP and NMJ tests requiring HFF of 3 kHz), even if different from general-purpose predicate devices. Predicate Protektor 32 has 30 Hz to 15 kHz. | 30 Hz to 3 kHz. Justified as appropriate for SSEP and NMJ tests. | (Comparison to Predicate) |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set: Non-clinical testing mainly involved hardware, software, and component-level assessments rather than a clinical "test set" of patient data for diagnostic performance.
- For the Alert Algorithm Testing, the summary states it was tested "under minimal, moderate, and extreme noise conditions," implying simulated or laboratory conditions rather than patient data. No specific number of cases or data provenance is mentioned.
- For Electrode Functional Testing (AAMI/ANSI EC12:2000), these are standard bench tests on electrode samples. The sample size would be number of electrodes tested, but this is not specified.
- For Biocompatibility Testing, the sample size would be biological assays and animal tests. Not specified in summary.
- Data Provenance: Not applicable for most non-clinical tests mentioned. For any implicitly simulated data (like for the alert algorithm), no provenance (country, retrospective/prospective) is provided.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- This information is not provided in the summary. Since the testing described is primarily non-clinical (engineering, software, biocompatibility), there was no "ground truth" derived from human experts for a diagnostic task in the traditional sense. The alert algorithm's performance criteria (amplitude and latency changes) are predefined thresholds not requiring expert adjudication in the context of this summary.
4. Adjudication Method for the Test Set
- Not applicable / None described. The non-clinical testing does not appear to involve human observers or an adjudication process for ground truth.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- No MRMC comparative effectiveness study was done or described in this 510(k) summary. The EPAD incorporates an alert algorithm, but its performance is evaluated in a standalone manner against predefined thresholds, not as an AI-assisted diagnostic tool for human readers in a clinical study.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Yes, a form of standalone performance was assessed for the "Alert Algorithm Testing." The algorithm's ability to detect waveform changes (reduced amplitude and increased latency) was tested independently under various noise conditions.
- Performance: "The EPAD was able to detect waveform changes of reduced amplitude (>50%) and increased latency (>10%) under all noise conditions."
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
- For the Alert Algorithm: The "ground truth" was defined by predefined quantitative thresholds for waveform changes: >50% amplitude reduction and >10% latency increase. This is a technical, rather than a clinical, ground truth.
- For other non-clinical tests (e.g., electrical safety, biocompatibility, signal quality), the ground truth is compliance with established engineering standards and specifications.
8. The Sample Size for the Training Set
- The summary does not provide information on a training set sample size. As a 510(k) submission for a device primarily focused on evoked potential recording and basic alert logic, it doesn't describe the development of a complex machine learning model requiring a distinct training set. If the alert algorithm involved any learned parameters, this information is not detailed.
9. How the Ground Truth for the Training Set was Established
- Not detailed / Not applicable as a distinct training set and its ground truth establishment are not discussed in this 510(k) summary. If the alert algorithm's thresholds were derived from clinical data, the method for establishing that ground truth is not provided.
Ask a specific question about this device
Page 1 of 1