(198 days)
The EarlySense Bed Sensing Unit is an accessory that is compatible with bedside units of EarlySense Systems (Models 2.0 and InSight) intended for continuous measurement of respiration rate, heart rate and movement, in an automatic contact-less manner. Environment of use for the accessory is defined as per compatible cleared bedside units labeling: EarlySense 2.0 - at home, in hospital or clinic setting and InSight - in hospital or clinic setting. The device is indicated for use in children, adolescents and adults. The operation of the EarlySense system has been studied in children (weight ≥10 Kg) and adults (weight
EarlySense is submitting a new model for its Bed Sensing Unit to be used with cleared EarlySense bedside unit models (EarlySense 2.0 -K131379 and EarlySense InSight -K152911) which are intended for contactless measurement of heart rate (HR), respiratory rate (RR) and motion. Similar to the cleared Bed Sensing units, the subject device is placed under the bed mattress and connected to supporting bedside unit, to allow contactless measurements of HR, RR and motion and detection of bed exit. The modification of the cleared sensing unit includes addition of two load cells elements intended to be used in the Bed Exit feature of the system. The cleared and subject device share exactly the same intended use, the same fundamental functionality and similar types of components, and the same fundamental principles and mode of operation. As also described above, the modification that includes addition of load cells is not considered to affect the system performance. The subject device is also compatible with the existing optional accessories of the cleared sensor, i.e., extension cable and solid metal plate. Utilization of extension cable is to allow placing the sensing unit under the mattress farther than 3 meters from compatible bedside units. The solid metal plate can be used for beds that have un-flat surface (such as grid like).
The provided text describes the EarlySense Bed Sensing Unit and its substantial equivalence to predicate devices, but it does not contain acceptance criteria or detailed results from a study proving the device meets those criteria in a format that would allow filling out all the requested fields.
The document states that the modification to the cleared sensing unit (addition of two load cell elements) did not affect the system performance. The performance data presented focuses on verifying that the outputs of the modified device are similar to the predicate device and within system algorithms' specifications, rather than explicitly stating and demonstrating achievement of specific, quantitative performance acceptance criteria for heart rate or respiration rate accuracy.
Therefore, I cannot provide a complete answer to all parts of your request. However, I can extract what is available regarding performance and testing.
Here's an analysis of what information is available and what is missing:
Information Available:
- Device Performance (Comparative): "Bench testing results showed that in all relating parameters the signals from the sensing unit were similar to the predicate sensor and all parameters were within system's algorithms specification. In addition, tests were performed to compare performance of the sensing unit to predicate sensor in providing 'time to alert' for bed exit notification. Controlled experiments showed that the time to alert for bed exit notifications are similar for both sensors, thus addition of the load cells does not affect system's performance and the sensing unit is substantially equivalent to the cleared sensor."
Information NOT Available (and thus cannot be filled in):
- Specific Acceptance Criteria: The document does not explicitly state quantitative acceptance criteria (e.g., "Accuracy of respiration rate shall be within X bpm of reference"). It only states that the modified device's signals were "similar" to the predicate and "within system's algorithms specification."
- Reported Device Performance (against specific criteria): Since specific criteria aren't provided, performance against them cannot be reported.
- Sample Size for Test Set: Not specified. The document mentions "controlled experiments" for bed exit, but no numbers.
- Data Provenance: Not specified (e.g., country of origin, retrospective/prospective).
- Number of Experts for Ground Truth: Not specified.
- Qualifications of Experts: Not specified.
- Adjudication Method: Not specified.
- Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: Not mentioned, and likely not applicable for a bed sensing unit measuring vital signs.
- Effect size of human readers with AI vs. without AI assistance: Not applicable.
- Standalone (algorithm only) performance: The performance data focuses on the new component (load cells) and its similarity to the predicate. The overall system (EarlySense System Models 2.0 and InSight) with the Bed Sensing Unit measures HR, RR, and movement, and its performance was likely established in prior 510(k)s (K131379 and K152911). This document asserts that the new bed sensing unit does not negatively impact that performance.
- Type of Ground Truth: Not explicitly stated, though for vital signs, it would typically be a reference device or manual measurement.
- Sample Size for Training Set: Not applicable for this submission, as the focus is on a hardware modification and its impact on signal characteristics and similarity to a predicate. It's not a new algorithm being trained.
- How Ground Truth for Training Set was Established: Not applicable.
Summary of Available Information:
1. A table of acceptance criteria and the reported device performance
| Performance Metric (Implicit) | Acceptance Criteria (Implicit) | Reported Device Performance |
|---|---|---|
| Signal characteristics (HR, RR, motion) | Signals (amplitudes, signal-to-noise ratios, time domain, frequency domain, spectral intensities) from the subject device should be "similar" to the predicate sensor and "within system's algorithms specification." | Bench testing results showed that in all relating parameters, the signals from the sensing unit were similar to the predicate sensor and all parameters were within system's algorithms specification. |
| "Time to alert" for bed exit | "Time to alert" for bed exit notifications should be "similar" for the subject device to the predicate sensor. | Controlled experiments showed that the time to alert for bed exit notifications are similar for both sensors, thus addition of the load cells does not affect system's performance and the sensing unit is substantially equivalent to the cleared sensor. |
2. Sample sized used for the test set and the data provenance
- Sample Size: Not specified. The document mentions "controlled experiments" and "bench tests" but provides no participant or case numbers.
- Data Provenance: Not specified.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not specified.
4. Adjudication method for the test set
- Not specified.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- No MRMC study was reported. This type of study is not applicable given the nature of the device (a vital signs bed sensing unit).
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- The performance data provided is related to the hardware component (Bed Sensing Unit) itself, assessing its signal characteristics compared to an earlier version. The system's algorithms process these signals, and the focus of this 510(k) is that the new hardware does not negatively impact the algorithmic performance already established. The document states, "Bench tests were performed to verify that the heart beat and respiration signals obtained from the subject device are similar to its predicate device, and to validate that the addition of load cells do not affect signal parameters as required by the EarlySense system's algorithms, to maintain specifications."
7. The type of ground truth used
- For heart rate and respiration rate signal similarity, the ground truth was effectively the predicate device's signals and the system's algorithms specifications. For bed exit "time to alert," the ground truth was implied to be direct observation in "controlled experiments."
8. The sample size for the training set
- Not applicable. This submission is for a hardware modification to an existing device, not a new algorithm training.
9. How the ground truth for the training set was established
- Not applicable.
§ 868.2375 Breathing frequency monitor.
(a)
Identification. A breathing (ventilatory) frequency monitor is a device intended to measure or monitor a patient's respiratory rate. The device may provide an audible or visible alarm when the respiratory rate, averaged over time, is outside operator settable alarm limits. This device does not include the apnea monitor classified in § 868.2377.(b)
Classification. Class II (performance standards).