(261 days)
The intended use of the iBed™ Wireless with iBed™ Mobile accessory is to assist healthcare professionals in setting, adjusting, and monitoring specific bed parameters from a different location within the healthcare delivery organization's campus. The iBed™ Wireless with iBed™ Mobile accessory is intended to be used only with Stryker Medical's AC-powered adjustable hospital beds that have been verified and validated with the iBed™ Wireless software and is not intended to provide information on non-Stryker Medical beds. The iBed™ Wireless with iBed™ Mobile accessory is intended to only transfer bed status and parameter data and does not store this data.
The Model 5212 iBed™ Wireless with iBed™ Mobile consists of iBed™ Wireless (WiFi module) and the iBed™ Mobile software application that is intended to be used with Stryker Medical's ACpowered adjustable hospital beds within a healthcare delivery organization. The iBed™ Wireless with iBed™ Mobile device accessory is an updated software platform that provides bi-directional data transmission between Stryker Medical's AC-powered adjustable hospital beds equipped with iBed™ Wireless, the healthcare delivery organization's server (owned and maintained by the healthcare delivery organization), and a healthcare professional's handheld electronic device. It is a convenience tool facilitating bi-directional data transmission of bed status data and parameters allowing healthcare professionals the ability to set, adjust, and monitor bed status from a remote location within the healthcare delivery organization facility.
This document is a 510(k) premarket notification for the "iBed™ Wireless with iBed™ Mobile" device, focusing on demonstrating substantial equivalence to a predicate device. It does not describe a clinical study that proves the device meets specific performance acceptance criteria for diagnostic or clinical effectiveness functions in the way an AI/ML medical device submission would.
The device is an accessory to hospital beds, providing healthcare professionals the ability to remotely set, adjust, and monitor bed parameters. The key difference from the predicate device (iBed™ Wireless with iBed™ Awareness, K103536) is the addition of bi-directional communication, allowing remote adjustment of parameters, whereas the predicate only allowed remote monitoring.
Therefore, the acceptance criteria and study described are related to engineering performance, software functionality, and safety rather than a diagnostic accuracy or clinical outcome study involving human readers or AI.
Here's an analysis based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not present a formal table of quantitative acceptance criteria for performance metrics (such as sensitivity, specificity, accuracy) typically seen in AI/ML medical device submissions. Instead, it describes general categories of testing and their purpose:
| Acceptance Criterion (Implicit) | Reported Device Performance (Summary) |
|---|---|
| Software Functionality (Bi-directional Capability) | "Software verification testing was conducted to ensure the bi-directional capability performed according to specification." |
| Integrated System Performance (Bed, Firmware, iBed™ Mobile) | "Bench performance testing was conducted to ensure the bed software, firmware, and iBed™ Mobile performed together according to specification." |
| Usability/Design Validation (Remote Parameter Management) | "Design validation testing was conducted in a simulated-use environment by health care professionals. Users were successfully able to set, adjust, and monitor bed status parameters from remote locations within the healthcare delivery organization as intended." |
| Safety and Compliance (Electrical, Wireless, Software, Risk) | The device was "designed, tested, and confirmed to comply with recognized safety and performance standards applicable to General Healthcare facility Medical Devices." (References include IEC 60601 series for electrical safety, IEEE 802.11 for WiFi, IEC 62304 for software lifecycle, ISO 14971 for risk management, and various FDA guidance documents for software, cybersecurity, EMC, and human factors.) Specific tests mentioned include Signal Integrity, Integration (Graybox, Software-to-Software, Software-to-Hardware), Lifecycle, Power Cycle, Low Power, Max Power Consumption, Security, WiFi Interoperability, Coexistence, Durability, Environmental, Static Analysis, Power Short, Blackbox, Performance, System, Usability, Torture Track, Drop Test, Box and Label Chemical and Cleaning, Roaming Test, Targeted Vulnerability Testing, Internal Testing, Impact Test, and Penetration. The conclusion is that differences "do not raise new questions of safety and effectiveness." |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: Not specified in terms of number of beds, users, or distinct test cases beyond the general descriptions of "testing" and "design validation." This is typical for a 510(k) focusing on engineering and software validation for a non-AI accessory.
- Data Provenance: The testing appears to be primarily conducted internally by Stryker Medical in a simulated environment ("simulated-use environment"). No mention of external or real-world clinical data from specific countries. The testing is prospective in nature, as it's part of the development and validation process for the device.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- "Design validation testing was conducted in a simulated-use environment by health care professionals."
- The number of healthcare professionals is not specified.
- Their qualifications are generally stated as "health care professionals," but no specific details (e.g., specific roles, years of experience, board certifications) are provided. Their role in "establishing ground truth" is less about making a clinical judgment (like diagnosing a condition) and more about confirming the device's functionality and usability aligns with their professional needs for bed management.
4. Adjudication Method for the Test Set
- No formal adjudication method is mentioned, as the "ground truth" is based on the device's adherence to its functional specifications and successful operation by healthcare professionals in a simulated environment, rather than a subjective interpretation task (e.g., image reading). The focus is on technical verification and validation.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No MRMC study was performed. The document explicitly states: "Clinical Studies were not required to demonstrate substantial equivalence to the predicate device."
- This device is an accessory for remote bed management, not a diagnostic tool where human readers interpret data. Therefore, a comparative effectiveness study measuring human reader improvement with AI assistance is not applicable.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- No standalone performance study in the context of an AI algorithm's independent diagnostic accuracy was performed.
- The device's "standalone" performance would be its ability to transmit and receive data, and apply parameter changes correctly, as verified through "software verification testing" and "bench performance testing." This is covered by the engineering and software validation.
7. Type of Ground Truth Used
- The "ground truth" for this device's validation is primarily engineering specifications, functional requirements, and user-defined operational needs.
- For software and bench testing, ground truth is whether the system performs "according to specification."
- For usability/design validation, ground truth is whether healthcare professionals can "successfully set, adjust, and monitor bed status parameters... as intended."
- It is not expert consensus on a clinical condition, pathology reports, or patient outcomes data.
8. Sample Size for the Training Set
- Not applicable. This device is an accessory with defined functional capabilities, not a machine learning or AI algorithm that "learns" from a training set. Its functionality is hard-coded based on design specifications.
9. How Ground Truth for the Training Set Was Established
- Not applicable. As stated above, there is no "training set" for this device. Its "ground truth" relates to its engineered design and verified performance against those design requirements.
§ 880.5100 AC-powered adjustable hospital bed.
(a)
Identification. An AC-powered adjustable hospital bed is a device intended for medical purposes that consists of a bed with a built-in electric motor and remote controls that can be operated by the patient to adjust the height and surface contour of the bed. The device includes movable and latchable side rails.(b)
Classification. Class II (special controls). The device is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to § 880.9.