(72 days)
The 3B and BMC RESmart CPAP and Auto CPAP Systems are intended to deliver positive pressure for the treatment of Obstructive Sleep Apnea. The optional integrated humidifier is indicated for the humidification and warming of air from the flow generator device. These devices are intended for single patient use by prescription in the home or hospital/institutional environment on adult patients.
The RESmart CPAP and Auto CPAP System is a microprocessorcontrolled, blower-based system that generates positive airway pressure from 4 to 20 cm H2O. The device is intended for use with a patient circuit that is used to connect the device to the patient interface (mask). The RESmart CPAP and Auto CPAP device has been modified to include porting the iCode software to a web-based application. The basic functional and performance characteristic of the RESmart CPAP and Auto CPAP is unchanged from the predicate device RESmart CPAP and Auto CPAP (K110629).
The provided text is a 510(k) Summary for the RESmart CPAP/Auto CPAP device (K131707). It describes modifications made to the iCode software feature of an existing device (K110629), porting it to a web-based application and developing a smartphone application for it.
The key takeaway is that this submission K131707 is NOT about the performance of the CPAP device itself in treating sleep apnea, but rather about the software modifications to the iCode feature, which is used for compliance reporting. The document explicitly states: "The basic functional and performance characteristic of the RESmart CPAP and Auto CPAP is unchanged from the predicate device RESmart CPAP and Auto CPAP (K110629)." and "There are no changes in logic, Rather the extent of the device algorithm, or function. modification is a simple change from a desktop environment to a web server based environment."
Therefore, the acceptance criteria and study information requested in the prompt, particularly those pertaining to medical device performance (e.g., effect size of human readers improving with AI, standalone algorithm performance, ground truth for medical outcomes), are not applicable to this specific 510(k) submission.
Here's the breakdown based on the provided text, focusing on the software modifications:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Software) | Reported Device Performance (Software) |
|---|---|
| Software Verification & Validation of iCode Report Generator | Demonstrated in "Software Requirement Specifications of iCode Report Generator, App. A" and "System Test Report of iCode Report Generator, App. B". |
| Software Verification & Validation of iCode Smartphone Application | Demonstrated in "Software Requirements Specification for 3B/BMC iCode Smartphone Applications, App. C" and "System Test Report of iCode Smartphone Application, App. D". |
| Porting iCode to web-based application without changing logic, algorithm, or function. | Successfully ported to a web-based application ("iCode Report Generator"). "No changes in logic, device algorithm, or function." |
| Smartphone application's ability to manually enter iCode string. | Smartphone application allows manual entry after optical character recognition (OCR) from a photograph of the device LCD. |
| Maintenance of substantial equivalence to predicate device (K110629). | "The RESmart CPAP and Auto CPAP System remain substantially equivalent to the RESmart CPAP and Auto CPAP System (K110629)... All tests were verified to meet the required acceptance criteria." |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: Not applicable. The "test set" here refers to software testing, not clinical data for device performance. The evaluation was focused on the functionality and integrity of the software changes.
- Data Provenance: Not applicable, as no clinical data for device performance was generated or used for this specific submission's modifications. The modifications relate to the iCode feature, which reports compliance data from the device, not clinical data about the device's efficacy.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Not applicable. Ground truth in a clinical sense (e.g., expert consensus on medical images) is not relevant for this software modification. Software verification and validation are typically performed by software engineers and quality assurance personnel.
- Qualifications of Experts: The document refers to "internal procedures" for code review and verification, implying software development and QA professionals were involved.
4. Adjudication Method for the Test Set
- Adjudication Method: Not applicable in the context of clinical expert adjudication. Software testing methodologies (e.g., unit testing, integration testing, system testing, user acceptance testing) would have been used to verify the new software features.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of Human Readers Improve with AI vs. Without AI Assistance
- MRMC Study: No.
- Effect Size of Human Readers with AI: Not applicable. This device is a CPAP machine, not an AI-assisted diagnostic tool that humans read. The software modifications are for compliance reporting, not clinical interpretation or assistance.
6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done
- Standalone Performance: While the "iCode Report Generator" could be considered an "algorithm" (processing the iCode string to generate reports), its standalone performance in a medical evaluative sense (e.g., diagnostic accuracy) is not applicable. Its function is to accurately process an input string and generate a report, verified through software testing. The smartphone app uses OCR, which is an algorithm, but its performance is in accurately recognizing the characters, not making medical diagnoses.
7. The Type of Ground Truth Used
- Type of Ground Truth: For the software modifications, the "ground truth" would be the expected output and behavior based on the software requirements and design specifications. For the OCR component of the smartphone app, the ground truth would be the actual characters displayed on the RESmart LCD.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not applicable. There is no mention of a training set in the context of machine learning for medical outcomes. For the OCR component, the vendor would have used training data to develop the OCR model, but its specifics are not provided in this regulatory summary.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not applicable in a medical device performance context. If referring to the OCR component, the ground truth would have been established by human verification of scanned characters. This information is not provided in the 510(k) summary.
In summary: This 510(k) pertains to software modifications for a compliance reporting feature of an already cleared CPAP device. The evaluation criteria and studies are focused on software verification and validation, ensuring the new web-based and smartphone applications correctly handle the iCode data without altering the device's fundamental medical function or performance. Therefore, many of the typical questions asked about AI/medical device clinical studies are not applicable here.
§ 868.5905 Noncontinuous ventilator (IPPB).
(a)
Identification. A noncontinuous ventilator (intermittent positive pressure breathing-IPPB) is a device intended to deliver intermittently an aerosol to a patient's lungs or to assist a patient's breathing.(b)
Classification. Class II (performance standards).