(118 days)
The Spacelabs Medical Full Disclosure System is indicated for use in clinical situations where there is a need for review of physiological waveform information and alarm events up to 72 hours after the fact. The Full Disclosure System is also indicated in those situations where a retrospective analysis of monitoring patients' ECG waveform data, that can be annotated and edited, is desired. The intended use of the Spacelabs Medical Full Disclosure System is to interface with the Spacelabs monitoring network in order to provide the user with a means of recalling waveform information and retrospectively analyzing up to 72 hours of monitoring patient's most recent ECG waveform data.
The Spacelabs Medical Full Disclosure System (FD), model 91810, is a software application intended to be installed on an Off-The-Shelf (OTS) computer system utilizing a Microsoft operating system. The primary purpose of the FD system is to review, up to 72 hours of monitored patients' historical physiological waveform and alarm event information. The system also provides for a Retrospective Analysis of the stored ECG waveform data. The Full Disclosure system is a software application that provides fulldisclosure functionality for Spacelabs Medical bedside monitors. Depending on options purchased, a maximum of 72 hours of patient waveform history can be viewed for patients connected to the monitoring network. The system supports the following waveform channels: ECG Primary and secondary, Arterial pressure, Pulmonary artery pressure, Central venous pressure, Right atrial pressure, Intracranial pressure, Left atrial pressure, General pressure, Umbilical artery pressure, Pulse oximetry, Umbilical venous pressure, Adult or neonatal ventilator Flexport, Carbon dioxide / multigas Flexport or module, Sp02/ET02 Flexport and Respiration. The Full Disclosure application allows the user to view and print the full array of waveform information collected from Spacelabs Medical bedside monitors connected to the Spacelabs Medical patient monitoring network. The Alarm events, 12 Lead Reports and waveform information is available to the user for up to 72 hours after the information is stored in the network's database. In addition, the system incorporates a shape-based, Retrospective Algorithm that may be applied to the ECG waveform data, if desired. This Retrospective Algorithm can identify clinically significant ECG events and make them available for viewing and printing. When ECG analysis is performed, the results are stored locally, not in the database. Preference information, such as display and report options, is saved on the local machine, not in the database.
The provided text describes a 510(k) premarket notification for the Spacelabs Medical Full Disclosure System, Model 91810. The notification focuses on establishing substantial equivalence to a predicate device rather than presenting a detailed clinical study with specific acceptance criteria in terms of analytical performance metrics or human reader comparisons.
Here's a breakdown of the requested information based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not specify quantitative acceptance criteria in terms of performance metrics (e.g., sensitivity, specificity, accuracy) for the new device. Instead, the "acceptance criteria" appear to be tied to demonstrating substantial equivalence to a predicate device and adherence to software development processes and standards.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Compliance with Standards | "rigorous testing that, in part, support the compliance of the software to the Standards mentioned in Section 9 of this submission." (Specific standards are not detailed in the provided text.) |
| Adherence to Robust Software Development Process | "the Full Disclosure software was developed following a robust software development process and was fully specified and validated." |
| Accurate Recall of Data | "The test program verified that data available to the Full Disclosure System could be accurately recalled." (No quantitative metrics provided for "accurately recalled.") |
| Retrospective Analysis Performs As Expected | "the Retrospective Analysis performed as expected." (No quantitative metrics provided for "performed as expected." The expectation is presumably to identify clinically significant ECG events.) |
| Substantial Equivalence in Design, Technologies, and Materials | "The Spacelabs Medical Full Disclosure System, Model 91810 and the Spacelabs Medical ECG analysis system, model 91810, K962930 are substantially equivalent in design concepts, technologies and materials." and "Testing demonstrates that Full Disclosure System is as safe and effective as the Spacelabs Medical ECG Analysis System, K962930." |
| Indicated Use (Review waveform data and retrospective ECG analysis) | The device is intended for reviewing physiological waveform and alarm event information and for retrospective analysis of ECG waveform data. (This is a statement of intended function, not a performance metric.) |
2. Sample Size Used for the Test Set and Data Provenance
The provided text does not specify a sample size for a test set in terms of patient data or ECG recordings. The testing appears to be focused on software validation and verification rather than a clinical performance study using a defined patient cohort.
The data provenance is not explicitly stated. Given it's a software application for reviewing patient physiological data, it would logically involve existing patient data, but whether this was retrospective or prospective, or from a specific country, is not detailed.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
The document does not mention the use of experts to establish a ground truth for a test set. This type of evaluation is common in AI/ML performance studies, but this 510(k) submission describes a software system for data review and a retrospective analysis algorithm, not a diagnostic AI system requiring expert-adjudicated ground truth for its primary claims.
4. Adjudication Method for the Test Set
Since no specific test set requiring expert ground truth establishment is described, there is no mention of an adjudication method (e.g., 2+1, 3+1).
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was Done
No, an MRMC comparative effectiveness study was not done according to the provided information. The submission focuses on the functionality and substantial equivalence of the software system and its retrospective analysis algorithm, not on improving human reader performance with AI assistance.
6. If a Standalone (i.e. algorithm only without human-in-the loop performance) was Done
The document states that the system incorporates a "shape-based, Retrospective Algorithm that may be applied to the ECG waveform data." It also mentions "The test program verified... that the Retrospective Analysis performed as expected." This implies some form of standalone evaluation of the algorithm's performance in identifying ECG events. However, the details of this "standalone" evaluation (e.g., specific metrics used, data size, ground truth for that specific algorithm's performance) are not provided. The overall substantial equivalence claim is for the system rather than just the algorithm in isolation.
7. The Type of Ground Truth Used
For the retrospective analysis algorithm, the type of ground truth used to evaluate its performance is not explicitly stated. In the context of ECG event identification, this would ideally involve physician-adjudicated annotations of ECG waveforms, but the document does not elaborate on this. For the general system's ability to recall data, the ground truth would inherently be the original monitored data itself.
8. The Sample Size for the Training Set
The document does not mention a training set sample size. This is not a typical requirement for a system whose primary purpose is data review and a shape-based retrospective algorithm, especially if it's not a deep learning or complex AI model that requires extensive training data. The focus is on functionality and existing standards.
9. How the Ground Truth for the Training Set Was Established
Since a training set is not mentioned, the method for establishing its ground truth is also not described.
§ 870.1425 Programmable diagnostic computer.
(a)
Identification. A programmable diagnostic computer is a device that can be programmed to compute various physiologic or blood flow parameters based on the output from one or more electrodes, transducers, or measuring devices; this device includes any associated commercially supplied programs.(b)
Classification. Class II (performance standards).