(169 days)
The TS2000 Medical Device Monitor is intended to be used as a central monitoring station on those patients being monitored by pulse oximeter and infusion pump medical devices. It is used to provide a secondary display of the data from the medical devices to the centrally located TS2000 System display. It is intended for use by healthcare professionals trained in the use of the equipment only.
The TS2000 is intended for use by healthcare professionals thoroughly familiar with the features and operations of the TS2000. The TS2000 is intended to supplement and not to replace any part of the current device monitoring procedures.
The TS2000 is not considered in and of itself to be diagnostic without skilled interpretation and does not replace physician's care
The TS2000 Medical Device Monitor is a PC based Central Monitoring Station that takes the information from different medical devices and redisplays them on a single monitor in a central location. It allows the remote monitoring of multiple medical devices simultaneously at the central station. The TS2000 provides secondary annunciation of the alarms from the medical devices at the central station as well.
The provided 510(k) Premarket Notification for the TS2000 Medical Device Monitor does not contain information regarding acceptance criteria, device performance, or a study that directly proves the device meets specific acceptance criteria in the way a modern AI/ML device submission would.
This submission is from 1998, and the device is a "Central Monitoring Station Software" that essentially redisplays information from other medical devices. This type of device's "performance" is primarily assessed on its ability to accurately and reliably transmit and display data and alarms, validate its software, and demonstrate substantial equivalence to predicate devices, rather than clinical performance metrics like sensitivity or specificity for a diagnostic algorithm.
Here's a breakdown of what is available in the document and what is missing based on your request:
1. Table of Acceptance Criteria and Reported Device Performance
This information is not explicitly stated in the provided document in the format of specific acceptance criteria (e.g., minimum accuracy, sensitivity, etc.) and corresponding performance numbers.
The document discusses "thorough validation for safety and effectiveness" by complying with guidance documents for computer-controlled medical devices and software validation (pages 4 and 5). This suggests that the "performance" was assessed against software validation standards rather than clinical endpoints.
The "performance" described is functional:
- Allows remote monitoring of multiple medical devices simultaneously.
- Provides secondary annunciation of alarms.
- "Provides additional assistance to the healthcare professional and makes the current local monitoring process safer and more effective." (Page 2)
2. Sample Size Used for the Test Set and Data Provenance
This information is not available in the provided document. The submission mentions "Non-clinical tests were conducted using both bench and simulation testing according to the test phase defined by the TS2000 Software Life Cycle" (Page 4). This refers to software testing, not a clinical study with a "test set" in the context of patient data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
This information is not applicable/available. Since there isn't a clinical test set with patient data being evaluated for a diagnostic or predictive outcome, there is no mention of experts establishing ground truth for such a purpose. The "ground truth" for this device would be the accurate and timely display of data and alarms from connected medical devices as confirmed by software validation.
4. Adjudication Method for the Test Set
This information is not applicable/available as there is no clinical test set requiring adjudication in the context of this 510(k) submission.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size
This information is not applicable/available. An MRMC study is typically for evaluating human performance (e.g., radiologists interpreting images) with and without AI assistance. The TS2000 is a monitoring display system, not a diagnostic AI algorithm that directly assists human interpretation of complex medical cases.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
The TS2000 is essentially a standalone software system in the sense that it processes and displays data automatically. Its "performance" would be assessed on its functional reliability and accuracy in replicating source device data and alarms. However, this is not a standalone "algorithm" in the modern AI sense, where a diagnostic or predictive output is generated. Its intended use explicitly states it "is intended to supplement and not to replace any part of the current device monitoring procedures" and "is not considered in and of itself to be diagnostic without skilled interpretation" (Page 7).
7. The Type of Ground Truth Used
For the software validation testing described, the "ground truth" would be the expected outputs from the simulated or bench-tested medical devices. For example, if a pulse oximeter was set to display a SpO2 of 98% and an alarm condition was simulated, the TS2000's "ground truth" would be to accurately display 98% and annunciate the alarm. This is a functional ground truth, not a clinical ground truth like pathology for a disease diagnosis.
8. The Sample Size for the Training Set
This information is not applicable/available. The TS2000 is not described as an AI/ML device that undergoes a "training" process with a dataset. It is a software system designed to perform specific functions.
9. How the Ground Truth for the Training Set was Established
This information is not applicable/available for the same reasons as point 8.
Summary of Device and Approval Context:
The TS2000 Medical Device Monitor, as described in this 1998 510(k) submission (K973640), is a Central Monitoring Station Software. Its primary function is to consolidate and redisplay data and alarms from existing medical devices (pulse oximeters and infusion pumps) to a central location.
The approval for this device was based on a demonstration of substantial equivalence to predicate devices (Baxter Flo-Gard 6301 Volumetric Infusion Pump (K915522) for its monitoring aspects and Nellcor Puritan Bennett Oxinet II (K942147) as a central monitoring station). The software was validated for "safety and effectiveness" by complying with then-current FDA guidance documents for computer-controlled medical devices and software development.
The "study" that proves the device meets criteria is primarily the software validation and non-clinical bench/simulation testing (Page 4) which confirmed its functional accuracy and reliability in transmitting and displaying data and alarms as expected, in comparison to the existing predicate technologies. It was not a clinical trial with patient outcomes or expert reads of diagnostic data, as the device's role is purely for secondary display and annunciation.
§ 870.2300 Cardiac monitor (including cardiotachometer and rate alarm).
(a)
Identification. A cardiac monitor (including cardiotachometer and rate alarm) is a device used to measure the heart rate from an analog signal produced by an electrocardiograph, vectorcardiograph, or blood pressure monitor. This device may sound an alarm when the heart rate falls outside preset upper and lower limits.(b)
Classification. Class II (performance standards).