Search Results

Use of the Fukuda Denshi model DS-5100E Portable Patient Monitor system is indicated in those clinical settings where

• Observations of one or more of the following parameters on an individual patient may be required: ECG (waveform, heart rate, ST-Level, and ventricular arrhythmias), respiration, non-invasive and/or invasive blood pressures, temperature, and/or pulse oximetry.
• The observations may include an audible and visual alarm if any of these parameters exceed values that are establish by the clinician.
• The observations may also include the individual or comparative trending of one or more of these parameters over a period of up to 24 hours.
• An instantaneous display of waveforms, numeric, and trended values is desired.
• a hard copy record of the physiological parameters, the alarmed conditions, or the trended values may be required.
• where the patient may need to be monitored while being transported within the healthcare facility.

The DS-5100E Patient Monitor System is a pre-configured monitor meant to acquire and monitor physiological signals from patients. The system is designed to be used in an ICU, CCU, OR, ER, or Recovery areas of a hospital or clinic. Battery operation allows the DS-5100E to be used to monitor patients being transported within the healthcare facility. Patient ages from neonates to adults can all be monitored. Waveforms, numeric, and trend data from these patients are available to the clinician on the system's display or it may be printed on the system's recorder.

The Fukuda Denshi model DS-5100E Portable Patient Monitoring system consists of a main unit and a power unit.

The main unit of the system can be remotely located from the power unit and connected via a cable to provide continuous AC power. Batteries are installed into the main unit and the power unit to allow both parts to be disconnected from AC power and still function. The main unit may also be disconnected from the power unit and function independently on battery power.

Small, lightweight, but powerful in its application of technology, the DS-5100E system is portable and extremely easy to use.

High speed RISC (Reduced Instruction Set Computing) microprocessors, along with a high resolution color display and touch screen technology has made the DS-5100E a unique and intuitive patient monitor.

Upgrade capability has been made simple and quick through the use of high speed flash memory.

A Recorder module (HR-500), a multi-parameter telemetry transmitter (HLX-501), and an IC memory card are available as options.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text.

Note: The provided document is a 510(k) summary for a patient monitor. As such, it focuses on demonstrating substantial equivalence to a predicate device rather than presenting detailed results of a novel clinical efficacy study. Therefore, some of the requested information, particularly regarding specific performance metrics with detailed acceptance criteria and expert-driven ground truth establishment for a new algorithm, is not present in the document. The information below reflects what can be extracted from the text.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size Used for the Test Set and Data Provenance

The document does not explicitly state the sample sizes used for the test sets for each specific performance metric (ECG, NIBP, Pulse Oximetry, Arrhythmia, ST Level). Instead, it refers to compliance with various industry standards (ANSI/AAMI, Nellcor Puritan Bennett's protocol) for which the predicate device (DS-5300) had already been reviewed.

• Sample Size for Test Set: Not explicitly stated. The testing implicitly relies on the data that was previously used to demonstrate compliance for the predicate device DS-5300.
• Data Provenance: Not explicitly stated as retrospective or prospective for this submission's testing. However, the nature of the testing (laboratory and compliance with standards) suggests it involves simulated or pre-recorded physiological data, or testing on human subjects as per the referenced standards for specific parameters (e.g., NIBP, pulse oximetry, arrhythmia). Given the reference to the predicate device's data, some of it would be "retrospective" relative to this specific 510(k) submission. No country of origin for the data is specified.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

• Number of Experts: Not mentioned.
• Qualifications of Experts: Not mentioned.

Given that this is a 510(k) for substantial equivalence of a patient monitor (not a new diagnostic AI algorithm), the ground truth for physiological parameters would typically come from reference devices or carefully calibrated simulators/methods specified by the AAMI/IEC standards, rather than expert human interpretation of raw waveforms for establishing "ground truth" in the way it's done for imaging or algorithmic diagnostics. In essence, the "ground truth" for these tests comes from the established performance requirements of the standards themselves.

4. Adjudication Method for the Test Set

Not applicable/not mentioned in the context of this type of device and testing. Adjudication methods like "2+1" are typically used in studies involving human interpretation of complex data (e.g., radiology images) where there's a need to resolve discrepancies between multiple readers. The testing here focuses on technical performance metrics against recognized standards.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not done, nor would it typically be expected for a patient monitor seeking 510(k) clearance based on substantial equivalence. This type of study is more common for diagnostic AI tools where human interpretation is a critical component and the AI's impact on human performance is being evaluated.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

Yes, the testing described appears to be primarily standalone performance testing against engineering specifications and industry standards. The device's various monitoring algorithms (ECG, NIBP, Pulse Oximetry, Arrhythmia, ST Level) are tested for their accuracy and compliance with these standards without a human explicitly "in the loop" for establishing their accuracy. The "Reporting Performance Results of Ventricular Arrhythmia Detection Algorithms" (ECAR-1987) specifically refers to algorithm performance.

7. The Type of Ground Truth Used

The ground truth for the various measurements (ECG, NIBP, Pulse Oximetry, Arrhythmia, ST Level) would be based on:

• Reference Devices/Calibrated Systems: For parameters like NIBP and pulse oximetry, highly accurate and calibrated reference equipment would be used to provide the "true" physiological values against which the device's measurements are compared.
• Standardized Test Signals: For ECG parameters like heart rate, ST-level, and arrhythmia detection, standardized ECG databases with annotations for known events (e.g., MIT-BIH Arrhythmia Database, as often used for ECAR-1987 compliance) or signal generators providing precisely defined electrical signals would serve as ground truth.
• Pathology/Outcomes Data: Not typically relevant for establishing ground truth for continuous physiological monitoring parameters in this context.

8. The Sample Size for the Training Set

Not applicable/not mentioned. This device is not described as an AI/ML-driven diagnostic algorithm that would typically require a "training set" in the context of machine learning model development. While the device contains software and algorithms, these are more likely based on established physiological principles and signal processing techniques rather than a trainable machine learning model requiring a distinct training data set that needs to be disclosed in this manner. The software and algorithms were likely developed and validated using general engineering principles and testing against a wide range of conditions, not a "training set" in the modern AI sense.

9. How the Ground Truth for the Training Set Was Established

Not applicable, as there's no mention of a "training set" for an AI/ML algorithm in this document for the reasons stated above.

Ask a specific question about this device