Search Results

The Polysmith Sleep System, Model NT17593 is intended to measure, amplify, and record physiological signals acquired from a patient for archival in a sleep study. The physiological signals are recorded and conditioned for analysis and display. The data may be analyzed in real-time or offline on dedicated polysomnography software running on a personal computer by a qualified sleep clinician to aid in the diagnosis of Sleep Disorders.

The Polysmith Sleep System, Model NT17593 is intended for use by healthcare professionals within a hospital, laboratory, clinic, or nursing home; or outside of a medical facility under direct supervision of a medical professional.

The Polysmith Sleep System, Model NTT7593 is intended for use on both adults and children only under the direction of a physician or qualified sleep technician.

The Polysmith Sleep System, Model NTT7593 includes automatic detection of some arrhythmias (including some potentially life threatening arrhythmias), however detection of an arrhythmia may be performed with 30 seconds or more delay, and is based on a single ECG lead only.

The Polysmith Sleep System, Model NTI7593, or any accessory, is not intended for the life monitoring of high risk patients, does not include or trigger alarms, and is not intended to be used alone as, or a critical component of,

• an alarm or alarm system:
• · an apnea monitor or apnea monitoring system; or
• · a life monitor or life monitoring system.

The Polysmith Sleep System, Model NT17593 is intended to amplify and record physiologic potentials used for Polysomnography (PSG) or Sleep Studies. The device consists of a compatible amplifier, head box, PC, patient sensors, and may include optional external devices, USB DC Box, and audio/video input devices.

Compatible amplifiers may use commercially available sensors and electrodes, an internal SpO2 module, and internal pressure transducers to collect, digitize, and send physiological signals to the host PC.

The Polysmith software may record from video, speaker and microphone equipment. The Polysmith software may also record auxiliary signals from compatible amplifiers or USB DC Box which allow for data inputs from compatible sources.

Polysmith records and displays the data for online or offline review. Qualified practitioners use the information to score polysomnograms and diagnose Sleep Disorders.

Here's an analysis of the acceptance criteria and study as described in the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

(Note: The document states the new device is "comparable" to the BSM-9100A, which includes the "same algorithm." It does not explicitly list the acceptance criteria values for the BSM-9100A, but rather assumes that comparable performance to a device with a more critical intended use is sufficient.)

2. Sample size used for the test set and the data provenance:

• Sample Size: Not explicitly stated as a number of patients or recordings. The document refers to the use of standard databases:
  • MIT: The Massachusetts Institute of Technology–Beth Israel Hospital Arrhythmia Database
  • AHA: The American Heart Association Database for Evaluation of Ventricular Arrhythmia Detectors
  • NST: The Noise Stress Test Database
• Data Provenance: The databases (MIT, AHA, NST) are widely recognized cardiological datasets. The document does not specify their country of origin for this particular study, nor whether the data was retrospective or prospective. Given they are established historical databases, they are inherently retrospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not explicitly stated in the provided text. The databases (MIT, AHA, NST) are widely recognized and have ground truths established by clinical experts during their creation. However, the document does not detail how this specific study confirmed ground truth for its testing or the number/qualifications of experts involved in the original ground truth creation of these databases.

4. Adjudication method for the test set:

• Not explicitly stated. Given the use of established databases, the ground truth annotations within these databases would have been created through expert consensus or established protocols, but the specific adjudication method for this particular study is not detailed.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not conducted or described. The study focuses solely on the standalone performance of the algorithm against reference databases.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Yes, a standalone algorithm-only performance evaluation was conducted. The tables provided show the "Polysmith Sleep System, NTI7593 (NEW)" performance metrics (Sensitivity, Predictivity, FPR) directly against the reference databases, without any mention of human-in-the-loop interaction. The document states: "The arrhythmia analysis results are to be reviewed by a qualified clinician and are not to serve as results for direct diagnosis or treatment of arrhythmia conditions. The arrhythmia analysis function is only to provide indicators for further investigation," which further reinforces its standalone, assistive role.

7. The type of ground truth used:

• The ground truth used is based on expert consensus annotations embedded within the standard, publicly available databases:
  • MIT: The Massachusetts Institute of Technology–Beth Beth Israel Hospital Arrhythmia Database
  • AHA: The American Heart Association Database for Evaluation of Ventricular Arrhythmia Detectors
  • NST: The Noise Stress Test Database

8. The sample size for the training set:

• Not explicitly stated. The document indicates that the "newly integrated algorithm is the same algorithm implemented in the reference device, BSM-9100A (K082785)," implying this algorithm was likely trained or developed previously, possibly using portions of these or other similar databases. However, the training set size specific to this submission for the Polysmith device is not provided.

9. How the ground truth for the training set was established:

• Not explicitly stated for this submission. Since the algorithm is adopted from the BSM-9100A, the ground truth for its original training would have been established during the development of that device or the algorithm itself, likely through expert annotation of ECG recordings, similar to how the ground truth for the testing databases was established. The document doesn't provide details on the development of this algorithm's ground truth.

Ask a specific question about this device

The Nihon Kohden CSM-1901 Bedside Monitor is intended to monitor, display and record physiological data to provide cardiac and vital signs monitoring within a medical facility. The device is intended to produce a visual record of the electrical signal produced by the heart and monitor the electrocardiogram to generate visible alarms when an arrhythmia exists. The device is also intended to monitor heart rate, blood oxygen saturation (SpO2), noninvasive blood pressure (NIBP), invasive blood pressure (IBP), body temperature, BIS, cardiac output (CO), oxygen concentration (FiO2), carbon dioxide concentration (CO2), EtCO2, respiratory rate, inspired and expired anesthetic agents and anesthetic gases including N20, halothane, enflurane, enflurane and desflurane. The device also displays patient data from external devices such as ventilators, TOF monitors, and EEG measuring unit.

The device may generate and audible and/or visual alarm when a measured rate falls outside preset limits.

The device will be available for use by trained medical facility on all patient populations, including adult, neonate, infant, child, and adolescent subgroups.

The Bedside monitor CSM-1901 is a device which continuously monitors physiological information of a patient and is used in an operation room, a recovery room, general wards, ICU, CCU, HCU, NICU and an emergency room. This bedside monitor is placed near the patient and is intended to display patient's vital signs. This device can also be connected to other external patient monitoring devices. In addition, this device can communicate patient's data to a central monitoring station via network to monitor multiple patients.

Here's an analysis of the provided text regarding the Nihon Kohden CSM-1901 Bedside Monitor, focusing on acceptance criteria and study details.

Important Note: The provided document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device. It primarily details compliance with recognized standards and internal testing protocols. It does not contain specific, detailed acceptance criteria in quantitative terms (e.g., sensitivity, specificity for arrhythmia detection) or a robust clinical study with detailed performance metrics like one might find for a novel AI device or a PMA submission. Therefore, some sections below will indicate that the information is not present in the provided document.

Acceptance Criteria and Reported Device Performance

Missing Specific Quantitative Acceptance Criteria: The document does not provide specific quantitative acceptance criteria for the performance of arrhythmia detection (e.g., minimum sensitivity or specificity targets for specific arrhythmia types), or for the accuracy and precision of physiological measurements against a gold standard. The performance is generally stated as "functions as intended" or "complies with standards."

Study Details

1. Sample Size Used for the Test Set and Data Provenance:

   • Test Set Sample Size: The document does not specify a distinct "test set" in terms of patient data or physiological recordings used for clinical performance evaluation. The testing described is primarily in the context of engineering verification and validation (software, electrical safety, EMC, etc.).
   • Data Provenance: Not applicable, as no specific patient data test set is described.

2. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Experts:

   • Not applicable. The document describes engineering and systems testing, not a clinical trial involving expert-labeled ground truth.

3. Adjudication Method for the Test Set:

   • Not applicable. No clinical test set with adjudicated ground truth is described.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • No, a MRMC comparative effectiveness study was not done (or at least not reported in this 510(k) summary). The device is a "bedside monitor" with integrated detection algorithms, not an AI-assisted diagnostic tool that augments human interpretation in a comparative reader study context.
   • Effect Size of Human Readers Improve with AI vs. Without AI Assistance: Not applicable, as no such study was conducted or reported.

5. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:

   • Yes, in essence, standalone performance was assessed though not in the form of a detailed clinical "study" with specific performance metrics for individual algorithms. The device's integrated arrhythmia detection and physiological measurement algorithms are designed to operate independently to generate alarms and display data. The testing mentioned (software unit testing, integration testing, system verification, system validation) would cover the standalone functionality of these algorithms and systems against their specifications. However, specific performance metrics (e.g., for arrhythmia detection accuracy against a recognized benchmark dataset like MIT-BIH) are not
     detailed in this summary.

6. Type of Ground Truth Used:

   • For the engineering and systems testing, the "ground truth" would be established by:
     • Defined specifications: Software units and system functions were tested against their intended design and functional requirements.
     • Standardized test signals/simulators: Electrical and EMC tests, and possibly some physiological parameter accuracy checks, would use calibrated test equipment and signals representing known conditions.
     • Compliance to standards: The ground truth for safety and performance would be the requirements laid out in the cited IEC and ANSI/AAMI standards.
     • Predicate device comparison: Functional equivalence was likely established by comparing the new device's behavior to the predicate device under similar test conditions.

7. Sample Size for the Training Set:

   • Not applicable. The document does not describe the use of machine learning or AI in a way that requires a "training set" for model development. This seems to be a traditional medical device employing established signal processing and rule-based algorithms. Therefore, there's no mention of a training set.

8. How the Ground Truth for the Training Set was Established:

   • Not applicable, as no training set is mentioned for AI/ML model development.

Ask a specific question about this device