(281 days)
PeraMobile Indications for Use:
The Rothman Index uses commonly recorded vital sign, nursing assessment, and lab data to provide a patient status index. The Rothman Index is a single measure of a patient's physiologic condition based on the aggregate statistical mortality risk associated with the values of the patient's vital signs, nursing assessments, and selected lab values. PeraMobile is indicated for use by healthcare providers within the hospital for displaying and/or trending Rothman Index (RI) scores and displaying associated configurable warning states as an adjunct to clinical decision support. PeraMobile is intended for use in the hospital to support Rapid Response Team clinicians or other dedicated clinical response staff responsible for pro-actively rounding on patients of concern and/or providing support to bed-side clinicians.
PeraWatch Indications for Use:
The Rothman Index uses commonly recorded vital sign, nursing assessment, and lab data to provide a patient status index. The Rothman Index is a single measure of a patient's physiologic condition based on the aggregate statistical mortality risk associated with the values of the patient's vital signs, nursing assessments, and selected lab values.
PeraWatch is indicated for use by healthcare providers whenever there is need within the hospital for displaying and/or trending Rothman Index (RI) scores and displaying associated configurable warning states as an adjunct to clinical decision support.
PeraWatch is intended to support clinicians in surveilling patients throughout the hospital setting (e.g. in the emergency department, on the wards, in intensive care units) and across multiple hospitals in a centralized and/or remote professional clinical surveillance setting.
PeraMobile is an interactive mobile application that provides an interface to display RI scores, trends, and configurable warnings for selected groups of patients within the hospital. PeraMobile reads and writes data directly to and from the PeraServer database. Designed for mobile clinicians, PeraMobile functionality also allows end-users to document both pre-defined interventions and free text notes that are stored in PeraServer and accessible through the user interface within PeraMobile. PeraServer was previously cleared in K172969.
PeraWatch is a read-only, web-based graphical user interface for displaying Rothman Index scores, trends and configurable warnings. PeraWatch reads data directly from the PeraServer database.
PeraMobile and PeraWatch are software-only devices that are installed on user-provided hardware that supports IEEE 802.11b or higher (802.11ac is recommended).
The provided text does not contain detailed information about a specific study proving the device meets acceptance criteria, nor does it present a table of acceptance criteria and reported device performance. The document is a 510(k) summary for the PeraMobile and PeraWatch System, focusing on establishing substantial equivalence to a predicate device (PeraTrend).
However, I can extract information related to the device's functionality and the general approach to validation mentioned in the document.
Here's an attempt to answer your questions based on the available text, highlighting what is present and what is missing:
Device: PeraMobile and PeraWatch System
1. Table of Acceptance Criteria and Reported Device Performance:
This information is not explicitly provided in the document. The document describes the core functionality of the device (displaying and trending Rothman Index scores and warning states) and compares its technological characteristics to a predicate device, but it does not specify quantitative acceptance criteria or report measured device performance against such criteria. The closest related statement is that "the results of software testing demonstrate that the PeraMobile and PeraWatch systems perform in accordance with specifications and meets user needs and intended uses."
2. Sample Size Used for the Test Set and Data Provenance:
- The document states that "Software verification and validation testing was conducted." However, it does not specify the sample size used for the test set (e.g., number of patients, records, or cases).
- Data Provenance: The Rothman Index (RI) uses "commonly recorded vital sign, nursing assessment, and lab data." This data comes from an "EHR and ancillary systems" via PeraServer. The document does not specify the country of origin of the data or explicitly state whether the data used for testing was retrospective or prospective. It implies the use of existing clinical data within hospital systems.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications:
- The document does not specify the number of experts used to establish ground truth or their qualifications.
- The Rothman Index (RI) itself is described as "a single measure of a patient's physiologic condition based on the aggregate statistical mortality risk associated with the values of the patient's vital signs, nursing assessments, and selected lab values." This suggests that the ground truth for the Rothman Index itself is derived from a statistical model based on patient outcomes (mortality risk), rather than expert consensus on individual cases for the purpose of this specific device's validation. The device then displays this calculated RI score and warning states.
4. Adjudication Method for the Test Set:
- The document does not mention any adjudication method (e.g., 2+1, 3+1) for establishing ground truth or evaluating the test set. Given that the device calculates a score based on a defined algorithm, formal adjudication by experts for each case's "ground truth" (e.g., as in image interpretation studies) is likely not applicable in the same way.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- A MRMC comparative effectiveness study was not conducted or described in this document. The device is an "adjunct to clinical decision support" displaying calculated scores, not an AI for interpreting medical images by human readers.
- The document states: "the subject devices to provide a warning list in the case of PeraWatch, and an out-of-app warning notification in the case of PeraMobile, assists end users in having a more timely awareness of warnings than was the case in the predicate device, which required users to access and review patient RI graphs to determine if the patient was in a warning state." This suggests an improvement in workflow and awareness, but it is not presented as a formal MRMC study effect size.
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study:
- The document does not explicitly describe a standalone performance study of the algorithm itself. It states that "The RI score algorithm has not changed since the previous submission, therefore the algorithm testing provided in the predicate submission (K172979) is relevant to this submission." This implies that the algorithm's performance was assessed during the predicate device's clearance. The current submission focuses on the display and notification capabilities of PeraMobile and PeraWatch, which are essentially interfaces to the existing RI calculation from PeraServer.
7. Type of Ground Truth Used:
- The core "ground truth" for the Rothman Index is based on "aggregate statistical mortality risk associated with the values of the patient's vital signs, nursing assessments, and selected lab values." This indicates historical outcomes data (mortality) was used to train or establish the underlying Rothman Index algorithm. For the PeraMobile and PeraWatch devices, the ground truth relative to their function (displaying RI scores and warning states) is simply the correct calculation and display of these values from the PeraServer.
8. Sample Size for the Training Set:
- The document does not specify the sample size for the training set for the Rothman Index algorithm. It refers back to the predicate device submission (K172959) for details on the RI score algorithm testing.
9. How the Ground Truth for the Training Set Was Established:
- For the Rothman Index algorithm itself, the ground truth was established by correlating patient data (vital signs, nursing assessments, labs) with "aggregate statistical mortality risk." This implies a data-driven, statistical approach based on historical patient outcomes (mortality) to quantify the physiologic condition and risk. The specifics of this process are not described in the current document but were presumably part of the K172959 submission.
§ 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).