Search Results

The Neu Platform is intended to quantify the kinematics of movement disorder symptoms, including tremor in adults (45 years and older) with mild to moderate Parkinson's disease.

Device Description

The Neu Platform is a platform designed to capture digital motor and patient-reported data in patients with mild to moderate Parkinson's Disease. The platform has two key components:

A smartphone application for the remote capture of symptoms - Patients utilise the smartphone application to perform the motor tremor measurement activities. The app is also used for the patient to self-reported data, including onboarding information and subjective symptom information,
A dashboard for the clinical team to view the captured data - The clinician dashboard presents the data to clinical staff responsible for managing the patient's condition for review.

The Platform is comprised of a patient app, supporting backend infrastructure, and a clinician web-based dashboard. The Neu Platform is related to the components of the platform specifically for data capture from patients with Parkinson's disease.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for the Neu Platform, based on the provided FDA 510(k) clearance letter:

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criterion (Implicit)	Reported Device Performance
Correlation with Clinical Standard (Rest Tremor)	0.92 (p < 0.01) between the Neu Platform's tremor measurement and the clinical standard (MDS-UPDRS). This is an improvement compared to the predicate device's reported correlation of r=0.72.
Correlation with Clinical Standard (Postural Tremor)	0.85 (p = 0.002) between the Neu Platform's tremor measurement and the clinical standard (MDS-UPDRS). This also appears to be an improvement compared to the predicate device's reported general correlation of r=0.72.
Agreement with Clinically Meaningful Differences in Tremor Severity	The performance data demonstrates that the Neu Health tremor measurements are in agreement with clinically meaningful differences in tremor severity.
Safety and Effectiveness	The device is deemed as safe and effective for its intended use, based on non-clinical performance data and substantial equivalence to the predicate. No new or different questions of safety or effectiveness are raised by the device, despite not measuring dyskinesia like the predicate (as this can still be clinically assessed or patient-reported). The device has undergone software validation per FDA guidance and international standards (IEC 62304, IEC 14971) and cybersecurity threat analysis and mitigation (per "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices"), including data encryption (TLS-1.2+ and AES-256) and MFA for access.

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

The document describes "bench testing" but does not explicitly state the sample size (number of patients or measurements) used for this test set.

Data Provenance: The study was "obtained in a controlled setting." The document does not specify the country of origin of the data
Retrospective or Prospective: Not specified, but "bench testing" often implies a controlled, possibly retrospective analysis of collected data or a prospective collection in a controlled environment.

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

The document states that the device's measurements were compared to "the clinical standard for the rest and postural tremor measurements respectively" and "the accepted clinical standard (MDS-UPDRS)."

It does not specify the number of experts used to establish this ground truth for the test set.
It does not specify the qualifications of these experts beyond referring to "clinical standard" and "UPDRS-III assessment." Typically, MDS-UPDRS assessments are performed by trained neurologists or movement disorder specialists, but this is not explicitly stated as the method for ground truth establishment for the test set.

4. Adjudication Method for the Test Set

The document does not describe an explicit adjudication method (e.g., 2+1, 3+1) for the comparison of the device's measurements against the clinical standard. The "ground truth" seems to be derived directly from the application of a clinical rating scale (MDS-UPDRS-III).

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

Was one done? No. The document explicitly states: "Substantial equivalence is based on an assessment of non-clinical performance data and no animal or clinical performance data is included." Therefore, a traditional MRMC study comparing human readers with and without AI assistance was not performed.
Effect Size: Not applicable, as no MRMC study was conducted. The study focused on the device's correlation with the clinical standard.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Performance

Yes, the performance data presented is for the standalone device's ability to measure tremor. The "bench testing" evaluated the device's tremor measurements directly against the clinical standard, implying an algorithm-only evaluation for the core tremor measurement functionality. The device itself is designed to quantify the kinematics, not to issue a diagnosis or treatment recommendation, making its core function a standalone measurement tool.

7. Type of Ground Truth Used

The ground truth used was based on the "clinical standard" as defined by the MDS-UPDRS-III assessment (Movement Disorder Society - Unified Parkinson's Disease Rating Scale, Part III), which is a clinical rating scale for motor symptoms in Parkinson's disease.

8. Sample Size for the Training Set

The document does not provide any information about the sample size used for the training set for the Neu Platform's algorithms.

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

The document does not provide any information on how the ground truth for the training set was established.

Ask a Question

Ask a specific question about this device

Page 1 of 1