(90 days)
The Personal Kinetigraph (PKG) is intended to quantify kinematics of movement disorder symptoms in conditions such as Parkinson's disease, including tremor, bradykinesia and dyskinesia. It includes a medication reminder, an event marker and is intended to monitor activity associated with movement during sleep. The device is indicated for use in individuals 46 to 83 years of age.
The new Personal Kinetigraph (PKG) System, Model GKC-2000 (Gen 2), utilizes a small, wrist-worn data logging activity monitor (the PKG Watch) that continuously records and quantifies the kinematics of movement disorder symptoms over a 6 to 10 day period in movement disorder conditions such as Parkinson's disease. At the end of the recording period, the movement recording data is uploaded via a Tablet application at the supervising clinic, to a cloud-based server. A report is produced using the recorded data that objectively distinguishes the movement patterns consistent with tremor, bradykinesia, dyskinesia and immobility. This information can be used by the clinician to assess the extent and severity of movement disorder symptoms, and how they vary throughout the day, and from day to day. The PKG Watch has a medication reminder to the patient that it is time to take their medication, and an event marker for the patient to record when they have taken their prescribed medication.
The provided text describes the 510(k) premarket notification for the Personal Kinetigraph (PKG) System, Model GKC-2000 (Gen 2). The submission aims to demonstrate substantial equivalence to a predicate device (K140086 - Global Kinetics Corporation's Personal Kinetigraph (PKG) System).
Here's an analysis of the acceptance criteria and the study that indicates the device meets them, based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria in a table format for the device's diagnostic performance (e.g., sensitivity, specificity for detecting tremor or bradykinesia). Instead, the performance evaluation primarily focuses on demonstrating functional equivalence of the new Gen 2 system to its predicate device.
The main "acceptance criterion" for the system validation relevant to its intended use appears to be: "functional performance of the PKG Gen 2 System is identical to the predicate system (within the specified acceptance criteria of system variability) for all measures."
| Acceptance Criteria (Inferred from Study) | Reported Device Performance (PKG Gen 2 System) |
|---|---|
| Functional Equivalence: The Gen 2 system's functional performance (movement recording, medication reminders, medication acknowledgment, PKG Analysis, PKG PDF report) should be identical to the predicate system's performance within specified system variability. | Met: "the functional performance of the PKG Gen 2 System is identical to the predicate system (within the specified acceptance criteria of system variability) for all measures, with the exception of accidental 'medication taken' acknowledgements, where the PKG Gen 2 System is improved over that of the predicate." |
| Biocompatibility: Device components in contact with skin must pose a low risk for cytotoxicity, irritation, and sensitization. | Met: All results demonstrated no adverse or unexplained events, no indications for cytotoxicity, irritation, and sensitization. Materials pose a low risk for surface application on intact skin for less than 30 days. |
| Electrical Safety and EMC: Compliance with relevant medical electrical equipment standards (IEC 60601 series, IEC 62133). | Met: The system complies with IEC 60601-1:2005, IEC 60601-1-11:2010, IEC 60601-1-2:2007, IEC 60601-1-2:2014 (selected tests), and IEC 62133:2012. |
| Mechanical Safety: Compliance with mechanical safety requirements of IEC 60601-1:2005. | Met: The PKG Watch complied with all tested mechanical safety parameters (push, drop, mold stress relief, altitude, thermal cycle, shock, broad-band random vibration, ingress protection). |
| Software Verification and Validation: Software should function as intended without introducing minor injury in case of failure. | Met: Verification and validation testing were conducted, and documentation provided. The software was deemed "moderate" level of concern. |
2. Sample size used for the test set and the data provenance
The document states: "The test was conducted over several days, with each of the test subjects wearing two recording loggers simultaneously on the same arm (PKG Watch and/or the predicate Data logger), performing predetermined actions and maintaining a diary."
The exact sample size (number of test subjects) is not specified in the provided text.
Data Provenance: The study was conducted as a "side-by-side validation of the new system with the predicate, when worn by test subjects." It appears to be a prospective study for this particular validation, conducted by the manufacturer. The country of origin of the data is not explicitly stated, but the manufacturer is based in Melbourne, Victoria, Australia.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not mention the involvement of experts for establishing ground truth in this specific comparative performance study. The comparison was primarily between the data generated by the Gen 2 device and the predicate device. The output reports are designed for use by a clinician, but the validation itself doesn't involve expert scoring of the device's output against a clinical ground truth.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
There is no mention of an adjudication method in the context of expert review for this comparative performance study, as there were no experts establishing ground truth for the device's output. The comparison was statistical and functional between the two devices.
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, a multi-reader multi-case (MRMC) comparative effectiveness study was not performed or described. The study focused on the equivalence of the device's output (PKG PDF reports) between the new Gen 2 system and the predicate, not on how human readers (clinicians) improve with or without AI assistance from the device. The device quantifies movement disorder symptoms; it's not described as an AI diagnostic aid for human readers in the traditional sense of an MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, the functional performance comparison described is essentially a standalone (algorithm only) comparison. The "side-by-side comparative testing" focused on comparing the "PKG PDF Reports that resulted from each device" (Gen 2 vs. predicate) against each other, without involving a human clinician's interpretation as part of the primary equivalence assessment. The algorithm processes raw movement data to produce these reports.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the "System Validation testing" comparing the Gen 2 and predicate systems, the "ground truth" was the performance of the legally marketed predicate device (K140086). The goal was to prove "performance equivalence" between the two systems. The PKG PDF reports generated by both devices were compared. The overall system's ability to quantify kinematics of movement disorder symptoms was previously established and cleared with the predicate device.
8. The sample size for the training set
The document does not mention a training set or any machine learning model training. The device quantifies movement based on kinematics, and the validation described focuses on comparing the output of the new hardware/software iteration with its predecessor. Therefore, the concept of a "training set" as it pertains to machine learning is not applicable here based on the provided text.
9. How the ground truth for the training set was established
As no training set is mentioned, this information is not applicable based on the provided document.
§ 882.1950 Tremor transducer.
(a)
Identification. A tremor transducer is a device used to measure the degree of tremor caused by certain diseases.(b)
Classification. Class II (performance standards).