(184 days)
The KP-7500 and KP-7500D are intended to measure the systolic and diastolic blood pressure and pulse rate (heart rate) by using an inflating cuff which is wrapped around the arm. It is indicated for use in adults.
The devices display irregular pulse detection (IPD) icon on LCD screen when irregular pulse is detected during blood pressure measurement.
The device is an electronic blood pressure monitor. The device consists of an inflating cuff, a LCD display, a bellows sensor, an internal air pump, a leakage valve, an exhaust valve, a battery power resource, and keys for operation.
Here's a summary of the acceptance criteria and study information for the K-jump Health Co., Ltd.'s Arm Blood Pressure Monitor Models KP-7500 and KP-7500D, based on the provided 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
The 510(k) summary explicitly states that the device "complies with the following FDA recognized consensus standards...to the extent that these standards are applicable to this device: AAMI/ANSI SP10 (2002 / A1:2003); IEC 60601-1 (1988); and IEC 60601-1-2 (2002)." It also mentions compliance with EN61000-4-2 (1995) and EN61000-4-3 (2002).
For blood pressure monitors, AAMI/ANSI SP10 (2002 / A1:2003) is the key standard for accuracy. While the document doesn't provide a direct table of numerical "acceptance criteria" alongside specific device performance numbers (e.g., mean difference and standard deviation), compliance with AAMI/ANSI SP10 inherently means meeting its accuracy thresholds. The standard typically requires:
- A mean difference between the device measurement and the reference measurement of ≤ ±5 mmHg.
- A standard deviation of that difference of ≤ 8 mmHg.
| Acceptance Criteria (Based on AAMI/ANSI SP10) | Reported Device Performance |
|---|---|
| Mean difference ≤ ±5 mmHg | "accurately measures the patient's blood pressure and pulse rate" (implied compliance with AAMI/ANSI SP10) |
| Standard deviation ≤ 8 mmHg | "accurately measures the patient's blood pressure and pulse rate" (implied compliance with AAMI/ANSI SP10) |
The document states, "In accordance with AAMI/ANSI SP10, a clinical trial also was performed to verify the accuracy of in vivo measurement. The results demonstrate that the KP-7500 and KP-7500D accurately measures the patient's blood pressure and pulse rate." This statement is the "reported device performance," indicating it met the AAMI/ANSI SP10 criteria. Specific numerical values for mean difference and standard deviation are not provided in this summary.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: Not specified in the provided text. The document only mentions "a clinical trial."
- Data Provenance: Not specified, but generally, such clinical trials for device clearance are conducted in a controlled, prospective manner. The country of origin of the data is not mentioned. It is implied to be prospective as it's a "clinical trial performed to verify the accuracy of in vivo measurement."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
For blood pressure monitor accuracy studies (like those compliant with AAMI/ANSI SP10), ground truth is established by trained observers (often physicians or nurses) using a reference sphygmomanometer and stethoscope, applying a standardized auscultatory method. The number and specific qualifications of these "experts" (trained observers) are not detailed in the provided 510(k) summary. However, AAMI/ANSI SP10 typically requires
- three trained observers in its protocol to minimize observer bias.
- These observers would be trained technicians or clinicians proficient in auscultatory blood pressure measurement, adhering to strict protocols.
4. Adjudication Method for the Test Set
The typical adjudication method for auscultatory blood pressure measurements in AAMI/ANSI SP10 compliant studies involves:
- Multiple observers (usually three) taking independent measurements.
- The average or consensus of these observers' measurements often serves as the reference (ground truth) against which the automated device is compared.
- Discrepancies exceeding a certain threshold among observers would necessitate re-measurement or specific handling as per the protocol.
The specific adjudication method (e.g., 2+1, 3+1, none) is not explicitly stated in the provided text, but it would have been part of the AAMI/ANSI SP10 protocol followed.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- No, an MRMC comparative effectiveness study was not conducted. This type of study is more common for diagnostic imaging AI systems where human readers interpret medical images. Blood pressure monitors primarily measure a physiological parameter, and their accuracy is evaluated against a direct physiological reference, not by comparing human interpretation of device output with and without AI assistance.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) Was Done
- Yes, the clinical trial described is a standalone performance study of the device. The device itself performs the measurement, and its output (algorithm only) is compared against the ground truth established by human observers using a reference method. There is no human-in-the-loop interacting with the device's measurement process; the device operates autonomously.
7. The Type of Ground Truth Used
- Expert Consensus / Reference Auscultatory Measurement: For blood pressure monitors, the gold standard (ground truth) is always established using auscultatory measurements performed by trained human observers with a calibrated mercury or aneroid sphygmomanometer and stethoscope. This effectively represents "expert consensus" on the true blood pressure at the time of measurement.
8. The Sample Size for the Training Set
- The provided document is a 510(k) summary for a blood pressure monitor, which is typically a hardware and firmware device. While it mentions "Smartlogic" and "Fuzzylogic," referring to control algorithms, there is no mention of a "training set" in the context of machine learning for an algorithm that learns from data in the same way modern AI systems do. The "Smartlogic" or "Fuzzylogic" refers to the control logic for cuff inflation/deflation and signal processing, which is generally pre-programmed and validated, not "trained" on a large dataset in the sense of deep learning. Therefore, no training set size is specified or applicable in the modern AI sense.
9. How the Ground Truth for the Training Set Was Established
- As mentioned above, the concept of a "training set" and associated ground truth establishment for a learning algorithm is not applicable to this type of device as described in the 510(k) summary. The internal algorithms (Smartlogic/Fuzzylogic) are likely based on established signal processing techniques for oscillometric blood pressure measurement. Their performance is validated through the clinical trial described, not by training on a labeled dataset.
§ 870.1130 Noninvasive blood pressure measurement system.
(a)
Identification. A noninvasive blood pressure measurement system is a device that provides a signal from which systolic, diastolic, mean, or any combination of the three pressures can be derived through the use of tranducers placed on the surface of the body.(b)
Classification. Class II (performance standards).