(265 days)
The SD1 is a pocket Doppler device used for detecting the fetal heartbeat from the 10th week of gestation. It is intended to be used by medical professionals only.
SD1 Ultrasonic Pocket Doppler is a device prescribed by a licensed physician for use by professional healthcare providers. It is a hand-held, battery powered audio Doppler device integrated with 3 MHz probe and with optional use of Bluetooth/app, used for detecting fetal heart beats. The device is for prescription use and is intended for use at or after 10 weeks gestation.
The provided text describes the SD1 Ultrasonic Pocket Doppler, a device intended for detecting fetal heartbeats from the 10th week of gestation. While the document outlines performance data and its substantial equivalence to predicate devices, it does not detail specific acceptance criteria for performance metrics like sensitivity, specificity, or predictive values that would typically be associated with AI/ML diagnostic devices. The acceptance criteria mentioned primarily relate to regulatory compliance, electrical safety, electromagnetic compatibility, and general performance standards for ultrasonic equipment.
Therefore, I cannot provide an acceptance criteria table or information related to AI/ML specific aspects such as sample size for test sets/training sets, expert adjudication methods, MRMC studies, or standalone algorithm performance, as these details are not present in the provided document.
However, I can extract the information relevant to the performance evaluation that was conducted:
Here's a summary of the available information:
1. A table of acceptance criteria and the reported device performance
Based on the document, specific, quantitative clinical performance acceptance criteria (e.g., minimum sensitivity/specificity thresholds) and their corresponding reported values are not explicitly stated for the SD1 Ultrasonic Pocket Doppler in the context of fetal heart rate detection accuracy. The document focuses on demonstrating substantial equivalence to predicate devices by ensuring the SD1 performs comparably and meets relevant safety and performance standards.
The closest to "acceptance criteria" for clinical performance is the conclusion that:
"The results showed that it did not take more time to find the fetal heart rate in pregnant patients, from 10 weeks of gestation onward, using the SD1 Pocket Doppler in comparison to the predicate SD3 Ultrasonic Pocket Doppler." This implies an acceptance criterion related to the time taken to detect FHR, with the performance meeting this criterion by being comparable to the predicate.
General performance characteristics (like FHR Accuracy) are listed in the predicate comparison table, and the SD1 matches the predicate for these:
| Acceptance Criteria (for FHR Performance) | Reported Device Performance (SD1) |
|---|---|
| FHR Accuracy: ±2bpm (Same as predicate) | ±2bpm |
| FHR Measuring Range: 50bpm ~ 240bpm (Same as predicate SD3) | 50bpm ~ 240bpm |
Other acceptance criteria are regulatory and non-clinical in nature:
| Acceptance Criteria (Category) | Reported Device Performance |
|---|---|
| Electrical Safety (IEC 60601-1) | Met pre-defined acceptance criteria |
| Electromagnetic Compatibility (IEC 60601-1-2) | Met pre-defined acceptance criteria |
| Requirements for ultrasonic medical diagnostic and monitoring equipment (IEC 60601-2-37) | Met pre-defined acceptance criteria |
| Hand-Held probe Doppler fetal heartbeat detectors Performance requirements (IEC 61266) | Met pre-defined acceptance criteria |
| Acoustic output measurement standard (NEMA UD 2) | Met pre-defined acceptance criteria |
| Acoustic output testing (FDA guideline) | Met pre-defined acceptance criteria |
| Biocompatibility (ISO 10993-5, ISO 10993-10) | Met pre-defined acceptance criteria |
| Wireless technology testing (FDA guidance, FCC rules) | Met pre-defined acceptance criteria |
| Software Verification and Validation Testing (FDA guidance) | Met pre-defined acceptance criteria |
2. Sample sized used for the test set and the data provenance
- Sample Size for Test Set: Not explicitly stated. The document mentions "clinical testing was conducted at a Chinese hospital" with "pregnant patients, from 10 weeks of gestation onward." The exact number of patients or cases is not provided.
- Data Provenance: Prospective, from a "Chinese hospital."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. The clinical study focused on comparing the time taken to detect fetal heart rate between the subject device (SD1) and a predicate device (SD3). The "ground truth" here would likely be the confirmed presence of a fetal heartbeat, assessed by medical professionals, but the number and qualifications of experts involved in this specific assessment are not detailed.
4. Adjudication method for the test set
Not applicable. The study design described does not involve a multi-reader adjudication process for establishing ground truth, as it's a comparative performance study of two Doppler devices in detecting FHR.
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
Not applicable. This device is a fetal Doppler, not an AI-assisted diagnostic tool for image interpretation. Therefore, an MRMC study comparing human readers with and without AI assistance was not performed.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Not applicable. The device is a hardware-based fetal Doppler, not an AI algorithm. Its performance inherently involves a human operator to locate the fetal heartbeat.
7. The type of ground truth used
The clinical study compared the SD1 to a legally marketed predicate device (SD3 Ultrasonic Pocket Doppler). The "ground truth" for the clinical performance aspect would be the successful detection of the fetal heart rate by a medical professional during the clinical test, effectively using the predicate device as a reference for comparison of detection time. There is no mention of pathology or other advanced outcomes data for ground truth in this context.
8. The sample size for the training set
Not applicable. This device is not an AI/ML device that requires a training set.
9. How the ground truth for the training set was established
Not applicable. This device is not an AI/ML device that requires a training set.
§ 884.2660 Fetal ultrasonic monitor and accessories.
(a)
Identification. A fetal ultrasonic monitor is a device designed to transmit and receive ultrasonic energy into and from the pregnant woman, usually by means of continuous wave (doppler) echoscopy. The device is used to represent some physiological condition or characteristic in a measured value over a period of time (e.g., perinatal monitoring during labor) or in an immediately perceptible form (e.g., use of the ultrasonic stethoscope). This generic type of device may include the following accessories: signal analysis and display equipment, electronic interfaces for other equipment, patient and equipment supports, and component parts. This generic type of device does not include devices used to image some relatively unchanging physiological structure or interpret a physiological condition, but does include devices which may be set to alarm automatically at a predetermined threshold value.(b)
Classification. Class II (performance standards).