(308 days)
PregSense is a maternal-fetal monitor that non-invasively measures and displays fetal heart rate (FHR) and maternal heart rate (MHR). The PregSense acquires and displays the FHR and MHR tracings from abdominal surface electrodes that pick up the fetal heart biopotential and maternal heart biopotential signal, and from surface acoustic sensors that pick up the fetal PCG (fPCG; phonocardiogram) and the maternal PCG (mPCG; phonocardiogram) signals.
PregSense is indicated for use by pregnant women who need documentation of fetal heart rate activity, and who are in their 32nd week of gestation (or later), with a singleton pregnancy. PregSense is intended to be used for a maximum of five minutes.
The PregSense maternal-fetal monitor is intended for use in the antepartum period by healthcare professionals in health care facilities and by the patient in the patient's home, on the order of a physician.
The PregSense is not intended for use in critical care situations or in laboring patients hospitalized for or suspected to have preterm labor.
PregSense is not intended to be used for antepartum monitoring (e.g., non-stress testing).
PregSense™ is a non-invasive medical device that acquires and displays vital signs of the pregnant woman and of her fetus. It measures and processes signals picked up on the abdominal surface using sensors, electronic circuitry and processing software. Two types of sensors pick up the signals: electrocardiogram (ECG)-like sensors that capture bio-potential signals, and acoustic sensors. The biopotential (ECG-like) sensors capture fECG (heartrate of the fetus) and mECG signals (heartrate of the pregnant woman). The acoustic sensors measure the sounds from the pregnant woman's abdomen, (PCG -phonocardiogram and fPCG -fetal PCG). Monitoring of the fetal and maternal heart rate using PregSense is limited to a five-minute session.
PregSense™ is an integrated platform that uses a signal acquisition tool to provide input to two separate software applications, one for the patient (PregSense™ ME) and one for the physician (PregSense™ MD). The sensors are incorporated in a belt (PregSense™ Belt) that is worn on the abdomen of the pregnant woman, where it acquires both biopotential and acoustic signals are processed at the cloud-server level where the inputs from the sensors are processed, merged and downloaded to the mobile devices of the pregnant woman and her health care provider. The PregSense™ ME application (for the patient) allows the pregnant woman to view the average maternal and fetal heart rate after a five minute session has been completed and PregSense™-MD application (for the health care provider) allows the health care provider to view the complete fetal and maternal heart rate data from the five minute session online and remotely via the internet. A monitoring session can only be initiated by a health care provider.
Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Fetal Heart Rate (FHR) Measurement Accuracy | For a 30-minute session, 97.08% of all differences between PregSense and a "standard of care" monitoring device (CTG) lie between the 95% agreement limits of [-8.84, 8.24] bpm. |
| For a 5-minute session (relevant to the device's indicated use): The lower limit of the 95% confidence interval of the lower agreement bound is -7.47 bpm and the upper limit is 8.16 bpm. Furthermore, 96.64% of the differences fall between the limits of agreement. | |
| Maternal Heart Rate (MHR) Measurement Accuracy | For a 30-minute session, 95.31% (48241/50616) of all differences between PregSense and a "standard of care" monitoring device (CTG) lie between the 95% agreement limits of [-5.30, 5.86] bpm. |
| Overall FHR Detection Percentage (Feasibility Study) | > 70% for the overall population. |
| 90% (±11.3) for subjects at least 32 weeks of gestation. | |
| Device Usability by Lay Users | Successfully demonstrated through a usability study. |
| Safety | No adverse events (procedure-related or device-related) reported during the feasibility study with 76 subjects. No adverse events reported in the pivotal clinical testing with 149 subjects. |
Study Details:
-
Sample sized used for the test set and the data provenance:
- Feasibility Study: 76 subjects. The text mentions "two in the United States and two outside the United States" for the pivotal study settings, which suggests a global data provenance, but it's not explicitly stated for the feasibility study. The feasibility study seems to have been retrospective based on the reporting ("510 recording sessions were executed").
- Pivotal Study: 149 subjects. The study was conducted in four healthcare settings (two in the United States and two outside the United States), indicating a prospective, multi-site approach.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
The document does not explicitly state the number or qualifications of experts used to establish ground truth for the test set. However, the pivotal study compared PregSense's performance to a "standard of care" monitoring device (CTG), implying that the CTG readings served as the reference standard, which would typically be interpreted by trained healthcare professionals. -
Adjudication method (e.g. 2+1, 3+1, none) for the test set:
The document does not specify an adjudication method like 2+1 or 3+1. The comparison was directly against a "standard of care" CTG system. -
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 done. This study focuses on the standalone performance of the PregSense device in measuring FHR and MHR compared to a standard, rather than evaluating how human readers' performance changes with AI assistance. -
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Yes, the performance data presented is for the standalone device (PregSense™ system, including its embedded sensors and associated software for analysis) compared to a "standard of care" CTG. The "PregSense ME App" and "PregSense MD App" are for displaying data, not for human interpretation during the measurement process that would alter the algorithm's output. The usability study involved lay users, but that was to ensure proper device handling, not to assess a human-in-the-loop diagnostic process. -
The type of ground truth used:
The ground truth was established by comparison to a "standard of care" monitoring device, specifically CTG (Cardiotocography). This is a widely accepted clinical method for monitoring fetal heart rate. -
The sample size for the training set:
The document does not provide information regarding the sample size used for the training set for the PregSense algorithms. It only discusses the clinical studies conducted for performance validation. -
How the ground truth for the training set was established:
The document does not provide information on how the ground truth for the training set was established, as details about the training set itself are absent.
§ 884.2730 Home uterine activity monitor.
(a)
Identification. A home uterine activity monitor (HUAM) is an electronic system for at home antepartum measurement of uterine contractions. The HUAM system comprises a tocotransducer and an at-home recorder. This device is intended for use in women with a previous preterm delivery to aid in the detection of preterm labor.(b)
Classification. Class II (special controls); guidance document (Class II Special Controls Guidance for Home Uterine Activity Monitors).