Delivery Date AI is an FDA De Novo-cleared, cloud-based Software as a Medical Device (SaMD) designed to assist healthcare providers in predicting the delivery date of a pregnancy using ultrasound imaging. It is intended for use in singleton pregnancies at or between 14 0/7 and 36 6/7 weeks gestation where a reliable estimated delivery date is unavailable.

Standard dating methods rely on last menstrual period and first-trimester biometry. When those are unavailable or unreliable, due to irregular cycles, absent first-trimester ultrasound, or late presentation, clinicians are left estimating gestational age without a reliable foundation. 

Delivery Date AI provides an independent, image-based Predicted Delivery Date (PDD) to support clinical judgment in these cases.

The PDD should be used as an aid to clinical judgment, alongside standard-of-care methods for assessing gestational age. It is not intended to replace clinical expertise or serve as the sole basis for clinical decisions. If the PDD differs from the clinician's EDD by more than 10 days, a holistic reassessment of the clinical scenario and patient history is recommended.

In clinical validation (N=247 suboptimally dated singleton pregnancies), Delivery Date AI achieved a Mean Absolute Error (MAE) of 15.22 days (95% CI: 13.67 to 16.77), compared to the Hadlock method's MAE of 36.41 days (95% CI: 32.88 to 39.94). This represents a 21.19-day absolute improvement over the pre-specified 7-day superiority margin (p<0.001), and a 58% reduction in prediction error compared to the current standard of care.

The study enrolled 247 patients with singleton pregnancies between 14 and 36 weeks gestation who lacked a reliable estimated delivery date due to irregular cycles, no first-trimester ultrasound, or late presentation. Results apply to this suboptimally dated population and should not be generalized to all pregnancies.

Delivery Date AI has been validated for use with 2D grayscale (including Doppler) images acquired from GE and Philips ultrasound systems, using convex, micro-convex, and transvaginal probes. Performance on images from vendors other than GE and Philips has not been established. Phased array and linear probes are not supported.

The system accepts DICOM files (.dcm) containing 2D grayscale static images, including Doppler. JPEG, PNG, 3D/4D, M-mode, cine loops, and video formats are not supported.

Delivery Date AI is not intended for use in multiple gestations, pregnancies with known fetal anomalies, first trimester pregnancies (under 14 0/7 weeks), or pregnancies at or beyond 37 0/7 weeks. It does not forecast medically induced delivery or predict the risk of preterm birth. It provides an estimate for spontaneous delivery only.

Delivery Date AI is intended to be used once per pregnancy, on the earliest eligible standard-of-care ultrasound examination in a suboptimally dated pregnancy. It is not intended for serial monitoring or repeated use to revise an existing EDD.

Delivery Date AI has received FDA De Novo clearance, establishing a new regulatory category for AI-powered delivery date prediction.

 It is also approved in Brazil (ANVISA) and offered in Chile under local regulatory allowances. Federal law restricts this device to sale by or on the order of a physician or other licensed healthcare professional.

Delivery Date AI complies with HIPAA and relevant privacy regulations. All data is encrypted using SSL/TLS protocols. The platform supports two-factor authentication for enhanced account security.