AI May Estimate Gestational Age

An adapted AI model estimated gestational age with accuracy comparable to the clinical standard when novice operators performed blind sweep ultrasonography in two clinical settings.

By
Andrea Surnit
September 15, 2026
3 min

MDSpire News

At a Glance

Category	Detail
Condition	Gestational Age Estimation
Key Mechanisms	Artificial intelligence model for estimating gestational age from blind sweep ultrasonography.
Target Population	Pregnant individuals between 16 and 36 weeks gestation.
Care Setting	Clinical environments using ultrasonography.

Key Highlights

AI model achieved a mean absolute error (MAE) of 4.2 days compared to 4.5 days for the clinical standard.
Performance was consistent across urban medical centers in Chicago and Nairobi.
No systematic bias in gestational age estimation was observed.
Improved accuracy noted among fetuses above the 90th weight percentile.
Performance variability was noted beyond 36 weeks’ gestation.

Guideline-Based Recommendations

Diagnosis

Use AI model for gestational age estimation in clinical settings.

Management

Consider AI model as a noninferior alternative to standard clinical ultrasonography.

Monitoring & Follow-up

Evaluate performance across different gestational ages and operator experience.

Risks

Potential variability in performance for late-term pregnancies.

Patient & Prescribing Data

Patients with pregnancies between 16 and 36 weeks.

AI model's performance should be evaluated in clinical settings.

Clinical Best Practices

Implement structured hands-on instruction for novice operators to improve image acquisition.
Refine AI model for better performance in later gestation.