AI-POCUS for Maternal and Neonatal Health in Ethiopia

NCT07171086 | Not Yet Recruiting Phase 4 DMC

• 2 other identifiers: PROJECT #: BRIGHT (202430045)BRIGHT (202430045)
• Study Type: interventional
• Target: 1,059
• Locations: 1 country
• Sites: 1

Brief Summary

Maternal and neonatal health remains one of the most pressing global health challenges, particularly in low- and middle-income countries (LMICs). Ethiopia continues to face a high burden, with maternal mortality estimated at 195 per 100,000 live births, neonatal mortality at 27 per 1,000 live births, and perinatal mortality rates ranging from 37‰ to 124‰ depending on the level of care. These outcomes remain substantially higher than the targets set under the United Nations Sustainable Development Goals (SDGs) for 2030. The World Health Organization (WHO) recommends that all pregnant women receive at least one ultrasound scan before 24 weeks of gestation, yet nearly two-thirds of women worldwide-especially in LMICs-lack access to this service. Barriers include high costs of ultrasound machines, limited technical expertise, and shortages of skilled sonographers in rural primary care. Artificial Intelligence-driven Point-of-Care Ultrasound (AI-POCUS) represents a promising innovation to expand prenatal imaging in resource-constrained settings by equipping frontline health workers with AI-supported diagnostic capabilities. This study, conducted under the Tsinghua University BRIGHT (Bringing Research to Impact for Global Health at Tsinghua) program, will evaluate the clinical effectiveness, feasibility, cost, and scalability of AI-POCUS in rural Ethiopia. A three-arm cluster randomized controlled trial will compare two AI-enabled ultrasound technologies-BabyChecker (Netherlands) and a China-developed AI-POCUS device-against standard antenatal care without ultrasound. Findings will generate robust clinical and policy-relevant evidence to guide the sustainable implementation of AI-enabled maternal health interventions in sub-Saharan Africa.

Conditions

Pregnancy; Pregnancy Complications; Preterm Birth; Fetal Growth Restriction; Stillbirth and Fetal Death; Pregnancy Abnormal

Keywords

Artificial Intelligence; Point-of-Care Ultrasound (POCUS); Maternal and Neonatal Health; Cluster Randomized Controlled Trial; Sub-Saharan Africa; Rural Centers

Outcome Measures

Primary Outcomes (6)

• Maternal Mortality Ratio

  Maternal deaths per 100,000 live births, defined as deaths occurring during pregnancy or within 42 days postpartum due to pregnancy-related causes.

  Baseline through 42 days postpartum

• Stillbirth Rate / Perinatal Mortality Rate

  Stillbirths (≥28 weeks gestation) per 1,000 total births, and perinatal mortality including stillbirths and neonatal deaths within the first 7 days of life.

  Delivery through 7 days postpartum

• Early Neonatal Mortality Rate

  Neonatal deaths within the first 7 days of life per 1,000 live births.

  Birth through 7 days postpartum

• Preterm Birth Rate

  Proportion of births before 37 completed weeks of gestation, subdivided into extremely preterm (\<32 weeks), very preterm (32-33 weeks), and late preterm (34-36 weeks).

  At delivery

• Maternal and Neonatal Referral Rate

  Proportion of mothers or newborns referred to higher-level hospitals due to severe complications.

  Antenatal period through 42 days postpartum

• Congenital Anomaly Rate

  Proportion of infants with major structural anomalies detected by prenatal ultrasound or confirmed postnatally (e.g., neural tube defects, limb malformations, cleft lip/palate).

  Antenatal period through delivery

Secondary Outcomes (4)

• Completion of ≥4/8 Antenatal Care (ANC) Visits

  Pregnancy through delivery

• High-Risk Pregnancy Detection Rate

  Pregnancy through delivery

• High-Risk Pregnancy Follow-Up Completion Rate

  Pregnancy through delivery

• Referral Completion Rate After Screening

  Pregnancy through delivery

Study Arms (3)

Standard Care Control

NO INTERVENTION

Participants in this arm will receive routine antenatal care (ANC) according to Ethiopian national guidelines, without the use of AI-POCUS devices. All examinations, screenings, and referrals will be conducted through standard clinical practice. This group serves as the baseline comparator for evaluating the added impact of AI-POCUS technology.

BabyChecker (Delft Imaging, Netherlands)

EXPERIMENTAL

Health centers in this arm will be equipped with the BabyChecker system developed by Delft Imaging (Netherlands). The portable device integrates fetal position, amniotic fluid volume, and biparietal diameter measurements, and provides diagnostic suggestions and risk alerts. After brief training, primary healthcare workers will independently perform antenatal examinations, screen for obstetric complications, and make referral decisions.

Device: AI-POCUS (BabyChecker, Delft Imaging)

AI-POCUS (Edan, China)

EXPERIMENTAL

This arm will use the AI-POCUS device developed by Edan (China), designed to analyze blind ultrasound sweeps and automatically extract fetal diagnostic parameters. The system supports the early detection of maternal and fetal risks and assists in clinical decision-making.

Device: AI-POCUS (Edan, China)

Interventions

AI-POCUS (BabyChecker, Delft Imaging) DEVICE

A portable AI-driven ultrasound system developed by Delft Imaging (Netherlands). The device integrates fetal position, amniotic fluid volume, and biparietal diameter measurements, with built-in diagnostic suggestions and risk alerts. Primary healthcare workers, after brief training, use it for antenatal screening, complication detection, and referral decision-making.

BabyChecker (Delft Imaging, Netherlands)

AI-POCUS (Edan, China) DEVICE

An AI-POCUS device developed by Edan (China), capable of analyzing blind ultrasound sweeps to extract fetal diagnostic parameters and assist in early risk identification. It supports clinical decision-making for antenatal care.

AI-POCUS (Edan, China)

Eligibility Criteria

• Age: 15 Years - 49 Years
• Sex: female
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64)

You may qualify if:

• Aged 15-49 years;
• Gestational age less than 24 weeks at the first ANC visit;
• No history of severe pregnancy complications (e.g., placenta previa, preeclampsia, etc.);
• Signed informed consent and agreed to participate in the study.

You may not qualify if:

• Pregnant women with cognitive impairments or unable to communicate effectively;
• Failure to complete antenatal care within the specified timeframe;
• Incomplete or unavailable records of antenatal care and delivery.

Sponsors & Collaborators

• Tsinghua University: lead
• Debre Berhan University: collaborator

Study Sites (1)

Hakim Gizaw Hospital

Debre Berhan, Amhara, 1000, Ethiopia

Location

MeSH Terms

Conditions

Pregnancy Complications; Premature Birth; Fetal Growth Retardation; Stillbirth; Fetal Death

Condition Hierarchy (Ancestors)

Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Obstetric Labor, Premature; Obstetric Labor Complications; Fetal Diseases; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Growth Disorders; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Death

Study Officials

• Kun TANG, Associate Professor

  Tsinghua University

  STUDY CHAIR

Central Study Contacts

Yuxuan LI, Doctoral Candidate

CONTACT

+86-18813076657; li-yx23@mails.tsinghua.edu.cn

Study Design

• Study Type: interventional
• Phase: phase 4
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Masking Details: Other parties masked in this trial include the data analysts, who will remain blinded to group assignments during statistical analyses to minimize bias in outcome assessment.
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Doctoral Candidate

Model Details: This study will employ a cluster randomized controlled trial design, with primary health care centers serving as the cluster (intervention) units and individual pregnant women as the primary observational units. A total of nine health centers will be selected and matched based on geographic location, maternal mortality rates, and the service capacity of health care personnel. The matched health centers will then be randomly assigned in a 1:1:1 ratio to one of three study arms, with each arm including three health centers. A total of 1,059 pregnant women will be recruited, with 353 participants per study arm. Interventions will be implemented at the cluster level, while outcomes - including maternal and neonatal health indicators - will be assessed at the individual participant level. This design allows for the evaluation of the effectiveness and feasibility of AI-POCUS interventions while accounting for intra-cluster correlation and contextual variability across health centers.

Study Record Dates

• First Submitted: September 5, 2025
• First Posted: September 12, 2025
• Study Start: September 30, 2025
• Primary Completion: March 31, 2026
• Study Completion (Estimated): August 31, 2026
• Last Updated: September 12, 2025

Record last verified: 2025-09

Locations

ET (1)