AI Blind-Sweep Ultrasound for Antenatal Screening by Non-Specialist Health Workers in Rural DR Congo
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexFemale
Age16+
SponsorSOIK Corporation Sarl
About this trial
FS2 evaluates the diagnostic accuracy and implementation feasibility of an AI-assisted blind-sweep obstetric ultrasound (SPAQ E-con AI), operated by trained non-specialist health workers, for antenatal screening in rural Democratic Republic of the Congo. Primary outcomes are gestational age mean absolute error (Trimester 2 and Trimester 3) with 95% confidence intervals and AI confidence calibration. The reference standard is manual measurement by a reference reader (early ultrasound first; manual BPD if unavailable; last menstrual period is not used). Target enrollment is approximately 1,430 (IRB-approved ceiling 3,000), with early termination permitted upon achievement of pre-specified analysis-plan thresholds. The study is a multi-center prospective Hybrid Type 1 Effectiveness-Implementation design and includes a pre-specified adaptive model-update (Batch 2 cut) plan following FDA PCCP and STARD-AI guidance.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Pregnant women
Identified at a participating facility routine ANC visit or RECO village outreach within the Kenge health zone catchment
Informed consent obtained (16-17 years with parent/guardian consent)
Disqualifiers
Emergency presentation
Multiple pregnancy
Duplicate re-registration of an already-enrolled woman
Lacking capacity to consent
Trial population
Pregnant women attending routine antenatal care at participating facilities or identified through community health worker (RECO) village outreach in the Kenge health zone, Kwango province, DRC.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
SPAQ E-con AI blind-sweep ultrasound
Diagnostic testSmartphone-based 9-sweep obstetric ultrasound with AI estimation of gestational age, fetal presentation, and placenta location, operated by trained non-specialist health workers after 30-60 minutes of training.
Treatment groups
3,000 Participants
are divided into 3 treatment groupsGroup A: Cohort A1 intervention
Group B: Cohort B-1 Placenta/malpresentation enriched1 intervention
Group C: Cohort B-2 - Trimester 1 (CRL/GS) enriched1 intervention
Trial outcomes
Primary outcomes
1
Gestational age mean absolute error (MAE), Trimester 2 (14-27 weeks)
MAE in days vs reference standard, with 95% CI; target MAE ≤7 days and upper 95% CI ≤10 days
Time frame
Through study completion, up to 12 months2
Gestational age mean absolute error (MAE), Trimester 3 (28-36 weeks)
MAE in days vs reference standard, with 95% CI; target MAE ≤10 days and upper 95% CI ≤14 days
Time frame
Through study completion, up to 12 months3
AI confidence calibration - Expected Calibration Error (ECE)
Expected Calibration Error from the reliability diagram of AI confidence versus reference-standard agreement; target \<=0.05
Time frame
At Batch 1 closure, up to 8 weeks4
AI confidence calibration - Brier score
Brier score of AI confidence versus reference-standard agreement; target \<=0.20
Time frame
At Batch 1 closure, up to 8 weeksSecondary outcomes
1
Trimester 1 gestational age MAE (CRL and GS models)
Integrated Cohort A T1 + Cohort B-2, N=30; CRL model MAE ≤5 days or GS model MAE ≤7 days
Time frame
Through study completion, up to 12 months2
Placenta praevia and fetal malpresentation sensitivity and specificity
Observed sensitivity/specificity with 95% CI (Clopper-Pearson) on enriched validation subset (Cohort B-1, target N=20-25); reported as observed values
Time frame
Through study completion, up to 12 months3
Inter-rater reliability of gestational age - Intraclass Correlation Coefficient (ICC)
ICC(2,1) between two independent readers for gestational age in days
Time frame
During the inter-rater assessment window, up to 1 week4
Inter-rater reliability of placenta praevia classification - Cohen's kappa
Cohen's kappa for placenta praevia (yes/no) between two independent readers
Time frame
During the inter-rater assessment window, up to 1 weekSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov