AI-Powered CURAᵀᴹ Application for Identifying At-Risk Pregnancies in Obstetric Management

NCT06974188 | Not Yet Recruiting DMC

• 1 other identifier: 2024-3832
• Study Type: interventional
• Target: 1,700
• Locations: 1 country
• Sites: 1

Brief Summary

It is important to identify high pregnancies early through screening so that appropriate care and intervention may be instituted. An AI-assisted risk categorisation approach may be advantageous compared with traditional means of screening. The purpose of this study is to determine if the adoption of an AI-assisted approach in general pregnancy risk screening will improve the accuracy of antenatal risk categorization into high- and low- risk pregnancy groups, ultimately resulting in fewer poor maternal and fetal/neonatal outcomes.

Conditions

High-risk Pregnancy; Pregnancy; Antenatal Health

Keywords

Machine-learning; Artificial Intelligence; Antenatal Risk Stratification; Software as a Medical Device; Machine Learning Algorithm; Pregnancy Complications; Neonatal Complications; Pregnancy outcomes; Obstetric complications; Antenatal care

Outcome Measures

Primary Outcomes (2)

• The number and proportion of cases displaying any one of the following outcomes listed below (composite):

  Presented as a relative risk (RR) with 95% CI, with and without stratification for parity, ethnicity and BMI. (i) Maternal * Postpartum haemorrhage more than/equal to 1000ml or requiring blood product transfusion * Eclampsia/severe eclampsia (blood pressure SBP\>160mmHg or diastolic \>110mmHg and/or significant end-organ damage which can include signs of liver or kidney impairment, low platelet count, fluid in the lungs or new-onset headache/visual disturbances) * ICU or HDU admission (excluding those who are admitted for precautionary monitoring) * Unplanned hysterectomy * Uterine rupture (symptomatic full thickness rupture) * Venous thromboembolism proven radiologically * Maternal mortality (ii) Neonatal: * Apgar scores \<7 at 5 minutes or less than/equal to 4 at 10 minutes * Respiratory distress requiring mechanical ventilation or surfactant treatment * Hypoxic ischaemic encephalopathy (HIE, any grade) * neonatal death (within 28 days of birth)/ * intrauterine demise

  At Delivery (Birth)

• In addition, these outcomes will be reported individually:

  Number and proportion, RR and 95% CI for each of the following: * Postpartum haemorrhage more than/equal to 1000ml or requiring blood product transfusion as well as mean difference in blood loss * Eclampsia/severe eclampsia (blood pressure SBP\>160mmHg or diastolic \>110mmHg and/or significant end-organ damage which can include signs of liver or kidney impairment, low platelet count, fluid in the lungs or new-onset headache/visual disturbances) as well as difference in gestational age of onset or diagnosis with and without adjustment for important covariates * ICU or HDU admission (excluding those who are admitted for precautionary monitoring) * Maternal mortality as well as cause of death * Respiratory distress requiring mechanical ventilation or surfactant treatment as well as aetiology for RDS * Hypoxic ischaemic encephalopathy (HIE, any grade) * Neonatal death (within 28 days of birth) * Intrauterine demise

  At Delivery (Birth)

Secondary Outcomes (3)

• To test the feasibility of an AI-assisted antenatal risk stratification approach in a real-life patient-care system - Quantitative; Mean Differences

  At baseline visit (first trimester antenatal visit)

• To test the feasibility of an AI-assisted antenatal risk stratification approach in a real-life patient-care system - Qualitative

  At baseline visit (first trimester antenatal visit)

• To test the feasibility of an AI-assisted antenatal risk stratification approach in a real-life patient-care system - Quantitative; Number

  At baseline visit (first trimester antenatal visit)

Study Arms (2)

AI-risk stratification arm

EXPERIMENTAL

During their first trimester antenatal visit, participants will be risk stratified by clinicians with the assistance of AI. The risk prediction of 'high risk' or 'low risk' will be immediately made known to the clinician during the visit. Similarly, during the 31 -34 weeks visit following release of oral glucose tolerance test and growth scan results, participants will be risk stratified by clinicians again with the assistance of AI.

Other: AI-risk Stratification

Non-AI arm (Current Risk Stratification)

NO INTERVENTION

During their first trimester antenatal visit, participants will be risk stratified by both clinicians alone and with the assistance of AI. However, the risk prediction of 'high risk' or 'low risk' will not be disclosed to the clinician at all. It will only be revealed to the study investigators at the end of the study. Similarly, during the 31 -34 weeks visit following release of oral glucose tolerance test and growth scan results, participants will be risk stratified by clinicians again with and without the assistance of AI. However, the risk prediction of 'high risk' or 'low risk' will not be disclosed to the clinician at all. It will only be revealed to the study investigators at the end of the study. Clinicians will use their own judgement as to the risk of the participants' pregnancies. They have to adhere to the same specific 'high-risk' and 'low-risk' management protocol.

Interventions

AI-risk Stratification OTHER

With the results being disclosed as 'high-risk' or 'low-risk' in the experimental arm, clinicians have to adhere to a specific 'high-risk' and 'low-risk' management protocol for participants.

AI-risk stratification arm

Eligibility Criteria

• Age: 21 Years - 50 Years
• Sex: female
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64)

You may qualify if:

• Age: 21 years old to 50 years old
• Singleton Pregnancy
• No more than 13 weeks' and 6 days' gestation at recruitment
• Able to provide written, informed consent

You may not qualify if:

• Not proficient in the English language (AI intervention is only available in English at this stage)

Sponsors & Collaborators

• National University Hospital, Singapore: lead
• National University of Singapore: collaborator
• National University of Singapore, Saw Swee Hock School of Public Health: collaborator
• Agency for Science, Technology and Research (A*STAR): collaborator

Study Sites (1)

National University Hospital

Singapore, Singapore

Location

Related Publications (10)

• Rivera SC, Liu X, Chan AW, Denniston AK, Calvert MJ; SPIRIT-AI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI Extension. BMJ. 2020 Sep 9;370:m3210. doi: 10.1136/bmj.m3210.

  PMID: 32907797 BACKGROUND

• Malacova E, Tippaya S, Bailey HD, Chai K, Farrant BM, Gebremedhin AT, Leonard H, Marinovich ML, Nassar N, Phatak A, Raynes-Greenow C, Regan AK, Shand AW, Shepherd CCJ, Srinivasjois R, Tessema GA, Pereira G. Stillbirth risk prediction using machine learning for a large cohort of births from Western Australia, 1980-2015. Sci Rep. 2020 Mar 24;10(1):5354. doi: 10.1038/s41598-020-62210-9.

  PMID: 32210300 BACKGROUND

• Jhee JH, Lee S, Park Y, Lee SE, Kim YA, Kang SW, Kwon JY, Park JT. Prediction model development of late-onset preeclampsia using machine learning-based methods. PLoS One. 2019 Aug 23;14(8):e0221202. doi: 10.1371/journal.pone.0221202. eCollection 2019.

  PMID: 31442238 BACKGROUND

• Arabi Belaghi R, Beyene J, McDonald SD. Prediction of preterm birth in nulliparous women using logistic regression and machine learning. PLoS One. 2021 Jun 30;16(6):e0252025. doi: 10.1371/journal.pone.0252025. eCollection 2021.

  PMID: 34191801 BACKGROUND

• Bhutta ZA, Das JK, Bahl R, Lawn JE, Salam RA, Paul VK, Sankar MJ, Blencowe H, Rizvi A, Chou VB, Walker N; Lancet Newborn Interventions Review Group; Lancet Every Newborn Study Group. Can available interventions end preventable deaths in mothers, newborn babies, and stillbirths, and at what cost? Lancet. 2014 Jul 26;384(9940):347-70. doi: 10.1016/S0140-6736(14)60792-3. Epub 2014 May 19.

  PMID: 24853604 BACKGROUND

• Gosavi A, Amin Z, Carter SWD, Choolani MA, Fee EL, Milad MA, Jobe AH, Kemp MW. Antenatal corticosteroids in Singapore: a clinical and scientific assessment. Singapore Med J. 2024 Sep 1;65(9):479-487. doi: 10.4103/SINGAPOREMEDJ.SMJ-2022-014. Epub 2022 Oct 6.

  PMID: 36254928 BACKGROUND

• Hewage S, Audimulam J, Sullivan E, Chi C, Yew TW, Yoong J. Barriers to Gestational Diabetes Management and Preferred Interventions for Women With Gestational Diabetes in Singapore: Mixed Methods Study. JMIR Form Res. 2020 Jun 30;4(6):e14486. doi: 10.2196/14486.

  PMID: 32602845 BACKGROUND

• Phibbs CM, Kozhimannil KB, Leonard SA, Lorch SA, Main EK, Schmitt SK, Phibbs CS. A Comprehensive Analysis of the Costs of Severe Maternal Morbidity. Womens Health Issues. 2022 Jul-Aug;32(4):362-368. doi: 10.1016/j.whi.2021.12.006. Epub 2022 Jan 12.

  PMID: 35031196 BACKGROUND

• Chi C, Pang D, Aris IM, Teo WT, Li SW, Biswas A, Yong EL, Chong YS, Tan K, Kramer MS. Trends and predictors of cesarean birth in Singapore, 2005-2014: A population-based cohort study. Birth. 2018 Dec;45(4):399-408. doi: 10.1111/birt.12341. Epub 2018 Feb 17.

  PMID: 29453821 BACKGROUND

• Fink DA, Kilday D, Cao Z, Larson K, Smith A, Lipkin C, Perigard R, Marshall R, Deirmenjian T, Finke A, Tatum D, Rosenthal N. Trends in Maternal Mortality and Severe Maternal Morbidity During Delivery-Related Hospitalizations in the United States, 2008 to 2021. JAMA Netw Open. 2023 Jun 1;6(6):e2317641. doi: 10.1001/jamanetworkopen.2023.17641.

  PMID: 37347486 BACKGROUND

MeSH Terms

Conditions

Pregnancy Complications

Condition Hierarchy (Ancestors)

Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases

Study Officials

• Sarah Li, MRCOG, MPH

  National University Hospital, Singapore

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Sarah Li, MRCOG, MPH

CONTACT

(+65)97833106; sarah_wl_li@nuhs.edu.sg

Harshaana Ramlal, BSc (Hons)

CONTACT

(+65) 90065802; ramlal_harshaana@nuhs.edu.sg

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: TRIPLE
• Who Masked: PARTICIPANT, INVESTIGATOR, OUTCOMES ASSESSOR
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Model Details: The study employs a two parallel arm, single-blinded, pragmatic randomised controlled trial design. In this design, pregnant women will be randomly assigned in a 1:1 ratio to an AI-assisted risk categorization approach or the current manual risk stratification method.

Study Record Dates

• First Submitted: April 29, 2025
• First Posted: May 15, 2025
• Study Start: August 1, 2025
• Primary Completion (Estimated): September 1, 2026
• Study Completion (Estimated): March 1, 2027
• Last Updated: July 15, 2025

Record last verified: 2024-11

Locations

SG (1)