Abstract #
Current predictive models for pregnancy and infant outcomes often focus on limited endpoints and rely on costly tests or imaging. Here we developed the Mother-Child AI Agent (MoChiAgent), an LLM-based clinical assistant that orchestrates multiple tools to integrate sequential electronic health record (EHR) data, including routine laboratory tests, for forecasting maternal and infant diseases. MoChiAgent’s core predictive engine, MoChiFormer, was developed and internally evaluated using 4,401,599 longitudinal clinical visits and externally validated using independent maternal and infant cohorts consisting of 263,452 and 23,192 visits, respectively. MoChiFormer reconstructs missing laboratory values, reduces batch effects and learns EHR representations that support gestational, fetal and infant age estimation, health-trajectory modelling and stratification of current and future disease risk. Subsequently, a Knowledge Search Tool utilizes these forecasts to retrieve evidence-based intervention and treatment recommendations from curated medical literature and authoritative guidelines. For maternal health, MoChiFormer accurately identified key gestational conditions, achieving AUROCs of 0.89 for placental abruption, 0.89 for premature rupture of membranes, and 0.91 for preterm labour. Analysis of paired mother-infant data further revealed transgenerational risk associations, with infants born to mothers in specific clusters showing substantially elevated risks of neonatal jaundice (HR = 2.81, 95% CI 2.60-3.03) and haematological diseases (HR = 2.83, 95% CI 2.62-3.05). Integrating maternal gestational EHRs with infant records improved prediction of infant conditions, including chromosomal abnormalities and respiratory disorders. These findings suggest that MoChiAgent can provide clinically relevant, actionable decision-support information to enhance risk-stratified care for mothers and infants.
Supplementary information #
Supplementary Information (download PDF )
Supplementary Figures 1–11 and associated figure legends.
Supplementary Tables (download XLSX )
Workbook containing Supplementary Tables 1–3: maternal high-versus low-risk cluster statistics for Figure 3b–i; infant transgenerational high-versus low-risk cluster statistics for Figure 5b–i; and abbreviations for clinical biomarkers and features used in Figure 2g–i.
Source data #
Source Data Extended Data Fig. 7 (download XLSX )
Source data for Extended Data Fig. 7. This Excel file contains individual physician evaluation scores for each case and each system (MoChiAgent, ChatGPT, Gemini and OpenEvidence) across diagnostic accuracy, evidence traceability, completeness of the diagnostic and therapeutic plan, and clinical safety.
Rights and permissions #
This article is published under an open access license.
Please check the 'Copyright Information' section either on this page or in the PDF
for details of this license and what re-use is permitted.
If your intended use exceeds what is permitted by the license or if
you are unable to locate the licence and re-use information,
please contact the [Rights and
Permissions team](mailto:journalpermissions@springernature.com).
About this article #
Cite this article
Liu, S., Zheng, W., Kang, J. et al. Prediction of maternal and infant outcomes from longitudinal electronic health records with a Mother-Child AI agent.
*Nat Med* (2026). https://doi.org/10.1038/s41591-026-04694-y
- Received:
- Accepted:
- Published:
- DOI: https://doi.org/10.1038/s41591-026-04694-y