fairfolio
Saved Projects

MaternalGuard AI: Protecting Every Precious Heartbeat

CSEF · 2026 Medicine & Physiology (Junior Division)

Arnav Kochar

Overview

Pregnancy complications drive approximately 13.4 million preterm births globally each year and contribute to roughly 900,000 preventable neonatal deaths from conditions such as preeclampsia, fetal distress, and gestational diabetes. Traditional prenatal care depends on infrequent clinical visits that frequently miss subtle, early changes in vital signs, leaving both mother and baby at risk. Inspired by my premature birth at 33 weeks, when my mother noticed reduced fetal movement and doctors later detected a slowed heartbeat, this project introduces MaternalGuard AI, an affordable, stomach-wearable prototype that provides continuous, offline monitoring and predictive alerts. The system integrates five Arduino-compatible sensors embedded in an abdominal belt: MPU6050 accelerometer for fetal movement and uterine contractions, AD8232 ECG module for maternal heart rate, DS18B20 digital temperature sensor, force-sensitive resistors for contraction pressure, and a piezoelectric sensor for maternal respiratory rate. Real-time data undergo preprocessing to remove noise and are labeled according to clinical complication indicators. A hybrid LSTM/CNN model, trained on Public Clinical validated datasets (PhysioNet and Kaggle) with data augmentation, learns predictive patterns for 14+ complications including preeclampsia, gestational diabetes, and fetal distress. In validation testing, the model achieved 95.87% predictive accuracy, significantly outperforming reactive monitoring approaches. Edge deployment on an Arduino R4 WiFi board enables encrypted, internet-independent operation with HIPAA-compliant data handling and extended battery life. MaternalGuard AI transforms prenatal care from reactive to proactive, delivering early alerts that can improve health outcomes for mothers and infants worldwide while remaining accessible in both high- and low-resource settings.

Competition history

  • CSEF 2026 Medicine & Physiology (Junior Division) · Entry J-15-04

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google