Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Oct 3, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

PredictPTB: an interpretable preterm birth prediction model using attention-based recurrent neural networks.

Rawan AlSaad¹, Qutaibah Malluhi¹, Sabri Boughorbel²

¹College of Engineering, Qatar University, Doha, Qatar.

|February 15, 2022

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Artificial intelligence for postpartum hemorrhage: a systematic review.

Frontiers in global women's health·2026

Same author

Endo-MedSAM: a promptable vision foundation model adaptation for uterus segmentation on pelvic MRI in endometriosis.

Frontiers in reproductive health·2026

Same author

Temporal and Behaviour-Aware Multimodal Modelling for Hour-Ahead Hypoglycaemia Prediction During Ramadan Fasting in Type 1 Diabetes.

Sensors (Basel, Switzerland)·2026

Same author

Depression subtype classification from social media posts: few-shot prompting vs. fine-tuning of large language models.

Frontiers in digital health·2026

Same author

Predicting Infant Sleep Patterns From Postpartum Maternal Mental Health Measures: Machine Learning Approach.

JMIR pediatrics and parenting·2026

Same author

Predicting mood swings in women of reproductive age using machine learning on metabolic, menstrual, and lifestyle indicators.

Frontiers in global women's health·2026

PredictPTB, a new model using electronic health records, accurately predicts preterm birth risk up to nine months in advance. This tool offers interpretable insights for clinicians, improving prenatal care for at-risk pregnancies.

Area of Science:

Medical Informatics
Computational Biology
Clinical Prediction Models

Background:

Preterm birth (PTB) is a leading cause of infant mortality and morbidity.
Effective prediction models for PTB are lacking, hindering timely prenatal care.
Electronic Health Records (EHR) contain valuable data for developing predictive tools.

Purpose of the Study:

To develop and validate PredictPTB, a clinical prediction model for preterm birth risk.
To utilize readily accessible EHR variables for accurate PTB forecasting.
To provide interpretable predictions for clinicians to enhance prenatal care.

Main Methods:

Recurrent Neural Networks (RNNs) were employed to model longitudinal EHR data.
A single code-level attention mechanism was utilized for improved predictive performance and interpretability.

Keywords:

Attention mechanism Deep learning Electronic health record Predictive models Pregnancy Preterm birth

More Related Videos

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

Preterm EEG: A Multimodal Neurophysiological Protocol

Preterm EEG: A Multimodal Neurophysiological Protocol

Published on: February 18, 2012

Related Experiment Videos

Last Updated: Oct 3, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Assessment and Evaluation of the High Risk Neonate: The NICU Network Neurobehavioral Scale

Published on: August 25, 2014

Preterm EEG: A Multimodal Neurophysiological Protocol

Preterm EEG: A Multimodal Neurophysiological Protocol

Published on: February 18, 2012

Model performance was evaluated across different prediction time-points, data modalities, and data windows.

Main Results:

PredictPTB achieved an ROC-AUC of 0.82 at 1 month and 0.78 at 6 months prior to delivery.
Observational data, such as diagnoses, proved more predictive of PTB than interventional data (medications, procedures).
The model was trained and validated on a large cohort of 222,436 deliveries.

Conclusions:

PredictPTB offers accurate and scalable preterm birth risk prediction.
The model provides interpretable explanations by highlighting EHR timeline evidence.
This tool has the potential to significantly improve prenatal care for high-risk pregnancies.