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: Jan 3, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine learning mortality classification in clinical documentation with increased accuracy in visual-based analyses.

Susan M Slattery^1,2,3, Daniel C Knight⁴, Debra E Weese-Mayer^1,2,3

¹Stanley Manne Children's Research Institute, Chicago, IL, USA.

Acta Paediatrica (Oslo, Norway : 1992)

|November 26, 2019

Summary

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

Wireless, skin-interfaced multimodal sensing system for continuous psychophysiological monitoring-A wearable polygraph device.

Science advances·2026

Same author

Recognition of a Critical Functional Domain and Improved <i>PHOX2B</i> Missense Variant Interpretation by Utilization of In Silico Prediction Tools.

Human mutation·2026

Same author

Dexmedetomidine and midazolam usage and association with BSRI scores in preterm infants with chronic respiratory failure.

Journal of perinatology : official journal of the California Perinatal Association·2026

Same author

Importance of Engaging Partners in Digital Postpartum Depression Prevention: Qualitative Study.

JMIR pediatrics and parenting·2025

Same author

Continuous wireless sensor monitoring with applied diagnostics: Clinical Sensor Pain Scale and Automated Sensor Pain Scale in the NICU.

BMJ health & care informatics·2025

Same author

Reliability of Composite Autonomic Symptom Score (COMPASS)-31 in Congenital Central Hypoventilation Syndrome.

Pediatric pulmonology·2025

Same journal

Prevalence of Breastfeeding in Infants With Down Syndrome: A Systematic Review and Meta-Analysis.

Acta paediatrica (Oslo, Norway : 1992)·2026

Same journal

Incidence of Childhood Dilated Cardiomyopathy in Sweden From 1991 to 2019: A National Population-Based Study.

Acta paediatrica (Oslo, Norway : 1992)·2026

Same journal

Critically Ill Children Show Disrupted Sleep Patterns and Atypical Electroencephalograms: An Observational Cohort Study.

Acta paediatrica (Oslo, Norway : 1992)·2026

Same journal

Multifactorial Nature of Childhood Stroke Presents a Major Challenge for Diagnosis and Management: A Population-Based Study From Southern Finland.

Acta paediatrica (Oslo, Norway : 1992)·2026

Same journal

Re: Comment on "Metabolic Risk Factors Are Associated With Weight Status Change Over Four Years in Children Aged 4-6 Years With Obesity".

Acta paediatrica (Oslo, Norway : 1992)·2026

Same journal

Impact of Phototherapy Blanket Treatment on Need for Overhead Phototherapy in Term Infants-A Randomised Controlled Trial (The Babies in Blankets Trial-BiB Trial).

Acta paediatrica (Oslo, Norway : 1992)·2026

See all related articles

This summary is machine-generated.

Machine learning models, including convolutional neural networks, can predict mortality in neonatal hypoxic-ischaemic encephalopathy (HIE) using clinical notes. Convolutional models showed high specificity, offering a foundation for clinical decision support tools.

Area of Science:

Neonatal Medicine
Artificial Intelligence
Clinical Informatics

Background:

The predictive value of machine learning (ML) in clinical documentation for patient outcomes is not well-established.
Predicting mortality in neonatal hypoxic-ischaemic encephalopathy (HIE) is crucial for timely intervention and resource allocation.

Purpose of the Study:

To compare the performance of three distinct neural network architectures in predicting mortality among neonates diagnosed with HIE.
To evaluate the utility of inpatient provider documentation for ML-driven mortality prediction in HIE.

Main Methods:

Utilized data from the Children's Hospitals Neonatal Database for neonates with HIE treated with therapeutic hypothermia.
Applied convolutional neural networks (CNNs) and two recurrent neural network (RNN) models to the initial seven days of clinical documentation.

Keywords:

clinical documentation deep learning electronic health records machine learning neural networks

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jan 3, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Assessed predictive accuracy and performance metrics, with mortality as the primary outcome.

Main Results:

The study included 52 eligible infants; 69% survived, and 44% had severe HIE.
All neural network models outperformed baseline predictions.
Convolutional networks demonstrated a median accuracy of 72% and a median specificity of 81% for mortality prediction.

Conclusions:

Neural network models, particularly convolutional networks, show promise in predicting mortality in neonatal HIE using clinical documentation.
These findings support the development of ML tools to aid clinicians in risk stratification and patient assessment for HIE.
Further research can build upon these models for enhanced clinical decision support systems.