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

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

Income level and the risk of incident dementia among adults aged ≥50 with newly diagnosed type 2 diabetes: a population-based cohort study using the NHIS-Senior database in South Korea.

BMJ open·2026

Same author

Global trends and geographic variations of hypertension in childhood and adolescence 1990-2021: a systematic analysis of the Global Burden of Disease Study 2021.

Clinical hypertension·2026

Same author

Association between household type and false reporting of smoking among South Korean adults.

Tobacco control·2026

Same author

Periodontitis and Incident Diabetes Mellitus: A Nationwide Cohort Study From Korea.

Journal of periodontal research·2026

Same author

Association Between Health Literacy and Prehypertension in South Korean Adults: Cross-Sectional Study Using the 2023 Korea National Health and Nutrition Examination Survey.

JMIR public health and surveillance·2026

Same author

Impact of Designated Recovery Rehabilitation Institutions on the Readmission Rate of Older Adults.

Journal of clinical medicine·2026

Search research articles

Related Experiment Video

Updated: Jul 23, 2025

The Use of Trace Eyeblink Classical Conditioning to Assess Hippocampal Dysfunction in a Rat Model of Fetal Alcohol Spectrum Disorders

The Use of Trace Eyeblink Classical Conditioning to Assess Hippocampal Dysfunction in a Rat Model of Fetal Alcohol Spectrum Disorders

Published on: August 5, 2017

Predicting Fetal Alcohol Spectrum Disorders Using Machine Learning Techniques: Multisite Retrospective Cohort Study.

Sarah Soyeon Oh^1,2, Irene Kuang³, Hyewon Jeong³

¹Department of Social and Behavioral Sciences, Harvard TH Chan School of Public Health, Boston, MA, United States.

Journal of Medical Internet Research

|July 18, 2023

Summary

This summary is machine-generated.

Machine learning accurately predicts Fetal Alcohol Syndrome (FAS) risk in infants exposed to alcohol during pregnancy. The CatBoost algorithm showed the best performance, identifying key risk factors like drinking duration and maternal age.

Keywords:

age alcohol alcohol exposure algorithm antenatal development developmental developmental disability diagnosis diagnostic disability fetal fetal alcohol syndrome fetus gynecology machine learning maternal obstetric postnatal predict pregnancy pregnant prenatal prenatal alcohol exposure race treatment

More Related Videos

Moderate Prenatal Alcohol Exposure and Quantification of Social Behavior in Adult Rats

Moderate Prenatal Alcohol Exposure and Quantification of Social Behavior in Adult Rats

Published on: December 14, 2014

Modeling Fetal Alcohol Spectrum Disorders in Zebrafish to Characterize the Impact of an Adverse Embryonic Environment on Adult Social Behavior

Modeling Fetal Alcohol Spectrum Disorders in Zebrafish to Characterize the Impact of an Adverse Embryonic Environment on Adult Social Behavior

Published on: February 9, 2024

Related Experiment Videos

Last Updated: Jul 23, 2025

The Use of Trace Eyeblink Classical Conditioning to Assess Hippocampal Dysfunction in a Rat Model of Fetal Alcohol Spectrum Disorders

The Use of Trace Eyeblink Classical Conditioning to Assess Hippocampal Dysfunction in a Rat Model of Fetal Alcohol Spectrum Disorders

Published on: August 5, 2017

Moderate Prenatal Alcohol Exposure and Quantification of Social Behavior in Adult Rats

Moderate Prenatal Alcohol Exposure and Quantification of Social Behavior in Adult Rats

Published on: December 14, 2014

Modeling Fetal Alcohol Spectrum Disorders in Zebrafish to Characterize the Impact of an Adverse Embryonic Environment on Adult Social Behavior

Modeling Fetal Alcohol Spectrum Disorders in Zebrafish to Characterize the Impact of an Adverse Embryonic Environment on Adult Social Behavior

Published on: February 9, 2024

Area of Science:

Medical Informatics
Machine Learning
Public Health

Background:

Fetal Alcohol Syndrome (FAS) is a significant developmental disability linked to prenatal alcohol exposure (PAE).
Early diagnosis and intervention are crucial for managing FAS, necessitating improved predictive models.
Understanding risk factors associated with PAE is key to prevention and treatment strategies.

Purpose of the Study:

To compare the effectiveness of various machine learning algorithms in predicting FAS.
To identify the most influential variables for accurate FAS prediction in cases of prenatal alcohol exposure.
To evaluate the predictive performance of models trained on data from women who consumed alcohol during pregnancy.

Main Methods:

Utilized data from a collaborative initiative on fetal alcohol spectrum disorders (2007-2017) involving 595 women with PAE.
Employed questionnaires, interviews, and record reviews to gather comprehensive alcohol consumption data.
Trained and compared four machine learning algorithms (logistic regression, XGBoost, light GBM, CatBoost) using 80% of data for training and 20% for testing, measuring performance via AUROC and AUPRC.

Main Results:

The CatBoost algorithm achieved the highest predictive performance with an AUROC of 0.92 and AUPRC of 0.51.
Key predictors identified by CatBoost included drinking throughout all three trimesters, maternal age, race, and type of alcohol consumed.
The model demonstrated strong overall accuracy (0.96) with specific performance metrics including precision (0.50), specificity (0.29), and F1 score (0.29).

Conclusions:

Machine learning models significantly enhance the prediction of FAS risk compared to previous methods.
Boosting algorithms like CatBoost are particularly effective for small, imbalanced datasets common in FAS research.
These advanced models offer a promising avenue for earlier identification and intervention for Fetal Alcohol Syndrome.