Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

188
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
188
Regression Toward the Mean01:52

Regression Toward the Mean

6.5K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.5K

You might also read

Related Articles

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

Sort by
Same author

Genome-Wide Identification of the P-Type Ca<sup>2+</sup>-ATPase Gene Family in Maize and Its Expression Dynamics Under Abiotic and Biotic Stress Conditions.

International journal of molecular sciences·2026
Same author

Factors affecting the gut microbiota of rural residents under different physical activity levels: a cross-sectional study.

Frontiers in microbiology·2026
Same author

GPR161 contributes to macrophage glycolytic reprogramming via targeting C5aR1 in acute lung injury.

Cellular & molecular biology letters·2026
Same author

Dual-tuning of morphology and coordination in single-atom catalysts via organic linker engineering for singlet oxygen-dominated Fenton-like reactions.

Journal of hazardous materials·2026
Same author

Mechanistic insights into Cd resilience enhancement by molybdenum trioxide nanoparticles in Solanum nigrum L.: Distinct molecular regulation from Mo<sup>6+</sup> through multi-omics perspective.

Journal of environmental sciences (China)·2026
Same author

A telomere-to-telomere gap-free genome of the new cultivar 'Zhongtian No. 5', combined with pan-genome analysis, aids in exploration and genetic enhancement of red clover (<i>Trifolium pratense</i> L.).

Horticulture research·2026

Related Experiment Video

Updated: Sep 9, 2025

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse
07:04

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

Published on: October 24, 2017

8.4K

Predicting the risk of threatened abortion using machine learning methods: a comparative study.

Zhenning Zhu1, Na Wei1, Junjie Guo2

  • 1The Second Affiliated Hospital of Shaanxi University of Chinese Medicine, Gynecology Department, Xianyang, 712000, China.

BMC Pregnancy and Childbirth
|August 30, 2025
PubMed
Summary

Machine learning models can predict threatened abortion using routine blood tests, improving early detection and intervention for this common pregnancy complication. This approach offers a faster, more accurate alternative to current diagnostic methods.

Keywords:
Hematologic testsMachine learningPredictionThreatened abortion

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.3K

Related Experiment Videos

Last Updated: Sep 9, 2025

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse
07:04

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

Published on: October 24, 2017

8.4K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

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

Published on: August 16, 2020

6.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

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

Published on: October 10, 2018

8.3K

Area of Science:

  • Obstetrics and Gynecology
  • Medical Informatics
  • Computational Biology

Background:

  • Threatened abortion is difficult to predict due to non-specific symptoms and overlapping causes with other early pregnancy bleeding.
  • Current diagnostic methods, such as serial ultrasounds and clinical monitoring, are time-consuming and lack timeliness for early intervention.
  • There is a need for advanced analytical tools to improve early detection and risk stratification of threatened abortion.

Purpose of the Study:

  • To develop and evaluate a machine learning (ML) model for predicting threatened abortion using routine blood test data.
  • To compare the performance of eight different ML algorithms in identifying threatened abortion.
  • To identify key blood indicators that are most influential in predicting threatened abortion.

Main Methods:

  • Collected medical records from 1764 threatened abortion patients and 1489 controls (Jan 2022-Mar 2024).
  • Applied Z-score normalization to blood routine indicators and used 'class_weight="balanced"' for hyperparameter optimization.
  • Trained and tested eight ML algorithms (LR, RF, SVM, GBM, XGB, DNN, DT, NB), evaluating performance using AUC, accuracy, specificity, sensitivity, and F1 score.

Main Results:

  • The Deep Neural Network (DNN) model achieved the highest predictive performance with an AUC of 96.76%.
  • DNN model demonstrated excellent metrics: accuracy (91.88%), specificity (91.62%), sensitivity (92.11%), and F1 score (92.48%).
  • SHAP analysis identified RDW-SD, PDW, MPV, RDW-CV, BAS#, PLT, MCHC, and LYM as crucial predictive features.

Conclusions:

  • Machine learning models utilizing routine blood tests show significant potential for early threatened abortion detection.
  • The developed ML model can aid healthcare providers in earlier intervention, potentially reducing abortion incidence.
  • Further extensive validation studies are required before clinical implementation of the ML model.