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

You might also read

Related Articles

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

Sort by
Same author

Wearable low-level laser therapy (laser acupuncture) versus manual acupuncture for chronic insomnia: protocol for a randomized, assessor-blinded, superiority trial.

Frontiers in psychiatry·2026
Same author

Heterologous expression of sfp from Bacillus subtilis enhances colanic acid biosynthesis in Escherichia coli S17-3.

Enzyme and microbial technology·2026
Same author

Combined application of the modified early warning score and the modified hematoma expansion prediction score for predicting hematoma expansion in intracerebral hemorrhage.

Scientific reports·2026
Same author

A comparative study of the risk of delayed cerebral ischemia after clipping and coiling of ruptured intracranial aneurysms: a systematic review and meta-analysis.

Frontiers in neurology·2026
Same author

Trends in Central Obesity Prevalence Among Adults With Hypertension in the United States, 2001-2023.

Journal of clinical hypertension (Greenwich, Conn.)·2026
Same author

Instrument-Free, Low-Cost and Dual-System Detection for Norovirus Based on Self-Assembling DNA Circuitry.

ACS omega·2026

Related Experiment Video

Updated: May 16, 2025

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury
09:49

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury

Published on: January 20, 2023

2.3K

Machine Learning-Based Modeling for Predicting Hypopituitarism After Cranial Trauma.

Ai Chen1, Hua Zhong1, Jie Peng1

  • 1Department of Neurosurgery, Nanchuan Hospital, Chongqing Medical University, Chongqing, China.

World Neurosurgery
|May 14, 2025
PubMed
Summary

Machine learning accurately predicts post-traumatic hypopituitarism (PTHP) after traumatic brain injury (TBI). Logistic regression is the top model, identifying key risk factors for earlier diagnosis and treatment.

Keywords:
AUC-ROCHypopituitarismLogistic regressionMachine learningModel calibrationTraumatic brain injury

More Related Videos

Electromagnetic Controlled Closed-Head Model of Mild Traumatic Brain Injury in Mice
09:07

Electromagnetic Controlled Closed-Head Model of Mild Traumatic Brain Injury in Mice

Published on: September 28, 2022

2.0K
Author Spotlight: Optimizing Rodent Models for Investigating the Mechanisms and Rehabilitation in Repeated Mild Traumatic Brain Injury
04:47

Author Spotlight: Optimizing Rodent Models for Investigating the Mechanisms and Rehabilitation in Repeated Mild Traumatic Brain Injury

Published on: April 19, 2024

330

Related Experiment Videos

Last Updated: May 16, 2025

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury
09:49

Assessing Changes in Synaptic Plasticity Using an Awake Closed-Head Injury Model of Mild Traumatic Brain Injury

Published on: January 20, 2023

2.3K
Electromagnetic Controlled Closed-Head Model of Mild Traumatic Brain Injury in Mice
09:07

Electromagnetic Controlled Closed-Head Model of Mild Traumatic Brain Injury in Mice

Published on: September 28, 2022

2.0K
Author Spotlight: Optimizing Rodent Models for Investigating the Mechanisms and Rehabilitation in Repeated Mild Traumatic Brain Injury
04:47

Author Spotlight: Optimizing Rodent Models for Investigating the Mechanisms and Rehabilitation in Repeated Mild Traumatic Brain Injury

Published on: April 19, 2024

330

Area of Science:

  • Neuroscience
  • Endocrinology
  • Medical Informatics

Background:

  • Traumatic brain injury (TBI) is a major global health issue causing significant disability and death.
  • Post-traumatic hypopituitarism (PTHP) is a frequent complication of TBI, yet accurate predictive models are lacking.
  • Early identification of PTHP is crucial for timely intervention and improved patient outcomes.

Purpose of the Study:

  • To develop and evaluate machine learning models for predicting the risk of hypopituitarism following TBI.
  • To identify key clinical and radiological factors associated with PTHP development after TBI.
  • To establish a robust predictive tool for enhancing clinical decision-making in TBI patients.

Main Methods:

  • Analysis of 620 TBI cases using the logistic independent variable event count method.
  • Evaluation of ten machine learning models, including Logistic Regression, Random Forest, and XGBoost, with 70% training and 30% test data split.
  • Utilized 5-fold cross-validation and assessed performance via accuracy, sensitivity, specificity, and AUC.

Main Results:

  • Logistic Regression demonstrated superior performance with an AUC of 0.905 (training) and 0.887 (test), showing balanced sensitivity and specificity.
  • Midline shift ≥5 mm was identified as the strongest predictor of PTHP.
  • Significant predictors included hypertension, ICU admission, GCS ≤8, diffuse cerebral edema, cerebral herniation, elevated ICP, craniotomy, skull base fracture, and length of stay.

Conclusions:

  • Logistic Regression is the optimal model for predicting PTHP post-TBI, offering high accuracy and excellent calibration.
  • The developed model can aid in the early diagnosis and management of PTHP in TBI patients.
  • Identifying high-risk patients facilitates proactive monitoring and intervention, potentially reducing long-term morbidity.