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

96
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:
96
Classification of Signals01:30

Classification of Signals

348
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
348
Classification of Systems-II01:31

Classification of Systems-II

127
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
127
Classification of Systems-I01:26

Classification of Systems-I

161
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
161
Statistical Software for Data Analysis and Clinical Trials01:12

Statistical Software for Data Analysis and Clinical Trials

428
Statistical software is pivotal in data analysis and clinical trials by providing tools to analyze data, draw conclusions, and make predictions. These software packages range from simple data management applications to complex analytical platforms, supporting various statistical tests, models, and simulation techniques. Their significance lies in their ability to handle vast amounts of data with precision and efficiency, enabling researchers to validate hypotheses, identify trends, and make...
428
Statistical Methods for Analyzing Epidemiological Data01:25

Statistical Methods for Analyzing Epidemiological Data

244
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
244

You might also read

Related Articles

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

Sort by
Same author

Investigating the Use of the Fast Health Care Interoperability Resources (FHIR) Standard to Support Data Activities Across the PCORnet® Infrastructure: Lessons Learned From the FHIR Pilots of the Coordinating Center for PCORnet®.

Medical care·2026
Same author

Decreasing Seven-Day Revisits After Pediatric Tonsillectomy: A Multidisciplinary and Comprehensive Unit-Based Safety Program (CUSP)-Driven Quality Improvement Initiative.

Cureus·2025
Same author

Quantra® Viscoelastic Testing in Pediatric Trauma: A Review of Emerging Evidence and Clinical Integration.

Cureus·2025
Same author

Unanticipated Intraoperative Seizure During Craniotomy: A Case Report and Anesthetic Considerations.

Cureus·2025
Same author

Patient Self-Testing of Kidney Function at Home, a Prospective Clinical Feasibility Study in Kidney Transplant Recipients.

Kidney international reports·2023
Same author

Evaluation of weight change and cardiometabolic risk factors in a real-world population of US adults with overweight or obesity.

Preventive medicine·2023

Related Experiment Video

Updated: May 15, 2025

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.1K

One-class support vector machines for detecting population drift in deployed machine learning medical diagnostics.

William S Jones1, Daniel J Farrow2

  • 1Centre of Excellence for Data Science, Artificial Intelligence and Modelling (DAIM), Faculty of Science and Engineering, University of Hull, Hull, UK. will.jones@hull.ac.uk.

Scientific Reports
|April 9, 2025
PubMed
Summary

Machine learning (ML) models can drift from real-world data, causing errors. A one-class support vector machine (OCSVM) effectively detects this population drift, ensuring safer ML diagnostics.

Keywords:
Covariate shiftDeploymentMachine learningMedical diagnosticsMonitoringPopulation drift

More Related Videos

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.4K

Related Experiment Videos

Last Updated: May 15, 2025

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
07:05

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

9.1K
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

15.6K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.4K

Area of Science:

  • Medical Informatics
  • Machine Learning
  • Data Science

Background:

  • Machine learning (ML) models are vital for disease diagnosis and prediction.
  • Population drift, a difference between training and real-world data, degrades ML model performance and risks diagnostic errors.
  • Existing drift detection methods are limited, often lacking direct measurement or requiring ground truth labels.

Purpose of the Study:

  • To propose and evaluate a novel method for detecting population drift in ML models using a one-class support vector machine (OCSVM).
  • To assess the sensitivity of OCSVM to varying levels of simulated data noise, indicative of population drift.

Main Methods:

  • A one-class support vector machine (OCSVM) was trained on the Wisconsin Breast Cancer dataset.
  • Simulated data, with controlled offsets and noise levels (5%, 10%, 30%), was used to test OCSVM's drift detection capabilities.
  • The number of inliers detected by OCSVM was recorded for each noise level.

Main Results:

  • The OCSVM detected an increasing number of inliers as noise levels rose: 27 inliers at 5% noise, 486 at 10% noise, and 851 at 30% noise.
  • This demonstrates a correlation between increased data noise (simulating population drift) and the number of inliers identified by OCSVM.
  • The results indicate OCSVM's sensitivity to detecting deviations in data distribution.

Conclusions:

  • The proposed OCSVM approach effectively detects population drift in ML models.
  • This method can serve as a crucial alert system, supporting the safe adoption of ML in diagnostics.
  • Future work should focus on real-world data validation, model transparency, and exploring complementary methods.