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

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic Models: Compartment Models in Individual and Population Analysis

Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...

Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches

Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches

Drug disposition in the body is a complex process and can be studied using two major approaches: the model and the model-independent approaches.
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...

Multicompartment Models: Overview

Multicompartment Models: Overview

Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...

Improving Translational Accuracy

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

Improving Translational Accuracy

Improving Translational Accuracy

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...

You might also read

Related Articles

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

Sort by

Same author

STDP-inspired temporal transition modeling for adaptive clinical risk prediction from electronic health records.

medRxiv : the preprint server for health sciences·2026

Same author

Deep Learning-Based Synthetic Contrast-Enhanced Breast MRI for Monitoring Response to Neoadjuvant Therapy.

Cancers·2026

Same author

Longitudinal Association of Quantitative Background Parenchymal Enhancement with Breast Cancer Risk Among Women with BRCA1/2 Pathogenic Variants.

Cancer epidemiology, biomarkers & prevention : a publication of the American Association for Cancer Research, cosponsored by the American Society of Preventive Oncology·2026

Same author

Global Sensitivity Analysis for Studies Extending Inferences From a Randomized Trial to a Target Population.

Statistics in medicine·2026

Same author

Estimating the Effects of MTEER in U.S. Practice: A Transportability Analysis of the COAPT Trial.

Journal of the American College of Cardiology·2026

Same author

Spillover Effects in Clinical Trials.

JAMA·2026

Same journal

Modelling the cost-effectiveness of non-invasive prenatal testing in the English sickle cell and thalassaemia screening pathway.

Diagnostic and prognostic research·2026

Same journal

Minimally acceptable criteria and required sample size for an accuracy study of non-invasive prenatal testing of sickle cell disease in screen positive women in England: results of a decision tree model.

Diagnostic and prognostic research·2026

Same journal

Urine and cerebrospinal fluid biomarkers for early glioma detection: a systematic review.

Diagnostic and prognostic research·2026

Same journal

Methods for Evaluating Models, Tests And Biomarkers (MEMTAB): Abstracts from the 7<sup>th</sup> International Conference, MEMTAB 2025.

Diagnostic and prognostic research·2026

Same journal

Agreement between heuristic shrinkage factor and optimal shrinkage factors in logistic regression for risk prediction: a simulation study across different sample sizes and settings.

Diagnostic and prognostic research·2026

Same journal

Variable selection for prediction models of Omicron infection: Insights from two population-based cohort studies.

Diagnostic and prognostic research·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 16, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Counterfactual prediction from machine learning models: transportability and joint analysis for model development and

Sarah C Voter¹, Issa J Dahabreh^2,3,4, Christopher B Boyer³

¹Department of Biostatistics, Brown University School of Public Health, Providence, RI, USA. sarah_voter@brown.edu.

Diagnostic and Prognostic Research

|October 2, 2025

Summary

This summary is machine-generated.

Machine learning model performance can be biased when treatment assignments differ between development and deployment settings. This study explores methods using randomized trials and observational data to improve model accuracy in new populations.

Keywords:

Counterfactual prediction Machine learning Model evaluation Observational analysis Transportability

Related Experiment Videos

Last Updated: Jan 16, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Area of Science:

Machine learning in healthcare
Causal inference in statistics
Epidemiological methods

Background:

Machine learning models face performance degradation and biased estimates when deployment contexts differ from development settings, particularly concerning treatment assignment.
Failure to address differing treatment assignment processes leads to suboptimal model development and inaccurate performance evaluations.

Purpose of the Study:

To develop and evaluate methods for machine learning model development and performance estimation when data originates from different treatment assignment settings.
To address the challenge of applying models developed in one setting (e.g., randomized trial) to another (e.g., observational study).

Main Methods:

Two approaches are proposed for estimating models and assessing performance in a target population using data from a randomized trial and an observational study.
Approach 1: Counterfactual predictions from observational data, assuming conditional exchangeability (no unmeasured confounding).
Approach 2: Transporting estimates from a trial to an observational population, assuming conditional exchangeability between populations.

Main Results:

The study examines the assumptions underpinning both observational and transportability approaches for model fitting and performance estimation.
Estimators are provided for fitting models and assessing performance in the target population under both approaches.
A joint estimation strategy combining trial and observational data is developed, with benchmarking discussed.

Conclusions:

Both observational and transportability analyses can estimate model performance under counterfactual strategies but rely on different, untestable assumptions.
Contextual consideration is crucial for selecting the appropriate method.
Combining data from randomized trials and observational studies can lead to more efficient estimation if assumptions are met.