Article

Metrics for Distinguishing Biological Versus Interventional Change in AI Models

2026-06-29

Abstract excerpt

Statistical and machine-learning models of longitudinal biological data evaluate change by comparing each new observation against the trajectory implied by prior observations, assuming the process generating that trajectory is stable. We use “data substrate” to mean the underlying structure of the longitudinal data that determines what any such model can recover, independent of its architecture or capacity. When t...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 578ec1ba-5365-5935-b38f-47d72d2fd56d
DOI: 10.64898/2026.06.24.733252

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Metrics for Distinguishing Biological Versus Interventional Change in AI ModelsDOI 10.64898/2026.06.24.733252Read

Metrics for Evaluating Biological AI Model Prediction Accuracy at the Data-Substrate LevelSemantic proximity Read

A Biologically Constrained Continuous-Time Framework for Long-Horizon Cognition Forecasting in Alzheimer’s DiseaseSemantic proximity Read

Visualization of Incrementally Learned Projection Trajectories for Longitudinal DataSemantic proximity Read

A formalization of the IdioNomo Framework for explanation and prediction in psychology: unifying idiographic and nomothetic approachesSemantic proximity Read

A formalization of the IdioNomo Framework for explanation and prediction in psychology: unifying idiographic and nomothetic approachesSemantic proximity Read

Learning a Continuous Progression Trajectory of Amyloid in Alzheimer diseaseSemantic proximity Read

Design-induced artifacts when “disease clocks” are plugged into second-stage analyses of symptom onsetSemantic proximity Read

A multi-modal phase plane method for constructing multivariate disease trajectoriesSemantic proximity Read

Aligning personalized biomarker trajectories onto a common time axis: a connectome-based ODE model for Tau–Amyloid beta dynamicsSemantic proximity Read

Medical World Model: From Passive Prediction to Active Simulation in MedicineSemantic proximity Read

Data-driven biomarkers outperform theory-based biomarkers in predicting stroke motor outcomesSemantic proximity Read

Mapping U.S. POINTER Cognitive-Slope Gains Onto Predicted Clinical Progression: An External-Cohort Translation Analysis With Exploratory Economic ThresholdsSemantic proximity Read