disease-progression

Multimodal Machine Learning-based Knee Osteoarthritis Progression Prediction from Plain Radiographs and Clinical Data

[ICASSP 2025 Oral] ImageFlowNet: forecasting multiscale image-level trajectories of disease progression with irregularly-sampled longitudinal medical images

Detection of PatIent-Level distances from single cell genomics and pathomics data with Optimal Transport (PILOT)

[ICASSP 2025 Oral] ImageFlowNet: forecasting multiscale image-level trajectories of disease progression with irregularly-sampled longitudinal medical images

Patient-Level Analysis of Single Cell Disease Atlas with Optimal Transport of Gaussian Mixtures Variational Autoencoders

MARIO Challenge MICCAI 2024

Official code for Learning Temporally Equivariance for Degenerative Disease Progression in OCT by Predicting Future Representations (MICCAI'24)

[WACV, 2027] Official implementation of "Multimodal-Conditioned Latent Diffusion Models for Spatiotemporal Brain MRI Forecasting"

[ECCV 2026] Physics-Grounded Disentangled Flow Modeling for Brain Disease Progression Trajectory

Analysing CSF biomarkers and APOE4 effects on late-onset AD characterisation based on age, sex, cognitive scores, CSF biomarkers, and apoe4 status of 213 patients obtained from https://doi.org/10.34810/data614

Biologically-constrained JEPA for disease progression - predicts who will decline, not just labels. Real ADNI data (2,347 patients), patient-level inference, honest evaluation incl. LLM head-to-head.

Overview of DS, Classification Tree, Regression Tree, Logistic Regression, Multiple Linear Regression, Random Forest Classifiers, p-value approach to Decision Tree, Disease Progression Models, Neural Networks and Deep Learning.

Diabetes Progression in Electronic Health Records

This repository contains python code which relates to this paper: Hyperbolic Embedding and Acoustic-based Learning for Topological Hierarchies in Parkinson’s Disease

A research framework for longitudinal EHR sequence modeling, exploring multiple temporal representations, learning objectives, and model classes for disease progression, survival analysis, and temporal phenotyping under censoring and irregular follow-up.

Analysis code for milestone-based progression classes and their baseline prediction in early Parkinson's disease (PPMI)

Calibrated, abstaining web app that recovers a Parkinson's disease progression subtype (fast vs slow) from routine clinical scores. It reports conformal uncertainty and SHAP explanations, and defers to the clinician when it cannot yet decide. Companion code to a manuscript in preparation.