Probabilistic Temporal Prediction of Continuous Disease Trajectories and Treatment Effects Using Neural SDEs
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909226937352192 |
|---|---|
| author | Durso-Finley, Joshua Barile, Berardino Falet, Jean-Pierre Arnold, Douglas L. Pawlowski, Nick Arbel, Tal |
| author_facet | Durso-Finley, Joshua Barile, Berardino Falet, Jean-Pierre Arnold, Douglas L. Pawlowski, Nick Arbel, Tal |
| contents | Personalized medicine based on medical images, including predicting future individualized clinical disease progression and treatment response, would have an enormous impact on healthcare and drug development, particularly for diseases (e.g. multiple sclerosis (MS)) with long term, complex, heterogeneous evolutions and no cure. In this work, we present the first stochastic causal temporal framework to model the continuous temporal evolution of disease progression via Neural Stochastic Differential Equations (NSDE). The proposed causal inference model takes as input the patient's high dimensional images (MRI) and tabular data, and predicts both factual and counterfactual progression trajectories on different treatments in latent space. The NSDE permits the estimation of high-confidence personalized trajectories and treatment effects. Extensive experiments were performed on a large, multi-centre, proprietary dataset of patient 3D MRI and clinical data acquired during several randomized clinical trials for MS treatments. Our results present the first successful uncertainty-based causal Deep Learning (DL) model to: (a) accurately predict future patient MS disability evolution (e.g. EDSS) and treatment effects leveraging baseline MRI, and (b) permit the discovery of subgroups of patients for which the model has high confidence in their response to treatment even in clinical trials which did not reach their clinical endpoints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12807 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Probabilistic Temporal Prediction of Continuous Disease Trajectories and Treatment Effects Using Neural SDEs Durso-Finley, Joshua Barile, Berardino Falet, Jean-Pierre Arnold, Douglas L. Pawlowski, Nick Arbel, Tal Artificial Intelligence Machine Learning Image and Video Processing Quantitative Methods Personalized medicine based on medical images, including predicting future individualized clinical disease progression and treatment response, would have an enormous impact on healthcare and drug development, particularly for diseases (e.g. multiple sclerosis (MS)) with long term, complex, heterogeneous evolutions and no cure. In this work, we present the first stochastic causal temporal framework to model the continuous temporal evolution of disease progression via Neural Stochastic Differential Equations (NSDE). The proposed causal inference model takes as input the patient's high dimensional images (MRI) and tabular data, and predicts both factual and counterfactual progression trajectories on different treatments in latent space. The NSDE permits the estimation of high-confidence personalized trajectories and treatment effects. Extensive experiments were performed on a large, multi-centre, proprietary dataset of patient 3D MRI and clinical data acquired during several randomized clinical trials for MS treatments. Our results present the first successful uncertainty-based causal Deep Learning (DL) model to: (a) accurately predict future patient MS disability evolution (e.g. EDSS) and treatment effects leveraging baseline MRI, and (b) permit the discovery of subgroups of patients for which the model has high confidence in their response to treatment even in clinical trials which did not reach their clinical endpoints. |
| title | Probabilistic Temporal Prediction of Continuous Disease Trajectories and Treatment Effects Using Neural SDEs |
| topic | Artificial Intelligence Machine Learning Image and Video Processing Quantitative Methods |
| url | https://arxiv.org/abs/2406.12807 |