Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokinetics
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909995002494976 |
|---|---|
| author | Marin, César Ali Ojeda Huisinga, Wilhelm Kavwele, Purity Sánchez, Ramsés J. Hartung, Niklas |
| author_facet | Marin, César Ali Ojeda Huisinga, Wilhelm Kavwele, Purity Sánchez, Ramsés J. Hartung, Niklas |
| contents | Accurate dose-response forecasting under sparse sampling is central to precision pharmacotherapy. We present the Amortized In-Context Mixed-Effect Transformer (AICMET) model, a transformer-based latent-variable framework that unifies mechanistic compartmental priors with amortized in-context Bayesian inference. AICMET is pre-trained on hundreds of thousands of synthetic pharmacokinetic trajectories with Ornstein-Uhlenbeck priors over the parameters of compartment models, endowing the model with strong inductive biases and enabling zero-shot adaptation to new compounds. At inference time, the decoder conditions on the collective context of previously profiled trial participants, generating calibrated posterior predictions for newly enrolled patients after a few early drug concentration measurements. This capability collapses traditional model-development cycles from weeks to hours while preserving some degree of expert modelling. Experiments across public datasets show that AICMET attains state-of-the-art predictive accuracy and faithfully quantifies inter-patient variability -- outperforming both nonlinear mixed-effects baselines and recent neural ODE variants. Our results highlight the feasibility of transformer-based, population-aware neural architectures as offering a new alternative for bespoke pharmacokinetic modeling pipelines, charting a path toward truly population-aware personalized dosing regimens. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15659 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokinetics Marin, César Ali Ojeda Huisinga, Wilhelm Kavwele, Purity Sánchez, Ramsés J. Hartung, Niklas Machine Learning Accurate dose-response forecasting under sparse sampling is central to precision pharmacotherapy. We present the Amortized In-Context Mixed-Effect Transformer (AICMET) model, a transformer-based latent-variable framework that unifies mechanistic compartmental priors with amortized in-context Bayesian inference. AICMET is pre-trained on hundreds of thousands of synthetic pharmacokinetic trajectories with Ornstein-Uhlenbeck priors over the parameters of compartment models, endowing the model with strong inductive biases and enabling zero-shot adaptation to new compounds. At inference time, the decoder conditions on the collective context of previously profiled trial participants, generating calibrated posterior predictions for newly enrolled patients after a few early drug concentration measurements. This capability collapses traditional model-development cycles from weeks to hours while preserving some degree of expert modelling. Experiments across public datasets show that AICMET attains state-of-the-art predictive accuracy and faithfully quantifies inter-patient variability -- outperforming both nonlinear mixed-effects baselines and recent neural ODE variants. Our results highlight the feasibility of transformer-based, population-aware neural architectures as offering a new alternative for bespoke pharmacokinetic modeling pipelines, charting a path toward truly population-aware personalized dosing regimens. |
| title | Amortized In-Context Mixed Effect Transformer Models: A Zero-Shot Approach for Pharmacokinetics |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.15659 |