AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Individualized Dosing Dynamics via Neural Eigen Decomposition

Stav Belogolovsky, Ido Greenberg, Danny Eytan, Shie Mannor

NeurIPS 2023 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural ODE training and analysis · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hypernetwork over patient context features (ablation)NESDE · UH dosingMSE: 529.7 -> 411.2Improved
add hypernetwork over patient context features (ablation)NESDE · UH dosingNLL: 5.42 -> 4.43Improved
add hypernetwork over patient context features (ablation)NESDE · Vancomycin dosingMSE: 87.32 -> 70.71Improved
add hypernetwork over patient context features (ablation)NESDE · Vancomycin dosingNLL: 3.73 -> 3.69Improved
decouple control from observations (NESDE) vs concatenating control as model output (GRU-ODE-Bayes)NESDE · Synthetic complex dynamics, OOD controlMSE: 0.361 -> 0.178Improved
change control policy from negative to positive correlation with observations (OOD test)NESDE · Synthetic complex dynamicsMSE: 0.176 -> 0.178No clear effect
change control policy to OOD testLSTM · Synthetic real dynamicsMSE: 0.381 -> 2.354Hurt
change control policy to OOD testCRU · Synthetic complex dynamicsMSE: 0.233 -> 0.584Hurt
reduce training set size (down to 100 trajectories)NESDE · Synthetic benchmarkstest MSENo clear effect
reduce training trajectories in OU benchmark (no control)GRU-ODE-Bayes · OU processlossHurt
reduce observations per training trajectory (10 down to 4)NESDE · Synthetic complex and real dynamicstest MSENo clear effect
increase LSTM prediction resolution (1, 8, 50 predictions per observation)LSTM · Synthetic regular observationsMSEHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy