AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare

Edward Choi, Cao Xiao, Walter Stewart, Jimeng Sun

NeurIPS 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 178 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 auxiliary diagnosis and treatment prediction tasks to MiME (ablation)MiME · HF prediction E1PR-AUC: 0.2711 -> 0.2831Improved
Add auxiliary diagnosis and treatment prediction tasks to MiME (ablation)MiME · HF prediction D3PR-AUC: 0.4685 -> 0.4787Improved
Model diagnosis-treatment relationships with multilevel embeddingsHF prediction · E1-E4PR-AUC: 0.2462 -> 0.2831Improved
Use MiME instead of the strongest baselineSequential disease prediction · Sequential disease predictionRecall@20: 0.7926 -> 0.7945Improved
Use MiME instead of Med2VecHF prediction · D1 (visit complexity 0-15%)PR-AUC: 0.2771 -> 0.2750No clear effect
Use tanh rather than ReLU for the visit embedding activationGRU baseline embedding · HF prediction D3PR-AUC: 0.4100 -> 0.4415Improved
Add a second sigmoid MLP layer to the visit embeddingGRU baseline embedding · Sequential disease predictionRecall@5: 0.5110 -> 0.2132Hurt
Use a sigmoid MLP visit embedding instead of a single sigmoid layerGRU baseline embedding · HF prediction E1PR-AUC: 0.2354 -> 0.0843Hurt
Use Med2Vec rather than MiME for rare-disease predictionSequential disease prediction · Rare diagnoses (0.01%-0.05% prevalence)Accuracy@5: 0.0965 -> 0.1156Improved
Use MiME rather than tanh_mlpSequential disease prediction · Diagnoses with 0.05%-0.2% prevalenceAccuracy@5: 0.2353 -> 0.2625Improved

Later papers that compared with this method

2 later accepted papers report MiME as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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