AI Paper Atlas

Research map / Large language models / AI and society

PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning

John Wu, Yongda Fan, Zhenbang Wu, Paul Landes, Eric Schrock, Sayeed Sajjad Razin, Arjun Chatterjee, Naveen Baskaran, Joshua Steier, Andrea Fitzpatrick, Bilal Arif, Rian Atri and 5 more

ICML 2026 · Large language models › AI and society · approach: Data commons and human baselines · 0 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
run PyHealth 2.0 on a MacBook instead of PyHealth 1.16 on the server workstationlabevents mortality task · MIMIC-IV mortality, 8 workerswall time (s): 2,235 -> 1,357Improved
replace PyHealth 1.16 with PyHealth 2.0MIMIC-IV mortality · 16 workers peak memoryGB: 457.42 -> 28.70Improved
replace PyHealth 1.16 with PyHealth 2.0MIMIC-IV drug recommendation · 16 workerswall time (s): 802 -> 569Improved
replace PyHealth 1.16 with PyHealth 2.0MIMIC-IV length of stay · 16 workerswall time (s): 1,922 -> 1,096Improved
replace PyHealth 1.16 with PyHealth 2.0MIMIC-IV mortality · 16 workers wall times: 2,235 -> 2,385Hurt
replace PyHealth 1.16 with PyHealth 2.0MIMIC-IV mortality · 1 worker wall times: 6,841 -> 17,671Hurt
replace Pandas with PyHealth 2.0 multi-workerMIMIC-IV mortality · 1 worker vs 16 workerswall time (s): 93,708 -> 2,385Improved
replace PyHealth 1.16 with PyHealth 2.0 data loadingMIMIC-IV dataloading · load and cache times: 3548.90 -> 1093.38Improved
replace PyHealth 1.16 with PyHealth 2.0 patient accessMIMIC-IV random patient access · patient access timems: 0.01 -> 208.85Hurt
use PyHealth 2.0 instead of 1.16 for patient explorationpatient exploration · lines of codelines: 14 -> 10Improved
add neighborhood conformal prediction over vanilla conformal predictionTUEV conformal prediction · TUEV (alpha=0.1)empirical coverage: 0.7461 -> 0.9152Improved
add KDE covariate shift adjustment to conformal predictionTUEV conformal prediction · TUEV (alpha=0.1)empirical coverage: 0.7461 -> 0.7457No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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