AI Paper Atlas

Research map / Large language models / AI and society

Cross-Corpora Unsupervised Learning of Trajectories in Autism Spectrum Disorders

Huseyin Melih Elibol, Vincent Nguyen, Scott Linderman, Matthew Johnson, Amna Hashmi, Finale Doshi-Velez

JMLR 2016 · Large language models › AI and society · approach: AI for health and public decisions · 6 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
use dynamic (stick-breaking DTM) topics instead of static LDALDA · ASD EHR and SM held-out wordsheld-out predictive log-likelihoodImproved
increase LDA topics to 15 (match number of yearly topics)LDA · ASD EHR and SM held-out wordsheld-out predictive log-likelihoodHurt
share one topic-proportion vector per patient (theta_p) across their notes (ablation)SB-DTM-θd · ASD EHR and SM held-out wordsheld-out predictive log-likelihoodImproved
add cross-corpora structure (shared dynamics, corpus-specific terms) (ablation)SB-DTM-θp · combined EHR+SM held-out wordsheld-out predictive log-likelihoodImproved
assume constant per-patient topic proportions (DTM-θp) (ablation)SB-DTM-θd · future notes at age seven and above (EHR, SM)predictive likelihood of future notesImproved
add cross-corpora transfer (ccDTM) on combined data (ablation)SB-DTM-θp · future notes, combined EHR+SMpredictive likelihood of future notesImproved
use DTM-θp instead of logistic regression for predicting future conditionsLogistic regression · future CUIs with at least 10% prevalenceAUCImproved
use DTM-θp instead of copying past conditions forwardCopy past · future CUIs with at least 10% prevalenceAUCImproved
train flat LDA on combined EHR+SM instead of EHR aloneLDA · EHR held-out datapredictive likelihoodImproved
train flat models on combined EHR+SM instead of SM aloneLDA · SM held-out datapredictive likelihoodHurt
use cross-corpora DTM when training on combined dataSB-ccDTM · EHR and SM, random and future held-outpredictive likelihoodImproved
use cross-corpora DTM instead of per-patient DTM for speedSB-DTM-θp · full corpusseconds per iteration: 2.14 -> 0.953Improved

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