Research map / Label-efficient and robust learning / Recognition and long-tail
Doctor2Vec: Dynamic Doctor Representation Learning for Clinical Trial Recruitment
Siddharth Biswal, Cao Xiao, Lucas M. Glass, Elizabeth Milkovits, Jimeng Sun
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use trial-conditioned dynamic doctor representations from patient EHR memory | Doctor2Vec · Clinical trial enrollment prediction | PR-AUC: 8.7% | Improved |
| use trial-conditioned dynamic doctor representations from patient EHR memory | Doctor2Vec · Clinical trial enrollment prediction | R² score: 2.4% | Improved |
| transfer the model trained on US trials to South Africa | Doctor2Vec · South Africa trial transfer | PR-AUC: 13.7% | Improved |
| transfer the model trained on US trials to South Africa | Doctor2Vec · South Africa trial transfer | R² score: 8.1% | Improved |
| transfer embeddings trained on common-disease trials to rare-disease trials | Doctor2Vec · Rare and low-prevalence disease trial transfer | PR-AUC: 8.1% | Improved |
| transfer embeddings trained on common-disease trials to rare-disease trials | Doctor2Vec · Rare and low-prevalence disease trial transfer | R² score: 5.6% | Improved |
| replace BERT text embedding with char-CNN (ablation) | Doctor2Vec · Clinical trial enrollment prediction | PR-AUC: 0.819±0.024 -> 0.861±0.021 | Hurt |
| replace BERT text embedding with Word2vec (ablation) | Doctor2Vec · Clinical trial enrollment prediction | PR-AUC: 0.801±0.018 -> 0.861±0.021 | Hurt |
Closest papers by meaning
- NeuralCohort: Cohort-aware Neural Representation Learning for Healthcare Analytics (ICML 2025 · similarity 0.84)
- Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data (ICLR 2025 · similarity 0.83)
- LLMs can construct powerful representations and streamline sample-efficient supervised learning (NeurIPS 2026 · similarity 0.83)
- MOTOR: A Time-to-Event Foundation Model For Structured Medical Records (ICLR 2024 · similarity 0.83)
- Contrastive Learning for Clinical Outcome Prediction with Partial Data Sources (ICML 2024 · similarity 0.82)
- Breaking the Barrier of Hard Samples: A Data-Centric Approach to Synthetic Data for Medical Tasks (ICML 2025 · similarity 0.82)
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.
