Research map / Label-efficient and robust learning / Test-time adaptation
Adaptive Test-Time Training for Predicting Need for Invasive Mechanical Ventilation in Multi-Center Cohorts
Xiaolei Lu, Shamim Nemati
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 |
|---|---|---|---|
| add dynamic masking and adaptive distribution matching (full AdaTTT) over pretrained model without adaptation | AdaTTT · Site A | AUC (%): 84.01 -> 85.02 | Improved |
| add dynamic task-aware masking instead of random masking (ablation) | AdaTTT · Site A | AUC (%): 82.45 -> 85.02 | Improved |
| add dynamic task-aware masking instead of random masking (ablation) | AdaTTT · MIMIC-IV | AUC (%): 74.21 -> 77.17 | Improved |
| add masked-feature modeling to reconstruction objective (ablation) | AdaTTT · Site A | AUC (%): 83.53 -> 85.02 | Improved |
| learn prototypes end-to-end instead of post hoc k-means centroids (ablation) | AdaTTT · Site A | AUC (%): 84.57 -> 85.02 | Improved |
| learn prototypes end-to-end instead of post hoc k-means centroids (ablation) | DynTTT · MIMIC-IV | AUC (%): 77.05 (w/o proto-learn) vs 76.79 | Hurt |
| add adaptive distribution matching (partial OT) to prototype masking (ablation) | PriTTT · Site A | AUC (%): 84.61 -> 85.02 | Improved |
| apply entropy-minimization TTA (TENT) to pretrained model | TENT · Site A | AUC (%): 84.01 -> 82.19 | Hurt |
| vary lambda weights and warm-up epochs (ablation) | AdaTTT · Site A/B/MIMIC | AUC (%): fluctuations <= 0.1-0.3 AUC | No clear effect |
| increase prototype size (ablation) | AdaTTT · Site B / MIMIC-IV | AUC | Mixed |
| add SAR test-time adaptation | SAR · Site B | AUC (%): 83.75 -> 83.20 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TENT — Tent: Fully Test-Time Adaptation by Entropy Minimization (ICLR 2021) · better on 3 of 3 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
- Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML (ICLR 2024 · similarity 0.86)
- Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework (AAAI 2025 · similarity 0.85)
- One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models (NeurIPS 2026 · similarity 0.83)
- Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data (ICLR 2025 · similarity 0.83)
- Timely Clinical Diagnosis through Active Test Selection (NeurIPS 2025 · similarity 0.82)
- ED-Copilot: Reduce Emergency Department Wait Time with Language Model Diagnostic Assistance (ICML 2024 · 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.
