STRATA scores each step of temporal clinical hypothesis tests
The benchmark has 8,735 vaccine-report hypotheses; ART narrows a record-selection gap and brings a 31B model near frontier scores.
Stories per day · 30 days
Relatedbenchmark1breast-lesions1cross-encoder1hypothesis-testing1language-models1mental-health1mimic-iii1rag1retrieval-evaluation1state-space-models1vaccine-reports1weak-supervision1
6 stories, newest first · one card per story
Stories tagged #clinical-nlp
Clinical notes used to flag mental-health risk in chronic illness
A weakly supervised MIMIC-III cohort of about 4,000 patients tracks risk from day-wise narratives.
Evidence-aware retrieval scores reported for a breast-lesion RAG system
The selected hybrid retriever reached 0.94 on Recall@3, R-Precision, MRR@3, and nDCG@3 for 17 of 18 queries.
Cross-Scale Transfer Learning for Depression Severity Prediction: From PHQ-8 to HAMD-17 Across Languages and Clinical Paradigms
Sequential LoRA transfer from English PHQ-8 interviews to Chinese HAMD-17 consultations improves depression-score prediction with Qwen3.
Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication
UID-preserving multimodal framework plus GAVEL LLM judge improves clinical timeline reconstruction, boosting event recovery 43% over prior matching.
Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk Assessment
Researchers audit 31 NLP techniques for clinician-annotated suicide risk prediction, finding only 5 of 31 comparisons yield reliable gains.