On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “i2b2”

Bidirectional LSTM-CRF for Clinical Concept Extractionstat.ML

Paper proposes a streamlined approach to clinical concept extraction using LSTM-CRF.

problem Automated extraction of concepts from clinical records for clinical research.

method Bidirectional LSTM with CRF decoding initialized with general-purpose word embeddings.

result Experimental results outperform all recent methods and rank closely to the best submission from the original i2b2/VA challenge.

clinical concept extraction LSTM-CRF word embeddings i2b2/VA challenge natural language processing

2016-11-25abs ↗pdf ↗

De-identification of Patient Notes with Recurrent Neural Networkscs.CL

ANNs improve de-identification of patient notes, outperforming existing systems.

problem De-identification of patient notes to protect patient confidentiality.

method Artificial Neural Networks (ANNs) without handcrafted features or rules.

result ANN model outperforms state-of-the-art systems, achieving high F1-scores.

ANNs de-identification patient notes HIPAA i2b2

2016-06-10abs ↗pdf ↗

A hybrid deep learning approach for medical relation extractioncs.LG

Deep learning model extracts medical treatment-problem relationships.

problem Mining relationships between treatments and medical problems.

method Hybrid approach combining deep learning and rule-based systems.

result System achieved promising performance on medical relation extraction task.

medical relation extraction deep learning rule-based systems treatment-problem relationships I2b2 2010

2018-06-26abs ↗pdf ↗

Named Entity Recognition in Electronic Health Records Using Transfer Learning Bootstrapped Neural Networkscs.CL

Improved named entity recognition in EHRs with transfer learning.

problem Scarce annotated datasets for named entity recognition in EHRs.

method Transfer learning and neural network embeddings.

result 94.6 F1 score in I2B2 2009 Medical Extraction Challenge.

named entity recognition transfer learning electronic health records natural language processing neural networks

2019-01-06abs ↗pdf ↗

Training without training data: Improving the generalizability of automated medical abbreviation disambiguationcs.LG

Improves medical note processing by training model on related concepts and global context.

problem Scarce and imbalanced labeled training data limits generalizability of automated abbreviation disambiguation models.

method Data augmentation using related medical concepts and global context information within medical notes.

result Model accuracy improved by almost 14% on CASI dataset and 4% on i2b2 dataset.

medical note processing abbreviation disambiguation data augmentation global context related concepts

2019-12-12abs ↗pdf ↗