caml-mimic and icd-prediction-mimic
These are complementary approaches to the same problem: CAML uses hierarchical label attention for efficient multilabel classification of diagnostic/procedural codes, while ICD-Prediction uses sequence-to-sequence models, so practitioners might combine both architectures or compare their trade-offs between computational efficiency and predictive accuracy on the same MIMIC dataset.
About caml-mimic
jamesmullenbach/caml-mimic
multilabel classification of EHR notes
Implements convolutional and attention-based neural architectures (CAML and DR-CAML) for automated ICD code assignment from clinical discharge summaries, with built-in support for both MIMIC-II and MIMIC-III datasets. The approach combines CNNs with per-label attention mechanisms to generate interpretable predictions by highlighting which text passages drive each code decision. Includes end-to-end data processing pipelines, pre-trained model weights, and evaluation scripts for reproducing published benchmarks.
About icd-prediction-mimic
3778/icd-prediction-mimic
Predicting ICD Codes from Clinical Notes
Scores updated daily from GitHub, PyPI, and npm data. How scores work