Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding
Open paper
Benchmark
Model
Rank
Results
medical-code-prediction-on-mimic-iii
MSMN+KEPTLongformer
#6
Micro-F1: 59.9
Macro-F1: 11.8
Precision@8: 77.1
Precision@15: 61.5
Rank counts only results with a code link.