ICD MSMN

ICD-MSMN

《Code Synonyms Do Matter：用於自動 ICD 編碼的多個同義詞匹配網路》正式實施 [ACL 2022]

環境

所有程式碼均在Python 3.7、PyTorch 1.7.0下測試。需要安裝 opt_einsum 進行 einsum 計算。訓練 MIMIC-III 完整設定至少需要 32GB GPU。

數據集

我們只為每個資料集放置幾個樣本。下載 MIMIC-III 資料集需要取得許可。取得MIMIC-III資料集後，請依照caml-mimic對資料集進行預處理。預處理後，您應該會獲得train_full.csv 、 test_full.csv 、 dev_full.csv 、 train_50.csv 、 test_50.csv 、 dev_50.csv 。請將它們放在sample_data/mimic3下。然後你應該使用preprocess/generate_data_new.ipynb來產生 json 格式的資料集。

詞嵌入

請從 LAAT 下載 word2vec_sg0_100.model。您需要更改詞嵌入的路徑。

使用我們的程式碼

MIMIC-III 完整版（1 支 GPU）：

 CUDA_VISIBLE_DEVICES=0 python main.py --n_gpu 1 --version mimic3 --combiner lstm --rnn_dim 256 --num_layers 2 --decoder MultiLabelMultiHeadLAATV2 --attention_head 4 --attention_dim 512 --learning_rate 5e-4 --train_epoch 20 --batch_size 2 --gradient_accumulation_steps 8 --xavier --main_code_loss_weight 0.0 --rdrop_alpha 5.0 --est_cls 1  --term_count 4  --sort_method random --word_embedding_path word_embedding_path

MIMIC-III Full（8 個 GPU）：

 NCCL_IB_DISABLE=1 CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node 8 --master_port=1212 --use_env  main.py --n_gpu 8 --version mimic3 --combiner lstm --rnn_dim 256 --num_layers 2 --decoder MultiLabelMultiHeadLAATV2 --attention_head 4 --attention_dim 512 --learning_rate 5e-4 --train_epoch 20 --batch_size 2 --gradient_accumulation_steps 1 --xavier --main_code_loss_weight 0.0 --rdrop_alpha 5.0 --est_cls 1  --term_count 4  --sort_method random --word_embedding_path word_embedding_path

MIMIC-III 50：

 CUDA_VISIBLE_DEVICES=0 python main.py --version mimic3-50 --combiner lstm --rnn_dim 512 --num_layers 1 --decoder MultiLabelMultiHeadLAATV2 --attention_head 8 --attention_dim 512 --learning_rate 5e-4 --train_epoch 20 --batch_size 16 --gradient_accumulation_steps 1 --xavier --main_code_loss_weight 0.0 --rdrop_alpha 5.0 --est_cls 1 --term_count 8 --word_embedding_path word_embedding_path

評估檢查點

 python eval_model.py MODEL_CHECKPOINT

模仿3檢查點

imit3-50 檢查點

引文

 @inproceedings{yuan-etal-2022-code,
    title = "Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic {ICD} Coding",
    author = "Yuan, Zheng  and
      Tan, Chuanqi  and
      Huang, Songfang",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-short.91",
    pages = "808--814",
    abstract = "Automatic ICD coding is defined as assigning disease codes to electronic medical records (EMRs).Existing methods usually apply label attention with code representations to match related text snippets.Unlike these works that model the label with the code hierarchy or description, we argue that the code synonyms can provide more comprehensive knowledge based on the observation that the code expressions in EMRs vary from their descriptions in ICD. By aligning codes to concepts in UMLS, we collect synonyms of every code. Then, we propose a multiple synonyms matching network to leverage synonyms for better code representation learning, and finally help the code classification. Experiments on the MIMIC-III dataset show that our proposed method outperforms previous state-of-the-art methods.",
}