HyperAI超神経

ホームニュース最新論文チュートリアルデータセット百科事典 SOTA LLMモデル GPU ランキング学会

サイトについて

日本語

システム

HyperAI超神経

Medical Code Prediction On Mimic Iii

評価指標

Macro-AUC

Macro-F1

Micro-AUC

Micro-F1

Precision@15

Precision@8

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Macro-AUC	Macro-F1	Micro-AUC	Micro-F1	Precision@15	Precision@8	Paper Title	Repository
DR-CAML	89.7	8.6	98.5	52.9	54.8	69.0	Explainable Prediction of Medical Codes from Clinical Text
MSMN	95.0	10.3	99.2	58.4	59.9	75.2	Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding
Bi-GRU	82.2	3.8	97.1	41.7	44.5	58.5	Explainable Prediction of Medical Codes from Clinical Text
HAN	88.5	3.6	98.1	40.7	-	61.4	Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation
Logistic Regression	56.1	1.1	93.7	27.2	41.1	54.2	Explainable Prediction of Medical Codes from Clinical Text
MultiResCNN	91.0	8.5	98.6	55.2	58.4	73.4	ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network
LAAT	91.9	9.9	98.8	57.5	59.1	73.8	A Label Attention Model for ICD Coding from Clinical Text
MSATT-KG	91.0	9.0	99.2	55.3	58.1	72.8	-	-
RAC	94.8	12.7	99.2	58.6	60.1	75.4	Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines	-
SVM	-	-	-	44.1	-	-	Explainable Prediction of Medical Codes from Clinical Text
CNN	80.6	4.2	96.9	41.9	44.3	58.1	Explainable Prediction of Medical Codes from Clinical Text
CAML	89.5	8.8	98.6	53.9	56.1	70.9	Explainable Prediction of Medical Codes from Clinical Text
MSMN+KEPTLongformer	-	11.8	-	59.9	61.5	77.1	Knowledge Injected Prompt Based Fine-tuning for Multi-label Few-shot ICD Coding
Discnet+RE	95.6	14.0	99.3	58.8	61.4	76.5	Automatic ICD Coding Exploiting Discourse Structure and Reconciled Code Embeddings
JointLAAT	92.1	10.7	98.8	57.5	59.0	73.5	A Label Attention Model for ICD Coding from Clinical Text
PLM-CA	-	24.7	-	60.0	-	-	An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records
EffectiveCAN	91.5	10.6	98.8	58.9	60.6	75.8	Effective Convolutional Attention Network for Multi-label Clinical Document Classification	-

0 of 17 row(s) selected.