Macro-AUC: 92.1Micro-AUC: 98.8Macro-F1: 10.7Micro-F1: 57.5
Papers with Code · CC BY-SA 4.0
Medical Code Prediction
Context: Prediction of medical codes from clinical notes is both a practical and essential need for every healthcare delivery organization within current medical systems. Automating annotation will save significant time and excessive effort by human coders today. A new milestone will mark a meaningful step toward fully Autonomous Medical Coding in machines reaching parity with human coders' performance in medical code prediction.
Question: What exactly is the medical code prediction problem?
Answer: Clinical notes contain much information about what precisely happened during the patient's entire stay. And those clinical notes (e.g., discharge summary) is typically long, loosely structured, consists of medical domain language, and sometimes riddled with spelling errors. So, it's a highly multi-label classification problem, and the forthcoming ICD-11 standard will add more complexity to the problem! The medical code prediction problem is to annotate this clinical note with multiple codes subset from nearly 70K total codes (in the current ICD-10 system, for example).
개요는 각 항목의 일부입니다. 위 탭에서 전체 기록을 페이지별로 탐색할 수 있습니다.
벤치마크
Papers with Code 아카이브의 데이터셋별 기록 예시입니다. 평가 조건과 지표 방향이 검증되지 않아 순위를 의미하지 않습니다.
데이터셋
7개논문
Macro-AUC: 96.2Micro-AUC: 99.3Macro-F1: 12.3Micro-F1: 61.2
Macro-F1: 24.7Micro-F1: 60.0mAP: 64.7
Macro-AUC: 95.6Micro-AUC: 99.3Macro-F1: 14.0Micro-F1: 58.8
Macro-AUC: 95.0Micro-AUC: 99.2Macro-F1: 10.3Micro-F1: 58.4
Macro-AUC: 91.5Micro-AUC: 98.8Macro-F1: 10.6Micro-F1: 58.9
Macro-AUC: 89.5Micro-AUC: 98.6Macro-F1: 8.8Micro-F1: 53.9
Macro-AUC: 91.0Micro-AUC: 98.6Macro-F1: 8.5Micro-F1: 55.2
Macro-F1: 11.8Micro-F1: 59.9Precision@8: 77.1Precision@15: 61.5
Macro-AUC: 94.8Micro-AUC: 99.2Macro-F1: 12.7Micro-F1: 58.6
라이브러리
Papers with Code 리더보드 row에 연결된 구현 저장소입니다.