Clinical Medical Text NLP Dataset

[ { "doc_id": "CLT-A0000821", "doc_type": "ADMISSION", "department": "CARDIOLOGY", "text": "患者[NAME]，[AGE]岁[GENDER]，因"反复胸闷、心悸[DURATION]"入院。既往有[DISEASE]病史[DRUG]治疗中。入院查体：[VALUE]次/分，血压[VALUE]/[VALUE]mmHg。", "entities": [ {"start": 62, "end": 70, "type": "SYMPTOM", "subtype": "胸闷", "text": "反复胸闷、心悸"}, {"start": 82, "end": 90, "type": "DISEASE", "subtype": "心血管疾病", "text": "[DISEASE]", "icd10_code": "I25.1"}, {"start": 92, "end": 98, "type": "DRUG", "subtype": "心血管药物", "text": "[DRUG]", "atc_code": "C07AB"} ], "relations": [ {"head_entity_idx": 0, "tail_entity_idx": 1, "relation_type": "SYMPTOM_OF"} ], "text_length": 156, "entity_count": 3, "annotator_id": "ANN-0421", "qc_score": 0.96 }, { "doc_id": "CLT-R0012345", "doc_type": "REPORT", "department": "RADIOLOGY", "text": "检查部位：[BODY_PART]。Imaging Findings：[BODY_PART]见[SIZE]cm[DESCRIPTOR][FINDING]，边界[DEGREE]，周边[DESCRIPTOR]。诊断意见：[DIAGNOSIS]。", "entities": [ {"start": 4, "end": 16, "type": "ANATOMY", "subtype": "检查部位", "text": "[BODY_PART]", "snomed_code": "123037004"}, {"start": 20, "end": 32, "type": "ANATOMY", "subtype": "检查部位", "text": "[BODY_PART]"}, {"start": 33, "end": 42, "type": "LAB", "subtype": "尺寸测量", "text": "[SIZE]cm"}, {"start": 43, "end": 55, "type": "FINDING", "subtype": "التصويرالكشف", "text": "[DESCRIPTOR][FINDING]"} ], "relations": [ {"head_entity_idx": 1, "tail_entity_idx": 3, "relation_type": "HAS_FINDING"} ], "text_length": 89, "entity_count": 4, "annotator_id": "ANN-0715", "qc_score": 0.94 }, { "doc_id": "CLT-D0003672", "doc_type": "DISCHARGE", "department": "ONCOLOGY", "text": "出院诊断：[DISEASE]（[STAGE]）。住院期间行[PROCEDURE]治疗，过程顺利。出院医嘱：1.[DRUG] [DOSAGE]；2.定期复查[LAB]；3.不适随诊。", "entities": [ {"start": 5, "end": 15, "type": "DISEASE", "subtype": "肿瘤", "text": "[DISEASE]", "icd10_code": "C34.9"}, {"start": 24, "end": 32, "type": "PROCEDURE", "subtype": "治疗操作", "text": "[PROCEDURE]"}, {"start": 47, "end": 53, "type": "DRUG", "subtype": "抗肿瘤药", "text": "[DRUG]", "atc_code": "L01XE"}, {"start": 64, "end": 70, "type": "LAB", "subtype": "实验室检查", "text": "[LAB]", "loinc_code": "24331-1"} ], "relations": [ {"head_entity_idx": 0, "tail_entity_idx": 1, "relation_type": "TREATED_BY"}, {"head_entity_idx": 0, "tail_entity_idx": 3, "relation_type": "MONITORED_BY"} ], "text_length": 112, "entity_count": 4, "annotator_id": "ANN-0388", "qc_score": 0.97 }, { "doc_id": "CLT-O0009105", "doc_type": "ORDER", "department": "INTERNAL", "text": "[DRUG] [DOSAGE] [ROUTE] [FREQUENCY] [DURATION]天", "entities": [ {"start": 0, "end": 6, "type": "DRUG", "subtype": "抗生素", "text": "[DRUG]", "atc_code": "J01MA"}, {"start": 7, "end": 15, "type": "DOSAGE", "subtype": "剂量", "text": "[DOSAGE]"}, {"start": 16, "end": 22, "type": "ROUTE", "subtype": "给药途径", "text": "[ROUTE]"} ], "relations": [], "text_length": 42, "entity_count": 3, "annotator_id": "ANN-0912", "qc_score": 0.99 }, { "doc_id": "CLT-L0001543", "doc_type": "LITERATURE", "department": "ONCOLOGY", "text": "本بحث旨在评估[DISEASE]患者中[DRUG]联合[DRUG]方案的有效性和安全性。共纳入[NUMBER]例患者，ORR为[VALUE]%，中位PFS为[VALUE]个月。", "entities": [ {"start": 6, "end": 16, "type": "DISEASE", "subtype": "肿瘤", "text": "[DISEASE]"}, {"start": 18, "end": 24, "type": "DRUG", "subtype": "抗肿瘤药", "text": "[DRUG]"}, {"start": 26, "end": 32, "type": "DRUG", "subtype": "抗肿瘤药", "text": "[DRUG]"}, {"start": 40, "end": 48, "type": "LAB", "subtype": "Clinical指标", "text": "ORR"}, {"start": 55, "end": 63, "type": "LAB", "subtype": "Clinical指标", "text": "中位PFS"} ], "relations": [ {"head_entity_idx": 0, "tail_entity_idx": 1, "relation_type": "TREATED_BY"}, {"head_entity_idx": 0, "tail_entity_idx": 3, "relation_type": "MEASURED_BY"} ], "text_length": 97, "entity_count": 5, "annotator_id": "ANN-0523", "qc_score": 0.95 } ]