Table 1 Studies on the construction of Chinese clinical text corpora in the last five years
Year | Author | Scale and target | Entities | Fine-grained | TCM clinical texts |
|---|---|---|---|---|---|
2014 | Xu et al. [9] | 336 Chinese discharge summaries of 71,355 words | Medication, anatomy, medical problems, treatments, and tests | N | N |
2014 | Lei et al. [5] | 400 admission notes and 400 discharge summaries | Clinical problems, procedures, laboratory tests, and medications | N | N |
2014 | Wang et al. [21] | 11,613 clinical records | Symptoms | N | Y |
2014 | Wang et al. [22] | 115 EMRs | 115 documents on tumor-related information from the notes of hepatic carcinoma operations | N | N |
2014 | Gao et al. [23] | 42 health records of stroke | Body structures and clinical description | N | Y |
2015 | Li et al. [24] | 700 initial diagnosis records, congestive heart failure data of 253 cases. | TCM herbs and symptoms | N | Y |
2015 | Xu et al. [25] | 24,817 anonymized Chinese EMRs | Symptoms, clinical tests, diseases, drugs, body parts, and procedure categories | N | Y |
2016 | Zhang et al. [26] | 2000 notes (1000 admission notes and 1000 discharge summaries) | Diseases and syndromes, symptoms and signs, treatments and drugs, and laboratory tests | N | N |
2016 | Wan et al. [27] | More than 100,000 TCM article abstracts | Herbs, syndromes, diseases, and formulas | N | Y |
2016 | Liu et al. [13] | 1778 clinical notes of 281 hospitalized patients | Temporal expression and normalization in Chinese clinical notes (type, value, and modifier) | N | N |
2017 | Ruan et al. [28] | 1000 EMRs | Symptoms, departments, diseases, medicines, and examinations | N | Y |
2017 | He et al. [10] | 500 discharge summaries and 492 progress notes | Diseases, symptoms, and treatments | N | N |
2018 | Zhang et al. [29] | 400 documents | Symptoms, tests, diagnoses, treatments, and body parts | N | N |
2018 | Miao et al. [30] | 540 reports | Breast Imaging Reporting and Data System | N | N |
2018 | Bao et al. [31] | 600 documents | History of present illnesses, personal history, and family history | N | N |
2019 | Wang et al. [32] | 1596 annotated instances (10,024 sentences) | Diseases, symptoms, exams, treatments, and body parts | N | N |
2019 | Gao et al. [11] | 255 authentic admission records | Medical discovery, body parts, temporal words, diseases, medications, treatments, inspections, laboratory tests, and measurements | N | N |
2019 | Cai et al. [12] | 1000 admission records | Anatomical parts, symptom descriptions, independent symptoms, drugs, and operations | N | N |
2019 | Xiong et al. [33] | 1000 admission notes and 800 discharge summaries | Body parts, diseases, symptoms, tests, and treatments | Y | N |