{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "imcs-21",
  "name": "IMCS-21",
  "summary": {
    "zh": "许可证声明：未声明（NOASSERTION）；本站处理：待确认，暂只链接原出处。许可证未声明许可：仓库页面未写许可证；确认前只链接原出处。",
    "en": "License: unstated (NOASSERTION); Mdexa hosting: pending. License unstated: No license on the repository page; link only until resolved."
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "clinical-medicine"
  ],
  "content_types": [
    "qa-dialogue",
    "annotated-corpus"
  ],
  "content_description": {
    "en": "Pediatric consultation dialogues (annotated)",
    "zh": "儿科问诊对话（标注）"
  },
  "languages": [
    "zh"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": "4,116份标注问诊记录，覆盖10种儿科疾病",
    "measures": [
      {
        "value": 4116,
        "unit": "records",
        "qualifier": "exact",
        "scope": "annotated consultations"
      },
      {
        "value": 10,
        "unit": "categories",
        "qualifier": "exact",
        "scope": "pediatric diseases"
      }
    ]
  },
  "publisher": "lemuria-wchen / 复旦大学（Bioinformatics 2022）",
  "year": {
    "value": 2022,
    "raw": "2022"
  },
  "expert_review": {
    "en": "Annotated (entities, dialogue acts, symptoms, etc.)",
    "zh": "带标注（实体、对话行为、症状等）"
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "NOASSERTION",
    "commercial_use": "unstated",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "No license on the repository page",
      "zh": "仓库页面未写许可证"
    },
    "evidence": [
      {
        "location": "repo-sidebar",
        "location_detail": {
          "en": "Repository page shows no license; test set hosted on the Tianchi CBLUE platform [Note: No license statement seen in snapshot s01, s02]",
          "zh": "仓库页面未写许可证；测试集托管于天池 CBLUE 平台［备注：快照中未见许可声明（快照 s01, s02）］"
        },
        "excerpt": null,
        "spdx": null,
        "url": "https://github.com/lemuria-wchen/imcs21",
        "verified_on": "2026-11-12",
        "snapshot_id": null,
        "observed": "page",
        "secondhand": false
      }
    ]
  },
  "license_status": "unstated",
  "hosting": "pending",
  "hosting_reason": {
    "zh": "许可证未声明许可：仓库页面未写许可证；确认前只链接原出处。",
    "en": "License unstated: No license on the repository page; link only until resolved."
  },
  "signoff": null,
  "risk_flags": [
    "real-patient-text"
  ],
  "provenance": {
    "source_description": {
      "en": "Online consultation records",
      "zh": "在线问诊记录"
    },
    "upstream": []
  },
  "known_issues": [
    {
      "en": "Terms of the source platform and the de-identification method were not checked",
      "zh": "问诊记录来源平台条款与隐私脱敏方式本次未核"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://github.com/lemuria-wchen/imcs21"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "bibtex": null,
    "references": []
  },
  "verification_level": "verified-no-license-statement",
  "last_verified": "2026-11-12",
  "tags": [
    {
      "facet": "task_format",
      "value": "multi-turn-dialogue",
      "basis": "author-stated",
      "excerpt": "- IMCS-21 is released, containing a total of 4,116 annotated medical consultation records that covers 10 pediatric diseases.",
      "snapshot_id": "s01"
    },
    {
      "facet": "population",
      "value": "pediatric",
      "basis": "author-stated",
      "excerpt": "- IMCS-21 is released, containing a total of 4,116 annotated medical consultation records that covers 10 pediatric diseases.",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "ner",
      "basis": "author-stated",
      "excerpt": "- NER task: [Lattice LSTM](https://arxiv.org/abs/1805.02023), [BERT](https://arxiv.org/abs/1810",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "text-classification",
      "basis": "author-stated",
      "excerpt": "- DAC task: [TextCNN](https://arxiv.org/abs/1408.5882), [TextRNN](https://www.ijcai.org/Proceed",
      "snapshot_id": "s01"
    },
    {
      "facet": "task_format",
      "value": "summarization",
      "basis": "author-stated",
      "excerpt": "MRG task, we use the concatenation of all NON-OTHER categories of utterances to generate medical reports. During inference, the categories of utterances in the test set is pre-predicted by the",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "author-stated",
      "excerpt": "This repo contains a new corpus benchmark called **IMCS-21** for automated medical consultation system, as well as the code for rep",
      "snapshot_id": "s01"
    },
    {
      "facet": "specialty",
      "value": "pediatrics",
      "basis": "author-stated",
      "excerpt": "- IMCS-21 is released, containing a total of 4,116 annotated medical consultation records that covers 10 pediatric diseases.",
      "snapshot_id": "s01"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-12",
      "change": {
        "en": "Card converted from an earlier manual catalog; no new facts added; reclassified under taxonomy v2.",
        "zh": "由早期人工整理的目录转换生成，未新增事实；按分类体系 v2 重新归类。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "License status split into license_status (what the license says) and hosting (what Mdexa does); the earlier conclusion is kept for traceability.",
        "zh": "把许可证状态拆成 license_status（许可证怎么写）与 hosting（本站怎么处理）；原结论保留以便追溯。"
      }
    },
    {
      "date": "2026-11-12",
      "change": {
        "en": "Added verbatim license excerpts and snapshot ids from captured page snapshots; no conclusion changed.",
        "zh": "补入来自已抓取页面快照的许可证逐字摘录与快照编号；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added dataset-level tags: 7 (6 stated by the authors with excerpts, 1 inferred from the content). No conclusion changed.",
        "zh": "新增数据集标签 7 个（作者声明 6 个，附逐字摘录；据内容推断 1 个）；未改动任何结论。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Removed the stored size-tier tag; the tier is now computed from the size field when pages are built.",
        "zh": "移除存储的规模档位标签；档位改为生成页面时由 size 字段计算。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added specialty tags: pediatrics(author-stated).",
        "zh": "新增专科标签：pediatrics(author-stated)。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "github",
    "repo_id": "lemuria-wchen/imcs21",
    "source": {
      "api_url": "https://api.github.com/repos/lemuria-wchen/imcs21",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "git clone https://github.com/lemuria-wchen/imcs21",
        "evidence": {
          "excerpt": "git clone https://github.com/YOUR-USERNAME/YOUR-REPOSITORY",
          "doc": "github-clone",
          "url": "https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": null,
      "last_modified": "2022-12-24T07:18:23Z",
      "default_branch": "main"
    },
    "license_note": {
      "license_status": "unstated",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": [
      "the platform publishes no checksum for these files; none was computed (we do not download data files)"
    ]
  },
  "_links": {
    "text": "在本库继续查找。本条目是 109 条已处理并核实的记录之一（数据集、数据资源与开源模型）。查找其他条目：调用 `https://mcp.mdexa.com/v1/datasets?q=<关键词>`，或连接 MCP 服务 `https://mcp.mdexa.com/mcp`；每分钟 20 次以内无需密钥。每行返回不到 1 KB；空结果即\"数据库未收录\"。核对一份清单：一次批量核对（免费账号）即返回报告。说明：/agents.md。相似条目：CBLUE (https://mdexa.com/zh/datasets/cblue/)；MedDG (https://mdexa.com/zh/datasets/meddg/)；CMtMedQA (https://mdexa.com/zh/datasets/cmtmedqa/)。",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=%E7%BB%93%E5%90%88%E4%BA%B2%E5%92%8C%E5%8A%9B"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/zh/agents.md",
    "faq": "https://mdexa.com/zh/developers/faq/",
    "similar": [
      {
        "name": "CBLUE",
        "url": "https://mdexa.com/zh/datasets/cblue/",
        "json": "https://mdexa.com/zh/datasets/cblue.json"
      },
      {
        "name": "MedDG",
        "url": "https://mdexa.com/zh/datasets/meddg/",
        "json": "https://mdexa.com/zh/datasets/meddg.json"
      },
      {
        "name": "CMtMedQA",
        "url": "https://mdexa.com/zh/datasets/cmtmedqa/",
        "json": "https://mdexa.com/zh/datasets/cmtmedqa.json"
      }
    ]
  }
}