{
  "dataset": {
    "records": 35003,
    "clinical_records": 6102
  },
  "deduplication": {
    "groups": 1526,
    "removed_records_if_one_per_group": 4576,
    "groups_with_nonidentical_clinical_texts": 627,
    "records_in_nonidentical_groups": 4743,
    "examples": [
      {
        "key": "substance:chlorid sodný",
        "records": 20,
        "different_texts": 7,
        "forms": [
          "CON INF - Infúzny koncentrát",
          "SOL INF - Infúzny roztok",
          "SOL INJ - Injekčný roztok"
        ]
      },
      {
        "key": "substance:inzulín glargín",
        "records": 8,
        "different_texts": 5,
        "forms": [
          "SOL INJ - Injekčný roztok"
        ]
      },
      {
        "key": "substance:bevacizumab",
        "records": 13,
        "different_texts": 7,
        "forms": [
          "CON IFO - Infúzny koncentrát",
          "CON INF - Infúzny koncentrát"
        ]
      },
      {
        "key": "substance:aripiprazol",
        "records": 25,
        "different_texts": 12,
        "forms": [
          "PLU IGF - Prášok a disperzné prostredie na injekčnú suspenziu s predĺženým uvoľňovaním",
          "SOL POR - Perorálny roztok",
          "SUS IPH - Injekčná suspenzia s predĺženým uvoľňovaním v naplnenej injekčnej striekačke",
          "TBL - Tablety",
          "TBL ORO - Orodispergovateľné tablety"
        ]
      },
      {
        "key": "substance:abiraterón acetát",
        "records": 15,
        "different_texts": 15,
        "forms": [
          "TBL - Tablety",
          "TBL FLM - Filmom obalené tablety"
        ]
      },
      {
        "key": "substance:bilastín",
        "records": 12,
        "different_texts": 7,
        "forms": [
          "TBL - Tablety",
          "TBL ORO - Orodispergovateľné tablety"
        ]
      },
      {
        "key": "substance:extrakt alergénov prachu|extrakt alergénov roztočov",
        "records": 7,
        "different_texts": 2,
        "forms": [
          "LYO SLG - Sublingválny lyofilizát",
          "TBL SLG - Sublingválna tableta"
        ]
      },
      {
        "key": "substance:acetylcysteín",
        "records": 13,
        "different_texts": 8,
        "forms": [
          "GRA - Granulát",
          "PAS ORD - Pastilka tvrdá",
          "PLV POS - Perorálny prášok vo vrecku",
          "PLV SIR - Prášok na sirup",
          "SOL INJ - Injekčný roztok",
          "SOL POR - Perorálny roztok",
          "TBL EFF - Šumivé tablety"
        ]
      },
      {
        "key": "substance:filgrastim",
        "records": 6,
        "different_texts": 3,
        "forms": [
          "SOL IJF - Injekčný a infúzny roztok"
        ]
      },
      {
        "key": "substance:aceklofenak",
        "records": 6,
        "different_texts": 4,
        "forms": [
          "CRM DER - Dermálny krém",
          "PLU POR - Prášok na perorálnu suspenziu",
          "TBL FLM - Filmom obalené tablety"
        ]
      },
      {
        "key": "substance:aciklovir",
        "records": 14,
        "different_texts": 9,
        "forms": [
          "CRM - Krém",
          "PLV IFO - Prášok na infúzny roztok",
          "SUS POR - Perorálna suspenzia",
          "TBL - Tablety",
          "UNG OPH - Očná masť"
        ]
      },
      {
        "key": "substance:kyselina askorbová (vitamín c)",
        "records": 8,
        "different_texts": 6,
        "forms": [
          "CPS PLD - Tvrdá kapsula s predĺženým uvoľňovaním",
          "PAS OCP - Lisovaná pastilka",
          "SOL INJ - Injekčný roztok",
          "TBL - Tablety",
          "TBL EFF - Šumivé tablety"
        ]
      },
      {
        "key": "substance:kyselina zoledrónová",
        "records": 8,
        "different_texts": 8,
        "forms": [
          "CON INF - Infúzny koncentrát",
          "SOL INF - Infúzny roztok"
        ]
      },
      {
        "key": "substance:celekoxib",
        "records": 4,
        "different_texts": 2,
        "forms": [
          "CPS DUR - Tvrdá kapsula"
        ]
      },
      {
        "key": "substance:hydrochlorotiazid|telmisartan",
        "records": 18,
        "different_texts": 7,
        "forms": [
          "TBL - Tablety",
          "TBL OBD - Obalené tablety"
        ]
      }
    ],
    "limitation": "Text differences are not evidence of clinically material differences; manual review is required."
  },
  "semantic_graph": {
    "nodes": 34540,
    "edges": 87104,
    "types": {
      "drug": 4236,
      "condition": 10775,
      "indication": 2378,
      "method": 1188,
      "activesubstance": 3747,
      "patientgroup": 2105,
      "event": 89,
      "drugclass": 3711,
      "other": 1339,
      "interaction": 760,
      "UNKNOWN": 1044,
      "location": 39,
      "contraindication": 1727,
      "data": 33,
      "concept": 742,
      "organism": 6,
      "content": 34,
      "device": 14,
      "procedure": 84,
      "anatomicalsite": 1,
      "organ": 32,
      "person": 17,
      "artifact": 28,
      "organization": 47,
      "activity": 8,
      "process": 9,
      "anatomicalstructure": 31,
      "anatomy": 21,
      "bodypart": 36,
      "timeperiod": 4,
      "effect": 7,
      "substance": 17,
      "system": 2,
      "food": 16,
      "medicaldevice": 8,
      "measurement": 6,
      "symptom": 37,
      "medicalprocedure": 6,
      "bodyregion": 1,
      "persongroup": 5,
      "category": 3,
      "biologicalsubstance": 1,
      "equipment": 5,
      "timeduration": 2,
      "treatment": 7,
      "metric": 2,
      "bacterium": 6,
      "bacteria": 14,
      "bodyfluid": 3,
      "bodystructure": 4,
      "duration": 4,
      "bloodvessel": 1,
      "physiologicalparameter": 7,
      "dosage": 6,
      "biologicalfluid": 1,
      "entity": 1,
      "biologicalprocess": 2,
      "test": 3,
      "gene": 2,
      "information": 1,
      "function": 1,
      "microorganism": 1,
      "timecondition": 2,
      "adverseeffect": 1,
      "documentsection": 1,
      "biologicalmarker": 1,
      "bodylocation": 1,
      "tissue": 2,
      "pharmacodynamiceffect": 2,
      "formulation": 1,
      "physiologicalprocess": 2,
      "product": 4,
      "organtissue": 1,
      "labvalue": 1,
      "biologicalstructure": 1,
      "target": 1,
      "medicalproduct": 1,
      "error": 1,
      "celltype": 2,
      "bodysystem": 1,
      "section": 1,
      "virus": 5,
      "source": 1,
      "sample": 1,
      "timeframe": 1,
      "drugform": 2,
      "proteintarget": 1,
      "cell": 1,
      "dosageform": 1,
      "biomarker": 3,
      "body": 4,
      "time": 3,
      "toxin": 1,
      "diet": 1,
      "packaging": 1,
      "]activesubstance": 1,
      "]method": 1,
      "]patientgroup": 1,
      "]condition": 2,
      "]indication": 3,
      "mechanismus": 1,
      "measure": 1,
      "treatmentduration": 1,
      "type": 1,
      "keywords": 1,
      "creature": 1,
      "naturalobject": 1,
      "medicalspecialty": 1,
      "sideeffect": 1,
      "pharmacologicaleffect": 1,
      "action": 1,
      "enzyme": 1
    },
    "normalized_duplicate_groups": 3670,
    "nodes_in_duplicate_groups": 8042,
    "excess_nodes_after_normalization": 4372
  },
  "document_status": {
    "processed": 1500
  }
}