{
  "corpus": {
    "source": "EMA centrally-authorised medicines, EPAR product information leaflets",
    "indexed": 1851,
    "parsed": 1360,
    "parse_errors": 447,
    "not_found": 44,
    "extraction_date": "2026-04-30T13:45:47+00:00"
  },
  "vocabulary": {
    "total_excipient_mentions": 12795,
    "distinct_raw_strings": 2975,
    "distinct_after_normalisation": 1842,
    "fragmentation_rate_pct": 38.1,
    "substances_with_multiple_spellings": 327,
    "mean_excipients_per_product": 9.4,
    "products_with_zero_parsed_excipients": 110
  },
  "top_excipients": [
    {
      "name": "titanium dioxide",
      "products": 479,
      "pct_of_corpus": 35.2
    },
    {
      "name": "magnesium stearate",
      "products": 435,
      "pct_of_corpus": 32.0
    },
    {
      "name": "water for injections",
      "products": 412,
      "pct_of_corpus": 30.3
    },
    {
      "name": "microcrystalline cellulose",
      "products": 325,
      "pct_of_corpus": 23.9
    },
    {
      "name": "talc",
      "products": 271,
      "pct_of_corpus": 19.9
    },
    {
      "name": "hypromellose",
      "products": 256,
      "pct_of_corpus": 18.8
    },
    {
      "name": "sodium chloride",
      "products": 225,
      "pct_of_corpus": 16.5
    },
    {
      "name": "mannitol",
      "products": 224,
      "pct_of_corpus": 16.5
    },
    {
      "name": "polysorbate 80",
      "products": 207,
      "pct_of_corpus": 15.2
    },
    {
      "name": "lactose monohydrate",
      "products": 204,
      "pct_of_corpus": 15.0
    },
    {
      "name": "croscarmellose sodium",
      "products": 193,
      "pct_of_corpus": 14.2
    },
    {
      "name": "sucrose",
      "products": 167,
      "pct_of_corpus": 12.3
    },
    {
      "name": "iron oxide yellow",
      "products": 144,
      "pct_of_corpus": 10.6
    },
    {
      "name": "propylene glycol",
      "products": 131,
      "pct_of_corpus": 9.6
    },
    {
      "name": "yellow iron oxide",
      "products": 125,
      "pct_of_corpus": 9.2
    },
    {
      "name": "polysorbate 20",
      "products": 118,
      "pct_of_corpus": 8.7
    },
    {
      "name": "iron oxide red",
      "products": 117,
      "pct_of_corpus": 8.6
    },
    {
      "name": "red iron oxide",
      "products": 107,
      "pct_of_corpus": 7.9
    },
    {
      "name": "shellac",
      "products": 104,
      "pct_of_corpus": 7.6
    },
    {
      "name": "sodium hydroxide (for ph adjustment)",
      "products": 103,
      "pct_of_corpus": 7.6
    },
    {
      "name": "gelatin",
      "products": 102,
      "pct_of_corpus": 7.5
    },
    {
      "name": "silica, colloidal anhydrous",
      "products": 97,
      "pct_of_corpus": 7.1
    },
    {
      "name": "macrogol",
      "products": 97,
      "pct_of_corpus": 7.1
    },
    {
      "name": "colloidal anhydrous silica",
      "products": 97,
      "pct_of_corpus": 7.1
    },
    {
      "name": "hydrochloric acid (for ph adjustment)",
      "products": 93,
      "pct_of_corpus": 6.8
    }
  ],
  "starch": {
    "products_with_any_starch_or_dextrin": 218,
    "pct_of_corpus": 16.0,
    "distinct_starch_strings": 84,
    "products_naming_botanical_source": 109,
    "products_with_source_undisclosed": 109,
    "source_disclosure_rate_pct": 50.0,
    "by_source": {
      "maize": 107,
      "corn": 2,
      "pea": 1
    }
  },
  "gluten_declarations": {
    "products_declaring_wheat_starch": 0,
    "products_voluntarily_annotating_gluten_free": 2,
    "pct_of_starch_products_annotated": 0.9,
    "annotated_products": [
      {
        "product": "Truvada",
        "text": "Pregelatinised starch (gluten free)"
      },
      {
        "product": "Combivir",
        "text": "sodium starch glycollate (gluten free)"
      }
    ]
  },
  "sodium_starch_glycolate": {
    "products": 87,
    "distinct_spellings": 17,
    "spellings_naming_a_source": 0
  }
}
