{
  "corpus": {
    "source": "EMA centrally-authorised medicines, EPAR product information leaflets",
    "indexed": 1874,
    "parsed": 1777,
    "parse_errors": 0,
    "not_found": 97,
    "extraction_date": "2026-10-23T15:02:20+00:00"
  },
  "vocabulary": {
    "total_excipient_mentions": 16086,
    "distinct_raw_strings": 3553,
    "distinct_after_normalisation": 2178,
    "fragmentation_rate_pct": 38.7,
    "substances_with_multiple_spellings": 375,
    "mean_excipients_per_product": 9.1,
    "products_with_zero_parsed_excipients": 215
  },
  "top_excipients": [
    {
      "name": "titanium dioxide",
      "products": 599,
      "pct_of_corpus": 33.7
    },
    {
      "name": "magnesium stearate",
      "products": 544,
      "pct_of_corpus": 30.6
    },
    {
      "name": "water for injections",
      "products": 513,
      "pct_of_corpus": 28.9
    },
    {
      "name": "microcrystalline cellulose",
      "products": 398,
      "pct_of_corpus": 22.4
    },
    {
      "name": "talc",
      "products": 338,
      "pct_of_corpus": 19.0
    },
    {
      "name": "hypromellose",
      "products": 316,
      "pct_of_corpus": 17.8
    },
    {
      "name": "mannitol",
      "products": 284,
      "pct_of_corpus": 16.0
    },
    {
      "name": "sodium chloride",
      "products": 264,
      "pct_of_corpus": 14.9
    },
    {
      "name": "polysorbate 80",
      "products": 244,
      "pct_of_corpus": 13.7
    },
    {
      "name": "croscarmellose sodium",
      "products": 239,
      "pct_of_corpus": 13.4
    },
    {
      "name": "lactose monohydrate",
      "products": 238,
      "pct_of_corpus": 13.4
    },
    {
      "name": "sucrose",
      "products": 209,
      "pct_of_corpus": 11.8
    },
    {
      "name": "propylene glycol",
      "products": 181,
      "pct_of_corpus": 10.2
    },
    {
      "name": "iron oxide yellow",
      "products": 181,
      "pct_of_corpus": 10.2
    },
    {
      "name": "iron oxide red",
      "products": 157,
      "pct_of_corpus": 8.8
    },
    {
      "name": "polysorbate 20",
      "products": 152,
      "pct_of_corpus": 8.6
    },
    {
      "name": "yellow iron oxide",
      "products": 150,
      "pct_of_corpus": 8.4
    },
    {
      "name": "shellac",
      "products": 144,
      "pct_of_corpus": 8.1
    },
    {
      "name": "gelatin",
      "products": 140,
      "pct_of_corpus": 7.9
    },
    {
      "name": "red iron oxide",
      "products": 129,
      "pct_of_corpus": 7.3
    },
    {
      "name": "sodium hydroxide (for ph adjustment)",
      "products": 127,
      "pct_of_corpus": 7.1
    },
    {
      "name": "colloidal anhydrous silica",
      "products": 126,
      "pct_of_corpus": 7.1
    },
    {
      "name": "silica, colloidal anhydrous",
      "products": 122,
      "pct_of_corpus": 6.9
    },
    {
      "name": "hydrochloric acid (for ph adjustment)",
      "products": 121,
      "pct_of_corpus": 6.8
    },
    {
      "name": "macrogol",
      "products": 120,
      "pct_of_corpus": 6.8
    }
  ],
  "starch": {
    "products_with_any_starch_or_dextrin": 271,
    "pct_of_corpus": 15.3,
    "distinct_starch_strings": 101,
    "products_naming_botanical_source": 133,
    "products_with_source_undisclosed": 138,
    "source_disclosure_rate_pct": 49.1,
    "by_source": {
      "maize": 128,
      "corn": 4,
      "potato": 1,
      "pea": 1
    }
  },
  "gluten_declarations": {
    "products_declaring_wheat_starch": 0,
    "products_voluntarily_annotating_gluten_free": 2,
    "pct_of_starch_products_annotated": 0.7,
    "annotated_products": [
      {
        "product": "Truvada",
        "text": "Pregelatinised starch (gluten free)"
      },
      {
        "product": "Combivir",
        "text": "sodium starch glycollate (gluten free)"
      }
    ]
  },
  "sodium_starch_glycolate": {
    "products": 109,
    "distinct_spellings": 22,
    "spellings_naming_a_source": 0
  }
}
