Skip to main content
. 2025 Jun 4;13:e68138. doi: 10.2196/68138

Table 2.

Summary statistics of the Malmo Diet and Cancer Cohort (MDC) dataset.


Pretraining dataset Fine-tuning dataset Test dataset Total dataset
Patients, n 21,000 6000 3000 30,000
Visits, n 373,000 107,000 52,000 531,000
ICD-10a codes, n 1,155,000 331,000 161,000 1,647,000
ATCb codes, n 4,185,000 1,223,000 580,000 5,988,000
All codes, n 5,339,000 1,554,000 741,000 7,634,000

aICD-10: International Statistical Classification of Diseases, Tenth Revision.

bATC: Anatomical Therapeutic Chemical Code.