HIPPO Benchmark

Gold Standard Full Text

This table contains the full text of the clinical notes, plus some patient demographics.

field type
note_id STRING
note_text STRING
note_title STRING
note_length INTEGER
sex STRING
age INTEGER
race STRING
ethnicity STRING
note_source_value STRING
stanford_patient_uid STRING
load_table_id STRING

Columns Description

note_id

Unique identifier for the clinical note

note_text

Text of the clinical note

note_title

Short description with the type of note

note_length

Length of the clinical note text in characters

sex

Biological Sex of the person to whom the note is about.

age

This is the years difference since 2025 and the birth date.

race

This is the self reported race of the person to whom the note is about.

ethnicity

Self reported ethnicity of the person to whom the note is about.

note_source_value

This is the unique identifier of the note in EPIC Clarity.

stanford_patient_uid

Unique patient identifier within the STARR DataLake that consist on the concatenation of patient MRN and DOB

load_table_id

Internal identifier for the data loading process that brought this record into the system.

Gold Standard Spans

This table contains the annotated spans.

field type
uuid STRING
note_id STRING
span_start INTEGER
span_end INTEGER
span_tag STRING

Columns Description

uuid

Unique identifier of the sample

note_id

Unique identifier for the clinical note to whom the spans corresponds.

span_start

Integer index of the start of the annotation inside the note_text.

span_end

Integer index of the end of the annotation inside the note_text.

span_tag

Label of the annotation.