Skip to content

Commit

Permalink
fix: README typos and "patient_id" description
Browse files Browse the repository at this point in the history
  • Loading branch information
MarIniOnz committed Dec 5, 2024
1 parent 0a3f443 commit e4bb073
Show file tree
Hide file tree
Showing 3 changed files with 13 additions and 12 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ The dataset is a synthetic dataset created to simulate a medium-scale medical re

The patient data consists of 600 hypothetical patients.

- **patient_id:** A unique identifier assigned each patient
- **patient_id:** Unique identifier assigned each patient
- **gender:** Recorded as Male, Female, or Non-Binary
- **age:** Patient's age in years

Expand Down Expand Up @@ -49,34 +49,34 @@ The drug data has 1 possible event

There are 5741 diagnosis instances for the 600 patients.

- **patient_id:** Linked to the Patient Demographics
- **patient_id:** Unique identifier assigned each patient
- **diagnosis_code:** Unique code identifiying a specific diagnosis
- **time:** Date of the diagnosis
- **duration_days** Duration in days in which the diagnosis held true

### 2. `patient_procedure.csv`

For all five patients there are 677 procedures in the dataset.
For all 600 patients there are 677 procedures in the dataset.

- **patient_id:** Linked to the Patient Demographics
- **patient_id:** Unique identifier assigned each patient
- **procedure_code:** Unique identifier for each procedure
- **time:** Exact time and date for the procedure
- **duration_minutes:** How long the procedure needed in minutes

### 3. `patient_drug.csv`

There are also 20373 prescribed medications for the five patients combined.
There are also 20373 prescribed medications for the 600 patients combined.

- **patient_id:** Linked to the Patient Demographics
- **patient_id:** Unique identifier assigned each patient
- **drug_code:** Unique identifier for the medication prescribed
- **time:** Time and date when the medication was prescribed
- **quantity:** how many doses were prescribed
- **cost:** Cost of the medication order in Dollar

### 4. `patient_event.csv`

There are also 20373 prescribed medications for the five patients combined.
There are also 20373 prescribed medications for the 600 patients combined.

- **patient_id:** Linked to the Patient Demographics
- **patient_id:** Unique identifier assigned each patient
- **event:** Name of the event linked to the patient
- **time:** Time and date when the event occurred
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ The drug data has 19 different prescribed medications.

There are 60 diagnosis instances for the five patients.

- **patient_id:** Linked to the Patient Demographics
- **patient_id:** Unique identifier assigned each patient
- **diagnosis_code:** Unique code identifiying a specific diagnosis
- **time:** Date of the diagnosis
- **duration_days** Duration in days in which the diagnosis held true
Expand All @@ -52,7 +52,7 @@ There are 60 diagnosis instances for the five patients.

For all five patients there are 50 procedures in the dataset.

- **patient_id:** Linked to the Patient Demographics
- **patient_id:** Unique identifier assigned each patient
- **procedure_code:** Unique identifier for each procedure
- **time:** Exact time and date for the procedure
- **duration_minutes:** How long the procedure needed in minutes
Expand All @@ -61,7 +61,7 @@ For all five patients there are 50 procedures in the dataset.

There are also 50 prescribed medications for the five patients combined.

- **patient_id:** Linked to the Patient Demographics
- **patient_id:** Unique identifier assigned each patient
- **drug_code:** Unique identifier for the medication prescribed
- **time:** Time and date when the medication was prescribed
- **quantity:** how many doses were prescribed
Expand Down
3 changes: 2 additions & 1 deletion medmodels/medrecord/medrecord.py
Original file line number Diff line number Diff line change
Expand Up @@ -268,7 +268,8 @@ def from_advanced_example_dataset(cls) -> MedRecord:
"""Creates a MedRecord instance from an example dataset with a higher number of nodes and edges.
The example dataset was created using the Synthea™ Patient Generator:
https://github.com/synthetichealth/synthea
https://github.com/synthetichealth/synthea and it includes 600 patients with
their diagnoses, prescriptions, procedures, and death events.
Returns:
MedRecord: A new instance created from the advanced example dataset.
Expand Down

0 comments on commit e4bb073

Please sign in to comment.