fix: remove deprecated code_mapping, dev, refresh_cache from examples (#935)

The v2.0 MIMIC3Dataset/MIMIC4Dataset (based on BaseDataset) no longer
accepts code_mapping, dev, or refresh_cache parameters. These were
part of the legacy BaseEHRDataset API.

Update README.rst, example scripts, and leaderboard utilities to use
the current v2.0 API.

Note: task file docstrings and pyhealth/datasets/mimicextract.py
still reference code_mapping but are left for separate PRs since
mimicextract.py has not yet been migrated to v2.0.

Fixes #535

Author: haoyu-haoyu

README.rst

@@ -189,8 +189,6 @@ Module 1: <pyhealth.datasets>
         root="https://storage.googleapis.com/pyhealth/Synthetic_MIMIC-III/",
         # raw CSV table name
         tables=["DIAGNOSES_ICD", "PROCEDURES_ICD", "PRESCRIPTIONS"],
-        # map all NDC codes to CCS codes in these tables
-        code_mapping={"NDC": "CCSCM"},
     )
 
 .. image:: figure/structured-dataset.png

examples/drug_recommendation/drug_recommendation_mimic4_gamenet.py

@@ -25,9 +25,6 @@ def prepare_drug_task_data():
     mimicvi = MIMIC4Dataset(
         root="/srv/local/data/physionet.org/files/mimiciv/2.0/hosp",
         tables=["diagnoses_icd", "procedures_icd", "prescriptions"],
-        code_mapping={"NDC": ("ATC", {"target_kwargs": {"level": 3}})},
-        dev=_DEV,
-        refresh_cache=False,
     )
 
     print("stat")

examples/mortality_prediction/mortality_mimic3_grasp.py

@@ -9,9 +9,6 @@
     base_dataset = MIMIC3Dataset(
         root="/srv/local/data/physionet.org/files/mimiciii/1.4",
         tables=["DIAGNOSES_ICD", "PROCEDURES_ICD", "PRESCRIPTIONS"],
-        code_mapping={"ICD9CM": "CCSCM", "ICD9PROC": "CCSPROC", "NDC": "ATC"},
-        dev=False,
-        refresh_cache=False,
     )
     base_dataset.stat()
 

examples/patient_linkage_mimic3_medlink.py

@@ -29,9 +29,6 @@
 base_dataset = MIMIC3Dataset(
     root="/srv/local/data/physionet.org/files/mimiciii/1.4",
     tables=["DIAGNOSES_ICD"],
-    code_mapping={"ICD9CM": ("CCSCM", {})},
-    dev=False,
-    refresh_cache=False,
 )
 base_dataset.stat()
 

leaderboard/utils.py

@@ -64,9 +64,6 @@ def get_dataset(dataset_name):
         mimic3dataset = MIMIC3Dataset(
             root="/srv/local/data/physionet.org/files/mimiciii/1.4",
             tables=["DIAGNOSES_ICD", "PROCEDURES_ICD", "PRESCRIPTIONS"],
-            dev=False,
-            code_mapping={"NDC": "ATC"},
-            refresh_cache=False,
         )
         dataset = mimic3dataset
 
@@ -83,9 +80,6 @@ def get_dataset(dataset_name):
         mimic4dataset = MIMIC4Dataset(
             root="/srv/local/data/physionet.org/files/mimiciv/2.0/hosp",
             tables=["diagnoses_icd", "procedures_icd", "prescriptions"],
-            dev=False,
-            code_mapping={"NDC": "ATC"},
-            refresh_cache=False,
         )
         dataset = mimic4dataset