Fix/eicu

docs/api/tasks/pyhealth.tasks.drug_recommendation.rst

@@ -1,4 +1,4 @@
-pyhealth.tasks.drug_recommendation
+pyhealth.tasks.drug_recommendation
 ===================================
 
 Task Classes
@@ -14,10 +14,14 @@ Task Classes
     :undoc-members:
     :show-inheritance:
 
+.. autoclass:: pyhealth.tasks.drug_recommendation.DrugRecommendationEICU
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
 Task Functions (Legacy)
 ------------------------
 
 .. autofunction:: pyhealth.tasks.drug_recommendation.drug_recommendation_mimic3_fn
 .. autofunction:: pyhealth.tasks.drug_recommendation.drug_recommendation_mimic4_fn
-.. autofunction:: pyhealth.tasks.drug_recommendation.drug_recommendation_eicu_fn
 .. autofunction:: pyhealth.tasks.drug_recommendation.drug_recommendation_omop_fn

docs/api/tasks/pyhealth.tasks.length_of_stay_prediction.rst

@@ -1,7 +1,25 @@
-pyhealth.tasks.length_of_stay_prediction
+pyhealth.tasks.length_of_stay_prediction
 ===========================================
 
-.. autofunction:: pyhealth.tasks.length_of_stay_prediction.length_of_stay_prediction_mimic3_fn
-.. autofunction:: pyhealth.tasks.length_of_stay_prediction.length_of_stay_prediction_mimic4_fn
-.. autofunction:: pyhealth.tasks.length_of_stay_prediction.length_of_stay_prediction_eicu_fn
-.. autofunction:: pyhealth.tasks.length_of_stay_prediction.length_of_stay_prediction_omop_fn
+Task Classes
+------------
+
+.. autoclass:: pyhealth.tasks.length_of_stay_prediction.LengthOfStayPredictionMIMIC3
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.tasks.length_of_stay_prediction.LengthOfStayPredictionMIMIC4
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.tasks.length_of_stay_prediction.LengthOfStayPredictioneICU
+    :members:
+    :undoc-members:
+    :show-inheritance:
+
+.. autoclass:: pyhealth.tasks.length_of_stay_prediction.LengthOfStayPredictionOMOP
+    :members:
+    :undoc-members:
+    :show-inheritance:

docs/api/tasks/pyhealth.tasks.readmission_prediction.rst

@@ -11,8 +11,10 @@
     :undoc-members:
     :show-inheritance:
 
-.. autofunction:: pyhealth.tasks.readmission_prediction.readmission_prediction_eicu_fn
-.. autofunction:: pyhealth.tasks.readmission_prediction.readmission_prediction_eicu_fn2
+.. autoclass:: pyhealth.tasks.readmission_prediction.ReadmissionPredictionEICU
+    :members:
+    :undoc-members:
+    :show-inheritance:
 
 .. autoclass:: pyhealth.tasks.readmission_prediction.ReadmissionPredictionOMOP
     :members:

examples/drug_recommendation/drug_recommendation_eicu_transformer.py

@@ -0,0 +1,59 @@
+"""
+Drug Recommendation on eICU with Transformer
+
+This example demonstrates how to use the modernized eICUDataset with the
+DrugRecommendationEICU task class for drug recommendation using a Transformer model.
+
+Features:
+- Uses the new BaseDataset-based eICUDataset with YAML configuration
+- Uses the new DrugRecommendationEICU BaseTask class
+- Demonstrates the standardized PyHealth workflow
+"""
+
+import tempfile
+
+from pyhealth.datasets import eICUDataset
+from pyhealth.datasets import split_by_patient, get_dataloader
+from pyhealth.models import Transformer
+from pyhealth.tasks import DrugRecommendationEICU
+from pyhealth.trainer import Trainer
+
+
+if __name__ == "__main__":
+    # STEP 1: Load dataset
+    base_dataset = eICUDataset(
+        root="https://storage.googleapis.com/pyhealth/eicu-demo/",
+        tables=["diagnosis", "medication", "physicalexam"],
+        cache_dir=tempfile.TemporaryDirectory().name,
+        dev=True,
+    )
+    base_dataset.stats()
+
+    # STEP 2: Set task
+    task = DrugRecommendationEICU()
+    sample_dataset = base_dataset.set_task(task)
+
+    # STEP 3: Split and create dataloaders
+    train_dataset, val_dataset, test_dataset = split_by_patient(
+        sample_dataset, [0.8, 0.1, 0.1]
+    )
+    train_dataloader = get_dataloader(train_dataset, batch_size=32, shuffle=True)
+    val_dataloader = get_dataloader(val_dataset, batch_size=32, shuffle=False)
+    test_dataloader = get_dataloader(test_dataset, batch_size=32, shuffle=False)
+
+    # STEP 4: Define model
+    model = Transformer(
+        dataset=sample_dataset,
+    )
+
+    # STEP 5: Train
+    trainer = Trainer(model=model)
+    trainer.train(
+        train_dataloader=train_dataloader,
+        val_dataloader=val_dataloader,
+        epochs=1,
+        monitor="pr_auc_samples",
+    )
+
+    # STEP 6: Evaluate
+    print(trainer.evaluate(test_dataloader))

examples/length_of_stay/length_of_stay_eicu_rnn.py

@@ -0,0 +1,73 @@
+"""
+Length of Stay Prediction on eICU with RNN
+
+This example demonstrates how to use the modernized eICUDataset with the
+LengthOfStayPredictioneICU task class for predicting ICU length of stay
+using an RNN model.
+
+Length of stay is categorized into 10 classes:
+- 0: < 1 day
+- 1: 1 day
+- 2: 2 days
+- 3: 3 days
+- 4: 4 days
+- 5: 5 days
+- 6: 6 days
+- 7: 7 days
+- 8: 1-2 weeks
+- 9: > 2 weeks
+
+Features:
+- Uses the new BaseDataset-based eICUDataset with YAML configuration
+- Uses the LengthOfStayPredictioneICU BaseTask class
+- Demonstrates the standardized PyHealth workflow
+"""
+
+import tempfile
+
+from pyhealth.datasets import eICUDataset
+from pyhealth.datasets import split_by_patient, get_dataloader
+from pyhealth.models import RNN
+from pyhealth.tasks import LengthOfStayPredictioneICU
+from pyhealth.trainer import Trainer
+
+
+if __name__ == "__main__":
+    # STEP 1: Load dataset
+    base_dataset = eICUDataset(
+        root="https://storage.googleapis.com/pyhealth/eicu-demo/",
+        tables=["diagnosis", "medication", "physicalexam"],
+        num_workers=4,
+        cache_dir=tempfile.TemporaryDirectory().name,
+        dev=True,
+    )
+    base_dataset.stats()
+
+    # STEP 2: Set task
+    task = LengthOfStayPredictioneICU()
+    sample_dataset = base_dataset.set_task(task, num_workers=16)
+
+    # STEP 3: Split and create dataloaders
+    train_dataset, val_dataset, test_dataset = split_by_patient(
+        sample_dataset, [0.8, 0.1, 0.1]
+    )
+    train_dataloader = get_dataloader(train_dataset, batch_size=32, shuffle=True)
+    val_dataloader = get_dataloader(val_dataset, batch_size=32, shuffle=False)
+    test_dataloader = get_dataloader(test_dataset, batch_size=32, shuffle=False)
+
+    # STEP 4: Define model
+    model = RNN(
+        dataset=sample_dataset,
+    )
+
+    # STEP 5: Train
+    trainer = Trainer(model=model)
+    trainer.train(
+        train_dataloader=train_dataloader,
+        val_dataloader=val_dataloader,
+        epochs=1,
+        monitor="accuracy",
+    )
+
+    # STEP 6: Evaluate
+    print(trainer.evaluate(test_dataloader))

examples/mortality_prediction/mortality_prediction_eicu_rnn.py

@@ -0,0 +1,60 @@
+"""
+Mortality Prediction on eICU with RNN
+
+This example demonstrates how to use the modernized eICUDataset with the
+MortalityPredictionEICU task class for in-hospital mortality prediction
+using an RNN model.
+
+Features:
+- Uses the new BaseDataset-based eICUDataset with YAML configuration
+- Uses the MortalityPredictionEICU BaseTask class
+- Demonstrates the standardized PyHealth workflow
+"""
+
+import tempfile
+
+from pyhealth.datasets import eICUDataset
+from pyhealth.datasets import split_by_patient, get_dataloader
+from pyhealth.models import RNN
+from pyhealth.tasks import MortalityPredictionEICU
+from pyhealth.trainer import Trainer
+
+
+if __name__ == "__main__":
+    # STEP 1: Load dataset
+    base_dataset = eICUDataset(
+        root="https://storage.googleapis.com/pyhealth/eicu-demo/",
+        tables=["diagnosis", "medication", "physicalexam"],
+        cache_dir=tempfile.TemporaryDirectory().name,
+        dev=True,
+    )
+    base_dataset.stats()
+
+    # STEP 2: Set task
+    task = MortalityPredictionEICU()
+    sample_dataset = base_dataset.set_task(task)
+
+    # STEP 3: Split and create dataloaders
+    train_dataset, val_dataset, test_dataset = split_by_patient(
+        sample_dataset, [0.8, 0.1, 0.1]
+    )
+    train_dataloader = get_dataloader(train_dataset, batch_size=32, shuffle=True)
+    val_dataloader = get_dataloader(val_dataset, batch_size=32, shuffle=False)
+    test_dataloader = get_dataloader(test_dataset, batch_size=32, shuffle=False)
+
+    # STEP 4: Define model
+    model = RNN(
+        dataset=sample_dataset,
+    )
+
+    # STEP 5: Train
+    trainer = Trainer(model=model)
+    trainer.train(
+        train_dataloader=train_dataloader,
+        val_dataloader=val_dataloader,
+        epochs=1,
+        monitor="roc_auc",
+    )
+
+    # STEP 6: Evaluate
+    print(trainer.evaluate(test_dataloader))