diff --git a/_episodes/04-modelling.md b/_episodes/04-modelling.md
index 2720304..3f51157 100644
--- a/_episodes/04-modelling.md
+++ b/_episodes/04-modelling.md
@@ -39,6 +39,7 @@ from sklearn.linear_model import LinearRegression
 reg = LinearRegression()
 
 # use a single feature (apache score)
+# note: remove the reshape if fitting to >1 input variable
 X = cohort.apachescore.values.reshape(-1, 1)
 y = cohort.actualhospitalmortality_enc.values
 
diff --git a/_episodes/05-validation.md b/_episodes/05-validation.md
index 2f40b1f..0a84643 100644
--- a/_episodes/05-validation.md
+++ b/_episodes/05-validation.md
@@ -50,6 +50,7 @@ y = cohort[outcome]
 x_train, x_test, y_train, y_test = train_test_split(X, y, train_size = 0.7, random_state = 42)
 
 # restructure data for input into model
+# note: remove the reshape if fitting to >1 input variable
 x_train = x_train.values.reshape(-1, 1)
 y_train = y_train.values.ravel()
 x_test = x_test.values.reshape(-1, 1)
diff --git a/_episodes/06-evaluation.md b/_episodes/06-evaluation.md
index cb5d5aa..c2a2d8e 100644
--- a/_episodes/06-evaluation.md
+++ b/_episodes/06-evaluation.md
@@ -44,6 +44,7 @@ y = cohort[outcome]
 x_train, x_test, y_train, y_test = train_test_split(X, y, train_size = 0.7, random_state =  42)
 
 # restructure data for input into model
+# note: remove the reshape if fitting to >1 input variable
 x_train = x_train.values.reshape(-1, 1)
 y_train = y_train.values.ravel()
 x_test = x_test.values.reshape(-1, 1)
diff --git a/_episodes/07-bootstrapping.md b/_episodes/07-bootstrapping.md
index 33f3896..99d82b2 100644
--- a/_episodes/07-bootstrapping.md
+++ b/_episodes/07-bootstrapping.md
@@ -55,6 +55,7 @@ y = cohort[outcome]
 x_train, x_test, y_train, y_test = train_test_split(X, y, train_size = 0.7, random_state = 42)
 
 # restructure data for input into model
+# note: remove the reshape if fitting to >1 input variable
 x_train = x_train.values.reshape(-1, 1)
 y_train = y_train.values.ravel()
 x_test = x_test.values.reshape(-1, 1)