Update app.py

app.py

@@ -12,40 +12,128 @@ np.random.seed(42)
 # Function to generate synthetic BreastCancer data
 def generate_breast_cancer_data(num_patients):
     primary_keys = [f"PPK_{i+1:05d}" for i in range(num_patients)]
-    ages = np.random.randint(30, 80, size=num_patients)
-    menopausal_status = ["Post-menopausal" if age >= 50 else "Pre-menopausal" for age in ages]
-    tumor_sizes = np.round(np.random.lognormal(mean=0.7, sigma=0.5, size=num_patients), 2)
-    lymph_nodes = np.random.choice(["Positive", "Negative"], size=num_patients, p=[0.4, 0.6])
-    tumor_grades = np.random.choice([1, 2, 3], size=num_patients, p=[0.3, 0.5, 0.2])
-    tumor_stages = np.random.choice(["I", "II", "III", "IV"], size=num_patients, p=[0.4, 0.3, 0.2, 0.1])
-    er_status = np.random.choice(["Positive", "Negative"], size=num_patients, p=[0.75, 0.25])
-    pr_status = np.random.choice(["Positive", "Negative"], size=num_patients, p=[0.7, 0.3])
-    her2_status = np.random.choice(["Positive", "Negative"], size=num_patients, p=[0.3, 0.7])
-    ki67_levels = np.random.choice(["High", "Low"], size=num_patients, p=[0.6, 0.4])
-    tnbc_status = ["Positive" if er == "Negative" and pr == "Negative" and her2 == "Negative" else "Negative" for er, pr, her2 in zip(er_status, pr_status, her2_status)]
-    brca_mutation = np.random.choice(["Positive", "Negative"], size=num_patients, p=[0.1, 0.9])
-    overall_health = np.random.choice(["Good", "Poor"], size=num_patients, p=[0.7, 0.3])
-    genomic_score = np.random.choice(["Low", "Intermediate", "High", "N/A"], size=num_patients, p=[0.3, 0.2, 0.1, 0.4])
-    treatments = np.random.choice(["Surgery", "Chemotherapy", "Radiation Therapy"], size=num_patients)
-
-    return pd.DataFrame({
+    
+    ages = []
+    menopausal_status = []
+    tumor_sizes = []
+    lymph_nodes = []
+    grades = []
+    stages = []
+    er_status = []
+    pr_status = []
+    her2_status = []
+    ki67_level = []
+    tnbc_status = []
+    brca_mutation = []
+    overall_health = []
+    genomic_score = []
+    treatment = []
+
+    for i in range(num_patients):
+        age = int(np.random.normal(60, 10))
+        age = max(30, min(age, 80))
+        ages.append(age)
+
+        menopausal = "Post-menopausal" if age >= 50 else "Pre-menopausal"
+        menopausal_status.append(menopausal)
+
+        tumor_size = round(np.random.lognormal(mean=0.7, sigma=0.5), 2)
+        tumor_sizes.append(tumor_size)
+
+        lymph_node = (
+            "Positive"
+            if (tumor_size > 2.0 and np.random.rand() < 0.6)
+            or (tumor_size <= 2.0 and np.random.rand() < 0.3)
+            else "Negative"
+        )
+        lymph_nodes.append(lymph_node)
+
+        grade = np.random.choice([1, 2, 3], p=[0.1, 0.4, 0.5] if tumor_size > 2.0 else [0.3, 0.5, 0.2])
+        grades.append(grade)
+
+        if tumor_size <= 2.0 and lymph_node == "Negative":
+            stage = "I"
+        elif (tumor_size > 2.0 and tumor_size <= 5.0) and lymph_node == "Negative":
+            stage = "II"
+        elif lymph_node == "Positive" or tumor_size > 5.0:
+            stage = "III"
+        else:
+            stage = "II"
+        if np.random.rand() < 0.05:
+            stage = "IV"
+        stages.append(stage)
+
+        er = np.random.choice(["Positive", "Negative"], p=[0.75, 0.25])
+        pr = "Positive" if er == "Positive" and np.random.rand() > 0.1 else "Negative"
+        er_status.append(er)
+        pr_status.append(pr)
+
+        her2 = np.random.choice(["Positive", "Negative"], p=[0.3, 0.7] if grade == 3 else [0.15, 0.85])
+        her2_status.append(her2)
+
+        ki67 = "High" if grade == 3 and np.random.rand() < 0.8 else "Low"
+        ki67_level.append(ki67)
+
+        tnbc = "Positive" if er == "Negative" and pr == "Negative" and her2 == "Negative" else "Negative"
+        tnbc_status.append(tnbc)
+
+        brca = "Positive" if (tnbc == "Positive" or age < 40) and np.random.rand() < 0.2 else "Negative"
+        brca_mutation.append(brca)
+
+        health = "Good" if age < 65 and np.random.rand() < 0.9 else "Poor"
+        overall_health.append(health)
+
+        recurrence_score = (
+            np.random.choice(["Low", "Intermediate", "High"], p=[0.6, 0.3, 0.1])
+            if er == "Positive" and her2 == "Negative"
+            else "N/A"
+        )
+        genomic_score.append(recurrence_score)
+
+        if stage in ["I", "II"]:
+            if tnbc == "Positive":
+                treat = "Surgery, Chemotherapy, and Radiation Therapy"
+            elif er == "Positive" and recurrence_score != "N/A":
+                if recurrence_score == "High":
+                    treat = "Surgery, Chemotherapy, Hormone Therapy, and Radiation Therapy"
+                elif recurrence_score == "Intermediate":
+                    treat = "Surgery, Consider Chemotherapy, Hormone Therapy, and Radiation Therapy"
+                else:
+                    treat = "Surgery, Hormone Therapy, and Radiation Therapy"
+            elif her2 == "Positive":
+                treat = "Surgery, HER2-Targeted Therapy, Chemotherapy, and Radiation Therapy"
+            else:
+                treat = "Surgery, Chemotherapy, and Radiation Therapy"
+        elif stage == "III":
+            treat = (
+                "Neoadjuvant Chemotherapy, Surgery, Radiation Therapy"
+                + (", HER2-Targeted Therapy" if her2 == "Positive" else "")
+                + (", Hormone Therapy" if er == "Positive" else "")
+            )
+        else:
+            treat = "Systemic Therapy (Palliative Care)"
+        treatment.append(treat)
+
+    breast_cancer_data = {
         "PRIMARY_PERSON_KEY": primary_keys,
         "Age": ages,
         "Menopausal Status": menopausal_status,
         "Tumor Size (cm)": tumor_sizes,
         "Lymph Node Involvement": lymph_nodes,
-        "Tumor Grade": tumor_grades,
-        "Tumor Stage": tumor_stages,
+        "Tumor Grade": grades,
+        "Tumor Stage": stages,
         "ER Status": er_status,
         "PR Status": pr_status,
         "HER2 Status": her2_status,
-        "Ki-67 Level": ki67_levels,
+        "Ki-67 Level": ki67_level,
         "TNBC Status": tnbc_status,
         "BRCA Mutation": brca_mutation,
         "Overall Health": overall_health,
         "Genomic Recurrence Score": genomic_score,
-        "Treatment": treatments
-    })
+        "Treatment": treatment,
+    }
+
+    return pd.DataFrame(breast_cancer_data)
 
 # Function to generate Members from BreastCancer
 def generate_members_from_breast_cancer(breast_cancer_df):
@@ -69,7 +157,7 @@ def generate_enrollments_from_breast_cancer(breast_cancer_df):
         "RELATION": np.random.choice(["SUBSCRIBER", "DEPENDENT"], len(breast_cancer_df)),
     })
 
-# Function to generate Services from BreastCancer
+# Function to generate Services
 def generate_services(num_services, primary_keys):
     return pd.DataFrame({
         "PRIMARY_PERSON_KEY": np.random.choice(primary_keys, num_services),
@@ -126,56 +214,4 @@ def generate_wearable_data(num_patients, num_measurements, start_datetime, time_
             heart_rate = max(heart_rate, 50)
             o2_sat = max(o2_sat, 90.0)
 
-            data_rows.append([pkey, ts.strftime("%Y-%m-%d %H:%M:%S"), activity, heart_rate, round(o2_sat, 1)])
-    
-    return pd.DataFrame(data_rows, columns=["PRIMARY_PERSON_KEY", "Measurement_Timestamp", "Activity_Level", "Heart_Rate", "O2_Saturation"])
-
-# Main Streamlit App
-st.title("Synthetic Medical Data Generator with Wearable Data")
-
-# Sliders
-num_patients = st.slider("Number of Breast Cancer Patients to Generate", 10, 1000, 100)
-num_measurements = st.slider("Measurements per Patient (Wearable Data)", 1, 100, 10)
-num_services = st.slider("Number of Services to Generate", 10, 2000, 500)
-num_providers = st.slider("Number of Providers to Generate", 10, 500, 100)
-
-start_date = st.date_input("Wearable Data Start Date", value=datetime(2024, 12, 1))
-start_time = st.time_input("Wearable Data Start Time", value=datetime(2024, 12, 1, 8, 0).time())
-cancer_rate = st.slider("Percentage of Patients with Cancer (Wearable Data)", 0, 100, 30)
-chemo_brain_effect = st.slider("Chemo Brain Impact on Activity Level (in % reduction)", 0, 50, 20)
-
-if st.button("Generate Data"):
-    primary_keys = [f"PPK_{i+1:05d}" for i in range(num_patients)]
-    wearable_start_datetime = datetime.combine(start_date, start_time)
-    breast_cancer_df = generate_breast_cancer_data(num_patients)
-    members_df = generate_members_from_breast_cancer(breast_cancer_df)
-    enrollments_df = generate_enrollments_from_breast_cancer(breast_cancer_df)
-    services_df = generate_services(num_services, primary_keys)
-    providers_df = generate_providers(num_providers)
-    wearable_data = generate_wearable_data(
-        num_patients, num_measurements, wearable_start_datetime, timedelta(hours=1), cancer_rate, chemo_brain_effect, primary_keys
-    )
-
-    st.subheader("Breast Cancer Data")
-    st.dataframe(breast_cancer_df.head())
-    st.download_button("Download Breast Cancer Data", breast_cancer_df.to_csv(index=False), "breast_cancer.csv")
-
-    st.subheader("Members Data")
-    st.dataframe(members_df.head())
-    st.download_button("Download Members Data", members_df.to_csv(index=False), "members.csv")
-
-    st.subheader("Enrollments Data")
-    st.dataframe(enrollments_df.head())
-    st.download_button("Download Enrollments Data", enrollments_df.to_csv(index=False), "enrollments.csv")
-
-    st.subheader("Services Data")
-    st.dataframe(services_df.head())
-    st.download_button("Download Services Data", services_df.to_csv(index=False), "services.csv")
-
-    st.subheader("Providers Data")
-    st.dataframe(providers_df.head())
-    st.download_button("Download Providers Data", providers_df.to_csv(index=False), "providers.csv")
-
-    st.subheader("Wearable Data")
-    st.dataframe(wearable_data.head())
-    st.download_button("Download Wearable Data", wearable_data.to_csv(index=False), "wearable_data.csv")
+            data_rows.append([pkey, ts.strftime("%Y-%m-%d %H:%M