Update logic/care_gap_engine.py

logic/care_gap_engine.py

@@ -1,39 +1,67 @@
-# File: logic/care_gap_engine.py
-
-import pandas as pd
-from datetime import datetime
-
-def evaluate_care_gaps(df: pd.DataFrame, config):
-    today = datetime.today()
-    rules = config["care_gap_rules"]
-    results = []
-
-    for _, row in df.iterrows():
-        gaps = []
-
-        if row['gender'] == 'F' and rules['Breast Cancer Screening']['min_age'] <= row['age'] <= rules['Breast Cancer Screening']['max_age']:
-            if not row['last_mammogram'] or (today - pd.to_datetime(row['last_mammogram'], errors='coerce')).days > rules['Breast Cancer Screening']['interval_days']:
-                gaps.append("Breast Cancer Screening")
-
-        if rules['Colorectal Cancer Screening']['min_age'] <= row['age'] <= rules['Colorectal Cancer Screening']['max_age']:
-            if not row['last_colonoscopy'] or (today - pd.to_datetime(row['last_colonoscopy'], errors='coerce')).days > rules['Colorectal Cancer Screening']['interval_days']:
-                gaps.append("Colorectal Cancer Screening")
-
-        if row.get('systolic_bp', '') != "" and pd.to_numeric(row['systolic_bp'], errors='coerce') > rules['Blood Pressure Control']['bp_threshold']:
-            gaps.append("Blood Pressure Control")
-
-        if row.get('hba1c_value', '') != "" and pd.to_numeric(row['hba1c_value'], errors='coerce') >= 9:
-            gaps.append("Diabetes: Poor HbA1c Control")
-
-        if row.get('FollowUp_Scheduled', '').strip().lower() == 'no' or row.get('Primary_Care_Established', '').strip().lower() == 'no':
-            gaps.append("Follow-Up Care")
-
-        if row.get('Previous_Readmissions', '').isdigit() and int(row['Previous_Readmissions']) >= 3:
-            gaps.append("Readmission Risk")
-
-        results.append({
-            'patient_id': row['patient_id'],
-            'care_gaps': gaps
-        })
-
-    return pd.DataFrame(results)
+# File: logic/care_gap_engine.py
+
+import pandas as pd
+from datetime import datetime
+
+def normalize_bool(value):
+    if isinstance(value, str):
+        value = value.strip().lower()
+        if value in ["yes", "true", "1"]:
+            return True
+        elif value in ["no", "false", "0"]:
+            return False
+    elif isinstance(value, (int, float)):
+        return bool(value)
+    return value
+
+def normalize_gender(value):
+    if isinstance(value, str):
+        v = value.strip().lower()
+        if v in ["f", "female", "2"]:
+            return "F"
+        elif v in ["m", "male", "1"]:
+            return "M"
+    elif isinstance(value, int):
+        return "F" if value == 2 else "M"
+    return value
+
+def evaluate_care_gaps(df: pd.DataFrame, config):
+    today = datetime.today()
+    rules = config["care_gap_rules"]
+    results = []
+
+    for _, row in df.iterrows():
+        gaps = []
+
+        gender = normalize_gender(row.get('gender'))
+
+        if gender == 'F' and rules['Breast Cancer Screening']['min_age'] <= row['age'] <= rules['Breast Cancer Screening']['max_age']:
+            if not row['last_mammogram'] or (today - pd.to_datetime(row['last_mammogram'], errors='coerce')).days > rules['Breast Cancer Screening']['interval_days']:
+                gaps.append("Breast Cancer Screening")
+
+        if rules['Colorectal Cancer Screening']['min_age'] <= row['age'] <= rules['Colorectal Cancer Screening']['max_age']:
+            if not row['last_colonoscopy'] or (today - pd.to_datetime(row['last_colonoscopy'], errors='coerce')).days > rules['Colorectal Cancer Screening']['interval_days']:
+                gaps.append("Colorectal Cancer Screening")
+
+        if row.get('systolic_bp', '') != "" and pd.to_numeric(row['systolic_bp'], errors='coerce') > rules['Blood Pressure Control']['bp_threshold']:
+            gaps.append("Blood Pressure Control")
+
+        if row.get('hba1c_value', '') != "" and pd.to_numeric(row['hba1c_value'], errors='coerce') >= 9:
+            gaps.append("Diabetes: Poor HbA1c Control")
+
+        if not normalize_bool(row.get('FollowUp_Scheduled')) or not normalize_bool(row.get('Primary_Care_Established')):
+            gaps.append("Follow-Up Care")
+
+        previous_readm = row.get('Previous_Readmissions', '')
+        if isinstance(previous_readm, str):
+            if previous_readm.isdigit() and int(previous_readm) >= 3:
+                gaps.append("Readmission Risk")
+        elif isinstance(previous_readm, (int, float)) and previous_readm >= 3:
+            gaps.append("Readmission Risk")
+
+        results.append({
+            'patient_id': row['patient_id'],
+            'care_gaps': gaps
+        })
+
+    return pd.DataFrame(results)