Update app.py

app.py

@@ -500,6 +500,7 @@ def get_diagnosis_and_severity_from_model(symptoms_text):
                         raw_predicted_diagnoses.append(item['label'])
 
         filtered_diagnoses = []
+        # EXPANDED AND REFINED GENERIC FILTER KEYWORDS
         generic_filter_keywords = [
             'unspecified', 'acute', 'chronic', 'use', 'status', 'other', 'not elsewhere classified',
             'no diagnosis', 'history of', 'finding', 'problem', 'syndrome', 'disease',
@@ -507,31 +508,60 @@ def get_diagnosis_and_severity_from_model(symptoms_text):
             'sequelae', 'factor', 'manifestation', 'procedure', 'examination', 'observation',
             'symptoms', 'sign', 'unconfirmed', 'type', 'group', 'normal', 'unknown', 'level',
             'positive', 'negative', 'patient', 'value', 'test', 'result', 'diagnosis',
-            'kidney', 'stage', 'without', 'essential',
-            'organ', 'function', 'system', 'body', 'region', 'with', 'due to', 'related to',
+            'kidney', 'stage', 'without', 'essential', 'with', 'due to', 'related to', 'of',
+            'organ', 'function', 'system', 'body', 'region',
             'clinical', 'consideration', 'presence', 'absence', 'mild', 'moderate', 'severe',
             'manifesting', 'affecting', 'affect', 'area', 'part', 'general', 'specific',
             'diagnosis of', 'history of', 'finding of', 'problem of', 'type of', 'group of',
-            'unlikely', 'possible', 'likely',
-            'symptom', 'sign', 'pain', 'fever', 'cough', 'vomiting', 'nausea', 'rash', 'headache', 'fatigue', 'diarrhea', 'sore throat', 'hemorrhage'
+            'unlikely', 'possible', 'likely', 'primary', 'secondary', 'and', 'or', 'by', 'for', 'in', 'on',
+            'symptom', 'sign', 'pain', 'fever', 'cough', 'vomiting', 'nausea', 'rash', 'headache', 'fatigue', 'diarrhea', 'sore throat', 'hemorrhage',
+            # Additional common non-diagnostic terms from ICD or general medical language
+            'i', 'ii', 'iii', 'iv', 'v', 'vi', 'vii', 'viii', 'ix', 'x', # Roman numerals
+            'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', # Single letters
+            'longterm', 'shortterm', 'controlled', 'uncontrolled', 'recurrent', 'intermittent', 'persistent',
+            'follow-up', 'observation', 'screening', 'encounter', 'admission', 'discharge',
+            'acute on chronic', 'other specified', 'not otherwise specified'
         ]
+
         for diagnosis_label in raw_predicted_diagnoses:
-            lower_diag = diagnosis_label.lower()
+            lower_diag = diagnosis_label.lower().strip()
             is_generic = False
+
+            # Rule 1: Check against expanded generic filter keywords
             for generic_kw in generic_filter_keywords:
-                if re.search(r'\b' + re.escape(generic_kw) + r'\b', lower_diag) and len(lower_diag.split()) <= 2:
+                # Use regex for whole word matching to avoid partial matches (e.g., 'use' matching 'house')
+                if re.fullmatch(r'\b' + re.escape(generic_kw) + r'\b', lower_diag):
                     is_generic = True
                     break
-            if lower_diag.replace('.', '').isdigit() and len(lower_diag.replace('.', '')) < 5:
+            if is_generic:
+                continue # Skip to next diagnosis if it's a generic keyword
+
+            # Rule 2: Filter out very short numerical or alphanumeric strings (e.g., 'ii', 'a1')
+            if len(lower_diag) <= 2 and (lower_diag.replace('.', '').isdigit() or lower_diag.isalnum()):
                 is_generic = True
-            if len(lower_diag.split()) <= 2 and lower_diag in ['pain', 'fever', 'cough', 'vomiting', 'nausea', 'rash', 'headache', 'fatigue', 'diarrhea', 'sore throat', 'hemorrhage']:
+            if is_generic:
+                continue
+
+            # Rule 3: Filter out terms that are purely numerical codes (e.g., '250.00', 'E11.9')
+            # This is a heuristic, as some numbers might be part of a valid diagnosis
+            if re.fullmatch(r'[\d\.]+', lower_diag) and len(lower_diag) < 7: # e.g., "250.00" or "E11.9"
                 is_generic = True
-            if not is_generic:
-                filtered_diagnoses.append(diagnosis_label)
+            if is_generic:
+                continue
+
+            # Rule 4: Filter out terms that are single words and are very common, non-specific symptoms
+            # (already covered by generic_filter_keywords, but an explicit check for robustness)
+            if len(lower_diag.split()) == 1 and lower_diag in ['pain', 'fever', 'cough', 'vomiting', 'nausea', 'rash', 'headache', 'fatigue', 'diarrhea', 'sore throat', 'hemorrhage']:
+                is_generic = True
+            if is_generic:
+                continue
+
+            # If none of the above rules flagged it as generic, add to filtered list
+            filtered_diagnoses.append(diagnosis_label)
 
-        filtered_diagnoses = list(dict.fromkeys(filtered_diagnoses))
+        filtered_diagnoses = list(dict.fromkeys(filtered_diagnoses)) # Remove duplicates
         if len(filtered_diagnoses) > 5:
-            filtered_diagnoses = filtered_diagnoses[:5]
+            filtered_diagnoses = filtered_diagnoses[:5] # Limit to top 5
 
         if not filtered_diagnoses:
             return "Overall Symptom Severity (AI Assessment): Undetermined Severity", []