Update annotated_casl_app.py

annotated_casl_app.py

@@ -118,13 +118,8 @@ def combine_sections_smartly(sections_dict):
         "4. FIGURATIVE LANGUAGE ANALYSIS",
         "5. PRAGMATIC LANGUAGE ASSESSMENT",
         "6. VOCABULARY AND SEMANTIC ANALYSIS",
-        "7. NLP-DERIVED LINGUISTIC FEATURES",
-        "8. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS",
-        "9. COGNITIVE-LINGUISTIC FACTORS",
-        "10. FLUENCY AND RHYTHM ANALYSIS",
-        "11. QUANTITATIVE METRICS",
-        "12. CLINICAL IMPLICATIONS",
-        "13. PROGNOSIS AND SUMMARY"
+        "7. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS",
+        "8. QUANTITATIVE METRICS AND NLP FEATURES"
     ]
     
     combined_parts = []
@@ -205,8 +200,6 @@ def answer_quick_question(transcript_content, question, age, gender, slp_notes):
     
     prompt = f"""
     You are a speech-language pathologist answering a specific question about a speech sample.
-
-    Patient: {age}-year-old {gender}
     
     TRANSCRIPT:
     {transcript_content}{notes_section}
@@ -217,7 +210,7 @@ def answer_quick_question(transcript_content, question, age, gender, slp_notes):
     - Provide a focused, detailed answer to the specific question asked
     - Include specific examples from the transcript with exact quotes
     - Provide quantitative data when relevant (counts, percentages, rates)
-    - Give clinical interpretation and significance
+    - Provide objective data interpretation only
     - Keep the response focused on the question but thorough in analysis
     - If the question relates to multiple areas, address all relevant aspects
     
@@ -263,10 +256,9 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
         - Note any fluency-enhancing contexts
         - Assess overall speech rhythm and flow
         
-        4. CLINICAL SIGNIFICANCE:
-        - Compare to age-appropriate norms
-        - Assess severity level
-        - Recommend intervention priorities
+        4. OBJECTIVE SUMMARY:
+        - Provide data summary only
+        - List observed patterns
         """,
         
         "Grammar and Syntax": """
@@ -288,10 +280,9 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
         - Count subject-verb agreement errors
         - Assess auxiliary verb usage
         
-        4. CLINICAL IMPLICATIONS:
-        - Identify primary grammatical targets for intervention
-        - Assess developmental appropriateness
-        - Recommend specific therapy goals
+        4. OBJECTIVE SUMMARY:
+        - List primary grammatical patterns observed
+        - Provide data summary only
         """,
         
         "Vocabulary and Semantics": """
@@ -317,9 +308,9 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
         - Identify compensatory strategies
         - Assess overall lexical access efficiency
         
-        5. CLINICAL RECOMMENDATIONS:
-        - Identify vocabulary intervention targets
-        - Recommend strategies for word-finding support
+        5. OBJECTIVE SUMMARY:
+        - List vocabulary patterns observed
+        - Provide data summary only
         """,
         
         "Pragmatics and Discourse": """
@@ -345,9 +336,9 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
         - Assess contextual appropriateness
         - Evaluate social awareness in communication
         
-        5. CLINICAL IMPLICATIONS:
-        - Identify pragmatic intervention priorities
-        - Recommend social communication goals
+        5. OBJECTIVE SUMMARY:
+        - List pragmatic patterns observed
+        - Provide data summary only
         """,
         
         "Sentence Complexity": """
@@ -370,12 +361,11 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
         
         4. SYNTACTIC MATURITY:
         - Calculate Mean Length of Utterance (MLU)
-        - Assess developmental appropriateness
-        - Identify areas for syntactic growth
+        - List syntactic patterns observed
         
-        5. CLINICAL RECOMMENDATIONS:
-        - Identify targets for increasing complexity
-        - Recommend scaffolding strategies
+        5. OBJECTIVE SUMMARY:
+        - Provide complexity data summary
+        - List observed patterns only
         """,
         
         "Word Finding and Retrieval": """
@@ -401,10 +391,9 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
         - Assess impact of topic familiarity
         - Evaluate effect of linguistic complexity on retrieval
         
-        5. CLINICAL IMPLICATIONS:
-        - Recommend word-finding intervention strategies
-        - Identify cueing hierarchies to trial
-        - Suggest compensatory strategy training
+        5. OBJECTIVE SUMMARY:
+        - List word-finding patterns observed
+        - Provide data summary only
         """
     }
     
@@ -413,8 +402,6 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
     
     prompt = f"""
     You are a speech-language pathologist conducting a targeted analysis of a specific area.
-
-    Patient: {age}-year-old {gender}
     
     TRANSCRIPT:
     {transcript_content}{notes_section}
@@ -426,8 +413,8 @@ def analyze_targeted_area(transcript_content, analysis_area, age, gender, slp_no
     INSTRUCTIONS:
     - Provide specific examples with exact quotes from the transcript
     - Include quantitative data (counts, percentages, rates per 100 words)
-    - Give detailed clinical interpretation
-    - Provide specific, measurable recommendations
+    - Provide objective data interpretation only
+    - Focus on measurable observations
     - Be thorough but focused on the specified area
     
     Conduct the targeted analysis:
@@ -487,8 +474,6 @@ def annotate_transcript(transcript_content, age, gender, slp_notes):
     
     annotation_prompt = f"""
     You are a speech-language pathologist preparing a transcript for detailed analysis. Your task is to ANNOTATE the ENTIRE transcript with linguistic markers at a WORD-BY-WORD level.
-
-    Patient: {age}-year-old {gender}
     
     ORIGINAL TRANSCRIPT:
     {transcript_content}{notes_section}
@@ -605,14 +590,12 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
     """
     
     analysis_prompt = f"""
-    You are a speech-language pathologist conducting a comprehensive analysis of an annotated speech sample. Provide a complete, clinically useful analysis without excessive formatting.
+    You are a speech-language pathologist conducting a comprehensive analysis of an annotated speech sample. Provide objective data analysis without clinical interpretations.
 
-    Patient: {age}-year-old {gender}
-    
     ANNOTATED TRANSCRIPT:
     {annotated_transcript}{notes_section}
     
-    INSTRUCTIONS: Complete ALL 13 sections below. Use simple formatting with NO BOLDING (no ** or asterisks), NO hashtags (###), and minimal markdown. Focus on clinical utility and completeness. Count all markers precisely and provide specific examples. Write section headers as plain text followed by a colon.
+    INSTRUCTIONS: Complete ALL 8 sections below. Use simple formatting with NO BOLDING (no ** or asterisks), NO hashtags (###), and minimal markdown. Focus on objective data only. Count all markers precisely and provide specific examples. Write section headers as plain text followed by a colon. DO NOT include age/gender comparisons, clinical interpretations, severity assessments, or treatment recommendations.
 
     COMPREHENSIVE SPEECH SAMPLE ANALYSIS
 
@@ -637,7 +620,6 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
       * Semantic revisions: "car- I mean bike"
     - Pauses ([PAUSE]): Count hesitation markers and silent pauses
     - Total disfluency rate: Calculate combined rate per 100 words
-    - Severity assessment: Compare to age norms
 
     B. Word Retrieval Issues (detailed analysis):
     - Circumlocutions ([CIRCUMLOCUTION]): Count and analyze strategies
@@ -709,7 +691,6 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
     - Clauses per utterance ratio
     - Subordination index
     - Coordination index
-    - Developmental appropriateness assessment
 
     4. FIGURATIVE LANGUAGE ANALYSIS
 
@@ -718,7 +699,7 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
       * Metaphors: "Time is money"
       * Similes: "Fast as lightning"
       * Idioms: "Raining cats and dogs"
-    - Appropriateness assessment: Context and age-level
+    - Appropriateness assessment: Context only
     - Comprehension vs. production abilities
     - Abstract language development indicators
 
@@ -754,7 +735,7 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
     - Vocabulary breadth: Range of semantic categories
     - Vocabulary depth: Precision and nuance within categories
     - Academic vs. conversational vocabulary ratio
-    - Age-appropriate vocabulary development
+    - Vocabulary development patterns observed
 
     7. NLP-DERIVED LINGUISTIC FEATURES (use bullet lists, NO tables)
 
@@ -769,13 +750,13 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
       * Provide exact MTLD score and interpretation
     - Hypergeometric Distribution D (HDD): Probability-based diversity measure
       * Controls for text length effects
-      * Provide HDD score and clinical significance
+      * Provide HDD score
 
     B. Word Frequency Analysis (as bullet list, not table):
     - Most frequent words used: List top 10 as "word (count)" format
     - High-frequency vs. low-frequency word distribution
     - Function words vs. content words ratio
-    - Repetitive word patterns and their clinical significance
+    - Repetitive word patterns observed
 
     C. Linguistic Complexity Indicators (bullet format):
     - Average word length in syllables
@@ -789,7 +770,7 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
     - Derivational morphology: Prefixes and suffixes
     - Inflectional morphology: Tense, number, case markers
     - Morphological awareness indicators
-    - Error patterns and developmental appropriateness
+    - Error patterns observed
 
     B. Phonological Considerations:
     - Sound pattern analysis (if evident in transcript)
@@ -811,75 +792,13 @@ def analyze_annotated_transcript(annotated_transcript, age, gender, slp_notes):
     C. Executive Function Evidence:
     - Self-monitoring and error correction
     - Planning and organization in discourse
-    - Cognitive flexibility in topic management
-
-    10. FLUENCY AND RHYTHM ANALYSIS
-
-    A. Disfluency Patterns:
-    - Total disfluency count and rate per 100 words
-    - Disfluency type distribution
-    - Clustering patterns and severity assessment
-    - Impact on communication effectiveness
-
-    B. Speech Flow and Rhythm:
-    - Natural pause patterns vs. disrupted flow
-    - Rhythm and prosodic patterns (if evident)
-    - Overall fluency profile and age-appropriateness
-
-    11. QUANTITATIVE METRICS
-
-    A. Basic Measures:
-    - Total words: [exact count]
-    - Total sentences: [exact count]
-    - Unique words: [exact count]
-    - MLU words: [calculation with formula shown]
-    - MLU morphemes: [calculation with formula shown]
-    - Type-Token Ratio: [calculation and interpretation]
-
-    B. Error Rates and Ratios:
-    - Disfluency rate per 100 words
-    - Grammatical accuracy percentage
-    - Vocabulary sophistication ratio
-    - Sentence complexity distribution percentages
-
-    12. CLINICAL IMPLICATIONS
-
-    A. Strengths (ranked by prominence):
-    - Primary strengths with supporting evidence
-    - Secondary strengths with examples
-    - Compensatory strategies observed
-
-    B. Areas of Need (prioritized by severity):
-    - Primary concerns with impact assessment
-    - Secondary concerns with supporting data
-    - Developmental vs. disorder considerations
-
-    C. Treatment Recommendations:
-    - Specific, measurable therapy goals
-    - Intervention approaches and techniques
-    - Frequency and duration recommendations
-    - Progress monitoring strategies
-
-    13. PROGNOSIS AND SUMMARY
-
-    A. Overall Communication Profile:
-    - Comprehensive summary of findings
-    - Developmental appropriateness assessment
-    - Functional communication impact
-
-    B. Treatment Planning:
-    - Priority intervention targets
-    - Expected outcomes and timeline
-    - Follow-up assessment recommendations
-    - Family/educational recommendations
-
     CRITICAL REQUIREMENTS:
-    1. Complete ALL 13 sections - do not stop early
+    1. Complete ALL 8 sections - do not stop early
     2. Provide exact counts for all markers with specific examples
     3. Calculate all percentages and rates with formulas shown
     4. Include direct quotes from transcript for examples
-    5. Analyze patterns and provide clinical interpretations
-    6. Focus on actionable, clinically relevant insights
+    5. Focus on objective data only - NO clinical interpretations or age/gender comparisons
+    6. NO treatment recommendations or clinical implications
     7. If response is incomplete, end with <CONTINUE>
     8. FORMATTING: Use NO asterisks (**), NO hashtags (###), NO bolding - plain text only
     """
@@ -1373,13 +1292,8 @@ def call_claude_api_with_continuation(prompt):
         "4. FIGURATIVE LANGUAGE ANALYSIS",
         "5. PRAGMATIC LANGUAGE ASSESSMENT",
         "6. VOCABULARY AND SEMANTIC ANALYSIS",
-        "7. NLP-DERIVED LINGUISTIC FEATURES",
-        "8. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS",
-        "9. COGNITIVE-LINGUISTIC FACTORS",
-        "10. FLUENCY AND RHYTHM ANALYSIS",
-        "11. QUANTITATIVE METRICS",
-        "12. CLINICAL IMPLICATIONS",
-        "13. PROGNOSIS AND SUMMARY"
+        "7. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS",
+        "8. QUANTITATIVE METRICS AND NLP FEATURES"
     ]
     
     # Safety limits to prevent infinite loops
@@ -1631,7 +1545,7 @@ def analyze_with_backup(annotated_transcript, original_transcript, age, gender,
     - Count [REPETITION] markers: Categorize by type (word, phrase, sound)
     - Count [REVISION] markers: Analyze self-correction patterns
     - Count [PAUSE] markers: Assess hesitation frequency
-    - Calculate total disfluency rate and severity level
+    - Calculate total disfluency rate
 
     B. Word Retrieval Issues:
     - Count [CIRCUMLOCUTION] markers: List each roundabout description
@@ -1674,7 +1588,7 @@ def analyze_with_backup(annotated_transcript, original_transcript, age, gender,
 
     C. Sentence Structure Analysis:
     - Use calculated MLU: {linguistic_metrics.get('mlu_words', 0)} words, {linguistic_metrics.get('mlu_morphemes', 0)} morphemes
-    - Calculate complexity ratios and assess developmental appropriateness
+    - Calculate complexity ratios
 
     4. FIGURATIVE LANGUAGE ANALYSIS (with exact counts):
 
@@ -1754,25 +1668,14 @@ def analyze_with_backup(annotated_transcript, original_transcript, age, gender,
     - Grammar error rate: Calculate from marker counts
     - Vocabulary sophistication ratio: {marker_analysis.get('category_totals', {}).get('vocab_sophistication_ratio', 0):.3f}
 
-    11. CLINICAL IMPLICATIONS:
-    - Primary strengths: List with supporting evidence from markers and metrics
-    - Primary weaknesses: Rank by severity with exact counts
-    - Intervention priorities: Based on error frequency and impact
-    - Therapy targets: Specific, measurable goals
-
-    12. PROGNOSIS AND SUMMARY:
-    - Overall communication profile with percentile estimates
-    - Developmental appropriateness assessment
-    - Summary of key findings from quantitative analysis
-    - Priority treatment goals and expected outcomes
-
     CRITICAL REQUIREMENTS:
     - Use the provided calculated metrics in your analysis
     - Provide EXACT counts for every marker type
     - Calculate precise percentages and show your work
     - Give specific examples from the transcript
     - If annotation is incomplete, supplement with analysis of the original transcript
-    - Complete ALL 13 sections - use <CONTINUE> if needed
+    - Complete ALL 8 sections - use <CONTINUE> if needed
+    - Focus on objective data only - NO clinical interpretations
     """
     
     return call_claude_api_with_continuation(analysis_prompt)
@@ -2148,20 +2051,17 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         
         Provide a comprehensive clinical interpretation organized into these sections:
 
-        1. LEXICAL DIVERSITY INTERPRETATION:
-        - Interpret the advanced lexical diversity measures (MTLD, HDD, MATTR, etc.)
-        - Compare to age-appropriate norms
-        - Clinical significance of diversity patterns
+        1. LEXICAL DIVERSITY DATA:
+        - Report the advanced lexical diversity measures (MTLD, HDD, MATTR, etc.)
+        - Provide objective data interpretation only
 
-        2. FLUENCY PATTERN ANALYSIS:
-        - Clinical interpretation of fluency marker counts and rates
-        - Severity assessment based on verified counts
-        - Impact on communication effectiveness
+        2. FLUENCY PATTERN DATA:
+        - Report fluency marker counts and rates
+        - Provide objective data summary only
 
-        3. GRAMMATICAL COMPETENCE ASSESSMENT:
-        - Analysis of grammar error patterns from verified counts
-        - Developmental appropriateness
-        - Areas of strength vs. weakness
+        3. GRAMMATICAL PATTERN DATA:
+        - Report grammar error patterns from verified counts
+        - Provide objective data summary only
 
         4. VOCABULARY AND SEMANTIC ANALYSIS:
         - Interpretation of vocabulary sophistication measures
@@ -2178,15 +2078,9 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         - Strengths and areas of need
         - Functional communication impact
 
-        7. CLINICAL RECOMMENDATIONS:
-        - Specific intervention targets based on verified data
-        - Therapy approaches and techniques
-        - Progress monitoring suggestions
-        - Prognosis and expected outcomes
-
-        Focus on INTERPRETATION and CLINICAL SIGNIFICANCE, not counting. 
+        Focus on OBJECTIVE DATA INTERPRETATION only, not clinical significance. 
         All measurements are already verified and accurate.
-        Cite specific examples from the transcript to support your interpretations.
+        Cite specific examples from the transcript to support your observations.
         """
         
         ai_interpretation = call_claude_api(verified_prompt)
@@ -2274,16 +2168,16 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         - Filler words: Use verified count of {marker_counts.get('FILLER', 0)} fillers
           * Calculate rate per 100 words: {marker_counts.get('FILLER', 0)/total_words*100:.2f}%
           * Identify types and provide examples from transcript
-          * Assess severity and impact on communication
+          * Provide objective count summary
         - False starts: Use verified count of {marker_counts.get('FALSE_START', 0)}
           * Provide specific examples from transcript
           * Analyze patterns and self-correction abilities
         - Repetitions: Use verified count of {marker_counts.get('REPETITION', 0)}
           * Categorize types (word, phrase, sound level)
-          * Provide examples and assess severity
+          * Provide examples and count summary
         - Total disfluency assessment: Use verified total of {category_totals['fluency_issues']} 
           * Rate: {category_totals['fluency_issues']/total_words*100:.2f} per 100 words
-          * Compare to age norms and assess severity
+          * Provide objective rate calculation
 
         B. Word Retrieval Issues:
         - Circumlocutions: Count and analyze from transcript
@@ -2308,7 +2202,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
 
         B. Grammar and Morphology:
         - Error pattern analysis using verified counts
-        - Developmental appropriateness assessment
+        - Pattern analysis only
         - Morphological complexity evaluation
 
         3. COMPLEX SENTENCE ANALYSIS (use verified counts)
@@ -2335,7 +2229,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         - Tangential speech: Use verified count of {marker_counts.get('TANGENT', 0)}
         - Coherence breaks: Use verified count of {marker_counts.get('COHERENCE_BREAK', 0)}
         - Referential clarity: Use verified count of {marker_counts.get('PRONOUN_REF', 0)}
-        - Overall conversational competence assessment
+        - Overall conversational patterns observed
 
         6. VOCABULARY AND SEMANTIC ANALYSIS
         - Semantic errors: Use verified count of {marker_counts.get('SEMANTIC_ERROR', 0)}
@@ -2347,21 +2241,9 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         - Morphological complexity assessment
         - Derivational and inflectional morphology patterns
         - Error analysis using verified counts
-        - Developmental appropriateness
-
-        8. COGNITIVE-LINGUISTIC FACTORS
-        - Working memory indicators from sentence complexity
-        - Processing speed markers from fluency patterns
-        - Executive function evidence from self-corrections
-        - Attention and cognitive load management
+        - Pattern analysis only
 
-        9. FLUENCY AND RHYTHM ANALYSIS
-        - Disfluency pattern analysis using verified counts
-        - Speech rhythm and flow assessment
-        - Natural vs. disrupted pause patterns
-        - Overall fluency profile
-
-        10. QUANTITATIVE METRICS (use ALL verified data)
+        8. QUANTITATIVE METRICS AND NLP FEATURES (use ALL verified data)
         - Total words: {total_words}
         - Total sentences: {linguistic_metrics.get('total_sentences', 0)}
         - Unique words: {linguistic_metrics.get('unique_words', 0)}
@@ -2369,25 +2251,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         - MLU morphemes: {linguistic_metrics.get('mlu_morphemes', 0):.2f}
         - All error rates and ratios from verified counts
 
-        11. CLINICAL IMPLICATIONS
-        A. Strengths (with supporting evidence):
-        - Identify primary strengths using verified data
-        - Provide specific examples from transcript
-        
-        B. Areas of Need (prioritized by severity):
-        - Primary concerns based on verified counts and rates
-        - Secondary areas for intervention
-        
-        C. Treatment Recommendations:
-        - Specific, measurable therapy goals
-        - Evidence-based intervention approaches
-        - Progress monitoring strategies
-
-        12. PROGNOSIS AND SUMMARY
-        - Overall communication profile synthesis
-        - Functional impact assessment
-        - Treatment planning and expected outcomes
-        - Follow-up recommendations
+
 
         CRITICAL: Complete ALL 13 sections using verified data and specific transcript examples.
         """