optimized results and new benchmark

Directional Errors of each functional system.

.gitignore

@@ -1,7 +1,88 @@
-# Ignore all contents of these directories
-!**/*.py
-/Data/
-/attach/
-/results/
-/enarcelona/
+# =========================
+# Python
+# =========================
+__pycache__/
+*.py[cod]
+*$py.class
+.ipynb_checkpoints/
+
+# =========================
+# Virtual environments
+# =========================
+env/
+env*/
+venv/
+.venv/
+enarcelona/
+
+# =========================
+# Secrets
+# =========================
 .env
+*.env
+
+# =========================
+# Patient data / sensitive data
+# =========================
+Data/
+data/raw/
+data/processed/
+data/ground_truth/
+reference/
+
+# =========================
+# Generated results and logs
+# =========================
+results/
+results_edss_benchmark/
+*.log
+
+# =========================
+# Large/generated file types
+# =========================
+*.csv
+*.tsv
+*.json
+*.jsonl
+*.xlsx
+*.xls
+*.png
+*.PNG
+*.jpg
+*.jpeg
+*.svg
+*.pdf
+
+# =========================
+# Temporary / backup files
+# =========================
+*.tmp
+*.bak
+*.orig
+.DS_Store
+
+# =========================
+# Keep important code/config/docs
+# =========================
+!README.md
+!requirements.txt
+!*.py
+!*.md
+!*.yml
+!*.yaml
+!*.toml
+
+# Keep prompt templates / schemas if safe to publish
+!prompts/
+!prompts/**
+!attach/
+!attach/*.gbnf
+!attach/just_edss_text.txt
+!attach/Komplett.txt
+
+# Keep example/synthetic data only
+!data/
+!data/example/
+!data/example/**
+!Data/example/
+!Data/example/**

PROJECT_STRUCTURE.md

@@ -0,0 +1,31 @@
+# Project Structure
+
+This project was reorganized into:
+
+- `data/`
+  - `raw/`: original raw data, if retained locally
+  - `processed/`: cleaned or derived input data
+  - `ground_truth/`: manually annotated reference data
+  - `external/`: externally provided data
+
+- `prompts/`
+  - EDSS instructions and prompt/schema assets
+
+- `scripts/`
+  - runnable analysis and plotting scripts
+
+- `results/`
+  - `benchmark_runs/`: full model benchmark runs
+  - `final_results/`: final selected model outputs
+  - `figures/`: generated figures
+  - `tables/`: generated tables
+  - `logs/`: terminal logs
+
+- `manuscript/`
+  - final figures and tables for paper/thesis writing
+
+- `archive/`
+  - old scripts, old results, temporary files, and unclear legacy files
+
+Important:
+The reorganization was performed after creating a full timestamped backup.

archive/old_scripts/app.py

@@ -214,3 +214,5 @@ if __name__ == "__main__":
     print(f"Results saved to {output_json}")
 ##
 
+
+

archive/old_scripts/total_app.py

@@ -0,0 +1,149 @@
+import time
+import json
+import os
+from datetime import datetime
+import pandas as pd
+from openai import OpenAI
+from dotenv import load_dotenv
+
+# Load environment variables
+load_dotenv()
+
+# === CONFIGURATION ===
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+OPENAI_BASE_URL = os.getenv("OPENAI_BASE_URL")
+MODEL_NAME = "GPT-OSS-120B"
+HEALTH_URL = f"{OPENAI_BASE_URL}/health"  # Placeholder - actual health check would need to be implemented
+CHAT_URL = f"{OPENAI_BASE_URL}/chat/completions"
+# File paths
+INPUT_CSV = "/home/shahin/Lab/Doktorarbeit/Barcelona/Data/MS_Briefe_400_with_unique_id_SHA3_explore_cleaned_unique.csv"
+EDSS_INSTRUCTIONS_PATH = "/home/shahin/Lab/Doktorarbeit/Barcelona/attach/Komplett.txt"
+#GRAMMAR_FILE = "/home/shahin/Lab/Doktorarbeit/Barcelona/attach/just_edss_schema.gbnf"
+# Initialize OpenAI client
+client = OpenAI(
+    api_key=OPENAI_API_KEY,
+    base_url=OPENAI_BASE_URL
+)
+# Read EDSS instructions from file
+with open(EDSS_INSTRUCTIONS_PATH, 'r') as f:
+    EDSS_INSTRUCTIONS = f.read().strip()
+
+# === RUN INFERENCE 2 ===
+def run_inference(patient_text, max_retries=3):
+    prompt = f'''Du bist ein medizinischer Assistent, der spezialisiert darauf ist, EDSS-Scores (Expanded Disability Status Scale) sowie alle Unterkategorien aus klinischen Berichten zu extrahieren.
+### Regeln für die Ausgabe:
+1. **Reason**: Erstelle eine prägnante Zusammenfassung (max. 400 Zeichen) der Befunde auf **DEUTSCH**, die zur Einstufung führen.
+2. **klassifizierbar**:
+   - Setze dies auf **true**, wenn ein EDSS-Wert identifiziert, berechnet oder basierend auf den klinischen Hinweisen plausibel geschätzt werden kann.
+   - Setze dies auf **false**, NUR wenn die Daten absolut unzureichend oder so widersprüchlich sind, dass keinerlei Einstufung möglich ist.
+3. **EDSS**:
+   - Dieses Feld ist **VERPFLICHTEND**, wenn "klassifizierbar" auf true steht.
+   - Es muss eine Zahl zwischen 0.0 und 10.0 sein.
+   - Versuche stets, den EDSS-Wert so präzise wie möglich zu bestimmen, auch wenn die Datenlage dünn ist (nutze verfügbare Informationen zu Gehstrecke und Funktionssystemen).
+   - Dieses Feld **DARF NICHT ERSCHEINEN**, wenn "klassifizierbar" auf false steht.
+4. **Unterkategorien**:
+   - Extrahiere alle folgenden Unterkategorien aus dem Bericht:
+   - VISUAL OPTIC FUNCTIONS (max. 6.0)
+   - BRAINSTEM FUNCTIONS (max. 6.0)
+   - PYRAMIDAL FUNCTIONS (max. 6.0)
+   - CEREBELLAR FUNCTIONS (max. 6.0)
+   - SENSORY FUNCTIONS (max. 6.0)
+   - BOWEL AND BLADDER FUNCTIONS (max. 6.0)
+   - CEREBRAL FUNCTIONS (max. 6.0)
+   - AMBULATION (max. 10.0)
+   - Jede Unterkategorie sollte eine Zahl zwischen 0.0 und der jeweiligen Obergrenze enthalten, wenn sie klassifizierbar ist
+   - Wenn eine Unterkategorie nicht klassifizierbar ist, setze den Wert auf null
+### Einschränkungen:
+- Erfinde keine Fakten, aber nutze klinische Herleitungen aus dem Bericht, um den EDSS und die Unterkategorien zu bestimmen.
+- Priorisiere die Vergabe eines EDSS-Wertes gegenüber der Markierung als nicht klassifizierbar.
+- Halte dich strikt an die JSON-Struktur.
+- Die Unterkategorien müssen immer enthalten sein, auch wenn sie null sind.
+EDSS-Bewertungsrichtlinien:
+{EDSS_INSTRUCTIONS}
+Patientenbericht:
+{patient_text}
+'''
+
+    start_time = time.time()
+    for attempt in range(max_retries + 1):
+        try:
+            response = client.chat.completions.create(
+                messages=[
+                    {
+                        "role": "system",
+                        "content": "You extract EDSS scores and all subcategories. You prioritize providing values even if data is partial, by using clinical inference."
+                    },
+                    {
+                        "role": "user",
+                        "content": prompt
+                    }
+                ],
+                model=MODEL_NAME,
+                max_tokens=2048,
+                temperature=0.0,
+                response_format={"type": "json_object"}
+            )
+            content = response.choices[0].message.content
+
+            if content is None or content.strip() == "":
+                raise ValueError("API returned empty or None response content")
+
+            parsed = json.loads(content)
+            inference_time = time.time() - start_time
+            return {
+                "success": True,
+                "result": parsed,
+                "inference_time_sec": inference_time
+            }
+
+        except Exception as e:
+            print(f"Attempt {attempt + 1} failed: {e}")
+            if attempt < max_retries:
+                time.sleep(2 ** attempt)  # Exponential backoff
+                continue
+            else:
+                print("All retries exhausted.")
+                return {
+                    "success": False,
+                    "error": str(e),
+                    "inference_time_sec": -1
+                }
+
+# === BUILD PATIENT TEXT ===
+def build_patient_text(row):
+    # Handle potential NaN or None values in the row
+    summary = str(row.get("T_Zusammenfassung", "")) if pd.notna(row.get("T_Zusammenfassung")) else ""
+    diagnoses = str(row.get("Diagnosen", "")) if pd.notna(row.get("Diagnosen")) else ""
+    clinical = str(row.get("T_KlinBef", "")) if pd.notna(row.get("T_KlinBef")) else ""
+    findings = str(row.get("T_Befunde", "")) if pd.notna(row.get("T_Befunde")) else ""
+    return "\n".join([summary, diagnoses, clinical, findings]).strip()
+if __name__ == "__main__":
+    # Read CSV file ONLY inside main block
+    df = pd.read_csv(INPUT_CSV, sep=';')
+    results = []
+    # Process each row
+    for idx, row in df.iterrows():
+        print(f"Processing row {idx + 1}/{len(df)}")
+        try:
+            patient_text = build_patient_text(row)
+            result = run_inference(patient_text)
+            # Add unique_id and MedDatum to result for tracking
+            result["unique_id"] = row.get("unique_id", f"row_{idx}")
+            result["MedDatum"] = row.get("MedDatum", None)
+            results.append(result)
+            print(json.dumps(result, indent=2, ensure_ascii=False))
+        except Exception as e:
+            print(f"Error processing row {idx}: {e}")
+            results.append({
+                "success": False,
+                "error": str(e),
+                "unique_id": row.get("unique_id", f"row_{idx}"),
+                "MedDatum": row.get("MedDatum", None)
+            })
+    # Save results to a JSON file
+    output_json = INPUT_CSV.replace(".csv", "_results_total.json")
+    with open(output_json, 'w', encoding='utf-8') as f:
+        json.dump(results, f, indent=2, ensure_ascii=False)
+    print(f"Results saved to {output_json}")
+
+

prompts/Komplett.txt

@@ -0,0 +1,481 @@
+1 VISUAL OPTIC FUNCTIONS
+
+VISUAL ACUITY
+The visual acuity score is based on the line in the Snellen chart at 20 feet 5 meters
+for which the patient makes no more than one error using best available correction
+Alternatively best corrected near vision can be assessed but this should be noted and
+consistently performed during follow up examinations Switching from near to distance
+visual acuity measurements should be avoided in follow up examinations
+
+VISUAL FIELDS
+0 normal
+1 signs only deficits present only on formal confrontational testing
+2 moderate patient aware of deficit but incomplete hemianopsia on examination
+3 marked complete homonymous hemianopsia or equivalent
+
+SCOTOMA
+0 none
+1 small detectable only on formal confrontational testing
+2 large spontaneously reported by patient
+
+* DISC PALLOR
+0 not present
+1 present
+
+NOTE
+When determining the EDSS step the Visual FS score must be converted to a lower
+score as follows
+Visual FS Score 6 5 4 3 2 1
+Converted Visual FS Score 4 3 3 2 2 1
+
+FUNCTIONAL SYSTEM SCORE
+0 normal
+1 disc pallor and or small scotoma and or visual acuity corrected of worse eye less than 20 20 1.0 but better than 20 30 0.67
+2 worse eye with maximal visual acuity corrected of 20 30 to 20 59 0.67 – 0.34
+3 worse eye with large scotoma and or moderate decrease in fields and or maximal visual acuity corrected of 20 60 to 20 99 0.33 – 0.21
+4 worse eye with marked decrease of fields and or maximal visual acuity corrected of 20 100 to 20 200 0.2 – 0.1 grade 3 plus maximal acuity of better eye of 20 60 0.33 or less
+5 worse eye with maximal visual acuity corrected less than 20 200 0.1 grade 4 plus maximal acuity of better eye of 20 60 0.33 or less
+6 grade 5 plus maximal acuity of better eye of 20 60 0.33 or less *  =  optional part of the examination
+
+
+### BRAINSTEM FUNCTIONS
+
+**DYSARTHRIA**
+- **0**: None
+- **1**: Signs only
+- **2**: Mild: Clinically detectable, patient is aware
+- **3**: Moderate: Obvious during conversation, impairs comprehension
+- **4**: Marked: Incomprehensible speech
+- **5**: Inability to speak
+
+**DYSPHAGIA**
+- **0**: None
+- **1**: Signs only
+- **2**: Mild: Difficulty with thin liquids
+- **3**: Moderate: Difficulty with liquids and solid food
+- **4**: Marked: Sustained difficulty, requires pureed diet
+- **5**: Inability to swallow
+
+**OTHER CRANIAL NERVE FUNCTIONS**
+- **0**: Normal
+- **1**: Signs only
+- **2**: Mild disability: Clinically detectable deficit, patient is usually aware
+- **3**: Moderate disability
+- **4**: Marked disability
+
+**EXTRAOCULAR MOVEMENTS (EOM) IMPAIRMENT**
+- **0**: None
+- **1**: Signs only: Subtle EOM weakness, no complaints of vision issues
+- **2**: Mild: Subtle EOM weakness or obvious incomplete paralysis not noticed by patient
+- **3**: Moderate: Obvious incomplete paralysis noticed by patient or complete loss in one direction
+- **4**: Marked: Complete loss in more than one direction
+
+**NYSTAGMUS**
+- **0**: None
+- **1**: Signs only or mild: Gaze-evoked nystagmus below moderate limits (equivalent to Brainstem FS score of 1)
+- **2**: Moderate: Sustained nystagmus on horizontal/vertical gaze at 30 degrees, patient may not notice
+- **3**: Severe: Nystagmus in primary position or coarse persistent nystagmus interfering with vision; complete internuclear ophthalmoplegia; oscillopsia
+
+**TRIGEMINAL DAMAGE**
+- **0**: None
+- **1**: Signs only
+- **2**: Mild: Clinically detectable numbness, patient is aware
+- **3**: Moderate: Impaired sharp/dull discrimination in one to three branches or trigeminal neuralgia (at least one recent attack)
+- **4**: Marked: Unable to discriminate between sharp/dull or complete loss of sensation in one or both nerves
+
+**FACIAL WEAKNESS**
+- **0**: None
+- **1**: Signs only
+- **2**: Mild: Clinically detectable weakness, patient is aware
+- **3**: Moderate: Incomplete facial palsy (e.g., eye closure requires patching, drooling)
+- **4**: Marked: Complete unilateral or bilateral facial palsy with lagophthalmus or difficulty with liquids
+
+**HEARING LOSS**
+- **0**: None
+- **1**: Signs only: Hears finger rub less on one/both sides, lateralized Weber test but no complaints
+- **2**: Mild: As in 1, aware of hearing problem
+- **3**: Moderate: Does not hear finger rub on one/both sides, misses several whispered numbers
+- **4**: Marked: Misses all or nearly all whispered numbers
+
+**FUNCTIONAL SYSTEM SCORE**
+- **0**: Normal
+- **1**: Signs only
+- **2**: Moderate nystagmus/EOM impairment/other mild disability
+- **3**: Severe nystagmus/marked EOM impairment/moderate other cranial nerve disability
+- **4**: Marked dysarthria/other marked disability
+- **5**: Inability to swallow or speak
+
+### PYRAMIDAL FUNCTIONS
+
+#### REFLEXES
+- **0**: Absent
+- **1**: Diminished
+- **2**: Normal
+- **3**: Exaggerated
+- **4**: Nonsustained clonus (a few beats of clonus)
+- **5**: Sustained clonus
+
+##### Cutaneous Reflexes
+- **0**: Normal
+- **1**: Weak
+- **2**: Absent
+
+###### Palmomental Reflex
+- **0**: Absent
+- **1**: Present
+
+###### Plantar Response
+- **0**: Flexor
+- **1**: Neutral or equivocal
+- **2**: Extensor
+
+#### LIMB STRENGTH
+The weakest muscle in each group defines the score for that muscle group. Optional functional tests (hopping on one foot and walking on heels/toes) are recommended for BMRC grades 3–5.
+
+##### BMRC Rating Scale
+- **0**: No muscle contraction detected
+- **1**: Visible contraction without visible joint movement
+- **2**: Visible movement only on the plane of gravity
+- **3**: Active movement against gravity, but not against resistance
+- **4**: Active movement against resistance, but not full strength
+- **5**: Normal strength
+
+#### FUNCTIONAL TESTS
+##### Pronator Drift (Upper Extremities)
+Pronation and downward drift:
+- **0**: None
+- **1**: Mild
+- **2**: Evident
+
+##### Position Test (Lower Extremities)
+Ask patient to lift both legs together, with legs fully extended at the knee. Sinking:
+- **0**: None
+- **1**: Mild
+- **2**: Evident
+- **3**: Able to lift only one leg at a time (grade from the horizontal position at the hip joints in degrees)
+- **4**: Unable to lift one leg at a time
+
+##### Walking on Heels/Toes
+- **0**: Normal
+- **1**: Impaired
+- **2**: Not possible
+
+##### Hopping on One Foot
+- **0**: Normal
+- **1**: 6–10 times
+- **2**: 1–5 times
+- **3**: Not possible
+
+#### LIMB SPASTICITY (AFTER RAPID FLEXION OF THE EXTREMITY)
+- **0**: None
+- **1**: Mild: barely increased muscle tone
+- **2**: Moderate: moderately increased muscle tone that can be overcome; full range of motion is possible
+- **3**: Severe: severely increased muscle tone that is extremely difficult to overcome; full range of motion is not possible
+- **4**: Contracted
+
+#### GAIT SPASTICITY
+- **0**: None
+- **1**: Barely perceptible
+- **2**: Evident: minor interference with function
+- **3**: Permanent shuffling: major interference with function
+
+#### OVERALL MOTOR PERFORMANCE
+- **0**: Normal
+- **1**: Abnormal weakness (as compared to peers) in performing more demanding tasks, e.g., walking longer distances; no reduction in limb strength on formal testing
+- **2**: Reduction in strength of individual muscle groups at confrontational testing
+
+#### FUNCTIONAL SYSTEM SCORE
+- **0**: Normal
+- **1**: Abnormal signs without disability
+- **2**: Minimal disability: patient complains of motor-fatigability or reduced performance in strenuous motor tasks (motor performance grade 1) and/or BMRC grade 4 in one or two muscle groups
+- **3**: Mild to moderate paraparesis or hemiparesis: usually BMRC grade 4 in more than two muscle groups; and/or BMRC grade 3 in one or two muscle groups (movements against gravity
+are possible); and/or severe monoparesis: BMRC grade 2 or less in one muscle group
+- **4**: Marked paraparesis or hemiparesis: usually BMRC grade 2 in two limbs or monoplegia with BMRC grade 0 or 1 in one limb; and/or moderate tetraparesis: BMRC grade 3 in three or more limbs
+- **5**: Paraplegia: BMRC grade 0 or 1 in all muscle groups of the lower limbs; and/or marked tetraparesis: BMRC grade 2 or less in three or more limbs; and/or hemiplegia
+- **6**: Tetraplegia: BMRC grade 0 or 1 in all muscle groups of the upper and lower limbs
+
+### CEREBELLAR FUNCTIONS
+
+#### HEAD TREMOR
+- **0**: none
+- **1**: mild
+- **2**: moderate
+- **3**: severe
+
+#### TRUNCAL ATAXIA
+- **0**: none
+- **1**: signs only
+- **2**: mild (swaying with eyes closed)
+- **3**: moderate (swaying with eyes open)
+- **4**: severe (unable to sit without assistance)
+
+#### LIMB ATAXIA (TREMOR / DYSMETRIA AND RAPID ALTERNATING MOVEMENTS)
+- **0**: none
+- **1**: signs only
+- **2**: mild (tremor or clumsy movements easily seen, minor interference with function)
+- **3**: moderate (tremor or clumsy movements interfere with function in all spheres)
+- **4**: severe (most functions are very difficult)
+
+#### TANDEM (STRAIGHT LINE) WALKING
+- **0**: normal
+- **1**: impaired
+- **2**: not possible
+
+#### GAIT ATAXIA
+- **0**: none
+- **1**: signs only
+- **2**: mild (problems with balance realized by patient and/or significant other)
+- **3**: moderate (abnormal balance with ordinary walking)
+- **4**: severe (unable to walk more than a few steps unassisted or requires a walking aid or assistance due to ataxia)
+
+#### ROMBERG TEST
+- **0**: normal
+- **1**: mild (mild instability with eyes closed)
+- **2**: moderate (not stable with eyes closed)
+- **3**: severe (not stable with eyes open)
+
+#### OTHER CEREBELLAR TESTS
+- **0**: normal
+- **1**: mild abnormality
+- **2**: moderate abnormality
+- **3**: severe abnormality
+
+**NOTE:**
+- The presence of severe gait and/or truncal ataxia alone (without severe ataxia in three or four limbs) results in a Cerebellar FS score of 3.
+- If weakness or sensory deficits interfere with the testing of ataxia, score the patient’s actual performance. Indicate the possible role of weakness by marking an "X" after the
+affected subsystems and Cerebellar FS score.
+
+#### FUNCTIONAL SYSTEM SCORE
+- **0**: normal
+- **1**: abnormal signs without disability
+- **2**: mild ataxia and/or moderate station ataxia (Romberg) and/or tandem walking not possible
+- **3**: moderate limb ataxia and/or moderate or severe gait/truncal ataxia
+- **4**: severe gait/truncal ataxia and severe ataxia in three or four limbs
+- **5**: unable to perform coordinated movements due to ataxia
+- **X**: pyramidal weakness (BMRC grade 3 or worse in limb strength) or sensory deficits interfere with cerebellar testing
+
+### SENSORY FUNCTIONS
+
+#### SUPERFICIAL SENSATION (LIGHT TOUCH AND PAIN)
+- **0**: normal
+- **1**: signs only (slightly diminished sensation on formal testing, patient not aware)
+- **2**: mild (patient aware of impaired light touch or pain but can discriminate sharp/dull)
+- **3**: moderate (impaired discrimination of sharp/dull)
+- **4**: marked (unable to discriminate between sharp/dull and/or unable to feel light touch)
+- **5**: complete loss (anesthesia)
+
+#### VIBRATION SENSE (AT THE MOST DISTAL JOINT)
+- **0**: normal
+- **1**: mild (graded tuning fork 5–7 of 8; detects more than 10 seconds but less than examiner)
+- **2**: moderate (graded tuning fork 1–4 of 8; detects between 2 and 10 sec.)
+- **3**: marked (complete loss of vibration sense)
+
+#### POSITION SENSE
+- **0**: normal
+- **1**: mild (1–2 incorrect responses, only distal joints affected)
+- **2**: moderate (misses many movements of fingers or toes; proximal joints affected)
+- **3**: marked (no perception of movement, astasia)
+
+* **LHERMITTE’S SIGN** (does not contribute to the Sensory FS score)
+  - **0**: negative
+  - **1**: positive
+
+* **PARAESTHESIAE (TINGLING)** (does not contribute to the Sensory FS score)
+  - **0**: none
+  - **1**: present
+
+#### FUNCTIONAL SYSTEM SCORE
+- **0**: normal
+- **1**: impaired superficial sensation in one or two limbs
+- **2**: mild impairment in more than two limbs, no major proprioceptive deficits
+- **3**: moderate impairment in more than two limbs with minor proprioceptive deficits
+- **4**: severe impairment in more than two limbs with significant proprioceptive deficits
+- **5**: loss of sensation in one or two limbs, significant proprioceptive deficits in most of the body below the head
+- **6**: essentially no sensation below the head
+
+### BOWEL AND BLADDER FUNCTIONS
+
+#### URINARY HESITANCY AND RETENTION
+- **0**: none
+- **1**: mild (no major impact on lifestyle)
+- **2**: moderate (urinary retention; frequent urinary tract infections)
+- **3**: severe (requires catheterization)
+- **4**: loss of function (overflow incontinence)
+
+#### URINARY URGENCY AND INCONTINENCE
+- **0**: none
+- **1**: mild (no major impact on lifestyle)
+- **2**: moderate (rare incontinence occurring no more than once a week; must wear pads)
+- **3**: severe (frequent incontinence occurring from several times a week to more than once a day; must wear urinal or pads)
+- **4**: loss of function (loss of bladder control)
+
+#### BLADDER CATHETERIZATION
+- **0**: none
+- **1**: intermittent self-catheterization
+- **2**: constant catheterization
+
+#### BOWEL DYSFUNCTION
+- **0**: none
+- **1**: mild (no incontinence, no major impact on lifestyle, mild constipation)
+- **2**: moderate (must wear pads or alter lifestyle to be near lavatory)
+- **3**: severe (in need of enemas or manual measures to evacuate bowels)
+- **4**: complete loss of function
+
+#### SEXUAL DYSFUNCTION
+**Male**
+- **0**: none
+- **1**: mild (difficulty maintaining erection during intercourse, but achieves erection and still has intercourse)
+- **2**: moderate (difficulty achieving erection, decreased libido, still has intercourse and reaches orgasm)
+- **3**: severe (marked decrease in libido, inability to achieve full erection, intercourse with difficulty, hypoorgasmia)
+- **4**: loss of function
+
+**Female**
+- **0**: none
+- **1**: mild (mild lack of lubrication, still sexually active and reaches orgasm)
+- **2**: moderate (dyspareunia, hypoorgasmia, decrease in sexual activity)
+- **3**: severe (marked decrease in sexual activity, anorgasmia)
+- **4**: loss of function
+
+**NOTE**
+When determining the EDSS step, the Bowel and Bladder FS score must be converted to a lower score as follows:
+- Bowel and Bladder FS Score: 6 → Converted Bowel and Bladder FS Score: 5
+- Bowel and Bladder FS Score: 5 → Converted Bowel and Bladder FS Score: 4
+- Bowel and Bladder FS Score: 4 → Converted Bowel and Bladder FS Score: 3
+- Bowel and Bladder FS Score: 3 → Converted Bowel and Bladder FS Score: 3
+- Bowel and Bladder FS Score: 2 → Converted Bowel and Bladder FS Score: 2
+- Bowel and Bladder FS Score: 1 → Converted Bowel and Bladder FS Score: 1
+
+Sexual dysfunction can be documented but generally does not impact the FS score due to assessment difficulties by examining physicians.
+
+### FUNCTIONAL SYSTEM SCORE
+- **0**: normal
+- **1**: mild urinary hesitancy, urgency, and/or constipation
+- **2**: moderate urinary hesitancy/retention and/or moderate urinary urgency/incontinence and/or moderate bowel dysfunction
+- **3**: frequent urinary incontinence or intermittent self-catheterization; needs enemas or manual measures to evacuate bowels
+- **4**: in need of almost constant catheterization
+- **5**: loss of bladder or bowel function (external or indwelling catheter)
+- **6**: loss of bowel and bladder function
+
+### CEREBRAL FUNCTIONS
+
+#### DEPRESSION AND EUPHORIA
+- **0**: none
+- **1**: present (Patient complains of depression or is considered depressed or euphoric by the investigator or significant other.)
+
+**Note**: Depression and Euphoria are documented on the scoring sheet but are not taken into consideration for FS and EDSS calculation.
+
+#### DECREASE IN MENTATION
+- **0**: none
+- **1**: signs only (not apparent to patient and/or significant other)
+- **2**: mild (Patient and/or significant other report mild changes in mentation. Examples include: impaired ability to follow a rapid course of association or survey complex matters;
+impaired judgment in certain demanding situations; capable of handling routine daily activities, but unable to tolerate additional stressors; intermittently symptomatic even with
+normal levels of stress; reduced performance; tendency toward negligence due to obliviousness or fatigue.)
+- **3**: moderate (Definite abnormalities on brief mental status testing, but still oriented to person, place, and time)
+- **4**: marked (Not oriented in one or two spheres (person, place, or time); marked effect on lifestyle)
+- **5**: dementia, confusion, and/or complete disorientation
+
+#### FATIGUE
+- **0**: none
+- **1**: mild (Does not usually interfere with daily activities)
+- **2**: moderate (Interferes but does not limit daily activities for more than 50%)
+- **3**: severe (Significant limitation in daily activities (> 50% reduction))
+
+**Note**: Because fatigue is difficult to evaluate objectively, in some studies it does not contribute to the Cerebral FS score or EDSS step. Please adhere to the study’s specific
+instructions.
+
+### FUNCTIONAL SYSTEM SCORE
+- **0**: normal
+- **1**: signs only in decrease in mentation; mild fatigue
+- **2**: mild decrease in mentation; moderate or severe fatigue
+- **3**: moderate decrease in mentation
+- **4**: marked decrease in mentation
+- **5**: dementia
+
+### AMBULATION
+
+**Unrestricted Ambulation**
+- The patient can walk a normal distance without assistance, comparable to healthy individuals of similar age and physical condition.
+- EDSS step can range from 0 to 5.0, depending on the Functional System (FS) scores.
+
+**Fully Ambulatory**
+- At least 500 meters of ambulation without assistance, but not unrestricted.
+- EDSS step can range from 2.0 to 5.0, depending on FS scores.
+- The Pyramidal and/or Cerebellar FS must be ≥ 2 to reflect this restriction in ambulation.
+
+**Ambulation < 500 Meters**
+- If the walking distance is less than 500 meters, the EDSS step must be ≥ 4.5, depending on the walking ranges provided by the ambulation score and combination of FS scores.
+- EDSS steps 5.5 to 8.0 are exclusively defined by the ability to ambulate and type of assistance required, or the ability to use a wheelchair.
+
+**Assistance Needed**
+- Definitions for EDSS steps 6.0 or 6.5 include both the type of assistance required when walking and the walking range.
+- Assistance by another person is equivalent to bilateral assistance.
+
+**Note:**
+- The ambulation score represents both the walking range and the type of assistance required.
+- This score replaces several checkboxes used previously on the scoring sheet but does not introduce new definitions.
+- Use of a wheelchair can now be scored on the scoring sheet.
+- Indicate the reported distance and time for the patient in the appropriate field on the scoring sheet, followed by the type of assistance and walking distance measured during assessment.
+
+
+### DISTANCE AND TIME REPORTED BY PATIENT
+
+**Maximal Unassisted Walking Distance**
+- Maximal unassisted walking distance reported by the patient (in meters) without rest or assistance.
+- Time required to walk the maximum distance according to the patient (in minutes).
+
+**Assistance**
+0. Without help or assistance (allowing use of an ankle-foot orthotic device, but no other assistive devices).
+1. Unilateral assistance: one stick/crutch/brace.
+2. Bilateral assistance: two sticks/crutches/braces or assistance by another person.
+3. Wheelchair.
+
+**Distance**
+- Measure the distance the patient can walk in meters.
+  - **Unassisted:** Observe walking for a minimum of 500 meters and measure time needed, if possible.
+  - **Assisted:** Observe walking with assistive devices or help from another person for a minimum of 130 meters, if possible.
+
+---
+
+### AMBULATION SCORE
+
+0. Unrestricted
+1. Fully ambulatory
+2. ≥ 300 meters but < 500 meters, without help or assistance (EDSS 4.5 or 5.0)
+3. ≥ 200 meters but < 300 meters, without help or assistance (EDSS 5.0)
+4. ≥ 100 meters but < 200 meters, without help or assistance (EDSS 5.5)
+5. Walking range < 100 meters without assistance (EDSS 6.0)
+6. Unilateral assistance, ≥ 50 meters (EDSS 6.0)
+7. Bilateral assistance, ≥ 120 meters (EDSS 6.0)
+8. Unilateral assistance, < 50 meters (EDSS 6.5)
+9. Bilateral assistance, ≥ 5 meters but < 120 meters (EDSS 6.5)
+10. Uses wheelchair without help; unable to walk 5 meters even with aid, essentially restricted to wheelchair; wheels self and transfers alone; up and about in wheelchair for some 12 hours a day (EDSS 7.0)
+11. Uses wheelchair with help; unable to take more than a few steps; restricted to wheelchair; may need some help in transferring and wheeling self (EDSS 7.5)
+12. Essentially restricted to bed or chair or perambulated in wheelchair, but out of bed most of the day; retains many self-care functions; generally has effective use of arms (EDSS 8.0)
+
+Expanded Disability Status Scale (EDSS)
+
+0   - Normal neurological exam (all Functional Systems [FS] grade 0)
+1.0 - No disability, minimal signs in one FS (one FS grade 1)
+1.5 - No disability, minimal signs in more than one FS (more than one FS grade 1)
+2.0 - Minimal disability in one FS (one FS grade 2, others 0 or 1)
+2.5 - Minimal disability in two FS (two FS grades 2, others 0 or 1)
+3.0 - Moderate disability in one FS (one FS grade 3, others 0 or 1) though fully ambulatory;
+or mild disability in three or four FS (three/four FS grades 2, others 0 or 1) though fully ambulatory
+3.5 - Fully ambulatory but with moderate disability in one FS (one FS grade 3) and mild disability in one or two FS (one/two FS grade 2) and others 0 or 1;
+or fully ambulatory with two FS grades 3 (others 0 or 1);
+or fully ambulatory with five FS grades 2 (others 0 or 1)
+4.0 - Unable to walk > 25 feet without aid
+4.5 - Unable to walk > 100 feet without aid
+5.0 - Relies on a walking aid; unable to walk > 300 feet without resting
+5.5 - Relies on a walking aid; unable to walk > 200 feet without resting
+6.0 - Unable to walk more than 50 feet with or without aid; cannot stand unaided for five minutes
+6.5 - Unable to walk more than 10 feet with or without aid; cannot stand unaided for two minutes
+7.0 - Unable to walk 5 meters even with aid, essentially restricted to wheelchair; wheels self and transfers alone; up and about in wheelchair some 12 hours a day
+7.5 - Unable to take more than a few steps; restricted to wheelchair; may need some help in transferring and in wheeling self
+8.0 - Essentially restricted to bed or chair or perambulated in wheelchair, but out of bed most of the day; retains many self-care functions; generally has effective use of arms
+8.5 - Essentially restricted to bed much of the day; has some effective use of arm(s); retains some self-care functions
+9.0 - Helpless bed patient; can communicate and eat
+9.5 - Totally helpless bed patient; unable to communicate effectively or eat/swallow
+10  - Death due to MS
+
+

prompts/just_edss_schema.gbnf

@@ -0,0 +1,11 @@
+EDSS-kv ::= "\"EDSS\"" space ":" space number
+Reason ::= "\"" char{0,400} "\"" space
+Reason-kv ::= "\"Reason\"" space ":" space Reason
+boolean ::= ("true" | "false") space
+char ::= [^"\\\x7F\x00-\x1F] | [\\] (["\\bfnrt] | "u" [0-9a-fA-F]{4})
+decimal-part ::= [0-9]{1,16}
+integral-part ::= [0] | [1-9] [0-9]{0,15}
+nicht-klassifizierbar-kv ::= "\"nicht_klassifizierbar\"" space ":" space boolean
+number ::= ("-"? integral-part) ("." decimal-part)? ([eE] [-+]? integral-part)? space
+root ::= "{" space Reason-kv "," space nicht-klassifizierbar-kv ( "," space ( EDSS-kv ) )? "}" space
+space ::= | " " | "\n"{1,2} [ \t]{0,20}

prompts/just_edss_text.txt

@@ -0,0 +1,25 @@
+Expanded Disability Status Scale (EDSS)
+
+0   - Normal neurological exam (all Functional Systems [FS] grade 0)
+1.0 - No disability, minimal signs in one FS (one FS grade 1)
+1.5 - No disability, minimal signs in more than one FS (more than one FS grade 1)
+2.0 - Minimal disability in one FS (one FS grade 2, others 0 or 1)
+2.5 - Minimal disability in two FS (two FS grades 2, others 0 or 1)
+3.0 - Moderate disability in one FS (one FS grade 3, others 0 or 1) though fully ambulatory;
+or mild disability in three or four FS (three/four FS grades 2, others 0 or 1) though fully ambulatory
+3.5 - Fully ambulatory but with moderate disability in one FS (one FS grade 3) and mild disability in one or two FS (one/two FS grade 2) and others 0 or 1;
+or fully ambulatory with two FS grades 3 (others 0 or 1);
+or fully ambulatory with five FS grades 2 (others 0 or 1)
+4.0 - Unable to walk > 25 feet without aid
+4.5 - Unable to walk > 100 feet without aid
+5.0 - Relies on a walking aid; unable to walk > 300 feet without resting
+5.5 - Relies on a walking aid; unable to walk > 200 feet without resting
+6.0 - Unable to walk more than 50 feet with or without aid; cannot stand unaided for five minutes
+6.5 - Unable to walk more than 10 feet with or without aid; cannot stand unaided for two minutes
+7.0 - Unable to walk 5 meters even with aid, essentially restricted to wheelchair; wheels self and transfers alone; up and about in wheelchair some 12 hours a day
+7.5 - Unable to take more than a few steps; restricted to wheelchair; may need some help in transferring and in wheeling self
+8.0 - Essentially restricted to bed or chair or perambulated in wheelchair, but out of bed most of the day; retains many self-care functions; generally has effective use of arms
+8.5 - Essentially restricted to bed much of the day; has some effective use of arm(s); retains some self-care functions
+9.0 - Helpless bed patient; can communicate and eat
+9.5 - Totally helpless bed patient; unable to communicate effectively or eat/swallow
+10  - Death due to MS

scripts/figure1.py

@@ -263,3 +263,120 @@ plt.legend(frameon=False, loc='upper center', bbox_to_anchor=(0.5, -0.05))
 plt.tight_layout()
 plt.show()
 ##
+
+
+
+
+# %% name
+import matplotlib.pyplot as plt
+
+# Data
+data = {
+    'Visit': [9, 8, 7, 6, 5, 4, 3, 2, 1],
+    'patient_count': [2, 3, 3, 6, 13, 17, 28, 24, 32]
+}
+
+# Create figure and axis
+fig, ax = plt.subplots(figsize=(10, 6))
+
+# Plot the bar chart
+bars = ax.bar(data['Visit'], data['patient_count'], color='darkblue', label='Patients by Visit Count')
+
+# Add labels and title
+ax.set_xlabel('Visit Number (from last to first)', fontsize=12)
+ax.set_ylabel('Number of Patients', fontsize=12)
+ax.set_title('Patient Visits by Visit Number', fontsize=14)
+
+# Invert x-axis to show Visit 9 on the left (descending order) if desired, but keep natural order (1–9 left to right)
+# For descending order (9→1 from left to right), we'd need to reverse:
+# Visit = data['Visit'][::-1], patient_count = data['patient_count'][::-1]
+# But standard practice is ascending (1 to 9), so we'll sort accordingly:
+# Let's sort by Visit to ensure left-to-right: 1,2,...,9
+
+# Actually, your current Visit list is [9,8,...,1], which is descending.
+# Let's sort by Visit for intuitive left-to-right increasing order:
+sorted_indices = sorted(range(len(data['Visit'])), key=lambda i: data['Visit'][i])
+visit_sorted = [data['Visit'][i] for i in sorted_indices]
+count_sorted = [data['patient_count'][i] for i in sorted_indices]
+
+# Re-plot with sorted x-axis:
+ax.clear()
+bars = ax.bar(visit_sorted, count_sorted, color='darkblue', label='Patients by Visit Count')
+
+# Re-apply labels, etc.
+ax.set_xlabel('Number of Visits', fontsize=12)
+ax.set_ylabel('Number of Unique Patients', fontsize=12)
+#ax.set_title('Number of Patients by Visit Number', fontsize=14)
+
+# Add legend
+ax.legend()
+
+# Improve layout and grid
+ax.grid(axis='y', linestyle='--', alpha=0.7)
+plt.xticks(visit_sorted)  # Ensure all integer visit numbers are shown
+
+# Show the plot
+plt.tight_layout()
+plt.show()
+
+##
+
+# %% Patientjourney Bubble chart
+import matplotlib.pyplot as plt
+import numpy as np
+
+import matplotlib as mpl
+
+mpl.rcParams["font.family"] = "DejaVu Sans"   # or "Arial", "Calibri", "Times New Roman", ...
+mpl.rcParams["font.size"] = 12                # default size for text
+mpl.rcParams["axes.titlesize"] = 14
+mpl.rcParams["axes.titleweight"] = "bold"
+
+
+# Data (your counts)
+visits = np.array([1, 2, 3, 4, 5, 6, 7, 8, 9])
+patient_count = np.array([32, 24, 28, 17, 13, 6, 3, 3, 2])
+
+# "Remaining" = patients with >= that many visits (cumulative from the right)
+remaining = np.array([patient_count[i:].sum() for i in range(len(patient_count))])
+
+# --- Plot ---
+fig, ax = plt.subplots(figsize=(12, 3))
+
+y = 0.0  # all bubbles on one horizontal line
+
+# Horizontal line
+ax.hlines(y, visits.min() - 0.4, visits.max() + 0.4, color="#1f77b4", linewidth=3)
+
+# Bubble sizes (scale as needed)
+# (Matplotlib scatter uses area in points^2)
+sizes = patient_count * 35  # tweak this multiplier if you want bigger/smaller bubbles
+
+ax.scatter(visits, np.full_like(visits, y), s=sizes, color="#1f77b4", zorder=3)
+
+# Title
+#ax.set_title("Patient Journey by Visit Count", fontsize=14, pad=18)
+
+# Top labels: "1 visits", "2 visits", ...
+for x in visits:
+    label = f"{x} visit" if x == 1 else f"{x} visits"
+    ax.text(x, y + 0.18, label, ha="center", va="bottom", fontsize=10)
+
+# Bottom labels: "X patients" and "Y remaining"
+for x, pc, rem in zip(visits, patient_count, remaining):
+    ax.text(x, y - 0.20, f"{pc} patients", ha="center", va="top", fontsize=9)
+    ax.text(x, y - 0.32, f"{rem} remaining", ha="center", va="top", fontsize=9)
+
+# Cosmetics: remove axes, keep spacing nice
+ax.set_xlim(visits.min() - 0.6, visits.max() + 0.6)
+ax.set_ylim(-0.5, 0.35)
+ax.set_xticks([])
+ax.set_yticks([])
+for spine in ax.spines.values():
+    spine.set_visible(False)
+
+plt.tight_layout()
+plt.show()
+plt.savefig("patient_journey.svg", format="svg", bbox_inches="tight")
+##
+