Registry Forge — Clinical-Note Extraction Dashboard

Cohort: Synthetic demonstration cohort  ·  Generated 2026-05-13 09:19  ·  Surfaces ALS-specific clinical content from unstructured narrative  ·  k-anonymity threshold k=2
Patients with any match
70
across all patterns
Pattern categories
6
after k≥2 filter
Distinct patterns
10
after k≥2 filter
Total matches
1,580
across all narrative sources

ALS-specific clinical content by category

Each row aggregates patients and records from all regex patterns within one clinical-content group. ALSFRS-R covers the functional rating scale and its four subdomain subscales; pulmonary captures FVC % predicted; diagnosis covers El Escorial / Awaji-Shima certainty and onset region; family history covers negative and positive constructs and genetic-mutation mentions; ECAS / FTD covers cognitive screening scores and FTD-spectrum references; treatment milestones cover dated procedures and drug starts (PEG, tracheostomy, NIV, riluzole, edaravone).

Clinical-content categoryUnique patientsRecordsPatterns
ALSFRS-R40
1941
Pulmonary70
3021
Diagnosis50
3372
Family history & genetics55
5203
ECAS / FTD45
1721
Treatment milestones8
552

All patterns

One row per regex pattern in the shipped library. Filter by name or category.

PatternCategoryUnique patientsRecords
fvc_percent_predictedPulmonary70302
family_history_negativeFamily history & genetics55263
onset_regionDiagnosis50207
ftd_spectrumECAS / FTD45172
alsfrs_r_totalALSFRS-R40194
genetic_mutationFamily history & genetics38166
el_escorialDiagnosis30130
family_history_positiveFamily history & genetics2091
peg_placement_dateTreatment milestones839
tracheostomy_dateTreatment milestones416

Patient × pattern matrix

PT-NNNN pseudonyms. Cell shows the number of records for that patient × that pattern; · = none. Patterns with fewer than k=2 unique patients are suppressed.

Patientfvc_percent_predictedfamily_history_negativeonset_regionftd_spectrumalsfrs_r_totalgenetic_mutationel_escorialfamily_history_positivepeg_placement_datetracheostomy_date
PT-0008847887588·
PT-0006821887488·
PT-00012365462877
PT-0007227557673·
PT-001286816824··
PT-00022431556672
PT-0005666261671·
PT-00035542833325
PT-00042571281832
PT-001145844653··
PT-001348733464··
PT-00286476457···
PT-001648137671··
PT-00216866155···
PT-001754216288··
PT-00308475813···
PT-001942766613··
PT-002045666521··
PT-000967243282··
PT-001566432345··
PT-003976578·····
PT-00231537717···
PT-0031571882····
PT-0038515668····
PT-001035218821··
PT-00245155337···
PT-004086473·····
PT-0032768312····
PT-0036281754····
PT-0037528264····
PT-00263712535···
PT-00271372526···
PT-001453232253··
PT-0033462238····
PT-0034148138····
PT-00227434312···
PT-001856241111··
PT-0035424155····
PT-00252321632···
PT-00446814······

Showing top 40 of 70 patients with at least one match.

Captured-value distribution

For numeric patterns (ALSFRS-R scores, FVC % predicted), shows min / median / max across captured values. For categorical / freetext patterns (El Escorial certainty, onset region, family-history constructs), shows the top distinct values and their record counts. Numeric extractions are not de-duplicated per patient at this view; use the Patient × pattern matrix to scope to per-patient counts.

Numeric findings (ALSFRS-R, ECAS, FVC% predicted)

fvc_percent_predicted

captured values302
min30.0
median78.0
max130.0

alsfrs_r_total

captured values194
min8.0
median30.0
max48.0

Categorical / freetext findings

family_history_negative — 263 captured values; top:

denies family history of neurodegenerative disease101
no family history of motor neuron disease86
denies family history of ALS76

onset_region — 207 captured values; top:

right lower extremity onset45
right upper extremity onset44
left lower extremity onset44
left upper extremity onset40
bulbar onset34

ftd_spectrum — 172 captured values; top:

ALS-FTD overlap suspected49
mild behavioral variant FTD features42
ECAS within normal limits41
cognitive impairment, ALS-specific40

genetic_mutation — 166 captured values; top:

all known ALS genes negative43
FUS p.R521C pathogenic33
C9orf72 hexanucleotide repeat expansion positive30
TARDBP variant of uncertain significance30
SOD1 c.272A>C variant detected30

el_escorial — 130 captured values; top:

clinically definite ALS36
laboratory-supported probable ALS33
clinically probable ALS31
clinically possible ALS30

family_history_positive — 91 captured values; top:

sister with motor neuron disease32
mother with confirmed ALS32
paternal uncle with ALS27

peg_placement_date — 39 captured values; top:

2023-089
2024-048
2024-018
2023-037
2022-117

tracheostomy_date — 16 captured values; top:

2024-077
2023-125
2024-024

Source-record snippets

Up to 3 representative text excerpts per regex pattern, prioritizing unique-patient diversity. Snippet text truncated to 200 chars. Useful for source verification and pattern-tuning review.

fvc_percent_predicted 70 unique patients · Pulmonary

FVC percent predicted

PT-0001 · ccda_section · captured 33
...spirometry today: FVC 33% predicted seated; supine slightly lower; consider NIV initiation if continues to decline...
PT-0002 · ccda_section · captured 57
...spirometry today: FVC 57% predicted seated; supine slightly lower; consider NIV initiation if continues to decline...
PT-0003 · document:rtf · captured 30
...spirometry today: FVC 30% predicted seated; supine slightly lower; consider NIV initiation if continues to decline...

family_history_negative 55 unique patients · Family history & genetics

Family history negative

PT-0001 · document:rtf · captured denies family history of ALS
...social history: denies family history of ALS. No first- or second-degree relatives with motor neuron disease or related conditions...
PT-0002 · ccda_section · captured no family history of motor neuron disease
...social history: no family history of motor neuron disease. No first- or second-degree relatives with motor neuron disease or related conditions...
PT-0003 · ccda_section · captured denies family history of ALS
...social history: denies family history of ALS. No first- or second-degree relatives with motor neuron disease or related conditions...

onset_region 50 unique patients · Diagnosis

Onset region

PT-0001 · document:rtf · captured bulbar onset
...patient first noted weakness with bulbar onset approximately 31 months prior to presentation; gradual progression to contralateral side...
PT-0002 · document:rtf · captured left upper extremity onset
...patient first noted weakness with left upper extremity onset approximately 11 months prior to presentation; gradual progression to contralateral side...
PT-0003 · ccda_section · captured right lower extremity onset
...patient first noted weakness with right lower extremity onset approximately 26 months prior to presentation; gradual progression to contralateral side...

ftd_spectrum 45 unique patients · ECAS / FTD

FTD spectrum

PT-0001 · ccda_section · captured mild behavioral variant FTD features
...cognitive / behavioral screening: mild behavioral variant FTD features. Family endorses mild personality and executive-function changes over the past year...
PT-0002 · document:rtf · captured ECAS within normal limits
...cognitive / behavioral screening: ECAS within normal limits. Family endorses mild personality and executive-function changes over the past year...
PT-0003 · ccda_section · captured ECAS within normal limits
...cognitive / behavioral screening: ECAS within normal limits. Family endorses mild personality and executive-function changes over the past year...

alsfrs_r_total 40 unique patients · ALSFRS-R

ALSFRS-R total

PT-0001 · ccda_section · captured 47
...ALSFRS-R administered in clinic, total score 47/48 (prior visit 50); calculated rate of decline -0.9 points/month...
PT-0002 · ccda_section · captured 33
...ALSFRS-R administered in clinic, total score 33/48 (prior visit 39); calculated rate of decline -0.4 points/month...
PT-0003 · document:rtf · captured 47
...ALSFRS-R administered in clinic, total score 47/48 (prior visit 51); calculated rate of decline -0.4 points/month...

genetic_mutation 38 unique patients · Family history & genetics

Genetic mutation

PT-0001 · ccda_section · captured all known ALS genes negative
...gene panel result: all known ALS genes negative. Family informed of implications; genetic counseling recommended for first-degree relatives...
PT-0002 · ccda_section · captured FUS p.R521C pathogenic
...gene panel result: FUS p.R521C pathogenic. Family informed of implications; genetic counseling recommended for first-degree relatives...
PT-0003 · ccda_section · captured all known ALS genes negative
...gene panel result: all known ALS genes negative. Family informed of implications; genetic counseling recommended for first-degree relatives...

el_escorial 30 unique patients · Diagnosis

El Escorial

PT-0001 · ccda_section · captured clinically definite ALS
...presentation and EMG findings consistent with clinically definite ALS; meets criteria per Awaji-Shima revisions; offered to enroll in registry...
PT-0002 · document:rtf · captured laboratory-supported probable ALS
...presentation and EMG findings consistent with laboratory-supported probable ALS; meets criteria per Awaji-Shima revisions; offered to enroll in registry...
PT-0003 · ccda_section · captured laboratory-supported probable ALS
...presentation and EMG findings consistent with laboratory-supported probable ALS; meets criteria per Awaji-Shima revisions; offered to enroll in registry...

family_history_positive 20 unique patients · Family history & genetics

Family history positive

PT-0001 · ccda_section · captured sister with motor neuron disease
...family history significant: sister with motor neuron disease; pedigree obtained over three generations; second-degree relative with possible ALS-FTD overlap...
PT-0002 · ccda_section · captured sister with motor neuron disease
...family history significant: sister with motor neuron disease; pedigree obtained over three generations; second-degree relative with possible ALS-FTD overlap...
PT-0003 · document:rtf · captured mother with confirmed ALS
...family history significant: mother with confirmed ALS; pedigree obtained over three generations; second-degree relative with possible ALS-FTD overlap...

peg_placement_date 8 unique patients · Treatment milestones

PEG placement date

PT-0001 · ccda_section · captured 2023-03
...PEG tube placed 2023-03 after sustained weight loss and dysphagia; tolerating feeds well at follow-up; no aspiration events...
PT-0002 · ccda_section · captured 2023-03
...PEG tube placed 2023-03 after sustained weight loss and dysphagia; tolerating feeds well at follow-up; no aspiration events...
PT-0003 · document:rtf · captured 2023-08
...PEG tube placed 2023-08 after sustained weight loss and dysphagia; tolerating feeds well at follow-up; no aspiration events...

tracheostomy_date 4 unique patients · Treatment milestones

Tracheostomy date

PT-0001 · ccda_section · captured 2024-02
...elective tracheostomy performed 2024-02 for chronic hypercapnic respiratory failure; transitioned from NIV to invasive ventilation...
PT-0002 · ccda_section · captured 2023-12
...elective tracheostomy performed 2023-12 for chronic hypercapnic respiratory failure; transitioned from NIV to invasive ventilation...
PT-0003 · ccda_section · captured 2024-07
...elective tracheostomy performed 2024-07 for chronic hypercapnic respiratory failure; transitioned from NIV to invasive ventilation...

About this dashboard

This dashboard surfaces ALS-specific clinical content captured by note_extraction.py from the unstructured narrative sections of the EHR feed (CCDA section narratives and decoded documents — RTF, HTML, PDF). Unlike the device and exposure dashboards, these are clinical findings (functional rating scores, cognitive scores, diagnostic certainty, treatment milestones, family history, genetic mutations) rather than risk factors or equipment.

Scope and limitations. The patterns shipped with note_extraction.py are seed patterns calibrated against a single registry (ARC). Adopters should validate every pattern against their own narrative corpus before using captured values for analysis; site-specific phrasing conventions, vendor-specific template structures, and individual-clinician dictation patterns vary substantially. Treat this dashboard as a chart-review-preparation and pattern-tuning aid; do not admit numeric values (ALSFRS-R, FVC%, ECAS) into downstream analysis without validation against the patient's structured measurement record or the original note.

Privacy controls (baked in):

  • Patient identifiers replaced with PT-NNNN pseudonyms, stable within this run.
  • Snippet text truncated to 200 characters.
  • Captured values truncated to 60 characters.
  • Patterns with fewer than k=2 unique patients are suppressed entirely.
  • Resource UUIDs are never emitted.

The companion module note_extraction.py produces the underlying note_extractions.csv; this dashboard is the privacy-safe visualization layer over that CSV.