Registry Forge: note extraction review

Invented ALS cohort (demo) · generated 2026-11-13 12:52 UTC
58
Participants with any candidate
2,416
Candidate matches
18
Patterns with a match
6
Categories found for at least 5 participants

Candidates in each content category

Participants with at least one candidate match in each category. A candidate is text that matched a pattern; it still needs review.

Content categoryParticipants with a candidate
ALSFRS-R58
Pulmonary58
Diagnosis58
Family history and genetics58
ECAS and FTD58
Treatment milestones56

All patterns

Context cues are checked in the words just before each match: a negation such as "no" or "negative for", a family member, uncertainty such as "possible" or "rule out", or a historical marker such as "history of". A cue does not mean the match is wrong; it marks candidates to read first.

PatternCategoryParticipantsCandidatesShare of candidates with a context cue
alsfrs_r_total
ALSFRS-R total score, range 0 to 48
ALSFRS-R58197none
alsfrs_r_bulbar
ALSFRS-R bulbar subscore, range 0 to 12
ALSFRS-R58197none
alsfrs_r_fine_motor
ALSFRS-R fine motor (upper extremity) subscore, range 0 to 12
ALSFRS-R58197none
alsfrs_r_gross_motor
ALSFRS-R gross motor (lower extremity) subscore, range 0 to 12
ALSFRS-R58197none
alsfrs_r_respiratory
ALSFRS-R respiratory subscore, range 0 to 12
ALSFRS-R58197none
ecas_total
ECAS total, maximum 136
ECAS and FTD58197none
ftd_spectrum
Frontotemporal-spectrum involvement mention
ECAS and FTD1765possible family history 54%
el_escorial
El Escorial or Awaji-Shima diagnostic certainty
Diagnosis46158none
onset_region
Site of disease onset
Diagnosis58197none
family_history_negative
Negative family history
Family history and genetics2896possible family history 100%
family_history_positive
Affected relative with ALS, MND or FTD (positive family history)
Family history and genetics30101possible family history 100%
genetic_mutation
ALS-associated gene with a reported variant or expansion
Family history and genetics4968none
fvc_percent_predicted
Forced vital capacity, percent predicted
Pulmonary58197none
peg_placement_date
Date of PEG or gastrostomy tube placement
Treatment milestones1853none
niv_initiation_date
Date non-invasive ventilation started
Treatment milestones2889none
riluzole_start_date
Date riluzole was started
Treatment milestones48162none
edaravone_start_date
Date edaravone was started
Treatment milestones1446none
tracheostomy_date
Date of tracheostomy
Treatment milestonesheld back for cell sizeheld back for cell sizeheld back for cell size

Captured values

Counts are participants, not records.

Numeric values, one per participant

PatternParticipants25th percentileMedian75th percentile
alsfrs_r_bulbar58789
alsfrs_r_fine_motor58678
alsfrs_r_gross_motor58678
alsfrs_r_respiratory586.2589
alsfrs_r_total5825.2530.533
ecas_total5894101110.75
fvc_percent_predicted5864.57078

Minimum and maximum are not shown because a single extreme value belongs to one participant. The number is the first number in the captured text.

Categorical values

onset_region
Captured valueParticipants
limb19
bulbar10
upper limb10
lower limb10
respiratory9
genetic_mutation
Captured valueParticipants
c9orf7249
fus10
el_escorial
Captured valueParticipants
clinically possible12
lab-supported probable12
clinically probable11
clinically definite11
family_history_positive
Captured valueParticipants
als20
frontotemporal dementia10
family_history_negative
Captured valueParticipants
no family history of als18
no known family history of neurodegenerative disease10
ftd_spectrum
Captured valueParticipants
frontotemporal dementia10
behavioral variant ftd9

Excerpts for pattern tuning

Up to three excerpts per pattern, each from a different participant. EX-NNNN pseudonyms are assigned in this file only.

alsfrs_r_bulbar

EX-0001 · ccda_section · no cue found
...a for clinically possible ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary func...
EX-0002 · ccda_section · no cue found
...or lab-supported probable ALS. ALSFRS-R total score: 32/48. ALSFRS-R subscores: bulbar 7, fine motor 8, gross motor 7, respiratory 10. Pulmonary fun...
EX-0003 · ccda_section · no cue found
...a for clinically probable ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary func...

alsfrs_r_fine_motor

EX-0001 · ccda_section · no cue found
...a for clinically possible ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary function today: FV...
EX-0002 · ccda_section · no cue found
...or lab-supported probable ALS. ALSFRS-R total score: 32/48. ALSFRS-R subscores: bulbar 7, fine motor 8, gross motor 7, respiratory 10. Pulmonary function today: F...
EX-0003 · ccda_section · no cue found
...a for clinically probable ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary function today: FV...

alsfrs_r_gross_motor

EX-0001 · ccda_section · no cue found
...a for clinically possible ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary function today: FVC 2.1 L (59% pr...
EX-0002 · ccda_section · no cue found
...or lab-supported probable ALS. ALSFRS-R total score: 32/48. ALSFRS-R subscores: bulbar 7, fine motor 8, gross motor 7, respiratory 10. Pulmonary function today: FVC 2.7 L (74% p...
EX-0003 · ccda_section · no cue found
...a for clinically probable ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary function today: FVC 2.3 L (64% pr...

alsfrs_r_respiratory

EX-0001 · ccda_section · no cue found
...a for clinically possible ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary function today: FVC 2.1 L (59% predicted), seate...
EX-0002 · ccda_section · no cue found
...or lab-supported probable ALS. ALSFRS-R total score: 32/48. ALSFRS-R subscores: bulbar 7, fine motor 8, gross motor 7, respiratory 10. Pulmonary function today: FVC 2.7 L (74% predicted), seate...
EX-0003 · ccda_section · no cue found
...a for clinically probable ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6, respiratory 8. Pulmonary function today: FVC 2.3 L (64% predicted), seate...

alsfrs_r_total

EX-0001 · ccda_section · no cue found
...s revised El Escorial criteria for clinically possible ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6,...
EX-0002 · ccda_section · no cue found
...evised El Escorial criteria for lab-supported probable ALS. ALSFRS-R total score: 32/48. ALSFRS-R subscores: bulbar 7, fine motor 8, gross motor 7,...
EX-0003 · ccda_section · no cue found
...s revised El Escorial criteria for clinically probable ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6, fine motor 6, gross motor 6,...

ecas_total

EX-0001 · ccda_section · no cue found
...started riluzole 50 mg twice daily on [date]. Cognition: ECAS total 101/136. No known family history of neurodegenerative disease. Soci...
EX-0002 · ccda_section · no cue found
...ated on [date] for nocturnal hypoventilation. Cognition: ECAS total 118/136. Mother had frontotemporal dementia. Social history: Worked...
EX-0003 · ccda_section · no cue found
...ted on [date] for nocturnal hypoventilation. Cognition: ECAS total 120/136. Family history of ALS in a paternal aunt. Social history:...

edaravone_start_date

EX-0004 · ccda_section · no cue found
...dications: started riluzole 50 mg twice daily on [date]. Edaravone started [date], oral suspension daily. Cognition: ECAS total 105/136. Fath...
EX-0007 · ccda_section · no cue found
...edications: started riluzole 50 mg twice daily on [date]. Edaravone started [date], oral suspension daily. BiPAP initiated on [date] for n...
EX-0008 · ccda_section · no cue found
...dications: started riluzole 50 mg twice daily on [date]. Edaravone started [date], oral suspension daily. Cognition: ECAS total 97/136. Mothe...

el_escorial

EX-0001 · ccda_section · no cue found
...onset February 2022. Meets revised El Escorial criteria for clinically possible ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6,...
EX-0002 · ccda_section · no cue found
...om onset March 2023. Meets revised El Escorial criteria for lab-supported probable ALS. ALSFRS-R total score: 32/48. ALSFRS-R subscores: bulbar 7,...
EX-0003 · ccda_section · no cue found
...onset November 2021. Meets revised El Escorial criteria for clinically probable ALS. ALSFRS-R total score: 26/48. ALSFRS-R subscores: bulbar 6,...

family_history_negative

EX-0001 · ccda_section · possible family history
...mg twice daily on [date]. Cognition: ECAS total 101/136. No known family history of neurodegenerative disease. Social history: Former smoker, 20 pack-years, quit 2010. E...
EX-0005 · ccda_section · possible family history
...or nocturnal hypoventilation. Cognition: ECAS total 89/136. No family history of ALS or dementia. Social history: Occupational exposure to lead...
EX-0006 · ccda_section · possible family history
...5 L (69% predicted), seated. Cognition: ECAS total 119/136. No family history of ALS or dementia. Social history: Lived near a lake with recurri...

family_history_positive

EX-0002 · ccda_section · possible family history
...r nocturnal hypoventilation. Cognition: ECAS total 118/136. Mother had frontotemporal dementia. Social history: Worked as a farmer with pesticide exposure...
EX-0003 · ccda_section · possible family history
...r nocturnal hypoventilation. Cognition: ECAS total 120/136. Family history of ALS in a paternal aunt. Social history: Played college football...
EX-0004 · ccda_section · possible family history
...0-28, oral suspension daily. Cognition: ECAS total 105/136. Father was diagnosed with ALS at age 61. Social history: Worked as an electrician for 25...

ftd_spectrum

EX-0002 · ccda_section · possible family history
...hypoventilation. Cognition: ECAS total 118/136. Mother had frontotemporal dementia. Social history: Worked as a farmer with pesticide exposure...
EX-0008 · ccda_section · possible family history
...suspension daily. Cognition: ECAS total 97/136. Mother had frontotemporal dementia. Social history: Never smoker. No military service. Equipme...
EX-0009 · ccda_section · no cue found
...r nocturnal hypoventilation. Cognition: ECAS total 114/136. Behavioral variant FTD features noted by family. Father was diagnosed with ALS at...

fvc_percent_predicted

EX-0001 · ccda_section · no cue found
...6, gross motor 6, respiratory 8. Pulmonary function today: FVC 2.1 L (59% predicted), seated. Medications: started riluzole 50 mg twice daily o...
EX-0002 · ccda_section · no cue found
...8, gross motor 7, respiratory 10. Pulmonary function today: FVC 2.7 L (74% predicted), seated. Medications: started riluzole 50 mg twice daily o...
EX-0003 · ccda_section · no cue found
...6, gross motor 6, respiratory 8. Pulmonary function today: FVC 2.3 L (64% predicted), seated. Medications: started riluzole 50 mg twice daily o...

genetic_mutation

EX-0001 · document:unknown · no cue found
...REPORT Report date: [date] Test: ALS gene panel with C9orf72 repeat-primed PCR (synthetic laboratory). Result: Genetic testing:...
EX-0002 · document:pdf · no cue found
...REPORT Report date: [date] Test: ALS gene panel with C9orf72 repeat-primed PCR (synthetic laboratory). Result: Genetic testing:...
EX-0003 · document:unknown · no cue found
...REPORT Report date: [date] Test: ALS gene panel with C9orf72 repeat-primed PCR (synthetic laboratory). Result: Genetic testing:...

niv_initiation_date

EX-0002 · ccda_section · no cue found
...ications: started riluzole 50 mg twice daily on [date]. BiPAP initiated on [date] for nocturnal hypoventilation. Cognition: ECAS total 118/13...
EX-0003 · ccda_section · no cue found
...dications: started riluzole 50 mg twice daily on [date]. BiPAP initiated on [date] for nocturnal hypoventilation. Cognition: ECAS total 120/13...
EX-0005 · ccda_section · no cue found
...[date]. PEG tube placed on [date]; tolerating feeds. BiPAP initiated on [date] for nocturnal hypoventilation. Cognition: ECAS total 89/136...

onset_region

EX-0001 · ccda_section · no cue found
...sis: amyotrophic lateral sclerosis, diagnosed October 2022; limb-onset, symptom onset February 2022. Meets revised El Escorial cri...
EX-0002 · ccda_section · no cue found
...sis: amyotrophic lateral sclerosis, diagnosed October 2023; bulbar-onset, symptom onset March 2023. Meets revised El Escorial criter...
EX-0003 · ccda_section · no cue found
...nosis: amyotrophic lateral sclerosis, diagnosed April 2023; upper limb onset, symptom onset November 2021. Meets revised El Escorial cri...

peg_placement_date

EX-0005 · ccda_section · no cue found
...dications: started riluzole 50 mg twice daily on [date]. PEG tube placed on [date]; tolerating feeds. BiPAP initiated on [date] for nocturn...
EX-0009 · document:html_fragment · no cue found
.../2024. Edaravone started [date], oral suspension daily. PEG tube placed on [date]; tolerating feeds. BiPAP initiated on [date] for nocturn...
EX-0010 · document:html_fragment · no cue found
...dications: started riluzole 50 mg twice daily on [date]. PEG tube placed on [date]; tolerating feeds. BiPAP initiated on [date] for nocturna...

riluzole_start_date

EX-0001 · ccda_section · no cue found
...tion today: FVC 2.1 L (59% predicted), seated. Medications: started riluzole 50 mg twice daily on [date]. Cognition: ECAS total 101/136. No known family history of...
EX-0002 · ccda_section · no cue found
...tion today: FVC 2.7 L (74% predicted), seated. Medications: started riluzole 50 mg twice daily on [date]. BiPAP initiated on [date] for nocturnal hypoventilation...
EX-0003 · ccda_section · no cue found
...tion today: FVC 2.3 L (64% predicted), seated. Medications: started riluzole 50 mg twice daily on [date]. BiPAP initiated on [date] for nocturnal hypoventilatio...

About these dashboards

note_extraction.py searches C-CDA section text, decoded documents (RTF, PDF, HTML, plain text) and text attached to FHIR DiagnosticReport, DocumentReference and Binary resources. Every match is written to note_extractions.csv with its content category, a context cue and review_status needs_review.

The patterns are seed patterns for ALS registries. Check each pattern against a sample of real documents from each contributing health system, and have a reviewer confirm candidates against the source before any value is used in analysis.

Settings: k = 5. Generated 2026-11-13 12:52 UTC.