MétaCan
Menu
Back to cohort
Record W2255590195 · doi:10.1038/sc.2015.137

Development and validation of a computerized algorithm for International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI)

2015· article· en· W2255590195 on OpenAlexafffund
Kristen Walden, Lise Bélanger, Fin Biering‐Sørensen, Stephen P. Burns, Erika Herrera de Echeverría, Steven Kirshblum, Ralph J. Marino, Vanessa K. Noonan, S E Park, Ronald K. Reeves, William Waring, Marcel F. Dvorak

Bibliographic record

VenueSpinal Cord · 2015
Typearticle
Languageen
FieldMedicine
TopicSpinal Cord Injury Research
Canadian institutionsUniversity of British ColumbiaVancouver General HospitalPraxis Spinal Cord Institute
FundersWestern Economic Diversification CanadaHealth CanadaRick Hansen Institute
KeywordsMedicineSpinal cord injurySpinal cordAlgorithmPoison controlPhysical medicine and rehabilitationMedical emergencyComputer sciencePsychiatry

Abstract

fetched live from OpenAlex

STUDY DESIGN: Validation study. OBJECTIVES: To describe the development and validation of a computerized application of the international standards for neurological classification of spinal cord injury (ISNCSCI). SETTING: Data from acute and rehabilitation care. METHODS: The Rick Hansen Institute-ISNCSCI Algorithm (RHI-ISNCSCI Algorithm) was developed based on the 2011 version of the ISNCSCI and the 2013 version of the worksheet. International experts developed the design and logic with a focus on usability and features to standardize the correct classification of challenging cases. A five-phased process was used to develop and validate the algorithm. Discrepancies between the clinician-derived and algorithm-calculated results were reconciled. RESULTS: Phase one of the validation used 48 cases to develop the logic. Phase three used these and 15 additional cases for further logic development to classify cases with 'Not testable' values. For logic testing in phases two and four, 351 and 1998 cases from the Rick Hansen SCI Registry (RHSCIR), respectively, were used. Of 23 and 286 discrepant cases identified in phases two and four, 2 and 6 cases resulted in changes to the algorithm. Cross-validation of the algorithm in phase five using 108 new RHSCIR cases did not identify the need for any further changes, as all discrepancies were due to clinician errors. The web-based application and the algorithm code are freely available at www.isncscialgorithm.com. CONCLUSION: The RHI-ISNCSCI Algorithm provides a standardized method to accurately derive the level and severity of SCI from the raw data of the ISNCSCI examination. The web interface assists in maximizing usability while minimizing the impact of human error in classifying SCI. SPONSORSHIP: This study is sponsored by the Rick Hansen Institute and supported by funding from Health Canada and Western Economic Diversification Canada.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.029
metaresearch head score (Gemma)0.074
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.029
Threshold uncertainty score0.151

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0290.074
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0100.004
Science and technology studies0.0020.001
Scholarly communication0.0050.003
Open science0.0030.003
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0040.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.210
GPT teacher head0.464
Teacher spread0.255 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations48
Published2015
Admission routes2
Has abstractno

Explore more

Same venueSpinal CordSame topicSpinal Cord Injury ResearchFrench-language works237,207