MétaCan
Menu
← Back to cohort
Record W4213165518 · doi:10.1093/jcag/gwab049.096

A97 DEVELOPMENT OF PREDICTION MODELS FOR THE TRIAGING OF REFERRALS OF INDIVIDUALS WITH SUSPECTED INFLAMMATORY BOWEL DISEASE TO IMPROVE PROMPT ACCESS TO CARE

2022· article· en· W4213165518 on OpenAlexaffabout
Joëlle St‐Pierre, Alexandra Frolkis, Cynthia H. Seow, John I. Oshiomogho, Gurmeet K. Bindra, Joan Heatherington, Gilaad G. Kaplan, Remo Panaccione, Kerri L. Novak, Yasmin Nasser, Humberto Jijon

Bibliographic record

VenueJournal of the Canadian Association of Gastroenterology · 2022
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicInflammatory Bowel Disease
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsMedicineReferralInflammatory bowel diseaseLogistic regressionTriageUlcerative colitisDiseaseCrohn's diseaseInternal medicineRetrospective cohort studyAbdominal painCohortUnivariate analysisFamily historyColonoscopyMultivariate analysisEmergency medicineFamily medicineColorectal cancerCancer

Abstract

fetched live from OpenAlex

Abstract Background The negative impact of a delayed inflammatory bowel disease (IBD) diagnosis has been well established. We created a clinical pathway referred to as the “High-Risk IBD clinic” within a centralized referral program in a tertiary referral centre, in order to improve access to subspecialist care for individuals suspected but not yet diagnosed with IBD. Despite the creation of this specialized clinic, wait times continue to be above the recommended benchmarks established by the Canadian Association of Gastroenterology (CAG). Aims The purpose of our study was to create predictive models to identify factors associated with an IBD diagnosis in order to improve triage of referrals of individuals with features highly suggestive of IBD. We hypothesized that features suggestive of IBD could be used to create discriminating prediction models between IBD and IBS. Methods We conducted a retrospective cohort study of referrals to the High-Risk IBD clinic from February 2014 to December 2018. Referral information, investigations, endoscopic findings and final diagnosis were obtained from 316 consented individuals. Information required included symptoms (e.g. diarrhea, abdominal pain, rectal bleeding), risk factors (e.g. family history, rheumatological disease) and investigations (e.g. hemoglobin, CRP, abdominal imaging). Univariate logistic regression was performed to explore the association between factors included in the referral form, and a diagnosis of Crohn’s disease (CD) and ulcerative colitis (UC). For creation of predictive models, any variable with a p-value of <0.1 in univariate logistic regression was selected for entry into the multivariate model for CD and UC. Results For UC, the predictive model included weight loss, the presence of rectal bleeding and abdominal pain. Using these criteria, the sensitivity and specificity of the model were 62.5% and 74.1%, respectively. The negative predictive value (NPV) was high at 94.2%. For CD, the predictive model included male gender, elevated CRP, presence of anemia and presence of weight loss. The sensitivity and specificity of this model were 61.7% and 71.2%, respectively. As for UC, the NPV was also high (89.2%). For IBS, the most common diagnosis encountered in patients referred to the HR-IBD clinic, the model included absence of weight loss, presence of abdominal pain and female gender. The sensitivity and specificity were 71.6% and 64.0%, respectively. The positive predictive value was 60.6% and NPV was 74.5%. Conclusions We established predictive tools associated with a final diagnosis of IBD and IBS as a means to expedite the care of individuals with undiagnosed IBD. Funding Agencies CCC

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)0.007
metaresearch head score (Gemma)0.021
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.022
Threshold uncertainty score0.043

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.021
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0040.002
Science and technology studies0.0010.000
Scholarly communication0.0020.001
Open science0.0020.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0040.001

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 head0.010
GPT teacher head0.233
Teacher spread0.224 · 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 designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations0
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueJournal of the Canadian Association of Gastroenterology→Same topicInflammatory Bowel Disease→French-language works237,207→