An Algorithm Using CART Analysis To Identify IBS-C and IBS-A from IBS-D
Bibliographic record
Abstract
Purpose: In Drossman, Gastro, 2005, we defined by prospective 1-yr evaluation, Rome II compatible IBS alternators (IBS-A) who alternate between IBS-C and IBS-D. IBS-A had similar bowel habit to IBS constipation-mixed (IBS-CM: alternates between IBS-C and IBS-M, but not IBS-D), while IBS diarrhea-mixed (IBS-DM: alternates between IBS-D and IBS-M, but not IBS-C) appears as a separate group. This suggest that treatments for constipation could apply to IBS-CM and IBS-A, but not IBS-DM, and treatments for diarrhea be restricted to IBS-DM. The aim of this study was to develop an algorithm to identify IBS-A, IBS-CM and IBS-DM patients for clinical trials, either as 3 distinct groups or with IBS-CM and IBS-A combined. Methods: Among 317 women entering an NIH treatment trial, Rome II compatible IBS-A, IBS-CM and IBS-DM subtypes were based on prospective assessment of stool habit. Subjects received clinical questionnaires at 3-mo. intervals for 1 yr. (N = 190 evaluable). A Classification and Regression Tree (CART) analysis (SAS V.8) identified, using cross-sectional data from 2-week diary cards, which clinical items discriminated between IBS-A, IBS-CM and IBS-DM, that would otherwise require prospective assessment of bowel habit over at least 1 year. Results: Several analyses were run to create a model that was parsimonious in the number of predictor items (N = 2–4) and also robust in identifying the defined groups (misclassification range 12.6% to 34.2%). Efforts to classify subjects into 3 groups (IBS-A, IBS-CM, IBS-DM) were unsuccessful because IBS-A could not be separated from IBS-CM, thus confirming our initial findings. The best model contained only 2 items (average stool consistency using Bristol Stool Scale, and stool frequency) with a 14.7% misclassification rate. The final clinical decision rule was: 1) Is stool frequency < 2/day? 2a) If Yes, is the stool consistency < 5 [Yes = IBS-A+IBS-CM; No = IBS-DM]? 2b) If No, is the stool consistency < 4 [Yes = IBS-A+IBS-CM; No = IBS-DM]? Conclusions: Using CART analysis, we developed a simple algorithm using a 2-week assessment of average stool frequency+consistency that identifies with 85% accuracy subjects who will have IBS-A & IBS-CM vs. IBS-DM over the subsequent year. The algorithm may be of value in clinical trials and in planning treatments. Supported by NIH: RO1DK49334, and R24 DK067674 and Novartis Pharmaceuticals.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.015 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.003 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".