Training Coding Specialists for the Future: Methods and Materials for the Beta Version of ICD-11
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
IntroductionIn June 2018, the World Health Organization (WHO) will release the 11th Version of International Classification of Diseases (ICD-11). New training methods and materials are required. As a WHO Collaborating Center, with Canadian Institute for Health Information (CIHI) members, we trained 6 coding professionals for testing ICD-11 coding processes. Objectives and ApproachThe objective was to achieve a high level of inter-rater reliability using ICD-11 for acute care chart coding. We used Adult Learning principles with CIHI members and 6 certified coding specialists to co-create presentations, practice materials, and decision trees to teach knowledge and skill with ICD-11 tooling and content. Training involved 14 hours of interactive learning plus additional practice hours. A bank of questions and coding scenarios tested knowledge and application of ICD-11 terminology and principles. Coding was undertaken on a set of 3000 randomly selected inpatient Calgary hospital discharges as part of a large CIHR funded ICD-11 field trial. ResultsThe coding team achieved an average score of 84% on the ICD-11 coding quiz and 0.65 (0.33 -1.0) agreement on parent code of main condition for the coding quiz scenarios. 60 inpatient charts were coded by more than one coder to test inter-rater reliability. Agreement was ≧ 0.80 for the majority of parent codes for main condition. Coding differences may be due to unfamiliar code choices or training gaps. New code descriptions in ICD-11 enhance code selection. Challenges included training while codes were being built in the ICD-11 browser, and minimal coding rules or standards. Conclusion/ImplicationsRecommendations include more code descriptions in the browser and rules in a reference guide, teaching from simple to complex conditions, and multiple scenarios with ‘gold standard’ codes for practice. Reference Guide, Coding Tool, and Browser recommendations have been shared with members of the WHO Morbidity and Quality & Safety Advisory groups.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.015 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it