Experiences with Coding using ICD-11: “The Codes Paint a Clearer Picture”
Bibliographic record
Abstract
IntroductionA high performing health data classification system requires clear, comprehensive code descriptions and user-friendly coding tools for effective coding. Coding specialists have essential specialized knowledge to contribute to the development and functionality of the 11th version of International Classification of Diseases (ICD-11) that will be released in June of 2018. Objectives and ApproachThe objective was to evaluate coding specialists’ experience of coding using ICD-11 for complete inpatient hospital charts. Mixed methods were employed for a survey and interviews. As part of a large field trial, 6 certified coding specialists underwent training to use the ICD-11 Beta Draft browser and ICD-11 Coding Tool. The coding team completed multiple coding exercises and coded over 60 charts each prior to evaluation of their experience. An electronic survey was used to evaluate ICD-11 knowledge, comprehension, and application of the coding training. Interviews explored the coders’ experience of learning and using the ICD-11 classification system. ResultsThe coding team (3 to 10 years of experience) received 14 hours classroom training and 5-10 hours per week of coding practice over 3 months. After training, perceived confidence in coding with ICD-11 was satisfactory; moderate (n=4), high (n=1), and low (n=1). Coding short scenarios was the most useful resource (n=6) and lack of guidelines was the most frustrating. Learning ICD-11 was deemed moderately (n=2) to somewhat (n=3) difficult but each coder described satisfaction in learning the new system. From the interviews, coders expressed liking the ability to more fully describe health conditions and hospital harms with code clusters. “The codes paint a clearer picture of what happened than with ICD-10”. With practice they achieved speed with the coding tools. Conclusion/ImplicationsCoding specialists learned and proficiently used the Beta Version of ICD-11 coding system with moderate perceived confidence. New ICD-11 codes and clustering functions allowed for more complete description of health scenarios and enhanced coder satisfaction.
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 | 0.023 | 0.081 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.005 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.001 | 0.006 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
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.
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".