Validity of an ICD-10 Coding Algorithm for Acute Heat Illness in the Emergency Department: A Retrospective Cohort Study
Bibliographic record
Abstract
Acute heat illness (AHI) from extreme environmental heat exposure can lead to emergency department (ED) visits, hospitalization, and even death. While the ICD ninth revision codes for AHI have been validated in the U.S., there have been no studies on the validity of ICD-10 codes for AHI in Canada. The objective of this study was to assess the validity of an ICD-10 coding algorithm for ED encounters for AHI. We conducted a retrospective cohort study of children and adults who had ED encounters at two large academic, tertiary hospitals in London, Canada, between May and September 2014-2018. We developed an algorithm of ICD-10 codes for AHI based upon a literature review and clinical expertise. Our "gold-standard" definition of AHI was patient-reported heat exposure and documentation of at least one heat-related complaint. To establish positive predictive value (PPV), we reviewed 62 algorithm-positive records and noted which met our "gold-standard" definition. To calculate negative predictive value (NPV), sensitivity (Sn), and specificity (Sp), we randomly reviewed 964 ED records for associated ICD-10 codes and diagnoses. Two independent reviewers completed blinded data abstraction, with duplicate abstraction in 20% of the sample. Of the 62 algorithm-positive records, mean (SD) age was 38.8 (23.8) years; 37% were female. PPV was 61.3 ± 12.1% (95% CI). Of the 964 randomly selected records, mean (SD) age was 41.7 (26.5) years; 51.1% were female. The NPV was 99.7 ± 0.4%, sensitivity 25.0 ± 42.4%, and specificity 100.0 ± 0.0%. An ICD-10 coding algorithm for AHI had high specificity but was limited in sensitivity. This algorithm can be used to assemble and study cohorts of patients who have had an AHI, but may underestimate the true incidence of AHI presentations in the ED.
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 | 0.009 | 0.030 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".