ICD-10 coding algorithms for defining comorbidities of acute myocardial infarction
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
BACKGROUND: With the introduction of ICD-10 throughout Canada, it is important to ensure that Acute Myocardial Infarction (AMI) comorbidities employed in risk adjustment methods remain valid and robust. Therefore, we developed ICD-10 coding algorithms for nine AMI comorbidities, examined the validity of the ICD-10 and ICD-9 coding algorithms in detection of these comorbidities, and assessed their performance in predicting mortality. The nine comorbidities that we examined were shock, diabetes with complications, congestive heart failure, cancer, cerebrovascular disease, pulmonary edema, acute renal failure, chronic renal failure, and cardiac dysrhythmias. METHODS: Coders generated a comprehensive list of ICD-10 codes corresponding to each AMI comorbidity. Physicians independently reviewed and determined the clinical relevance of each item on the list. To ensure that the newly developed ICD-10 coding algorithms were valid in recording comorbidities, medical charts were reviewed. After assessing ICD-10 algorithms' validity, both ICD-10 and ICD-9 algorithms were applied to a Canadian provincial hospital discharge database to predict in-hospital, 30-day, and 1-year mortality. RESULTS: Compared to chart review data as a 'criterion standard', ICD-9 and ICD-10 data had similar sensitivities (ranging from 7.1-100%), and specificities (above 93.6%) for each of the nine AMI comorbidities studied. The frequencies for the comorbidities were similar between ICD-9 and ICD-10 coding algorithms for 49,861 AMI patients in a Canadian province during 1994-2004. The C-statistics for predicting 30-day and 1 year mortality were the same for ICD-9 (0.82) and for ICD-10 data (0.81). CONCLUSION: The ICD-10 coding algorithms developed in this study to define AMI comorbidities performed similarly as past ICD-9 coding algorithms in detecting conditions and risk-adjustment in our sample. However, the ICD-10 coding algorithms should be further validated in external databases.
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 | 0.010 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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